{"meta":{"query_hash":"fef9bd4f6705","filters":{"topic":"Speech Recognition and Synthesis"},"cohort_total":749,"direct_labels_cover":1,"predictions_cover":749,"exported":749,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/fef9bd4f6705","api":"https://metacan.xera.ac/api/v1/cohort?topic=Speech+Recognition+and+Synthesis"},"results":[{"id":"W100623710","doi":"10.1007/3-540-33486-6_6","title":"Neural Probabilistic Language Models","year":2006,"lang":"en","type":"book-chapter","venue":"Studies in fuzziness and soft computing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":491,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Generalization; Sentence; Curse of dimensionality; Artificial intelligence; Word (group theory); Language model; Natural language processing; Probabilistic logic; Representation (politics); Sequence (biology); Set (abstract data type); Linguistics; Mathematics","score_opus":0.06406113222153774,"score_gpt":0.28941119288099004,"score_spread":0.2253500606594523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W100623710","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011583711,0.005934897,0.94549507,0.002386558,0.00043255827,0.000027428461,0.0005538813,0.0014155952,0.03217041],"genre_scores_gemma":[0.65369904,0.008991632,0.23669092,0.0009063329,0.0009764914,0.00026663576,0.0028262613,0.0006974025,0.094945274],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996055,0.00011091668,0.00001995028,0.00011194397,0.00012228116,0.000029537541],"domain_scores_gemma":[0.99876946,0.0008431393,0.00005414742,0.00016175426,0.00014236044,0.000029046834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074896205,0.00070857524,0.0009071883,0.000767518,0.0005122952,0.0017967811,0.0014864334,0.0012367081,0.008150233],"category_scores_gemma":[0.0046348716,0.0007441502,0.00077226106,0.00096524484,0.0010393353,0.0033973034,0.0009826131,0.0022774965,0.0028021194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006603264,0.0000476696,0.00039004858,0.00013495707,0.00008709678,0.00009578526,0.00016981154,0.17771015,0.0020219027,0.6350734,0.013540293,0.17066284],"study_design_scores_gemma":[0.0000065742056,0.000009971405,0.0001533192,0.00002145357,0.000020549518,0.00007404952,0.00001710162,0.5116266,0.0005952089,0.47949076,0.00796802,0.000016510521],"about_ca_topic_score_codex":0.002519765,"about_ca_topic_score_gemma":0.0027926846,"teacher_disagreement_score":0.008150233,"about_ca_system_score_codex":0.00071614265,"about_ca_system_score_gemma":0.0006534586,"threshold_uncertainty_score":0.027265191},"labels":[],"label_agreement":null},{"id":"W1269046860","doi":"10.1201/9781482276237","title":"Speech Processing","year":2018,"lang":"en","type":"book","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":239,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université du Québec à Montréal","funders":"","keywords":"Speech recognition; Computer science; Natural language processing","score_opus":0.027255205319896805,"score_gpt":0.24671951605143588,"score_spread":0.21946431073153908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1269046860","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031915768,0.09637336,0.28144652,0.004751036,0.0130989365,0.00043512907,0.0030766756,0.0069310055,0.59069586],"genre_scores_gemma":[0.021510536,0.04494285,0.07578741,0.002558302,0.0039187605,0.0003014208,0.004517754,0.0011858926,0.8452771],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993419,0.000058689133,0.000047142217,0.00014301372,0.00037853527,0.000030717125],"domain_scores_gemma":[0.99939704,0.000119870216,0.000021856258,0.00010686499,0.00032008832,0.00003429175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005027199,0.001187617,0.00078892044,0.0014651128,0.00072918885,0.0028914928,0.0010572164,0.0014095871,0.09150737],"category_scores_gemma":[0.0013558664,0.00035622917,0.00054011244,0.0014849324,0.0006441026,0.0017497329,0.0013192734,0.0014140853,0.10281714],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059723203,0.000034896617,0.00009179264,0.0007073423,0.000032563785,0.00018588584,0.00014589846,0.00120292,0.010419613,0.02835307,0.22481227,0.733954],"study_design_scores_gemma":[0.000007894409,0.000046316978,0.00037289836,0.00023909325,0.000011602403,0.0006755522,0.00007051687,0.0018941117,0.003783353,0.015418814,0.977459,0.000020892254],"about_ca_topic_score_codex":0.0006980454,"about_ca_topic_score_gemma":0.0007944025,"teacher_disagreement_score":0.09150737,"about_ca_system_score_codex":0.0005313615,"about_ca_system_score_gemma":0.00070775737,"threshold_uncertainty_score":0.30612266},"labels":[],"label_agreement":null},{"id":"W129600432","doi":"10.1522/18186435","title":"Exploration de reseaux de neurones a decharges dans un contexte de reconnaissance de parole /","year":2004,"lang":"fr","type":"book","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Université du Québec à Chicoutimi","funders":"","keywords":"Humanities; Geography; Philosophy","score_opus":0.08794847652498944,"score_gpt":0.28725285037479914,"score_spread":0.1993043738498097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W129600432","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7171669,0.0041890913,0.26189786,0.0010975503,0.00037171648,0.00019076157,0.00023256332,0.002510719,0.012342826],"genre_scores_gemma":[0.9055953,0.0012111819,0.077534586,0.00024765093,0.000029803181,0.00011771951,0.00016513288,0.00014160183,0.0149571495],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99968493,0.000043538836,0.000014885836,0.000094299925,0.00011273703,0.000049605263],"domain_scores_gemma":[0.9993774,0.00020612412,0.000061514256,0.000100582736,0.0001931602,0.00006130279],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005353311,0.00054346217,0.0005110764,0.00028703082,0.00048233842,0.0010361687,0.0008230445,0.0010424937,0.0045900494],"category_scores_gemma":[0.0012375831,0.000300984,0.0005450623,0.00024328897,0.0006495685,0.0012266635,0.0006054548,0.000619175,0.001087978],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024317896,0.00007769569,0.0014086922,0.00032162166,0.000037750615,0.0003711132,0.00043079964,0.0060233767,0.8953917,0.0013274709,0.00045871094,0.093907826],"study_design_scores_gemma":[0.000056829675,0.0027154116,0.022674372,0.00013247704,0.0002047839,0.0017565051,0.0018430887,0.104025185,0.8364329,0.005013887,0.02503244,0.00011210471],"about_ca_topic_score_codex":0.0020818927,"about_ca_topic_score_gemma":0.004351979,"teacher_disagreement_score":0.0045900494,"about_ca_system_score_codex":0.00056559284,"about_ca_system_score_gemma":0.0005639575,"threshold_uncertainty_score":0.015355289},"labels":[],"label_agreement":null},{"id":"W141927798","doi":"10.21437/interspeech.2009-111","title":"Cepstral and long-term features for emotion recognition","year":2009,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Mel-frequency cepstrum; Term (time); Speech recognition; Emotion recognition; Cepstrum; Recall; Artificial intelligence; Class (philosophy); Pattern recognition (psychology); Logistic regression; Machine learning; Feature extraction; Cognitive psychology; Psychology","score_opus":0.033999945749153625,"score_gpt":0.27037137966234537,"score_spread":0.23637143391319174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W141927798","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045641564,0.013254611,0.9210282,0.0007235829,0.0016195931,0.00021898573,0.0021870325,0.006902031,0.008424424],"genre_scores_gemma":[0.39861426,0.004064511,0.5722633,0.0004845423,0.0012394916,0.00030895142,0.007490559,0.0006547307,0.014879668],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99866796,0.0002818246,0.00008993518,0.00030583752,0.00049746357,0.0001570379],"domain_scores_gemma":[0.99849,0.00046526376,0.00009799059,0.00031129317,0.0005745309,0.00006088635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013770027,0.0011616588,0.0008297181,0.0010366085,0.00034110603,0.0011326056,0.0008482598,0.0011973566,0.005730931],"category_scores_gemma":[0.0037303322,0.0002647084,0.0004868762,0.001178456,0.00021534986,0.0014614209,0.0008505005,0.0011809849,0.004398856],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004860943,0.00014967498,0.0009882629,0.000246874,0.00009312259,0.00016582527,0.000049076323,0.0065627526,0.08282648,0.0021343762,0.012720887,0.89357644],"study_design_scores_gemma":[0.00017396218,0.001223255,0.022550235,0.00020904059,0.0004980049,0.0018272323,0.00016761191,0.61144507,0.26230937,0.010244529,0.089014344,0.0003373062],"about_ca_topic_score_codex":0.0013247208,"about_ca_topic_score_gemma":0.0019911523,"teacher_disagreement_score":0.005730931,"about_ca_system_score_codex":0.00030943417,"about_ca_system_score_gemma":0.0003145429,"threshold_uncertainty_score":0.019171834},"labels":[],"label_agreement":null},{"id":"W1501761272","doi":"10.1109/icassp.1988.196632","title":"Three probabilistic language models for a large-vocabulary speech recognizer","year":2003,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bell (Canada); Institut National de la Recherche Scientifique","funders":"","keywords":"Trigram; Computer science; Language model; Vocabulary; Decoding methods; Speech recognition; Word (group theory); Natural language processing; Artificial intelligence; Bigram; Probabilistic logic; Conversation; Linguistics; Algorithm","score_opus":0.0377717494101761,"score_gpt":0.2618095162160192,"score_spread":0.2240377668058431,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1501761272","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013685326,0.0003896925,0.9685074,0.00044991603,0.00013529886,0.00020930651,0.00045731876,0.014073768,0.0020919556],"genre_scores_gemma":[0.18075275,0.0005530225,0.8059153,0.00038526204,0.00010478487,0.0013241558,0.0026218935,0.00084135315,0.0075014103],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998473,0.00055229245,0.00011847516,0.00027226127,0.000459698,0.00012430201],"domain_scores_gemma":[0.9964796,0.002201405,0.00013886126,0.0003469124,0.00071565487,0.000117583164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027677736,0.0015903239,0.0011442634,0.000882341,0.00080355164,0.0020667226,0.003129156,0.0024639925,0.0082215555],"category_scores_gemma":[0.007809786,0.001066322,0.001851825,0.0007189014,0.00043817004,0.0027897512,0.001296479,0.0022666361,0.0072799916],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018435246,0.00044149245,0.0019757168,0.00045329254,0.00041679695,0.00022190406,0.00018655711,0.44470245,0.019529464,0.014816012,0.009913296,0.50549954],"study_design_scores_gemma":[0.000048561316,0.00007452381,0.00024591017,0.000012183824,0.000059547274,0.000058226524,0.000019200117,0.9911074,0.0036431705,0.003233012,0.0014586343,0.00003974216],"about_ca_topic_score_codex":0.011952693,"about_ca_topic_score_gemma":0.015056391,"teacher_disagreement_score":0.011952693,"about_ca_system_score_codex":0.0015528352,"about_ca_system_score_gemma":0.00184387,"threshold_uncertainty_score":0.027503908},"labels":[],"label_agreement":null},{"id":"W1509434377","doi":"10.1109/nnsp.1991.239500","title":"Neural-network architecture for linear and nonlinear predictive hidden Markov models: application to speech recognition","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Speech recognition; Artificial neural network; Hidden Markov model; Linear prediction; Nonlinear system; Artificial intelligence; Term (time); Frame (networking); Markov model; Pattern recognition (psychology); Linear model; Markov chain; Machine learning","score_opus":0.033613259919094314,"score_gpt":0.241170703534018,"score_spread":0.2075574436149237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1509434377","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008911592,0.00059960625,0.98693013,0.0002300878,0.000052440453,0.000024274214,0.00005379084,0.0012145265,0.0019834836],"genre_scores_gemma":[0.4459667,0.001142045,0.5419329,0.00015812446,0.000095717,0.00017993072,0.0002727241,0.0001690936,0.010082799],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998658,0.000045475335,0.000010343981,0.00003086022,0.000033581266,0.000013952918],"domain_scores_gemma":[0.9996803,0.00019359705,0.000020686304,0.000023983215,0.00007086231,0.000010473135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062523223,0.0004638711,0.00031551722,0.00026394075,0.00026641996,0.00060607254,0.00074125687,0.0007956707,0.0023139436],"category_scores_gemma":[0.0019162237,0.00032058332,0.00030978952,0.0004225083,0.00030859862,0.0008486414,0.00046258725,0.0009483583,0.0008385977],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000094115516,0.000051767456,0.0005782267,0.00008538862,0.00005107913,0.000112378,0.0000643592,0.7726627,0.0054635117,0.018341137,0.0016437599,0.2008516],"study_design_scores_gemma":[0.0000018548524,0.000005088593,0.00004058135,0.000002737571,0.0000030732526,0.0000069436305,0.0000015954108,0.99716955,0.00054218236,0.0019195507,0.00030450444,0.0000024192482],"about_ca_topic_score_codex":0.008732608,"about_ca_topic_score_gemma":0.009194627,"teacher_disagreement_score":0.008732608,"about_ca_system_score_codex":0.0008042277,"about_ca_system_score_gemma":0.0005179037,"threshold_uncertainty_score":0.017363548},"labels":[],"label_agreement":null},{"id":"W1512994456","doi":"10.1023/a:1015568521453","title":"Learning Prosodic Patterns for Mandarin Speech Synthesis","year":2002,"lang":"en","type":"article","venue":"Journal of Intelligent Information Systems","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Alberta","funders":"Chinese Academy of Sciences","keywords":"Naturalness; Computer science; Prosody; Intelligibility (philosophy); Speech synthesis; Speech recognition; Cluster analysis; Artificial intelligence; Decision tree; Artificial neural network; Natural language processing","score_opus":0.03588713324134827,"score_gpt":0.24375575159079285,"score_spread":0.2078686183494446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1512994456","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17373826,0.0007835721,0.8190946,0.00016562422,0.000103393446,0.00009592728,0.00037876747,0.0022932212,0.0033466928],"genre_scores_gemma":[0.6167891,0.00048078175,0.37762466,0.00008182262,0.000060330716,0.00016155842,0.0009329877,0.00020873455,0.003659929],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99981076,0.00005501442,0.0000142311055,0.00006883206,0.000029945784,0.000021294787],"domain_scores_gemma":[0.9995546,0.00025222334,0.000027615577,0.00004859032,0.00009118613,0.000025743],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047915353,0.0005170045,0.0004451274,0.0004829282,0.0002355177,0.00039507487,0.0004744842,0.00048219107,0.0030751827],"category_scores_gemma":[0.0016724747,0.00043344204,0.00038497077,0.00041405394,0.00016872288,0.00057758583,0.00062505057,0.00075983745,0.0007232505],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004099193,0.00010424882,0.0013108163,0.000078403114,0.000050060647,0.00007594562,0.000075936354,0.034131028,0.030884534,0.0010022323,0.0014440916,0.9304327],"study_design_scores_gemma":[0.00007902429,0.00022288393,0.002334846,0.000017708877,0.00006279707,0.00007787797,0.000080425525,0.9727631,0.018474493,0.0044714543,0.0014001456,0.000015182694],"about_ca_topic_score_codex":0.00155012,"about_ca_topic_score_gemma":0.003006499,"teacher_disagreement_score":0.0030751827,"about_ca_system_score_codex":0.00019561315,"about_ca_system_score_gemma":0.0003518865,"threshold_uncertainty_score":0.010287523},"labels":[],"label_agreement":null},{"id":"W1519446688","doi":"10.1109/isspit.2004.1433721","title":"Acoustic training system for speaker independent continuous Arabic speech recognition system","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Bigram; Computer science; Speech recognition; Word error rate; Acoustic model; Vocabulary; Context (archaeology); Grammar; Natural language processing; Artificial intelligence; Language model; Test set; Word (group theory); Speaker recognition; Context-free grammar; Set (abstract data type); Hidden Markov model; Rule-based machine translation; Speech processing; Linguistics; Programming language","score_opus":0.04519592834410268,"score_gpt":0.24455521439190864,"score_spread":0.19935928604780595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1519446688","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07371607,0.00045542116,0.8866769,0.0002593055,0.00041338737,0.0004523744,0.0009116645,0.028690653,0.008424256],"genre_scores_gemma":[0.562706,0.00035094708,0.40538964,0.0003591301,0.000227078,0.0009324672,0.0036210355,0.000603236,0.025810422],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995995,0.000060221235,0.000029000086,0.000109446744,0.00017175995,0.000030107616],"domain_scores_gemma":[0.99938226,0.00011517965,0.000023711611,0.000085055246,0.00034279554,0.000051001396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005210176,0.00056511164,0.0005503595,0.00037609646,0.00035708962,0.00045335185,0.00076170533,0.000545333,0.0136583],"category_scores_gemma":[0.0013061005,0.00029816845,0.00024739676,0.0001751963,0.0001538793,0.00056571607,0.00048533434,0.00065783923,0.009333178],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008701734,0.00023017006,0.0026894317,0.00032862386,0.000069842856,0.00037410954,0.0003135353,0.010403832,0.3880424,0.0012272289,0.013624938,0.5818258],"study_design_scores_gemma":[0.00022689906,0.0013019085,0.011573174,0.00010084061,0.0003006205,0.0017168338,0.00022409196,0.59420955,0.32388687,0.001596232,0.06468258,0.00018041205],"about_ca_topic_score_codex":0.002065196,"about_ca_topic_score_gemma":0.0017007961,"teacher_disagreement_score":0.0136583,"about_ca_system_score_codex":0.00024854625,"about_ca_system_score_gemma":0.00042965036,"threshold_uncertainty_score":0.04569161},"labels":[],"label_agreement":null},{"id":"W1525833316","doi":"10.1109/isspit.2003.1341231","title":"On the use of dynamic spectral parameters in speech recognition","year":2004,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Speech recognition; Computer science; Mel-frequency cepstrum; Cepstrum; Feature extraction; Set (abstract data type); Feature (linguistics); Dynamics (music); Speech processing; Pattern recognition (psychology); Artificial intelligence; Task (project management); Linear predictive coding; Feature vector; Acoustics; Engineering","score_opus":0.07952758791153693,"score_gpt":0.2500826680213651,"score_spread":0.17055508010982817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1525833316","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034432635,0.0092676785,0.946114,0.00047011828,0.00017963574,0.0001117057,0.00016837935,0.0012555585,0.0080003],"genre_scores_gemma":[0.46902844,0.011962838,0.5124054,0.00035225885,0.00039865426,0.00020705108,0.000730315,0.00049072434,0.004424331],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991241,0.00029477134,0.00008022431,0.0001937227,0.00027562134,0.000031463664],"domain_scores_gemma":[0.99669075,0.0023050935,0.00012437417,0.000500468,0.00033993306,0.00003933607],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013875233,0.0007066675,0.00070024916,0.0009898419,0.0003200196,0.001714387,0.0005571343,0.0011336819,0.0019437768],"category_scores_gemma":[0.0077028247,0.00037846036,0.00024904963,0.0015700706,0.0013622281,0.0028460692,0.00085247733,0.0008516399,0.0019583595],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045342324,0.000100323916,0.0010382307,0.00025828183,0.000056618723,0.00027493614,0.00018783093,0.04125158,0.098830424,0.028634762,0.001824553,0.827089],"study_design_scores_gemma":[0.00010000226,0.0006536171,0.006569329,0.00034444217,0.00018381096,0.003115926,0.00026742884,0.7141172,0.14859481,0.07934135,0.046459306,0.0002527596],"about_ca_topic_score_codex":0.0008171261,"about_ca_topic_score_gemma":0.0006730629,"teacher_disagreement_score":0.0019437768,"about_ca_system_score_codex":0.00023814834,"about_ca_system_score_gemma":0.00020431045,"threshold_uncertainty_score":0.0073379874},"labels":[],"label_agreement":null},{"id":"W1527831725","doi":"10.1109/sipnn.1994.344894","title":"A theory on optimal construction of dynamic features of speech for HMM-based speech recognition","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Hidden Markov model; Speech recognition; Computer science; Weighting; Generalization; Domain (mathematical analysis); Dynamic programming; Artificial intelligence; Pattern recognition (psychology); Speech processing; Algorithm; Mathematics","score_opus":0.026997126286302024,"score_gpt":0.2480160064840671,"score_spread":0.22101888019776508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1527831725","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002250966,0.00031810623,0.99815,0.000088834866,0.000042416264,0.000009235599,0.00002562219,0.00007848073,0.0010623203],"genre_scores_gemma":[0.06422395,0.0032117702,0.9247324,0.00041952144,0.00049790053,0.0004126469,0.00039055193,0.0002868751,0.005824296],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99880004,0.0003697222,0.00010988202,0.00029979073,0.00035331695,0.0000672748],"domain_scores_gemma":[0.99855524,0.0010026507,0.0001033709,0.00015262987,0.00015519024,0.000030871197],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019978476,0.0013155155,0.0011203245,0.0010543163,0.00072703674,0.0022387945,0.0018748759,0.001828466,0.0050930437],"category_scores_gemma":[0.005498878,0.0011352911,0.0014626189,0.0015953728,0.0024427117,0.0029924589,0.0018944679,0.002557851,0.0023833162],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045960598,0.00003739579,0.00021872063,0.0002582818,0.00006698677,0.00012423546,0.0002081376,0.12898779,0.0043544755,0.73128366,0.005592748,0.12882167],"study_design_scores_gemma":[0.000014652044,0.000055490113,0.00022885909,0.000091771035,0.000035627687,0.00015728071,0.000030073565,0.45100096,0.0028932472,0.5271436,0.018294608,0.000053857286],"about_ca_topic_score_codex":0.0021597391,"about_ca_topic_score_gemma":0.0020635664,"teacher_disagreement_score":0.0050930437,"about_ca_system_score_codex":0.0012561249,"about_ca_system_score_gemma":0.0010712424,"threshold_uncertainty_score":0.017037928},"labels":[],"label_agreement":null},{"id":"W1529062431","doi":"10.1002/9781118561911.ch7","title":"Voice Biometrics: Speaker Verification and Identification","year":2012,"lang":"en","type":"other","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université du Québec; Université de Moncton; Université du Québec à Montréal","funders":"","keywords":"Speaker recognition; Biometrics; Speech recognition; Speaker identification; Computer science; Speaker verification; Identification (biology); Artificial intelligence","score_opus":0.025402642770240055,"score_gpt":0.24913427525055878,"score_spread":0.22373163248031874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1529062431","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0071133957,0.10730668,0.70860124,0.0020209984,0.0064618625,0.00064738037,0.0029106182,0.010047092,0.15489067],"genre_scores_gemma":[0.050141495,0.13208392,0.24773814,0.0012607991,0.004986099,0.0008684701,0.011312358,0.0025713118,0.54903746],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985185,0.0002108757,0.000115121824,0.00024103072,0.00084214844,0.000072364404],"domain_scores_gemma":[0.9985625,0.00036193168,0.00006466809,0.00019739299,0.0007779804,0.000035539364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010501122,0.0012776837,0.0013130202,0.002279943,0.0007132571,0.0021437274,0.0012155958,0.0015602583,0.035970803],"category_scores_gemma":[0.0022405025,0.00060915947,0.00047417308,0.00318774,0.0005768921,0.0020837707,0.0010708816,0.001030649,0.048679374],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005862106,0.00004363694,0.00025246685,0.00072757865,0.000025614432,0.00007575183,0.000077750396,0.001086813,0.010620664,0.0045699435,0.07391222,0.90854895],"study_design_scores_gemma":[0.000018626715,0.00019761577,0.0037742942,0.0006587871,0.00007913746,0.0013957093,0.00016219798,0.011502453,0.041282132,0.008376617,0.93245846,0.00009406485],"about_ca_topic_score_codex":0.0015592693,"about_ca_topic_score_gemma":0.0020227635,"teacher_disagreement_score":0.035970803,"about_ca_system_score_codex":0.0005617662,"about_ca_system_score_gemma":0.0007969418,"threshold_uncertainty_score":0.12033433},"labels":[],"label_agreement":null},{"id":"W1532958172","doi":"10.1109/icassp.2005.1415194","title":"Factor Analysis Simplified","year":2006,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":94,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Factor (programming language); Programming language","score_opus":0.015439453837839722,"score_gpt":0.22813516016071944,"score_spread":0.2126957063228797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1532958172","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002107536,0.00024346808,0.9926643,0.00017015106,0.000106199026,0.00004939764,0.00021440195,0.001149968,0.0032944935],"genre_scores_gemma":[0.24062145,0.00097360066,0.7362797,0.00031968803,0.00028443732,0.00032749184,0.0016335442,0.0006977403,0.018862383],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998009,0.0006393531,0.00010064715,0.0006090297,0.00047802652,0.0001639372],"domain_scores_gemma":[0.9975515,0.0008239954,0.00015371983,0.00072580983,0.0006951599,0.000049789],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022659828,0.0016650923,0.00062539737,0.0009141236,0.00060359895,0.0017028118,0.0009013119,0.00090978167,0.019080587],"category_scores_gemma":[0.010812633,0.00035258816,0.0013357105,0.0011013304,0.0007822236,0.0019158316,0.00088301685,0.001477288,0.01468464],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034912172,0.000089819936,0.0028731392,0.0003159516,0.0002656705,0.00033877298,0.00044528747,0.06736342,0.018666113,0.2034093,0.028504549,0.6773788],"study_design_scores_gemma":[0.000055950437,0.0002177244,0.0027007272,0.00010543043,0.00011850177,0.00080716796,0.00019124003,0.6889562,0.022154894,0.18549462,0.099084914,0.00011271428],"about_ca_topic_score_codex":0.0041261213,"about_ca_topic_score_gemma":0.0024806808,"teacher_disagreement_score":0.019080587,"about_ca_system_score_codex":0.0005402888,"about_ca_system_score_gemma":0.0009138092,"threshold_uncertainty_score":0.06383091},"labels":[],"label_agreement":null},{"id":"W1543961788","doi":"10.1109/ccece.1995.526599","title":"A syllabic-filler-based continuous speech recognizer for unlimited vocabulary","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Speech recognition; Vocabulary; Syllabic verse; Hidden Markov model; Natural language processing; Artificial intelligence; Viterbi algorithm; Word (group theory); Context (archaeology); Audio mining; Speech processing; Acoustic model; Linguistics","score_opus":0.044705110074156264,"score_gpt":0.2341426591592357,"score_spread":0.18943754908507945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1543961788","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03277791,0.00061344623,0.9367746,0.00012782031,0.00024137908,0.0003369263,0.0005332919,0.022951452,0.0056431135],"genre_scores_gemma":[0.2326654,0.00026918936,0.74566716,0.00023507857,0.00014164504,0.00042662816,0.002149658,0.00094478764,0.017500486],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993037,0.000110078225,0.000062208084,0.00024131643,0.00022553762,0.00005716341],"domain_scores_gemma":[0.99872273,0.00043295693,0.000059057456,0.0003730973,0.0003117871,0.00010035182],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071045914,0.00043593737,0.0008036359,0.00052308245,0.00045147544,0.00068151427,0.0015221577,0.001183238,0.011629584],"category_scores_gemma":[0.0016197383,0.00040291116,0.00051269337,0.00029668031,0.00040258715,0.000947475,0.0005883816,0.0009948906,0.010207816],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012653655,0.00028009765,0.000922046,0.0002722261,0.00009085786,0.0005179401,0.00017607311,0.004033749,0.41835994,0.0053402423,0.010649588,0.5580918],"study_design_scores_gemma":[0.00039492993,0.002915036,0.0077788723,0.00009237013,0.00043831856,0.0067213266,0.00012188986,0.45161238,0.44240606,0.0045702467,0.08261915,0.00032942792],"about_ca_topic_score_codex":0.0017978735,"about_ca_topic_score_gemma":0.0023408048,"teacher_disagreement_score":0.011629584,"about_ca_system_score_codex":0.0002437731,"about_ca_system_score_gemma":0.0005282326,"threshold_uncertainty_score":0.038904846},"labels":[],"label_agreement":null},{"id":"W1556470778","doi":"","title":"Prosodylab-aligner: A tool for forced alignment of laboratory speech","year":2011,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":228,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Computer science; Hidden Markov model; Unix; Scripting language; Speech recognition; Operating system; Process (computing); Computer graphics (images); Software","score_opus":0.02785983580016489,"score_gpt":0.21887743944143986,"score_spread":0.19101760364127499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1556470778","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00273416,0.00024176476,0.75829923,0.00013526074,0.00042476022,0.00025843194,0.019426301,0.21319184,0.005288276],"genre_scores_gemma":[0.028833663,0.00019166079,0.8366712,0.00023380603,0.00018856955,0.0016148718,0.052798063,0.06843407,0.011034278],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99818665,0.00041742102,0.00019085935,0.0006257382,0.0004517428,0.00012758674],"domain_scores_gemma":[0.99714005,0.0013051245,0.00022255321,0.00061537465,0.0005451412,0.00017181972],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031113115,0.0025915697,0.0014480161,0.0029299327,0.0014641254,0.0022612873,0.0028159693,0.0014873622,0.19185047],"category_scores_gemma":[0.010140286,0.0016735205,0.001187332,0.0016626684,0.0005538366,0.0030208244,0.0038715291,0.0027148642,0.09114804],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009072715,0.0001756455,0.0012402801,0.0010202961,0.00019465877,0.00062896934,0.00068936485,0.0035645436,0.051510688,0.0059015867,0.38318956,0.55097705],"study_design_scores_gemma":[0.0005686095,0.00046868407,0.008583353,0.00033180555,0.00014903225,0.0026081696,0.00069030205,0.15106006,0.13112381,0.028121544,0.6757885,0.000506062],"about_ca_topic_score_codex":0.0014070676,"about_ca_topic_score_gemma":0.0024320774,"teacher_disagreement_score":0.19185047,"about_ca_system_score_codex":0.00045128158,"about_ca_system_score_gemma":0.001130962,"threshold_uncertainty_score":0.64180374},"labels":[],"label_agreement":null},{"id":"W1560330215","doi":"","title":"Speaker identification by computer and human evaluated on the SPIDRE corpus","year":2000,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Handset; Confusion; Speech recognition; Identification (biology); Set (abstract data type); Speaker identification; Computer science; Speaker recognition; Block (permutation group theory); Speaker diarisation; Telecommunications; Mathematics; Psychology","score_opus":0.019226333859752205,"score_gpt":0.22697263187271016,"score_spread":0.20774629801295796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1560330215","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9254212,0.003348308,0.032334156,0.0002615828,0.00034207696,0.0008895211,0.011803681,0.005206869,0.020392602],"genre_scores_gemma":[0.8875615,0.0010665917,0.062119953,0.00020315898,0.00022629963,0.0010011172,0.030003602,0.00062984147,0.017188055],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.997609,0.00079699676,0.00033926556,0.00063851924,0.00049939676,0.000116857635],"domain_scores_gemma":[0.9960962,0.0020922192,0.0001371725,0.0007377933,0.000838523,0.00009813069],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028512,0.0008437668,0.0010446426,0.00197978,0.00055623887,0.0013768491,0.00057488395,0.00096303155,0.013816978],"category_scores_gemma":[0.005260011,0.00017501948,0.00024093282,0.0008349956,0.00069202215,0.001406292,0.0011666901,0.00036800766,0.0057720207],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0043618586,0.0014944397,0.021654652,0.0021771295,0.00029810535,0.0012431723,0.0024324097,0.010751554,0.16073145,0.0017071855,0.02487451,0.76827353],"study_design_scores_gemma":[0.00075006,0.0072715823,0.29434043,0.00026726953,0.00046366476,0.009250142,0.0056923586,0.13761258,0.45395437,0.0040321853,0.085715115,0.0006502288],"about_ca_topic_score_codex":0.00248997,"about_ca_topic_score_gemma":0.0026725216,"teacher_disagreement_score":0.013816978,"about_ca_system_score_codex":0.0002945415,"about_ca_system_score_gemma":0.00025838133,"threshold_uncertainty_score":0.04622239},"labels":[],"label_agreement":null},{"id":"W1563583513","doi":"10.1109/cccrv.2004.1301488","title":"Categorization and learning of pen motion using hidden Markov models","year":2004,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Hidden Markov model; Artificial intelligence; Categorization; Categorical variable; Pattern recognition (psychology); Motion (physics); Segmentation; Feature extraction; Representation (politics); Computer vision; Gesture; Speech recognition; Machine learning","score_opus":0.035867179137375055,"score_gpt":0.2423057353273397,"score_spread":0.20643855618996465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1563583513","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07752589,0.00082474813,0.9188294,0.00031217854,0.00006525019,0.00008939788,0.0002924308,0.000872002,0.0011887125],"genre_scores_gemma":[0.8194625,0.00072408974,0.17481859,0.00015769301,0.00008996703,0.0001390044,0.0011998533,0.00007785738,0.0033304063],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995141,0.00015314345,0.000028876624,0.0001659195,0.0000749941,0.00006307908],"domain_scores_gemma":[0.9986481,0.0008967861,0.00014807557,0.00012380593,0.00012735644,0.000055821536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009474195,0.00064400316,0.0007209717,0.0014770644,0.00033871876,0.0009144216,0.00084775395,0.0007200035,0.0013553972],"category_scores_gemma":[0.0027341868,0.00040813786,0.0008427423,0.0008397363,0.00048473402,0.001337554,0.000533479,0.0012036441,0.00051068974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003797965,0.0003362613,0.014106782,0.00021325609,0.00015778432,0.00028230593,0.0003836476,0.30850977,0.011693659,0.01434782,0.0033024128,0.6462865],"study_design_scores_gemma":[0.00000605464,0.00003831361,0.0013009823,0.000017293276,0.000009459852,0.000028303917,0.000025869162,0.9894371,0.0013315815,0.0072963876,0.00049903605,0.000009630787],"about_ca_topic_score_codex":0.004488764,"about_ca_topic_score_gemma":0.005030533,"teacher_disagreement_score":0.004488764,"about_ca_system_score_codex":0.0007375143,"about_ca_system_score_gemma":0.00048125134,"threshold_uncertainty_score":0.008925259},"labels":[],"label_agreement":null},{"id":"W1565000507","doi":"10.1109/icassp.2015.7178921","title":"Multi-lingual speech recognition with low-rank multi-task deep neural networks","year":2015,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Speech recognition; Task (project management); Artificial neural network; Deep neural networks; Rank (graph theory); Artificial intelligence; Time delay neural network; Deep learning; Natural language processing; Pattern recognition (psychology); Mathematics; Engineering","score_opus":0.055310939327397494,"score_gpt":0.266749287209576,"score_spread":0.21143834788217852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1565000507","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038384255,0.0013367874,0.9462593,0.0003960689,0.00017868287,0.000119108845,0.00074334984,0.008809064,0.0037733037],"genre_scores_gemma":[0.4318643,0.00057644135,0.5565564,0.00034216297,0.0001841414,0.00024871528,0.002982424,0.0003837866,0.0068615377],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992718,0.00020397644,0.000040731415,0.00019215046,0.00020574746,0.000085649786],"domain_scores_gemma":[0.99933296,0.00022701378,0.00006788192,0.00016690997,0.00016122009,0.000044002627],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001035807,0.0018531228,0.000826514,0.000658581,0.00044080938,0.0011226118,0.0016082244,0.0012429707,0.0057094144],"category_scores_gemma":[0.0027950916,0.0005342708,0.00075597997,0.00082768156,0.0003754413,0.0020910944,0.0019100814,0.001948726,0.003787692],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037101927,0.00037061842,0.0009148908,0.00024346638,0.00017456767,0.00020892815,0.00012580786,0.16728702,0.02636456,0.0037510486,0.012436671,0.7877513],"study_design_scores_gemma":[0.000012285073,0.000065834225,0.00024150638,0.000009352749,0.0000143289535,0.00005795091,0.000026239442,0.9879836,0.00803444,0.0019491597,0.0015877172,0.000017504126],"about_ca_topic_score_codex":0.006295296,"about_ca_topic_score_gemma":0.01661416,"teacher_disagreement_score":0.006295296,"about_ca_system_score_codex":0.00077179505,"about_ca_system_score_gemma":0.0008548651,"threshold_uncertainty_score":0.019099891},"labels":[],"label_agreement":null},{"id":"W156741778","doi":"10.1007/978-3-319-06483-3_38","title":"Effects of Frequency-Based Inter-frame Dependencies on Automatic Speech Recognition","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Hidden Markov model; Computer science; Speech recognition; Concatenation (mathematics); Independence (probability theory); Frame (networking); Artificial intelligence; Pattern recognition (psychology); State (computer science); Conditional independence; Natural language processing; Algorithm; Mathematics","score_opus":0.01700488331830339,"score_gpt":0.23309256416691512,"score_spread":0.21608768084861174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W156741778","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6553122,0.005152289,0.3154952,0.00050051,0.00083467865,0.00011301826,0.0016789897,0.0035598914,0.017353194],"genre_scores_gemma":[0.91372424,0.0037242097,0.06830089,0.00022866785,0.00037819537,0.000079716265,0.0025667544,0.001809185,0.009188225],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990681,0.00023151575,0.00005546202,0.00019484204,0.00034410314,0.00010606519],"domain_scores_gemma":[0.98538893,0.012735271,0.00037336544,0.0005562044,0.0007757834,0.00017049519],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009350405,0.0012492564,0.00075423927,0.00068083033,0.0005158097,0.0008092387,0.0005187107,0.0009810171,0.008199954],"category_scores_gemma":[0.010042029,0.00068390503,0.0004682089,0.0008312157,0.0004620113,0.0015329812,0.000653529,0.0012601201,0.0024646441],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004923979,0.0002822726,0.0022734257,0.0005019115,0.00011821718,0.000934824,0.00024960836,0.039539535,0.6656958,0.0020196743,0.0023368439,0.2811239],"study_design_scores_gemma":[0.00011406528,0.0010316031,0.053663783,0.0001630712,0.00085639645,0.0022690948,0.00019984135,0.37093875,0.56062376,0.003086153,0.006911023,0.00014243196],"about_ca_topic_score_codex":0.0029493535,"about_ca_topic_score_gemma":0.005307642,"teacher_disagreement_score":0.008199954,"about_ca_system_score_codex":0.00037032197,"about_ca_system_score_gemma":0.00060626114,"threshold_uncertainty_score":0.027431607},"labels":[],"label_agreement":null},{"id":"W1573256281","doi":"10.1109/icassp.1987.1169587","title":"Specifying intonation in a text-to-speech system using only a small dictionary","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Intonation (linguistics); Sentence; Parsing; Natural language processing; Artificial intelligence; Speech synthesis; Set (abstract data type); Speech recognition; Linguistics; Programming language","score_opus":0.046446059321591515,"score_gpt":0.2596009731072042,"score_spread":0.2131549137856127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1573256281","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10044353,0.00028567793,0.8849595,0.00012436062,0.00006543596,0.00020658855,0.00058140315,0.008756049,0.004577532],"genre_scores_gemma":[0.35805714,0.00035808553,0.6334592,0.00015788425,0.000038853603,0.0003871942,0.0012298835,0.0010681879,0.005243523],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99950993,0.000109337416,0.000108105036,0.00016849468,0.00007537044,0.000028772814],"domain_scores_gemma":[0.998847,0.00083131844,0.000051086794,0.0001201695,0.00011585168,0.000034591027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006018139,0.00064499734,0.0007951478,0.00035436457,0.00045137707,0.0011822613,0.0007293518,0.00074989616,0.0044400548],"category_scores_gemma":[0.002353993,0.0007146915,0.00036850284,0.00043487086,0.0005446505,0.0025319422,0.00074054307,0.0005138585,0.002826872],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016464277,0.0001524963,0.0022919504,0.0010135388,0.000063643376,0.0010943704,0.0025474702,0.03491173,0.56181484,0.025172163,0.0037450672,0.36554638],"study_design_scores_gemma":[0.0005290606,0.00048817752,0.0016110037,0.00009493403,0.00021612129,0.0013622841,0.00081128656,0.35028067,0.55980384,0.023575356,0.06102236,0.00020488216],"about_ca_topic_score_codex":0.00081460684,"about_ca_topic_score_gemma":0.0020734416,"teacher_disagreement_score":0.0044400548,"about_ca_system_score_codex":0.00029546316,"about_ca_system_score_gemma":0.0004269805,"threshold_uncertainty_score":0.014853537},"labels":[],"label_agreement":null},{"id":"W1577476315","doi":"","title":"Better analysis for automatic speech recognition","year":2002,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Speech recognition; Computer science; Linear predictive coding; Speech coding; Linear prediction; Speech processing; Coding (social sciences); Filter (signal processing); Voice activity detection; Ideal (ethics); Artificial intelligence; Mathematics; Computer vision","score_opus":0.046145550814051445,"score_gpt":0.22786070183211787,"score_spread":0.18171515101806643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1577476315","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003154422,0.006841018,0.9750636,0.0006491734,0.0005343434,0.000107165164,0.00028238783,0.0029253005,0.010442539],"genre_scores_gemma":[0.06015136,0.005408663,0.89715534,0.0009648197,0.00076958595,0.00024439732,0.0014626611,0.0010483016,0.0327948],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99707866,0.0008105333,0.00023428629,0.0007301683,0.0010255793,0.00012087165],"domain_scores_gemma":[0.9971355,0.00070584635,0.00011825408,0.00066980097,0.0013199564,0.000050659597],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002406414,0.0017553061,0.0012535475,0.0022527925,0.0008928057,0.0023917619,0.0009290277,0.0018611567,0.02929425],"category_scores_gemma":[0.0044961064,0.00063738594,0.0010662936,0.0018100395,0.0007228388,0.0036948535,0.0011092827,0.0014938413,0.019751493],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004452858,0.00010888247,0.0004906313,0.0006116447,0.00012066901,0.00021513258,0.0001789403,0.009375574,0.12957019,0.08291708,0.027391933,0.74857396],"study_design_scores_gemma":[0.00011163345,0.00047910426,0.0024664446,0.0004260888,0.00024829066,0.0016755675,0.00019404177,0.22880353,0.18240991,0.08115735,0.5017895,0.00023852549],"about_ca_topic_score_codex":0.00094854174,"about_ca_topic_score_gemma":0.00092993764,"teacher_disagreement_score":0.02929425,"about_ca_system_score_codex":0.0007582389,"about_ca_system_score_gemma":0.0006510274,"threshold_uncertainty_score":0.09799904},"labels":[],"label_agreement":null},{"id":"W1577971346","doi":"10.1016/j.patrec.2008.12.013","title":"-Gaussian mixture modelling for speaker recognition","year":2009,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Mixture model; Computer science; Speech recognition; Speaker recognition; Set (abstract data type); Pattern recognition (psychology); Gaussian process; Artificial intelligence; Gaussian; Process (computing)","score_opus":0.04911657388391709,"score_gpt":0.24529012247867654,"score_spread":0.19617354859475944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1577971346","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013059322,0.00082535367,0.9949797,0.0001020677,0.00014312353,0.000018700282,0.00021472463,0.0017345338,0.0006759888],"genre_scores_gemma":[0.174116,0.0033420774,0.7875646,0.00043271534,0.00041786465,0.00028772574,0.0047068857,0.0016271216,0.027504994],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99854493,0.0005516699,0.00007448816,0.0003342641,0.00036032093,0.00013426716],"domain_scores_gemma":[0.99882025,0.0005447553,0.000045983612,0.0002682844,0.0002892498,0.00003151649],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017806963,0.0014892501,0.0017429314,0.0009974213,0.00064043567,0.001213748,0.0018753962,0.0022018494,0.006766401],"category_scores_gemma":[0.0033580384,0.000923569,0.0024105601,0.0017082585,0.00061178824,0.0018342913,0.0016526498,0.0022871895,0.0113714775],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005026709,0.0001736009,0.0010310537,0.0003695241,0.00045952218,0.00022097469,0.00015136457,0.18393208,0.023008246,0.03013948,0.016653422,0.7433581],"study_design_scores_gemma":[0.0000140951715,0.000029104222,0.00075987657,0.000028147992,0.000057714027,0.00014773183,0.000019307106,0.96535194,0.006722972,0.020040872,0.006790427,0.00003782023],"about_ca_topic_score_codex":0.0067178644,"about_ca_topic_score_gemma":0.0065503526,"teacher_disagreement_score":0.006766401,"about_ca_system_score_codex":0.0005593352,"about_ca_system_score_gemma":0.00090234826,"threshold_uncertainty_score":0.022635877},"labels":[],"label_agreement":null},{"id":"W1582122176","doi":"10.5772/6376","title":"Practical Issues of Building Robust HMM Models Using HTK and SPHINX Systems","year":2008,"lang":"en","type":"book-chapter","venue":"InTech eBooks","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sphinx; Hidden Markov model; Computer science; Artificial intelligence; Pattern recognition (psychology); Geography","score_opus":0.15384614204963004,"score_gpt":0.31019928073344255,"score_spread":0.1563531386838125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1582122176","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002344487,0.0004949243,0.9915495,0.0003141604,0.00007721517,0.000036133424,0.00011859643,0.0034884615,0.0015766057],"genre_scores_gemma":[0.10119848,0.0010562114,0.8893231,0.0002462596,0.00016597098,0.0001769821,0.0006664514,0.0011042878,0.006062325],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99803,0.000863547,0.0001385664,0.00036287162,0.0005166218,0.000088309556],"domain_scores_gemma":[0.9949502,0.0032215726,0.00013125852,0.0009422778,0.00068377313,0.00007092605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003747154,0.0010848023,0.0016141913,0.000625254,0.0007285762,0.002185307,0.0023732495,0.002319515,0.011956663],"category_scores_gemma":[0.010867033,0.0016001855,0.00090450235,0.0007868756,0.00092507416,0.004024225,0.0016194577,0.0021579056,0.010601188],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003834636,0.000073665324,0.000875698,0.0005786813,0.00016913374,0.00034022762,0.0004051164,0.29281288,0.019751977,0.037191063,0.0124546895,0.63496345],"study_design_scores_gemma":[0.000041960786,0.00006292468,0.00084357406,0.00008995279,0.000052161417,0.00027333887,0.00016031062,0.9390678,0.0129956305,0.031743705,0.014588621,0.000080098886],"about_ca_topic_score_codex":0.00693808,"about_ca_topic_score_gemma":0.00656212,"teacher_disagreement_score":0.011956663,"about_ca_system_score_codex":0.0008410436,"about_ca_system_score_gemma":0.0010187718,"threshold_uncertainty_score":0.03999901},"labels":[],"label_agreement":null},{"id":"W1588166307","doi":"10.1007/978-3-540-24840-8_61","title":"An Investigation of Grammar Design in Natural-Language Speech Recognition","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Robustness (evolution); Speech recognition; Natural language; Natural language processing; Grammar; Artificial intelligence; Linguistics","score_opus":0.02942735014565632,"score_gpt":0.2518051128363049,"score_spread":0.2223777626906486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1588166307","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051267732,0.0009865143,0.93316597,0.00087648316,0.000069738686,0.00013656764,0.000082114435,0.00078211294,0.012632718],"genre_scores_gemma":[0.507715,0.00089485483,0.48435837,0.00027972754,0.000081531514,0.0001301283,0.00022056044,0.0005285927,0.0057912488],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99717283,0.001499978,0.00019325553,0.00042878513,0.0005566441,0.0001483526],"domain_scores_gemma":[0.98444194,0.012740632,0.00055735785,0.0010387267,0.0010854373,0.00013601604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032443795,0.00033865173,0.00065840624,0.00071490393,0.00076911115,0.0026183682,0.0013965985,0.0012140804,0.0034971035],"category_scores_gemma":[0.019576741,0.0009587375,0.0008843161,0.0009658834,0.0029263312,0.004811065,0.00092114136,0.0014909201,0.0008339504],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018384945,0.00016489401,0.0035658388,0.0005577282,0.000046285535,0.00045063466,0.0024896152,0.04361534,0.019076679,0.63211346,0.0025506513,0.295185],"study_design_scores_gemma":[0.00006313404,0.00019986287,0.0010911054,0.0001135441,0.00007591069,0.00061052147,0.0007899485,0.31241438,0.017735438,0.65247566,0.014385044,0.000045456745],"about_ca_topic_score_codex":0.0018985312,"about_ca_topic_score_gemma":0.002065995,"teacher_disagreement_score":0.0034971035,"about_ca_system_score_codex":0.00118238,"about_ca_system_score_gemma":0.0014356688,"threshold_uncertainty_score":0.01715815},"labels":[],"label_agreement":null},{"id":"W1589469711","doi":"10.5772/6388","title":"Normalization and Transformation Techniques for Robust Speaker Recognition","year":2008,"lang":"en","type":"book-chapter","venue":"InTech eBooks","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Speaker recognition; Normalization (sociology); Speech recognition; Computer science; Speaker diarisation; Identity (music); Task (project management); Artificial intelligence; Pattern recognition (psychology); Frame (networking); Feature (linguistics); Transformation (genetics); Linguistics; Engineering","score_opus":0.05414298100150217,"score_gpt":0.23917453223290874,"score_spread":0.18503155123140658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1589469711","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021802175,0.0026552416,0.98011655,0.00027147488,0.00037676722,0.00012447579,0.000373673,0.0034657542,0.010435892],"genre_scores_gemma":[0.066747926,0.0061595044,0.8832614,0.0005118273,0.0006925392,0.0006545749,0.0031712563,0.001648151,0.037152957],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9980259,0.00021780307,0.00013628625,0.0005005843,0.0010130273,0.00010628711],"domain_scores_gemma":[0.9991359,0.00019182847,0.000070814065,0.00020354686,0.00038178946,0.000016194736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012531303,0.0011872352,0.0012433443,0.0018903284,0.00080156437,0.0011564608,0.0017625433,0.001069075,0.01907858],"category_scores_gemma":[0.0030442828,0.00056948164,0.0016457033,0.0026574149,0.0007732265,0.0018314787,0.001038408,0.0021228439,0.021751955],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001225263,0.000063392064,0.00039763673,0.0003613654,0.00008898044,0.00021992272,0.00017110912,0.012450603,0.064550824,0.02558838,0.02022728,0.87575805],"study_design_scores_gemma":[0.00005841912,0.00026632485,0.0061619002,0.00027424382,0.0001553339,0.0030887465,0.0002812192,0.35663223,0.13473877,0.050585724,0.4474829,0.00027422525],"about_ca_topic_score_codex":0.0026483133,"about_ca_topic_score_gemma":0.0028284977,"teacher_disagreement_score":0.01907858,"about_ca_system_score_codex":0.00076688634,"about_ca_system_score_gemma":0.00088670716,"threshold_uncertainty_score":0.06382424},"labels":[],"label_agreement":null},{"id":"W1597208282","doi":"10.1109/icassp.2015.7178806","title":"Speaker change point detection using deep neural nets","year":2015,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Speaker diarisation; Change detection; Computer science; Speech recognition; Frame (networking); Artificial neural network; Point (geometry); Set (abstract data type); Speaker recognition; Test set; Speech processing; Word error rate; Voice activity detection; Artificial intelligence; Mathematics; Telecommunications","score_opus":0.1755712714818029,"score_gpt":0.28642138628171554,"score_spread":0.11085011479991264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1597208282","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57662314,0.0010355412,0.41245618,0.00040289955,0.0001458302,0.000112689486,0.0006418597,0.003327333,0.005254503],"genre_scores_gemma":[0.92043763,0.00013067527,0.07643013,0.00009926254,0.000026696742,0.000026574357,0.0006066903,0.00007620629,0.0021662218],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992482,0.00017302297,0.000041602845,0.00020575282,0.00022496743,0.00010638421],"domain_scores_gemma":[0.99808866,0.0010899098,0.00013504317,0.00013038114,0.00047758166,0.00007840738],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013305431,0.0008346555,0.0004767687,0.00097105553,0.0003059816,0.00063801004,0.00065870467,0.00056214514,0.0017576555],"category_scores_gemma":[0.0036181908,0.00027246433,0.0003890297,0.0004115753,0.0002536826,0.00082882756,0.0005398001,0.00087025505,0.00064019527],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016001542,0.00036843508,0.02336141,0.00017704636,0.00027724265,0.00041343304,0.00030760572,0.24890229,0.11754418,0.0016445544,0.0031002422,0.6023034],"study_design_scores_gemma":[0.000016529906,0.000116703566,0.0054663215,0.0000076178917,0.000033749868,0.00008955964,0.00004467218,0.9577801,0.035046626,0.00060639955,0.0007724821,0.000019260415],"about_ca_topic_score_codex":0.011319473,"about_ca_topic_score_gemma":0.014213816,"teacher_disagreement_score":0.011319473,"about_ca_system_score_codex":0.0008357542,"about_ca_system_score_gemma":0.00043841946,"threshold_uncertainty_score":0.022507131},"labels":[],"label_agreement":null},{"id":"W1599370399","doi":"10.22215/etd/2005-07974","title":"Speaker recognition in reverberant environments","year":2005,"lang":"en","type":"dissertation","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Reverberation; Speech recognition; Autoregressive model; Covariance; Computer science; Measure (data warehouse); Divergence (linguistics); Mixture model; Perceptron; Hidden Markov model; Pattern recognition (psychology); Speaker recognition; Artificial intelligence; Acoustics; Artificial neural network; Mathematics; Statistics","score_opus":0.020984961485154177,"score_gpt":0.24283301073382352,"score_spread":0.22184804924866935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1599370399","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4913456,0.0021084426,0.471401,0.0005868235,0.000829761,0.00011913167,0.00092532905,0.008688729,0.023995213],"genre_scores_gemma":[0.79967785,0.0016756562,0.11703601,0.00027836717,0.0005024629,0.00009899688,0.0019285157,0.0010580424,0.0777441],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99961805,0.00010287773,0.000013294101,0.00011607741,0.0000904048,0.000059204445],"domain_scores_gemma":[0.9995177,0.00020740408,0.000020146117,0.000063703555,0.0001452065,0.00004580377],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046116606,0.00062548555,0.0006326911,0.00034681952,0.00033059935,0.00084261707,0.00048598618,0.0007021687,0.009189873],"category_scores_gemma":[0.0013731525,0.00026363716,0.00039339386,0.00017154423,0.00024959302,0.0006733439,0.0005505384,0.00061000977,0.007269368],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001378321,0.00012669376,0.0027511176,0.0002690705,0.0001540366,0.0013968322,0.0010510603,0.0138580315,0.53289765,0.0016333613,0.009762646,0.43472114],"study_design_scores_gemma":[0.00014318644,0.0009916258,0.027699955,0.00007614843,0.0003457007,0.0039032362,0.0012427003,0.29087707,0.6370814,0.003175962,0.034329355,0.00013369501],"about_ca_topic_score_codex":0.0015634141,"about_ca_topic_score_gemma":0.0025655462,"teacher_disagreement_score":0.009189873,"about_ca_system_score_codex":0.00016212184,"about_ca_system_score_gemma":0.00020497445,"threshold_uncertainty_score":0.030743182},"labels":[],"label_agreement":null},{"id":"W1600818689","doi":"10.1109/icassp.1983.1172259","title":"Further experiments in text-independent speaker recognition over communications channels","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Speech recognition; Computer science; Set (abstract data type); Noise (video); Cepstrum; Variation (astronomy); Speaker recognition; Mel-frequency cepstrum; Telephony; Data set; Pattern recognition (psychology); Feature extraction; Artificial intelligence; Telecommunications","score_opus":0.06782045268047239,"score_gpt":0.30437250612255395,"score_spread":0.23655205344208158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1600818689","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9319054,0.000280856,0.06128048,0.00026318617,0.0001320253,0.0009405867,0.00071730174,0.0017892733,0.0026909427],"genre_scores_gemma":[0.93107814,0.00029650357,0.058329947,0.0002773997,0.000068674795,0.00082832045,0.0023276894,0.00027217885,0.0065211044],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9960074,0.0012109574,0.00035539904,0.000788064,0.0011503162,0.00048799143],"domain_scores_gemma":[0.98847735,0.0076720044,0.0002988198,0.0013385586,0.0018165063,0.00039670244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032028211,0.0013019639,0.0017332465,0.00056466716,0.0013347486,0.0009850449,0.0016807193,0.001965548,0.004781041],"category_scores_gemma":[0.012591812,0.00053666014,0.0009891504,0.0010602842,0.0007708476,0.0012668028,0.001043542,0.0015726703,0.001720476],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.015003186,0.007507948,0.006576913,0.0018168334,0.0006783558,0.0029145656,0.0033059127,0.07378251,0.6426239,0.0015946532,0.005088515,0.23910676],"study_design_scores_gemma":[0.0023050332,0.023047652,0.02293397,0.000091578986,0.0008189457,0.0036395593,0.0013459552,0.21878442,0.71588385,0.0025573575,0.008098514,0.00049317814],"about_ca_topic_score_codex":0.005730849,"about_ca_topic_score_gemma":0.002345011,"teacher_disagreement_score":0.005730849,"about_ca_system_score_codex":0.00046465397,"about_ca_system_score_gemma":0.00037307685,"threshold_uncertainty_score":0.016938388},"labels":[],"label_agreement":null},{"id":"W1603105762","doi":"10.1109/icassp.2015.7178988","title":"Document-specific context plsa language model for speech recognition","year":2015,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Bigram; Perplexity; Computer science; Natural language processing; Artificial intelligence; Language model; Word error rate; Word (group theory); Context (archaeology); Speech recognition; Probabilistic latent semantic analysis; Context model; Probabilistic logic; Linguistics","score_opus":0.10465832487019365,"score_gpt":0.29118332861545226,"score_spread":0.1865250037452586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1603105762","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004924855,0.00087384926,0.98963237,0.0003702986,0.00014661512,0.00006167275,0.0008847876,0.0018360723,0.0012695257],"genre_scores_gemma":[0.42039567,0.0025820485,0.54843324,0.00087030407,0.0006036462,0.0010806449,0.004893651,0.00088820583,0.020252641],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896884,0.00041169336,0.00006473163,0.00029332607,0.00019661734,0.00006481168],"domain_scores_gemma":[0.9988255,0.0006623251,0.00009454649,0.0001367964,0.00025227672,0.000028512706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012194441,0.001184914,0.0010731483,0.0009441642,0.0004155831,0.0010546759,0.002023444,0.0013134324,0.0048796926],"category_scores_gemma":[0.0025778238,0.0006270049,0.0016784206,0.0015142405,0.0005086649,0.0017952003,0.0008646676,0.0026105002,0.0050884187],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00056188373,0.00024503592,0.0016193346,0.0005130162,0.0004390383,0.00040298543,0.0003259311,0.52424634,0.01669827,0.0762774,0.014751367,0.36391947],"study_design_scores_gemma":[0.000011584184,0.000029755229,0.00015436184,0.000009597034,0.000026394677,0.000059609032,0.0000107439255,0.98397243,0.000817621,0.012483323,0.0024072803,0.00001737341],"about_ca_topic_score_codex":0.004292514,"about_ca_topic_score_gemma":0.0065642027,"teacher_disagreement_score":0.0048796926,"about_ca_system_score_codex":0.00088850356,"about_ca_system_score_gemma":0.0011884419,"threshold_uncertainty_score":0.016324162},"labels":[],"label_agreement":null},{"id":"W1607690733","doi":"10.1109/ccece.2015.7129496","title":"A study on dimensions of feature space for text-independent speaker verification systems","year":2015,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Normalization (sociology); Computer science; TIMIT; Mel-frequency cepstrum; Speech recognition; Pattern recognition (psychology); Feature vector; Artificial intelligence; Feature extraction; Feature (linguistics); Speaker verification; Speaker recognition; Hidden Markov model","score_opus":0.07998948450069451,"score_gpt":0.2978836968724527,"score_spread":0.21789421237175818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1607690733","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45286345,0.006090845,0.5368884,0.00044370317,0.00012967947,0.000206755,0.0002251501,0.00087181485,0.0022801994],"genre_scores_gemma":[0.8613092,0.0008438603,0.13667326,0.00004553785,0.00006660023,0.00010425358,0.00030191813,0.000087272434,0.00056803745],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99467885,0.0027027302,0.00055799476,0.00063941506,0.0012704243,0.00015065692],"domain_scores_gemma":[0.9684948,0.024585746,0.0009152691,0.0029297231,0.002904686,0.000169703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039107553,0.0007744602,0.0007410591,0.0005036365,0.00047679167,0.0010558849,0.0005163451,0.00055086386,0.0012255897],"category_scores_gemma":[0.03217555,0.00031163206,0.0007866218,0.00092361175,0.0005505746,0.0025486278,0.00081953447,0.00092864444,0.00027609235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016735294,0.00032667004,0.0067816805,0.0006048675,0.00023655832,0.00017938149,0.00043635184,0.09254882,0.07031216,0.005914037,0.0011385758,0.8198474],"study_design_scores_gemma":[0.000084914915,0.0028878103,0.019360539,0.00014778765,0.00026814177,0.0009611202,0.00036751438,0.86174035,0.10307144,0.0051366743,0.005795357,0.00017838634],"about_ca_topic_score_codex":0.0009151541,"about_ca_topic_score_gemma":0.00083186623,"teacher_disagreement_score":0.0039107553,"about_ca_system_score_codex":0.00045943639,"about_ca_system_score_gemma":0.00036521623,"threshold_uncertainty_score":0.020682275},"labels":[],"label_agreement":null},{"id":"W1618069598","doi":"10.1109/icassp.1995.479661","title":"On the use of stochastic inference networks for representing multiple word pronunciations","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Science Council","keywords":"Computer science; Inference; Vocabulary; Speech recognition; Syllabic verse; Word (group theory); Artificial intelligence; Natural language processing; Linguistics","score_opus":0.1777085634039263,"score_gpt":0.2724514577590311,"score_spread":0.09474289435510483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1618069598","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019000212,0.00013620692,0.99717295,0.00005565919,0.000013029711,0.0000104681,0.000043333737,0.0002672793,0.00040096982],"genre_scores_gemma":[0.18547975,0.0010683732,0.809344,0.0001669587,0.00014874063,0.00026463138,0.0005394252,0.00023415836,0.0027538836],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999054,0.00039012908,0.000070030925,0.00018288802,0.00024193537,0.000060994684],"domain_scores_gemma":[0.99617344,0.003055574,0.00019742693,0.00024966433,0.00027103728,0.000052937856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022120136,0.00117982,0.00088112825,0.0009951892,0.00073408335,0.0019504414,0.00206885,0.0011275471,0.002326353],"category_scores_gemma":[0.00873369,0.0007153807,0.0010028902,0.001176928,0.0014805914,0.0031153935,0.0012508609,0.0019182146,0.0007899043],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013826952,0.000040951243,0.00078347384,0.000072435294,0.00010059926,0.0001283735,0.00017692802,0.7574162,0.0035417643,0.115447454,0.0010964981,0.12105711],"study_design_scores_gemma":[0.000005168815,0.000010030153,0.00006935433,0.000008179614,0.000009850327,0.00001804825,0.0000052545297,0.95972604,0.00049037783,0.038712494,0.00093372626,0.000011476455],"about_ca_topic_score_codex":0.011117,"about_ca_topic_score_gemma":0.014303243,"teacher_disagreement_score":0.011117,"about_ca_system_score_codex":0.0008375587,"about_ca_system_score_gemma":0.0010777321,"threshold_uncertainty_score":0.022104621},"labels":[],"label_agreement":null},{"id":"W1629536855","doi":"10.1109/icassp.1995.479602","title":"Improved speech modeling and recognition using multi-dimensional articulatory states as primitive speech units","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; TIMIT; Speech recognition; Asynchronous communication; Feature (linguistics); Context (archaeology); Task (project management); Artificial intelligence; Hidden Markov model; Natural language processing","score_opus":0.09840003892361633,"score_gpt":0.2645703920844242,"score_spread":0.16617035316080786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1629536855","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0086800195,0.000119415214,0.9897804,0.000023905397,0.000023027073,0.000025119822,0.000049414095,0.0008324574,0.00046618844],"genre_scores_gemma":[0.15158863,0.0003144912,0.84475714,0.000045971585,0.00006805599,0.00014521283,0.000336403,0.00015781866,0.0025861892],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99959666,0.00007691512,0.00004440414,0.0001083942,0.00014549593,0.00002805057],"domain_scores_gemma":[0.9995703,0.00015142452,0.000042429696,0.00015047973,0.000075040894,0.000010309315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055411825,0.00062649563,0.0006820581,0.00033897543,0.00021545951,0.00064004,0.0010008147,0.00048752775,0.0015628389],"category_scores_gemma":[0.0014521753,0.00035462462,0.0007218785,0.00028207438,0.00036478878,0.0011066219,0.0005118984,0.0008413594,0.0014268787],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003826693,0.00012754987,0.0011071858,0.00031523284,0.000079971964,0.0002505504,0.00018245289,0.21009444,0.3417511,0.018415902,0.00135659,0.42593637],"study_design_scores_gemma":[0.000013409705,0.0001780282,0.000757738,0.00001305938,0.00004618861,0.0002912855,0.000012761362,0.91143847,0.07824528,0.003340618,0.0056280755,0.000035207842],"about_ca_topic_score_codex":0.0010306097,"about_ca_topic_score_gemma":0.001961221,"teacher_disagreement_score":0.0015628389,"about_ca_system_score_codex":0.0001978553,"about_ca_system_score_gemma":0.0004582,"threshold_uncertainty_score":0.0052282214},"labels":[],"label_agreement":null},{"id":"W1633122917","doi":"10.5281/zenodo.42857","title":"Lda-Based Lm Adaptation Using Latent Semantic Marginals And Minimum Discriminant Information","year":2012,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Latent Dirichlet allocation; Perplexity; Computer science; Artificial intelligence; Probabilistic latent semantic analysis; Topic model; Linear discriminant analysis; Cluster analysis; Language model; Latent variable; Hidden Markov model; Word (group theory); Pattern recognition (psychology); Decoding methods; Word error rate; Speech recognition; Natural language processing; Mathematics; Algorithm","score_opus":0.0771586839017472,"score_gpt":0.25201567795297825,"score_spread":0.17485699405123106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1633122917","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006445832,0.00043591476,0.98766476,0.0001093441,0.00017404884,0.000043492168,0.00016493298,0.0025375197,0.0024241058],"genre_scores_gemma":[0.26184735,0.00076204044,0.7111821,0.00031201137,0.000290565,0.00051807385,0.002016339,0.0025005904,0.02057089],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992612,0.00033089667,0.00003544508,0.00016148793,0.00013962215,0.000071241455],"domain_scores_gemma":[0.9990778,0.00037760264,0.00003225528,0.00018497503,0.00028227197,0.000045041576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008405008,0.00101071,0.0010353433,0.0007498644,0.0005938244,0.0007719351,0.0010611254,0.0009913354,0.011525629],"category_scores_gemma":[0.002842292,0.00048595373,0.0013101969,0.00088333414,0.00047513907,0.001124788,0.0011811531,0.0013886509,0.008539965],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00069274666,0.000213863,0.00068298646,0.0002953339,0.00022094528,0.00016627971,0.0001703228,0.07549285,0.0865417,0.008005715,0.018626869,0.8088903],"study_design_scores_gemma":[0.000039006172,0.000051533054,0.0008459653,0.000023410881,0.00007204047,0.00011634691,0.000041084673,0.9721067,0.01653844,0.0037724562,0.006356295,0.00003674047],"about_ca_topic_score_codex":0.0025817044,"about_ca_topic_score_gemma":0.0064016525,"teacher_disagreement_score":0.011525629,"about_ca_system_score_codex":0.00035151298,"about_ca_system_score_gemma":0.00071018626,"threshold_uncertainty_score":0.038557053},"labels":[],"label_agreement":null},{"id":"W164170074","doi":"10.21437/interspeech.2005-141","title":"Augmented state space acoustic decoding for modeling local variability in speech","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Normalization (sociology); Speech recognition; Decoding methods; Image warping; Word error rate; Viterbi algorithm; Hidden Markov model; Dynamic time warping; Viterbi decoder; Artificial intelligence; Vocal tract; Language model; Context (archaeology); Computation; Pattern recognition (psychology); Algorithm","score_opus":0.03088791563739247,"score_gpt":0.2718763472945246,"score_spread":0.24098843165713213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W164170074","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00533113,0.00008068299,0.9937989,0.000024720906,0.000014427047,0.000007492574,0.000030543808,0.00031144702,0.00040058262],"genre_scores_gemma":[0.41602227,0.00052134675,0.57688826,0.00005761162,0.00008804316,0.00015388716,0.00038366235,0.00027329373,0.0056116325],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996687,0.00012197662,0.000017489407,0.00006058025,0.00011267371,0.00001862077],"domain_scores_gemma":[0.9993381,0.0004187958,0.00005176177,0.0000822105,0.000099090306,0.000010038708],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052191084,0.0007100063,0.0005734275,0.00027516024,0.00025647794,0.00058115035,0.0004979088,0.0005458268,0.001648301],"category_scores_gemma":[0.0026992399,0.00028333394,0.00037134386,0.00035551251,0.00039051153,0.0007471681,0.0004440556,0.0010478267,0.0007423812],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014412994,0.000040348008,0.00041758275,0.00007208604,0.000043174376,0.00006690448,0.00013386569,0.7600732,0.018963367,0.01863308,0.0007376797,0.20067464],"study_design_scores_gemma":[0.000003302153,0.00001833605,0.0000697784,0.000003627539,0.000005239162,0.000017960387,0.000002989133,0.9942683,0.0027894182,0.0021269887,0.0006877918,0.00000625923],"about_ca_topic_score_codex":0.0028079825,"about_ca_topic_score_gemma":0.0034399733,"teacher_disagreement_score":0.0028079825,"about_ca_system_score_codex":0.00028398706,"about_ca_system_score_gemma":0.00053552195,"threshold_uncertainty_score":0.0055832863},"labels":[],"label_agreement":null},{"id":"W165087859","doi":"10.21437/interspeech.2010-529","title":"Novel weighting scheme for unsupervised language model adaptation using latent dirichlet allocation","year":2010,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Latent Dirichlet allocation; Computer science; Weighting; Scheme (mathematics); Hierarchical Dirichlet process; Adaptation (eye); Artificial intelligence; Language model; Latent variable; Topic model; Machine learning; Natural language processing; Mathematics","score_opus":0.07224011613154238,"score_gpt":0.2863947272958288,"score_spread":0.21415461116428644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W165087859","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022730741,0.00010012825,0.99697304,0.000027878716,0.00003921359,0.000020172072,0.000026824893,0.00031489794,0.000224712],"genre_scores_gemma":[0.12685816,0.000282943,0.8672199,0.00017928437,0.0001296924,0.000310715,0.0006427766,0.0005073628,0.0038690853],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848324,0.00060698297,0.00011097859,0.0003233709,0.00035444056,0.00012108382],"domain_scores_gemma":[0.99856704,0.0005475537,0.00006718333,0.00031567254,0.00042581893,0.00007678301],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002272298,0.0009861605,0.0012063328,0.00090667594,0.00067642215,0.0009107691,0.0021211084,0.0011917924,0.0030468395],"category_scores_gemma":[0.0050484333,0.0006297733,0.001078637,0.001219378,0.000511025,0.0019502327,0.0022370545,0.0020649503,0.0017270582],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004831271,0.00031071168,0.0010006034,0.00016620147,0.00023929038,0.00008808544,0.00024525158,0.10498297,0.04823092,0.024215652,0.006064746,0.81397235],"study_design_scores_gemma":[0.000037646267,0.000037582235,0.00028118404,0.0000101055275,0.00004237595,0.0000627474,0.00001936807,0.97842205,0.008370994,0.010026376,0.002661357,0.000028257396],"about_ca_topic_score_codex":0.0042186393,"about_ca_topic_score_gemma":0.007966731,"teacher_disagreement_score":0.0042186393,"about_ca_system_score_codex":0.00060169655,"about_ca_system_score_gemma":0.0011441882,"threshold_uncertainty_score":0.01201719},"labels":[],"label_agreement":null},{"id":"W1663228875","doi":"10.1109/icslp.1996.606915","title":"New developments in the INRS continuous speech recognition system","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Speech recognition; Computer science; Phone; Vocabulary; Artificial intelligence; Pruning; Task (project management); Tree (set theory); Hidden Markov model; Graph; Natural language processing; Pattern recognition (psychology); Mathematics; Linguistics; Theoretical computer science","score_opus":0.04481888551069555,"score_gpt":0.21890995217122564,"score_spread":0.1740910666605301,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1663228875","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017514998,0.011374664,0.85269606,0.0025548036,0.0017864744,0.0002842775,0.0010470945,0.041171785,0.07156981],"genre_scores_gemma":[0.13033828,0.0060755555,0.779639,0.0014036391,0.0016911866,0.00023710083,0.0034522838,0.002557265,0.07460578],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9963103,0.00053248164,0.0003090314,0.0008372663,0.0018445174,0.00016642796],"domain_scores_gemma":[0.9965209,0.00063259184,0.00010715972,0.0010649624,0.0014307066,0.00024366366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004490226,0.000809423,0.0013174615,0.001357252,0.0004053904,0.0025833775,0.002444133,0.0011683695,0.01887989],"category_scores_gemma":[0.00535041,0.0006775183,0.0007377217,0.001150887,0.0008742656,0.0032673234,0.001139306,0.0018161183,0.021247094],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006368773,0.0002454208,0.0013766721,0.00035642,0.000073970885,0.0003281474,0.0002529062,0.006051145,0.071777105,0.027167475,0.032741018,0.8589928],"study_design_scores_gemma":[0.00018998394,0.0014328804,0.003646432,0.00021312913,0.00019749062,0.002595943,0.00013928859,0.19101043,0.079189844,0.00881142,0.71234816,0.00022502658],"about_ca_topic_score_codex":0.0042875404,"about_ca_topic_score_gemma":0.004050864,"teacher_disagreement_score":0.01887989,"about_ca_system_score_codex":0.0010463847,"about_ca_system_score_gemma":0.0011770804,"threshold_uncertainty_score":0.063159525},"labels":[],"label_agreement":null},{"id":"W1688440848","doi":"10.1109/icslp.1996.607209","title":"Detection of ambiguous portions of signal corresponding to OOV words or misrecognized portions of input","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Word (group theory); Artificial intelligence; Speech recognition; Noise (video); Frame (networking); Vocabulary; Key (lock); Base (topology); SIGNAL (programming language); Pattern recognition (psychology); Natural language processing; Algorithm; Image (mathematics); Mathematics","score_opus":0.04833407454510028,"score_gpt":0.26299407245431927,"score_spread":0.214659997909219,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1688440848","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6508401,0.0011081444,0.34073222,0.00018745057,0.00011309369,0.00025747836,0.00019704431,0.0034467264,0.0031177313],"genre_scores_gemma":[0.7843828,0.00029519663,0.21050078,0.00016682364,0.000045848814,0.00013793877,0.00057989656,0.00063845044,0.0032523419],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99777704,0.00065054535,0.00019773643,0.00051986525,0.0006155018,0.00023931723],"domain_scores_gemma":[0.989122,0.0068852687,0.0008075456,0.0016051709,0.0012565886,0.0003234421],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020816023,0.0013868336,0.0019340881,0.0012576998,0.0006612514,0.0013058374,0.0008775101,0.0016397997,0.0022159333],"category_scores_gemma":[0.010200962,0.00026947196,0.00045912428,0.00064701,0.00084231846,0.001645759,0.0011852996,0.0010536285,0.001951266],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0047079897,0.00026899198,0.009888595,0.000583134,0.00011957159,0.0012811893,0.00097552215,0.004469965,0.49870542,0.0012524889,0.0009964557,0.4767507],"study_design_scores_gemma":[0.00017924167,0.002269548,0.037084475,0.00008462232,0.00027735083,0.006806436,0.0014458229,0.17689086,0.7653884,0.0029027686,0.006498901,0.00017157043],"about_ca_topic_score_codex":0.00055793114,"about_ca_topic_score_gemma":0.0010058982,"teacher_disagreement_score":0.0022159333,"about_ca_system_score_codex":0.00023387812,"about_ca_system_score_gemma":0.00033815476,"threshold_uncertainty_score":0.01100868},"labels":[],"label_agreement":null},{"id":"W1736190149","doi":"10.1109/icassp.1990.115896","title":"Acoustic recognition component of an 86000-word speech recognizer","year":2002,"lang":"en","type":"article","venue":"International Conference on Acoustics, Speech, and Signal Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Hidden Markov model; Speech recognition; Computer science; Context (archaeology); Word (group theory); Vocabulary; Artificial intelligence; Natural language processing; Word recognition; Mixture model; Pattern recognition (psychology); Mathematics; Linguistics","score_opus":0.0784269689885228,"score_gpt":0.2843761123875949,"score_spread":0.2059491433990721,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1736190149","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.111203514,0.000771619,0.8511508,0.0002426634,0.00036274167,0.00050871057,0.0016482465,0.02372739,0.010384329],"genre_scores_gemma":[0.28333125,0.00054772047,0.6737894,0.00040610906,0.00018444922,0.0007472153,0.005646717,0.0008511972,0.03449598],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99914694,0.00014668993,0.0000748058,0.00023950874,0.0003500116,0.000042030817],"domain_scores_gemma":[0.99903774,0.00034496278,0.000038431423,0.00015668698,0.00036001913,0.00006212282],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009841373,0.0006992102,0.00073092984,0.0005719379,0.00021801224,0.0005220312,0.0008089099,0.0005049894,0.010192223],"category_scores_gemma":[0.0019538752,0.0003556552,0.0004152639,0.00036583128,0.00021410995,0.000619407,0.00038250518,0.00054197724,0.01203802],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00076019194,0.00030563914,0.0014287037,0.0002660433,0.00011270198,0.0003004115,0.00014501173,0.008631438,0.4933108,0.0013048042,0.0057771355,0.48765722],"study_design_scores_gemma":[0.00024682144,0.0025032964,0.01855997,0.00007331279,0.0005992659,0.0026622245,0.00011400599,0.30208728,0.5989823,0.0014696032,0.07247564,0.00022624005],"about_ca_topic_score_codex":0.0018461515,"about_ca_topic_score_gemma":0.0016584757,"teacher_disagreement_score":0.010192223,"about_ca_system_score_codex":0.0002779395,"about_ca_system_score_gemma":0.00037976666,"threshold_uncertainty_score":0.03409636},"labels":[],"label_agreement":null},{"id":"W1749856071","doi":"","title":"A new algorithm for the alignment of phonetic sequences","year":2000,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":167,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Similarity (geometry); Algorithm; Basis (linear algebra); Scheme (mathematics); Sequence (biology); Phonology; Multiple sequence alignment; Artificial intelligence; Speech recognition; Sequence alignment; Mathematics; Image (mathematics); Linguistics","score_opus":0.022999810208332715,"score_gpt":0.24775321148392893,"score_spread":0.2247534012755962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1749856071","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005975416,0.00012875935,0.99675614,0.0000668437,0.00015171315,0.000070150476,0.00008042975,0.0011900137,0.000958378],"genre_scores_gemma":[0.005658611,0.00013521576,0.99074954,0.00008363251,0.00009293826,0.00016677818,0.00035924593,0.0003126116,0.0024414412],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99692744,0.00043022982,0.00032213324,0.0011033849,0.0010544488,0.00016231727],"domain_scores_gemma":[0.9977998,0.0007683873,0.00015585059,0.0004088603,0.00077696744,0.00009012133],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019804838,0.001824988,0.0017427142,0.0033785705,0.002257758,0.003623916,0.0033104036,0.0029181882,0.017719576],"category_scores_gemma":[0.008012691,0.0012653545,0.0017883333,0.003507993,0.0018202229,0.005472222,0.003389508,0.004021844,0.013307869],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015635353,0.000069991016,0.0004955342,0.00026087157,0.00008365116,0.000155089,0.0003118543,0.022871083,0.011895601,0.045997206,0.01549909,0.9022036],"study_design_scores_gemma":[0.00022565397,0.0003390696,0.00085839484,0.00019368483,0.0001251991,0.001466868,0.0002874425,0.59634876,0.021406248,0.20185079,0.17672001,0.00017785304],"about_ca_topic_score_codex":0.002082611,"about_ca_topic_score_gemma":0.0023080618,"teacher_disagreement_score":0.017719576,"about_ca_system_score_codex":0.0008670742,"about_ca_system_score_gemma":0.0016907839,"threshold_uncertainty_score":0.059277833},"labels":[],"label_agreement":null},{"id":"W1823609680","doi":"10.5430/air.v4n2p72","title":"Cross-language phoneme mapping for phonetic search keyword spotting in continuous speech of under-resourced languages","year":2015,"lang":"en","type":"article","venue":"Artificial Intelligence Research","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Keyword spotting; Computer science; Spotting; Speech recognition; Natural language processing; Keyword search; Artificial intelligence; Information retrieval","score_opus":0.2760964527524231,"score_gpt":0.44965197702364745,"score_spread":0.17355552427122434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1823609680","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21335565,0.00039954158,0.77823824,0.000114292394,0.00006012633,0.00018095992,0.00035718165,0.003254731,0.004039241],"genre_scores_gemma":[0.6940569,0.00018442635,0.30274874,0.00004621088,0.000016810629,0.00013206982,0.00055546284,0.00021965723,0.0020396195],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99919647,0.00024965653,0.00006962461,0.0002045468,0.00022284742,0.000056842808],"domain_scores_gemma":[0.99826247,0.00090138486,0.00015580603,0.00029228345,0.0003115058,0.00007659842],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095275126,0.000606878,0.0005192811,0.0013193368,0.00038323496,0.0009678353,0.00074943784,0.00052376674,0.002933738],"category_scores_gemma":[0.0043756072,0.00024117046,0.00040680415,0.0006872801,0.00041297424,0.0016685694,0.0011580327,0.000486975,0.0013689904],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00090405793,0.00023177995,0.007450477,0.00031898025,0.00009660026,0.00051283813,0.00090641476,0.022323877,0.17525358,0.004373271,0.001107741,0.7865203],"study_design_scores_gemma":[0.0000578755,0.0006501123,0.019647006,0.00005076242,0.00012603457,0.0017516443,0.001293153,0.63912845,0.31773156,0.0080976365,0.011316619,0.00014913076],"about_ca_topic_score_codex":0.0016700617,"about_ca_topic_score_gemma":0.0031836818,"teacher_disagreement_score":0.002933738,"about_ca_system_score_codex":0.00038121906,"about_ca_system_score_gemma":0.0007113056,"threshold_uncertainty_score":0.009814322},"labels":[],"label_agreement":null},{"id":"W182365161","doi":"10.21437/interspeech.2013-691","title":"Text-dependent speaker recognition using PLDA with uncertainty propagation","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":72,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Utterance; Speech recognition; Phrase; Speaker recognition; Artificial intelligence; Channel (broadcasting); Speaker verification; Bridge (graph theory); Natural language processing; Pattern recognition (psychology)","score_opus":0.03518198583893034,"score_gpt":0.23009311793928353,"score_spread":0.19491113210035318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W182365161","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008816039,0.0008115356,0.98717135,0.00019128145,0.00011215747,0.000041116422,0.000232864,0.002035046,0.00058855716],"genre_scores_gemma":[0.35402545,0.0010964663,0.63567245,0.0003225104,0.00032808914,0.00022959961,0.002192505,0.00058057933,0.005552317],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984427,0.0004786189,0.000105943116,0.000552635,0.0003139539,0.00010610986],"domain_scores_gemma":[0.9982887,0.00077477994,0.00016181645,0.00024351347,0.00047624088,0.000054908563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018051715,0.0018794002,0.0011180866,0.00075411954,0.0004285257,0.0013161397,0.0012976317,0.0011090904,0.0020896967],"category_scores_gemma":[0.0045155636,0.000554896,0.001416015,0.0007687814,0.00048231753,0.0021440918,0.0015588907,0.0026128674,0.0022092662],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006647068,0.00013922506,0.0010775335,0.00024772895,0.0004646898,0.00030001774,0.00020006714,0.18487987,0.04514465,0.0034209862,0.004230196,0.7592303],"study_design_scores_gemma":[0.00001606461,0.00007157507,0.0005279747,0.000013568095,0.000051506413,0.000095432835,0.000022203416,0.98223346,0.011924903,0.0031292015,0.0018793839,0.000034624387],"about_ca_topic_score_codex":0.0036004113,"about_ca_topic_score_gemma":0.0044257217,"teacher_disagreement_score":0.0036004113,"about_ca_system_score_codex":0.000578482,"about_ca_system_score_gemma":0.0006417151,"threshold_uncertainty_score":0.009546757},"labels":[],"label_agreement":null},{"id":"W1826414049","doi":"10.1109/icassp.1989.266372","title":"A locus model of coarticulation in an HMM speech recognizer","year":2003,"lang":"en","type":"article","venue":"International Conference on Acoustics, Speech, and Signal Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bell (Canada); Institut National de la Recherche Scientifique","funders":"","keywords":"Coarticulation; Hidden Markov model; Speech recognition; Vowel; Computer science; Consonant; Artificial intelligence; Gaussian; Physics","score_opus":0.07357010464901313,"score_gpt":0.30215801015917104,"score_spread":0.2285879055101579,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1826414049","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0053608357,0.000105603445,0.9921976,0.000057403227,0.000040278013,0.000013166591,0.00012155717,0.0013060753,0.0007974431],"genre_scores_gemma":[0.53250897,0.00065538415,0.44903296,0.00017763859,0.00012993293,0.00026802707,0.0011640529,0.00090472604,0.015158302],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99924856,0.00018279161,0.000051392082,0.00028655372,0.00018081389,0.000049888782],"domain_scores_gemma":[0.9994665,0.00027586648,0.000039600836,0.00009049158,0.00009864909,0.000028987433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00088412815,0.00047209195,0.00079522544,0.00041557578,0.00029660424,0.00089962257,0.0016568397,0.0009452367,0.003039443],"category_scores_gemma":[0.0020088265,0.0006006878,0.00083700026,0.00042957912,0.00056394783,0.0015836625,0.0007984416,0.0014809748,0.003188966],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005470391,0.00014638499,0.002777308,0.00022145946,0.00017862234,0.0005036802,0.0006338739,0.70134825,0.04283705,0.07981693,0.0035380532,0.16745134],"study_design_scores_gemma":[0.000009433702,0.000037633497,0.00032037808,0.0000073908545,0.000020766547,0.00007439454,0.000012101129,0.9873044,0.00342638,0.007081312,0.001688109,0.000017654218],"about_ca_topic_score_codex":0.0023421238,"about_ca_topic_score_gemma":0.0025401914,"teacher_disagreement_score":0.003039443,"about_ca_system_score_codex":0.0005140192,"about_ca_system_score_gemma":0.00070257904,"threshold_uncertainty_score":0.010167956},"labels":[],"label_agreement":null},{"id":"W1829432249","doi":"10.1109/icassp.1994.389344","title":"Application of vector quantized hidden Markov modeling to telephone network based connected digit recognition","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Codebook; Hidden Markov model; Speech recognition; Telephone network; Computer science; Telephony; Pattern recognition (psychology); Artificial intelligence; Markov model; Markov chain; Machine learning; Telecommunications","score_opus":0.04209136715797211,"score_gpt":0.23181024252240348,"score_spread":0.18971887536443138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1829432249","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05951813,0.00042145705,0.9378214,0.00020367838,0.00003793551,0.00003069154,0.00009311462,0.00073215103,0.0011414436],"genre_scores_gemma":[0.84727937,0.0003959918,0.1505732,0.000055009452,0.000024609844,0.00003697939,0.00016659599,0.00004915306,0.0014190649],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995907,0.0002200871,0.000022641852,0.000054215616,0.000087680375,0.00002464211],"domain_scores_gemma":[0.9983797,0.0013308114,0.00007203522,0.00008623864,0.00011518356,0.000016077247],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008433087,0.00024116933,0.00033632602,0.00028668402,0.00015795277,0.00043908157,0.00037469863,0.0003320014,0.001020404],"category_scores_gemma":[0.0038580177,0.00020025887,0.00023233233,0.00040104627,0.00027721704,0.00044586524,0.00029526127,0.0004008617,0.00020303244],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008314963,0.00003489309,0.0012872923,0.000054267886,0.00003167803,0.00007369635,0.000079551806,0.8832506,0.004464572,0.008964742,0.0005805613,0.101095],"study_design_scores_gemma":[0.000001753791,0.000009935817,0.00015384264,0.0000019710358,0.0000025246884,0.00001041652,0.0000034401146,0.99744934,0.0007752337,0.0014637754,0.00012473276,0.000002946822],"about_ca_topic_score_codex":0.0071695773,"about_ca_topic_score_gemma":0.0055567008,"teacher_disagreement_score":0.0071695773,"about_ca_system_score_codex":0.0005192482,"about_ca_system_score_gemma":0.00037220118,"threshold_uncertainty_score":0.0142557025},"labels":[],"label_agreement":null},{"id":"W1835856534","doi":"","title":"Effects of acoustic interaction between the subglottic and supraglottic cavities of the human phonatory system","year":2009,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Glottis; Vocal tract; Acoustics; Phase (matter); Physics; SIGNAL (programming language); Coupling (piping); Larynx; Vocal folds; Resonance (particle physics); Optics; Computer science; Materials science; Anatomy; Medicine","score_opus":0.010766971592418888,"score_gpt":0.2158009963327643,"score_spread":0.20503402474034543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1835856534","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9746249,0.00041202316,0.022818329,0.00005126232,0.000024596024,0.000029874196,0.000038379643,0.00011050792,0.0018900802],"genre_scores_gemma":[0.9975661,0.00008225521,0.0015638985,0.000016620706,0.0000065331965,0.000013485144,0.000018285918,0.000018915522,0.00071385107],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996892,0.00008627265,0.000011601113,0.00006273226,0.000092035174,0.000058180805],"domain_scores_gemma":[0.9993886,0.00042394546,0.000059206606,0.00003931865,0.000037114733,0.000051735864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003169085,0.00047739266,0.00031774468,0.00018335294,0.00021297303,0.00042072262,0.00032986296,0.00057306007,0.0037524337],"category_scores_gemma":[0.0017383768,0.00030740176,0.000401845,0.00007211103,0.0004925336,0.0003420917,0.0007561414,0.00025176606,0.0004519383],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009912289,0.00012216858,0.004400578,0.00026243753,0.00009519463,0.0010163055,0.00037091124,0.081911586,0.89268523,0.0007899416,0.00011887125,0.017235396],"study_design_scores_gemma":[0.00018343174,0.006484319,0.11468114,0.00010564685,0.00054037664,0.004215943,0.0009573738,0.3520288,0.51194006,0.0023810554,0.006302806,0.00017900406],"about_ca_topic_score_codex":0.0004526357,"about_ca_topic_score_gemma":0.0002601378,"teacher_disagreement_score":0.0037524337,"about_ca_system_score_codex":0.00018978074,"about_ca_system_score_gemma":0.00017706394,"threshold_uncertainty_score":0.012553155},"labels":[],"label_agreement":null},{"id":"W1846073453","doi":"10.1109/icassp.2000.859138","title":"Towards language independent acoustic modeling","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":111,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Universidade Federal de Alagoas; Rice University","keywords":"Computer science; Czech; Discriminative model; Hidden Markov model; Acoustic model; Language model; Speech recognition; Natural language processing; Mandarin Chinese; Artificial intelligence; Adaptation (eye); Speech processing; Linguistics","score_opus":0.04217330464563866,"score_gpt":0.24696833763924592,"score_spread":0.20479503299360724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1846073453","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002708348,0.00011567078,0.9927127,0.00009369066,0.00006523867,0.000029375662,0.00015791832,0.0016979527,0.002419225],"genre_scores_gemma":[0.1072553,0.0006510031,0.87831056,0.00035501283,0.00013775368,0.0003045662,0.0025972985,0.0014520359,0.008936524],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983804,0.00044421462,0.000066170964,0.00046988178,0.0005550459,0.00008423946],"domain_scores_gemma":[0.99856347,0.00038056241,0.000065636115,0.00047704938,0.00046791387,0.00004542013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013962841,0.0014682659,0.0009631688,0.00078258483,0.0006358511,0.0017074569,0.0016838394,0.001077069,0.004141639],"category_scores_gemma":[0.00306411,0.00089097355,0.0020152905,0.0006857302,0.000625072,0.00185815,0.0018764854,0.0025211193,0.0077143535],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028944155,0.00021225896,0.0016792652,0.00037377232,0.00034877157,0.00030558705,0.0006219222,0.27199537,0.15038145,0.044214908,0.008081771,0.52149546],"study_design_scores_gemma":[0.00003118285,0.00008248757,0.0006633384,0.000041071733,0.000086720785,0.00024429493,0.00010210511,0.9087569,0.03556014,0.02424183,0.0301094,0.00008061741],"about_ca_topic_score_codex":0.0026779124,"about_ca_topic_score_gemma":0.003970749,"teacher_disagreement_score":0.004141639,"about_ca_system_score_codex":0.0004311954,"about_ca_system_score_gemma":0.0011139626,"threshold_uncertainty_score":0.0138551},"labels":[],"label_agreement":null},{"id":"W1849264953","doi":"10.1109/icassp.1994.389695","title":"Fast match acoustic models in large vocabulary continuous speech recognition","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Vocabulary; Speech recognition; Computer science; Context (archaeology); Word (group theory); Task (project management); Computation; Hidden Markov model; State (computer science); Artificial intelligence; Natural language processing; Mathematics; Algorithm; Engineering; Linguistics","score_opus":0.037260184739906416,"score_gpt":0.2281018144157373,"score_spread":0.19084162967583088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1849264953","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0074058627,0.00030573097,0.9886192,0.000065097665,0.000042152078,0.000034662316,0.00012800464,0.0027225371,0.00067676214],"genre_scores_gemma":[0.31006116,0.0006131205,0.67518985,0.00012168224,0.00011425061,0.00033758007,0.0013681045,0.00061985344,0.011574463],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999366,0.00019256318,0.000030572064,0.00012703553,0.00023143199,0.00005227817],"domain_scores_gemma":[0.99911696,0.00051839947,0.000043194825,0.00015206696,0.0001386832,0.000030717652],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010145197,0.00051289424,0.0006159293,0.0005086118,0.00030366424,0.0009908368,0.0010550885,0.0010966955,0.0036717607],"category_scores_gemma":[0.0036073236,0.00063002127,0.00048092852,0.00054188736,0.00037568886,0.0015531855,0.00095052796,0.0010261226,0.0032219894],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035372318,0.00011042918,0.0007045354,0.00014530003,0.00007010622,0.00022499597,0.00013608317,0.43232653,0.020800557,0.0150466245,0.0065676533,0.52351344],"study_design_scores_gemma":[0.000013994481,0.000032751374,0.00018162258,0.0000048100073,0.000007228765,0.000038332433,0.000013250833,0.9910019,0.0034212833,0.0036461211,0.0016289343,0.000009800985],"about_ca_topic_score_codex":0.0075217364,"about_ca_topic_score_gemma":0.009799975,"teacher_disagreement_score":0.0075217364,"about_ca_system_score_codex":0.0003755435,"about_ca_system_score_gemma":0.000640668,"threshold_uncertainty_score":0.014955938},"labels":[],"label_agreement":null},{"id":"W1882201698","doi":"10.1109/ccece.2001.933735","title":"Efficient recognition of continuously-spoken numbers","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Speech recognition; Vocabulary; Hidden Markov model; Mel-frequency cepstrum; Telephone line; Task (project management); Telephony; Noise (video); Computation; Artificial intelligence; Pattern recognition (psychology); Feature extraction; Telecommunications; Algorithm; Engineering","score_opus":0.03455514357779255,"score_gpt":0.21929813520673452,"score_spread":0.18474299162894198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1882201698","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1171378,0.0018543071,0.85525894,0.00027297664,0.0003376666,0.00009647917,0.0007127731,0.0064012446,0.017927902],"genre_scores_gemma":[0.54653764,0.0013672027,0.42523688,0.00016086565,0.00024979527,0.00011033772,0.0026064739,0.00022949319,0.023501368],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99964094,0.000051568022,0.000025211852,0.00008754365,0.00015879463,0.000035858633],"domain_scores_gemma":[0.9994764,0.00018283799,0.000035118053,0.00010293125,0.0001839086,0.000018757763],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002160769,0.0004016353,0.0004759405,0.00048596025,0.00018784865,0.00078858476,0.00060634466,0.000545476,0.0048532123],"category_scores_gemma":[0.0015137575,0.00016621081,0.00019908117,0.00038414958,0.00020757987,0.0010710153,0.00047571666,0.0002804355,0.0044927443],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028045836,0.000064774445,0.0008426387,0.00017007288,0.000019756595,0.00019556645,0.000085748135,0.0072007105,0.2190308,0.0050609093,0.008692452,0.75835615],"study_design_scores_gemma":[0.00006833733,0.00028592857,0.010839554,0.000058729274,0.00007263491,0.0012629459,0.00019281065,0.49897784,0.4216626,0.010601571,0.055912435,0.0000646062],"about_ca_topic_score_codex":0.0008981858,"about_ca_topic_score_gemma":0.001946253,"teacher_disagreement_score":0.0048532123,"about_ca_system_score_codex":0.00016537296,"about_ca_system_score_gemma":0.00030261226,"threshold_uncertainty_score":0.01623565},"labels":[],"label_agreement":null},{"id":"W1885745269","doi":"10.1109/icassp.2005.1415064","title":"Discriminative Training Based on the Criterion of Least Phone Competing Tokens for Large Vocabulary Speech Recognition","year":2006,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University","keywords":"Security token; Computer science; Discriminative model; Hidden Markov model; Speech recognition; Word error rate; Phone; Normalization (sociology); Vocabulary; Sigmoid function; Artificial intelligence; Set (abstract data type); Generalization; Overfitting; Pattern recognition (psychology); Artificial neural network; Mathematics","score_opus":0.06140262388372575,"score_gpt":0.26316123209178,"score_spread":0.20175860820805425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1885745269","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0122928955,0.00014422461,0.98591566,0.000091106216,0.00001843137,0.00004630041,0.00004933187,0.00092938886,0.00051261747],"genre_scores_gemma":[0.45956743,0.0001865086,0.53275204,0.00041549068,0.00007887361,0.00046370924,0.0010437539,0.0005523688,0.0049398397],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984864,0.0005165321,0.000095008916,0.00040739225,0.00037355974,0.000121146586],"domain_scores_gemma":[0.99714977,0.0018032523,0.00017529516,0.00041196708,0.00035377857,0.00010593567],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020028786,0.00093837664,0.0017058216,0.00066912244,0.00051453046,0.0005906657,0.0018786106,0.0008906688,0.0022296347],"category_scores_gemma":[0.0068626693,0.000708915,0.00048589284,0.0010967844,0.0008400689,0.0014479844,0.001422319,0.0013153119,0.0012269673],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040973915,0.00028496757,0.0024102833,0.00022856118,0.00012384065,0.00015610915,0.00014698393,0.2569126,0.036572013,0.009110552,0.0048214267,0.6888231],"study_design_scores_gemma":[0.0000254114,0.00006678528,0.00085135025,0.000005321208,0.000013595077,0.000107149455,0.00001723013,0.9882423,0.0068975682,0.002969163,0.0007900013,0.000014083677],"about_ca_topic_score_codex":0.0031095063,"about_ca_topic_score_gemma":0.00670455,"teacher_disagreement_score":0.0031095063,"about_ca_system_score_codex":0.0006948979,"about_ca_system_score_gemma":0.0013867345,"threshold_uncertainty_score":0.010592341},"labels":[],"label_agreement":null},{"id":"W1898340511","doi":"10.1109/icassp.1976.1169963","title":"Computer synthesis of Mandarin","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Mandarin Chinese; Speech recognition; Intelligibility (philosophy); Computer science; Syllable; String (physics); Speech synthesis; Mathematics; Linguistics","score_opus":0.015528201415972557,"score_gpt":0.22890639170066504,"score_spread":0.2133781902846925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1898340511","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4262278,0.0012669653,0.49828228,0.00028389596,0.000525418,0.00062897324,0.0020924604,0.007558573,0.063133694],"genre_scores_gemma":[0.7133208,0.00044389846,0.2661799,0.00011563506,0.00007742852,0.0004799483,0.0027802468,0.0004690215,0.016133191],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9998362,0.000028019802,0.00001659596,0.000052538133,0.000047160407,0.000019402456],"domain_scores_gemma":[0.9997931,0.00009177748,0.00000791337,0.000024371522,0.00007258355,0.000010277193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029627755,0.0003934891,0.00033676895,0.00047347866,0.00025337757,0.00041956492,0.0002683526,0.00033128366,0.009709453],"category_scores_gemma":[0.00077553804,0.00013206818,0.00022257696,0.0003472243,0.00015037759,0.00019771668,0.00025273097,0.0002014956,0.0014481388],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009905584,0.00013082499,0.0004736044,0.00067307363,0.000058424084,0.00061922066,0.00059143355,0.023418477,0.69819266,0.014494591,0.0035700237,0.25678715],"study_design_scores_gemma":[0.00039370114,0.0024213532,0.006327342,0.00008089337,0.0001818579,0.0012425504,0.00028455353,0.2055017,0.6452292,0.00537452,0.13285592,0.0001064695],"about_ca_topic_score_codex":0.001015433,"about_ca_topic_score_gemma":0.0012784787,"teacher_disagreement_score":0.009709453,"about_ca_system_score_codex":0.00022303284,"about_ca_system_score_gemma":0.00028653865,"threshold_uncertainty_score":0.032481313},"labels":[],"label_agreement":null},{"id":"W1902248030","doi":"10.1109/icassp.1995.479599","title":"Use of generalized dynamic feature parameters for speech recognition: maximum likelihood and minimum classification error approaches","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Weighting; Speech recognition; Preprocessor; TIMIT; Hidden Markov model; Pattern recognition (psychology); Speech processing; Mel-frequency cepstrum; Word error rate; Feature (linguistics); Artificial intelligence; Feature extraction","score_opus":0.19788699775342944,"score_gpt":0.26767754017287687,"score_spread":0.06979054241944743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1902248030","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002736104,0.00011376865,0.99683326,0.000025092964,0.0000043728,0.000008850949,0.000005249753,0.00011683126,0.00015648801],"genre_scores_gemma":[0.17919686,0.00029518327,0.8190725,0.0000717257,0.00003615259,0.00016803709,0.00009876101,0.00015484967,0.00090594415],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983866,0.0006262904,0.000107671025,0.00033840913,0.00046429524,0.00007675816],"domain_scores_gemma":[0.9975526,0.0015045644,0.0001931769,0.0003706852,0.0003377828,0.000041329004],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003074421,0.0011111002,0.0013904666,0.0009989423,0.0002944876,0.0012539249,0.0016600997,0.0014106407,0.00091854885],"category_scores_gemma":[0.009146426,0.00066208665,0.0007489985,0.00081517646,0.0009242504,0.0029926226,0.0015673804,0.001509111,0.00045411437],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016640435,0.00012259337,0.0010083877,0.0001425784,0.00015184256,0.00010259679,0.00021716532,0.5194363,0.013470742,0.04109312,0.0004905994,0.42359772],"study_design_scores_gemma":[0.000013822656,0.00003333397,0.00018722958,0.00001113935,0.000017573107,0.00003809594,0.00001162101,0.9809668,0.0033403668,0.014684696,0.00067333074,0.000021953212],"about_ca_topic_score_codex":0.0013116779,"about_ca_topic_score_gemma":0.0014900686,"teacher_disagreement_score":0.003074421,"about_ca_system_score_codex":0.0006636423,"about_ca_system_score_gemma":0.00066002907,"threshold_uncertainty_score":0.016259313},"labels":[],"label_agreement":null},{"id":"W1906553149","doi":"10.1109/icpr.1998.711998","title":"HMM-KNN word recognition engine for bank cheque processing","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Hidden Markov model; Cheque; Classifier (UML); Phone; Word (group theory); Alphabet; Speech recognition; Artificial intelligence; Natural language processing; Segmentation; Modular design; Document processing; Scheme (mathematics); Set (abstract data type); Pattern recognition (psychology); Linguistics","score_opus":0.0708022711339814,"score_gpt":0.24500677916979036,"score_spread":0.17420450803580895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1906553149","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0079197865,0.00057134463,0.88952607,0.000067674206,0.00014617965,0.00031001482,0.004114788,0.09134431,0.0059999153],"genre_scores_gemma":[0.08453321,0.0006768024,0.8558373,0.00024097707,0.00008830902,0.0008247182,0.022450076,0.0034812186,0.031867325],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994993,0.00006644905,0.0000561865,0.00015911745,0.00016094519,0.00005783212],"domain_scores_gemma":[0.9995426,0.00013666373,0.000031814005,0.00009967428,0.0001621743,0.000027158809],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007233659,0.0008942628,0.0009880518,0.0012544504,0.00048824883,0.0009505353,0.0013767502,0.00093530386,0.025379024],"category_scores_gemma":[0.0016971058,0.00087934395,0.0005156416,0.0010741507,0.00026268675,0.0014416607,0.0006570228,0.00079949945,0.02588489],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007762319,0.0002670051,0.00391204,0.0006843014,0.00022279304,0.00046305463,0.00024882655,0.020724975,0.083321944,0.0059967856,0.07389765,0.80948436],"study_design_scores_gemma":[0.00014965139,0.00024397661,0.012637548,0.00017369569,0.00023806276,0.0015937693,0.00014378417,0.6732336,0.12834221,0.0070531964,0.17594703,0.00024349218],"about_ca_topic_score_codex":0.008185323,"about_ca_topic_score_gemma":0.015348,"teacher_disagreement_score":0.025379024,"about_ca_system_score_codex":0.0006068291,"about_ca_system_score_gemma":0.0006688754,"threshold_uncertainty_score":0.08490133},"labels":[],"label_agreement":null},{"id":"W1920148782","doi":"10.1109/icassp.1979.1170591","title":"Speech synthesis from vocal tract area function acoustical measurements","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Vocal tract; Formant; Glottis; Vowel; Speech synthesis; Interpolation (computer graphics); Acoustics; Speech recognition; Computer science; Speech production; Larynx; Artificial intelligence; Physics; Anatomy; Medicine; Motion (physics)","score_opus":0.06744084468741475,"score_gpt":0.2526280988849138,"score_spread":0.18518725419749904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1920148782","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.463412,0.001077822,0.5255734,0.00011829729,0.00021391783,0.00013546798,0.00072892295,0.0023014834,0.0064387927],"genre_scores_gemma":[0.9053541,0.00050387194,0.09093456,0.000027408198,0.000048085734,0.000100723846,0.00048374428,0.00026244298,0.0022850733],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99973017,0.00006331018,0.00001529972,0.00006979473,0.00010938914,0.000012066424],"domain_scores_gemma":[0.9994661,0.00032878254,0.000026694663,0.000059058035,0.00009897039,0.000020328747],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037483903,0.00045927922,0.0003956329,0.0003567211,0.0001630371,0.0005123563,0.0003145594,0.00031825644,0.0032396766],"category_scores_gemma":[0.001670802,0.00018916451,0.0003014633,0.00017657231,0.00027334248,0.00040142037,0.00026374854,0.0002705243,0.00081916095],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005092294,0.00003421738,0.0009485495,0.0004533782,0.000050230236,0.00012278548,0.00021372184,0.009789155,0.82941747,0.0013747292,0.0003052206,0.15678139],"study_design_scores_gemma":[0.00011069561,0.00072663114,0.014188213,0.00008627851,0.00015971393,0.00071019994,0.00019485671,0.13104966,0.8400449,0.002379313,0.010256195,0.0000933355],"about_ca_topic_score_codex":0.00031105088,"about_ca_topic_score_gemma":0.0003145648,"teacher_disagreement_score":0.0032396766,"about_ca_system_score_codex":0.00022777644,"about_ca_system_score_gemma":0.00015659515,"threshold_uncertainty_score":0.010837853},"labels":[],"label_agreement":null},{"id":"W1929451993","doi":"","title":"A CROSS-LANGUAGE VOWEL NORMALISATION PROCEDURE","year":2006,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Normalization (sociology); Vowel; Vocal tract; Mathematics; Speech recognition; Correlation; Computer science; Statistics","score_opus":0.008281416018026528,"score_gpt":0.22551136531735344,"score_spread":0.2172299492993269,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1929451993","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08487916,0.00025843733,0.890275,0.00013937714,0.0008424641,0.00062364264,0.0013110995,0.012477195,0.009193572],"genre_scores_gemma":[0.37978768,0.00029438696,0.55817604,0.00034976559,0.00021935969,0.0010860506,0.007606824,0.0045533716,0.04792662],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9972036,0.0004661597,0.0002498062,0.0012623487,0.00047963572,0.0003385128],"domain_scores_gemma":[0.9967894,0.00058164,0.00008108361,0.000843698,0.0016302216,0.0000740481],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030613595,0.0020780307,0.001209755,0.0021935406,0.0016018457,0.0020010248,0.0013818028,0.0012695694,0.024019223],"category_scores_gemma":[0.0059468313,0.0006965791,0.0024822648,0.0013344523,0.000948151,0.0015380181,0.0043266024,0.0024824715,0.018654304],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009679087,0.00040489982,0.003931466,0.00027670764,0.00037482003,0.00032332205,0.0007051591,0.009009886,0.16942416,0.007017595,0.0072971405,0.80026686],"study_design_scores_gemma":[0.0002155795,0.0012209613,0.045777343,0.00012182065,0.0009030842,0.0027122784,0.0014655001,0.3753797,0.45196545,0.012757756,0.10697946,0.00050105236],"about_ca_topic_score_codex":0.0057497094,"about_ca_topic_score_gemma":0.009624949,"teacher_disagreement_score":0.024019223,"about_ca_system_score_codex":0.00049718836,"about_ca_system_score_gemma":0.0017291114,"threshold_uncertainty_score":0.08035225},"labels":[],"label_agreement":null},{"id":"W1930794383","doi":"10.1109/icassp.1987.1169578","title":"Integration of acoustic information in a large vocabulary word recognizer","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":89,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Codebook; Computer science; Vector quantization; Speech recognition; Hidden Markov model; Vocabulary; Word (group theory); Linde–Buzo–Gray algorithm; Feature vector; Artificial intelligence; Learning vector quantization; Pattern recognition (psychology); Gaussian; Feature (linguistics); Curse of dimensionality; Set (abstract data type); Mathematics","score_opus":0.016004160455804595,"score_gpt":0.24165227794504474,"score_spread":0.22564811748924013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1930794383","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029644853,0.000632732,0.9651294,0.00013196799,0.00013879185,0.00006931737,0.000040744802,0.0029904954,0.0012217888],"genre_scores_gemma":[0.34272668,0.0004342675,0.65141225,0.0002177294,0.00015555773,0.00012972235,0.00033087778,0.00032084595,0.004272181],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988883,0.00020576542,0.000093292634,0.00022450263,0.00051736826,0.00007082448],"domain_scores_gemma":[0.99843735,0.0007619757,0.00007159448,0.00023033527,0.0004450193,0.000053713808],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010891219,0.00066245213,0.0011628561,0.00055248255,0.00027468818,0.00067238323,0.0010452818,0.00058370805,0.002701243],"category_scores_gemma":[0.0040762248,0.00055546087,0.00041734002,0.0004671519,0.0003949563,0.001917489,0.0008452592,0.0009451714,0.0019235482],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004506926,0.00024178701,0.0008697462,0.00012452148,0.000074577736,0.00009650294,0.0001380856,0.026969675,0.18421833,0.002414438,0.0012382322,0.78316337],"study_design_scores_gemma":[0.000110559486,0.0010588178,0.00326137,0.000037467104,0.00019811743,0.00038276953,0.00008131243,0.77333575,0.20701669,0.0049541243,0.009446514,0.00011656714],"about_ca_topic_score_codex":0.002401924,"about_ca_topic_score_gemma":0.0045728376,"teacher_disagreement_score":0.002701243,"about_ca_system_score_codex":0.00030316497,"about_ca_system_score_gemma":0.00054312375,"threshold_uncertainty_score":0.009036601},"labels":[],"label_agreement":null},{"id":"W1940972223","doi":"10.1109/icassp.1978.1170469","title":"A phoneme recognition system based on human audition","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Speech recognition; Artificial intelligence","score_opus":0.05221428637379322,"score_gpt":0.2634940145083017,"score_spread":0.21127972813450846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1940972223","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29519948,0.0019168431,0.66512394,0.0003214435,0.0011851412,0.0005579909,0.001661227,0.022401186,0.011632634],"genre_scores_gemma":[0.69610864,0.0009148446,0.28053853,0.0003842017,0.00024536974,0.00037724082,0.0015192645,0.00038992835,0.019522103],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99975747,0.00002744714,0.00001828813,0.00007475122,0.000084962056,0.00003718283],"domain_scores_gemma":[0.9994748,0.00015537848,0.000018245599,0.00006979441,0.00021764947,0.000064170206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036546597,0.00044321254,0.00085707306,0.00053806126,0.0004318021,0.00062800036,0.00054153963,0.00068198825,0.0075336737],"category_scores_gemma":[0.00076146657,0.0003287328,0.00030188236,0.0003063117,0.00019622082,0.00057429087,0.0005180108,0.000428295,0.002993313],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010431256,0.0000994541,0.0020750393,0.00020596701,0.00006997449,0.00024439505,0.00006665892,0.000730932,0.69994134,0.00070198375,0.0034012732,0.29141977],"study_design_scores_gemma":[0.00039644152,0.0016689642,0.04600761,0.00013820123,0.0008016795,0.0030339435,0.00014169245,0.15834291,0.75421226,0.002011522,0.032986365,0.00025840697],"about_ca_topic_score_codex":0.0017246587,"about_ca_topic_score_gemma":0.0029055192,"teacher_disagreement_score":0.0075336737,"about_ca_system_score_codex":0.00016112752,"about_ca_system_score_gemma":0.0005989111,"threshold_uncertainty_score":0.025202632},"labels":[],"label_agreement":null},{"id":"W1942035323","doi":"10.21437/interspeech.2015-654","title":"A study of the recurrent neural network encoder-decoder for large vocabulary speech recognition","year":2015,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":95,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Speech recognition; Vocabulary; Encoder; Artificial neural network; Recurrent neural network; Artificial intelligence; Natural language processing; Linguistics","score_opus":0.10396958659478608,"score_gpt":0.2999294749775426,"score_spread":0.1959598883827565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1942035323","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026238933,0.0028817612,0.9624009,0.00067152805,0.00012504375,0.00006152707,0.00014089812,0.0007498294,0.0067295795],"genre_scores_gemma":[0.6821048,0.0027293465,0.30054313,0.00030651974,0.00027980388,0.00020543006,0.0004560176,0.000297494,0.013077456],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999161,0.00038896344,0.000051346724,0.00016914171,0.00017307157,0.000056478162],"domain_scores_gemma":[0.9971227,0.0022062515,0.000128238,0.00017357865,0.0003191075,0.000049987975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020389035,0.0007921914,0.0006147786,0.00037248744,0.0003538187,0.0011360028,0.0012665518,0.0014379142,0.0028798294],"category_scores_gemma":[0.006510768,0.00068263756,0.00048803317,0.00048720863,0.00085865095,0.001878767,0.00056965806,0.001767214,0.00079998217],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029538517,0.00015839095,0.0015883817,0.00031301499,0.00014944015,0.00044957089,0.0002680169,0.6183497,0.025579318,0.14338405,0.0045417002,0.20492303],"study_design_scores_gemma":[0.0000047371664,0.000043541655,0.00011646819,0.000007640826,0.000010775414,0.000054113327,0.0000068552563,0.990035,0.0024277642,0.006561972,0.0007254746,0.000005701708],"about_ca_topic_score_codex":0.006712916,"about_ca_topic_score_gemma":0.009440484,"teacher_disagreement_score":0.006712916,"about_ca_system_score_codex":0.0013983699,"about_ca_system_score_gemma":0.0011149219,"threshold_uncertainty_score":0.013347685},"labels":[],"label_agreement":null},{"id":"W1954526745","doi":"10.1109/ccece.2000.849540","title":"Automatic identification of filled pauses in spontaneous speech","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Speech recognition; Computer science; Utterance; Spectral envelope; Confusion; Mel-frequency cepstrum; Identification (biology); Voice activity detection; Speech processing; Natural language processing; Artificial intelligence; Feature extraction; Psychology","score_opus":0.026060496288684152,"score_gpt":0.23438707841155257,"score_spread":0.20832658212286842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1954526745","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63359964,0.0013363023,0.35217252,0.00011174437,0.00017725173,0.00030216158,0.0021117828,0.006497672,0.0036908435],"genre_scores_gemma":[0.8489754,0.0004732445,0.14501892,0.0000383944,0.000081485225,0.0002198679,0.0028880853,0.0002073702,0.002097257],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99901414,0.00032426632,0.0000998532,0.00026481447,0.00022579459,0.00007115608],"domain_scores_gemma":[0.99555945,0.0026017444,0.0004295983,0.0005656554,0.0007159732,0.00012757098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084518385,0.00042638747,0.00040878754,0.0011595169,0.0002260711,0.0008518447,0.0005743656,0.00047072791,0.0014850058],"category_scores_gemma":[0.0053197136,0.00032110483,0.000261209,0.00042662004,0.00028404663,0.0008981357,0.000550914,0.00031321216,0.0011844464],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018907061,0.00015903762,0.018274873,0.00066321436,0.00007804212,0.0012352838,0.0016951826,0.0027449075,0.42024833,0.0020332271,0.0033564826,0.5476208],"study_design_scores_gemma":[0.00024548746,0.0017996398,0.20324798,0.00019138119,0.0002632538,0.0084351115,0.0017495987,0.21401575,0.53023404,0.008415375,0.031145025,0.0002574117],"about_ca_topic_score_codex":0.00028362148,"about_ca_topic_score_gemma":0.0003395725,"teacher_disagreement_score":0.0014850058,"about_ca_system_score_codex":0.00012863333,"about_ca_system_score_gemma":0.00017562664,"threshold_uncertainty_score":0.0049678683},"labels":[],"label_agreement":null},{"id":"W1960168474","doi":"10.1109/icassp.1983.1172102","title":"A comparison of distance measures for text-independent speaker identification","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Mahalanobis distance; Distance measures; Measure (data warehouse); Pattern recognition (psychology); k-nearest neighbors algorithm; Artificial intelligence; A priori and a posteriori; Earth mover's distance; Speech recognition; Maximum a posteriori estimation; Distance measurement; Correlation; Mathematics; Statistics; Computer science; Maximum likelihood; Data mining","score_opus":0.057792731379237454,"score_gpt":0.3270319084667389,"score_spread":0.26923917708750145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1960168474","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2815663,0.015151313,0.6867677,0.00041155212,0.00048480465,0.00044952575,0.000827115,0.0023885097,0.011953122],"genre_scores_gemma":[0.5201423,0.0024190198,0.47334242,0.00005229839,0.00010716206,0.0002692605,0.0013806405,0.0002922954,0.0019946042],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.990319,0.0029471787,0.0007963471,0.0006475698,0.00501212,0.0002777407],"domain_scores_gemma":[0.9760166,0.01590784,0.0008540358,0.0016393843,0.005250011,0.0003322371],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008342308,0.0010167016,0.0013897357,0.006880473,0.00077371404,0.0019335939,0.0012981608,0.0012969682,0.0015605689],"category_scores_gemma":[0.03728818,0.00030318782,0.00083213655,0.0042979284,0.0005341987,0.0025774045,0.0016129676,0.0007362233,0.0010967468],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021377602,0.00021744805,0.0059137545,0.00074177823,0.0003246793,0.00009787515,0.0004084742,0.054591127,0.014719258,0.011525365,0.0027342655,0.9065882],"study_design_scores_gemma":[0.0002129042,0.0026757335,0.023988357,0.00021174355,0.00024285502,0.0009391516,0.00084069074,0.90045017,0.044238817,0.015765147,0.010051763,0.00038273266],"about_ca_topic_score_codex":0.0024846995,"about_ca_topic_score_gemma":0.0017875895,"teacher_disagreement_score":0.008342308,"about_ca_system_score_codex":0.0010622127,"about_ca_system_score_gemma":0.0008775361,"threshold_uncertainty_score":0.04411888},"labels":[],"label_agreement":null},{"id":"W1963733617","doi":"10.1007/s10772-012-9146-4","title":"Speaker-independent ASR for Modern Standard Arabic: effect of regional accents","year":2012,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Speech recognition; Hidden Markov model; Arabic; Stress (linguistics); Modern Standard Arabic; Natural language processing; Artificial intelligence; Linguistics","score_opus":0.020494706954978407,"score_gpt":0.304830386805333,"score_spread":0.2843356798503546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1963733617","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8844714,0.0016014476,0.09667365,0.00031317212,0.00036039788,0.00009493879,0.0009633867,0.0021557182,0.013365866],"genre_scores_gemma":[0.9436872,0.00092983,0.04426977,0.00016729525,0.00013991659,0.00006768337,0.0015565774,0.00089394354,0.00828776],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993099,0.00024655391,0.00005133557,0.0001482212,0.00015685885,0.00008703492],"domain_scores_gemma":[0.99530196,0.0029435714,0.00015324203,0.0003716691,0.0010797197,0.00014982585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009314899,0.0009597995,0.00063359534,0.0003247899,0.00038867182,0.0007722515,0.00042507684,0.0006727576,0.006791135],"category_scores_gemma":[0.004594365,0.00027040954,0.00036687887,0.0003485848,0.00031528267,0.0009825237,0.00057407276,0.00091302244,0.0032823686],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0073426734,0.00023780654,0.0018395368,0.00044921474,0.00013835751,0.00043281342,0.00041339817,0.010556588,0.7722173,0.00075977715,0.0019029921,0.20370948],"study_design_scores_gemma":[0.00027307007,0.0030481813,0.037182007,0.000108354136,0.0008923093,0.0026204903,0.0006283313,0.19540338,0.7488014,0.0013746091,0.009476407,0.00019148353],"about_ca_topic_score_codex":0.0015769453,"about_ca_topic_score_gemma":0.00266878,"teacher_disagreement_score":0.006791135,"about_ca_system_score_codex":0.00015458962,"about_ca_system_score_gemma":0.00040919633,"threshold_uncertainty_score":0.022718668},"labels":[],"label_agreement":null},{"id":"W1963794214","doi":"10.1159/000265737","title":"Speaker Race Identification of Selected Adult North American Indians","year":2009,"lang":"en","type":"article","venue":"Folia Phoniatrica et Logopaedica","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Race (biology); Identification (biology); Speech recognition; Linguistics; Psychology; Computer science; Biology; Sociology; Gender studies","score_opus":0.0067712174134919294,"score_gpt":0.23543182760619846,"score_spread":0.22866061019270653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1963794214","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9984908,0.000039651775,0.00008890114,0.000018611532,0.000006953209,0.000008672832,0.00014604033,0.0000043644523,0.0011960344],"genre_scores_gemma":[0.9976172,0.00007808439,0.0001305117,0.000030521445,0.000008985783,0.00001526581,0.00021240098,0.0000068364075,0.0019001806],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9997831,0.000051053685,0.000019651176,0.00005033648,0.000041402065,0.000054533633],"domain_scores_gemma":[0.99967873,0.000060410657,0.000059141057,0.000018233508,0.00010925768,0.00007420179],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025192046,0.00022163078,0.00025762172,0.00066325284,0.0006328588,0.0004779046,0.00015976866,0.00021549774,0.0036480105],"category_scores_gemma":[0.0006979257,0.00008663652,0.00016541382,0.00028897813,0.00014558037,0.00017601893,0.00028839684,0.00019045,0.0012662937],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020814864,0.00036622732,0.91939485,0.000049713548,0.0000668344,0.0010521122,0.010264686,0.00009638151,0.039256405,0.00013923574,0.0006685027,0.026563626],"study_design_scores_gemma":[0.00000530545,0.0001463207,0.99397224,0.0000041564076,0.000026106547,0.0005012528,0.0034795252,0.00020146092,0.0011001024,0.00001759542,0.0005392345,0.0000067664387],"about_ca_topic_score_codex":0.009101587,"about_ca_topic_score_gemma":0.017412698,"teacher_disagreement_score":0.009101587,"about_ca_system_score_codex":0.00018751774,"about_ca_system_score_gemma":0.00016342044,"threshold_uncertainty_score":0.018097222},"labels":[],"label_agreement":null},{"id":"W1966290010","doi":"10.1063/1.3615726","title":"Nonlinear vocal fold dynamics resulting from asymmetric fluid loading on a two-mass model of speech","year":2011,"lang":"en","type":"article","venue":"Chaos An Interdisciplinary Journal of Nonlinear Science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Science Foundation","keywords":"Glottis; Bernoulli's principle; Inviscid flow; Nonlinear system; Vocal folds; Bifurcation; Fold (higher-order function); Flow (mathematics); Physics; Mechanics; Mathematics; Computer science; Larynx; Anatomy; Thermodynamics","score_opus":0.05962507340745751,"score_gpt":0.31863793774453036,"score_spread":0.2590128643370728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1966290010","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9332205,0.00019965111,0.05241841,0.00046230038,0.000056825622,0.00006664408,0.00016102748,0.0001480299,0.013266632],"genre_scores_gemma":[0.99345946,0.00009330158,0.0020040516,0.000026880234,0.00001289065,0.000038638427,0.000040215094,0.00001722292,0.004307356],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999192,0.000022600141,0.0000037265577,0.000013821937,0.00002229164,0.000018454706],"domain_scores_gemma":[0.99978,0.00009713403,0.000038786842,0.000018038656,0.000025798212,0.000040418414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017085306,0.0006352639,0.00055176375,0.00033477068,0.00052093045,0.00067590276,0.0006607409,0.0014179642,0.0014680673],"category_scores_gemma":[0.0006542987,0.00028604435,0.0005339686,0.00013245737,0.0011017417,0.0004582107,0.000696516,0.0004252507,0.00027262312],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000115864954,0.000041708634,0.0010162299,0.0000386964,0.000013121602,0.0004989312,0.00014452999,0.9666858,0.024197964,0.0054052896,0.00020615134,0.0016357483],"study_design_scores_gemma":[0.000008424507,0.00001645606,0.0002586778,0.0000022952297,0.0000029499424,0.00001683134,0.000013497098,0.9988122,0.00046325492,0.00032656873,0.00007373464,0.000005253557],"about_ca_topic_score_codex":0.008290023,"about_ca_topic_score_gemma":0.0036256195,"teacher_disagreement_score":0.008290023,"about_ca_system_score_codex":0.0006061878,"about_ca_system_score_gemma":0.0005155079,"threshold_uncertainty_score":0.016483545},"labels":[],"label_agreement":null},{"id":"W1968419113","doi":"10.1109/asru.2013.6707745","title":"Deep maxout neural networks for speech recognition","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":76,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Université de Montréal","keywords":"Sigmoid function; Computer science; Benchmark (surveying); Artificial neural network; Dropout (neural networks); Artificial intelligence; Task (project management); Deep neural networks; Speech recognition; Nonlinear system; Generalization; Machine learning; Engineering; Mathematics","score_opus":0.03354279461887392,"score_gpt":0.23932929487816432,"score_spread":0.2057865002592904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968419113","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015958786,0.002276926,0.9741805,0.00034775195,0.00017105878,0.000036097135,0.0003011348,0.0034441533,0.0032836145],"genre_scores_gemma":[0.5348635,0.0018537857,0.43538782,0.0005774673,0.0002586851,0.00021367821,0.0018919192,0.00055122504,0.02440192],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996518,0.00009881937,0.000023141727,0.00011442922,0.00007462308,0.000037301637],"domain_scores_gemma":[0.9994899,0.00024508184,0.000048827882,0.00008503772,0.00011050457,0.0000206714],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011527818,0.001318631,0.00059773406,0.0004140518,0.0003738685,0.00076324755,0.0012994187,0.0010938216,0.004959896],"category_scores_gemma":[0.0022021134,0.00053380907,0.00060086703,0.00058894046,0.000522295,0.0018610655,0.00089418446,0.0016549953,0.0016546124],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040417793,0.000114190676,0.00077993947,0.00021801871,0.00012184666,0.00012638346,0.00010193824,0.39168763,0.01990449,0.011801778,0.009869043,0.56487054],"study_design_scores_gemma":[0.0000070271217,0.000036768324,0.00019477766,0.000014043263,0.000011921262,0.000028605831,0.000007880757,0.9817183,0.008381328,0.0066510746,0.0029362098,0.0000120925715],"about_ca_topic_score_codex":0.002998872,"about_ca_topic_score_gemma":0.0049845157,"teacher_disagreement_score":0.004959896,"about_ca_system_score_codex":0.00071243587,"about_ca_system_score_gemma":0.00055362197,"threshold_uncertainty_score":0.016592562},"labels":[],"label_agreement":null},{"id":"W1970000881","doi":"10.1016/s0167-6393(02)00013-4","title":"Analytic assessment of telephone transmission impact on ASR performance using a simulation model","year":2002,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Nutrition, Metabolism and Diabetes","keywords":"Computer science; Telephone network; Transmission channel; Transmission (telecommunications); Speech recognition; Degradation (telecommunications); Voice activity detection; Relation (database); Speech processing; Telecommunications; Data mining","score_opus":0.08195727356324413,"score_gpt":0.34907161388960445,"score_spread":0.26711434032636033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970000881","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7951549,0.0006133482,0.18272065,0.0004401731,0.0000592107,0.00014452747,0.0004626988,0.0011311397,0.019273262],"genre_scores_gemma":[0.9948265,0.0001139352,0.0037132965,0.000020728296,0.0000099358185,0.000029932095,0.000082218525,0.00003983316,0.0011634898],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995265,0.00019240264,0.000017292572,0.000046024335,0.00012933215,0.00008848187],"domain_scores_gemma":[0.99619126,0.002905967,0.00022477318,0.00012485613,0.00051104336,0.00004214089],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006912885,0.00081506063,0.0007856853,0.00060071214,0.0004362822,0.0006797175,0.0008302614,0.0013361762,0.0029280917],"category_scores_gemma":[0.0052788644,0.00048468504,0.00058259175,0.0005627204,0.00047478912,0.0009241751,0.00041216207,0.00055089116,0.0005224693],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011565233,0.00002492839,0.000408416,0.00003315009,0.000011782819,0.000060593236,0.000029936014,0.99345016,0.0025439416,0.0010428596,0.00013225492,0.0021463349],"study_design_scores_gemma":[0.00000839614,0.000063425556,0.00020775387,0.000004127815,0.000014313077,0.000021991416,0.000010051654,0.9982564,0.0011390653,0.00017678886,0.00009223023,0.0000055176197],"about_ca_topic_score_codex":0.008289681,"about_ca_topic_score_gemma":0.0031115676,"teacher_disagreement_score":0.008289681,"about_ca_system_score_codex":0.0009495953,"about_ca_system_score_gemma":0.0005080795,"threshold_uncertainty_score":0.01648289},"labels":[],"label_agreement":null},{"id":"W1970749564","doi":"10.2316/journal.201.2007.1.201-1545","title":"SPEECH RECOGNITION USING MULTILAYER RECURRENT NEURAL PREDICTION MODELS AND HMM","year":2007,"lang":"en","type":"article","venue":"Control and Intelligent Systems","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Hidden Markov model; Speech recognition; Computer science; Artificial neural network; Artificial intelligence; Pattern recognition (psychology)","score_opus":0.0753432608597366,"score_gpt":0.2743650464735851,"score_spread":0.19902178561384853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970749564","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022844456,0.0005516203,0.9727672,0.0000803138,0.000062443614,0.000022539894,0.00007420994,0.0018842974,0.0017129976],"genre_scores_gemma":[0.5749372,0.00092482835,0.41709486,0.00009754152,0.00006575601,0.00008126748,0.0004406685,0.00014690131,0.0062109325],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99951005,0.00013483099,0.000038028324,0.00011748174,0.00016265693,0.000036982856],"domain_scores_gemma":[0.9994804,0.0002315225,0.000053964934,0.00008433098,0.00013606314,0.000013671617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007999737,0.0004026539,0.00043412056,0.0003306681,0.0001628359,0.0005455215,0.00052520947,0.0004992982,0.0014673064],"category_scores_gemma":[0.0017557065,0.0003042006,0.00050433184,0.00036098334,0.00021691974,0.0010277648,0.00033822475,0.0005119296,0.00092136685],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003309619,0.000095365525,0.002277255,0.00028213277,0.0001948922,0.00029042287,0.00023392773,0.32288587,0.07165753,0.011866259,0.0024891375,0.5873962],"study_design_scores_gemma":[0.0000056621548,0.0000409357,0.00043483233,0.0000103318125,0.000022656137,0.00005704357,0.000009100185,0.9878842,0.008954764,0.0013411508,0.001226236,0.000013124427],"about_ca_topic_score_codex":0.0042836904,"about_ca_topic_score_gemma":0.004983175,"teacher_disagreement_score":0.0042836904,"about_ca_system_score_codex":0.0003518231,"about_ca_system_score_gemma":0.00033805307,"threshold_uncertainty_score":0.008517504},"labels":[],"label_agreement":null},{"id":"W1970996882","doi":"10.1121/1.1420380","title":"An overlapping-feature-based phonological model incorporating linguistic constraints: Applications to speech recognition","year":2002,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":71,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Hidden Markov model; Feature (linguistics); Syllable; Speech recognition; Phrase; Artificial intelligence; Morpheme; Word (group theory); Natural language processing; Dependency (UML); Acoustic model; Linguistics; Speech processing","score_opus":0.04045392051542798,"score_gpt":0.2698564663430641,"score_spread":0.2294025458276361,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970996882","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016571715,0.00022937212,0.9816373,0.000112154594,0.000027157103,0.000016595486,0.00004494622,0.00049205817,0.00086874224],"genre_scores_gemma":[0.5342016,0.00072710594,0.46219692,0.000086766464,0.00006179802,0.00012422891,0.00015635577,0.00014409101,0.002301163],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998634,0.000031149564,0.000010030468,0.000041185867,0.00004264435,0.000011631564],"domain_scores_gemma":[0.9995671,0.00026490318,0.00003079269,0.000057797002,0.00006230743,0.000017170647],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035117,0.00030279148,0.00060111133,0.00025492278,0.00027791035,0.00050627196,0.000869109,0.0006588723,0.0015508448],"category_scores_gemma":[0.0013674266,0.0002608255,0.0003985581,0.0004010786,0.00044240613,0.0011309352,0.00037817235,0.0005975532,0.000532879],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000113381204,0.00010562466,0.0008752664,0.00015973157,0.00006663335,0.00033093456,0.00021814756,0.63423634,0.0283925,0.035071496,0.0012544341,0.2991755],"study_design_scores_gemma":[0.000003107518,0.000017053788,0.00010648123,0.0000046408377,0.000007401892,0.00006120724,0.0000075710877,0.9895307,0.0010714356,0.008698074,0.00048251418,0.000009832752],"about_ca_topic_score_codex":0.0029414014,"about_ca_topic_score_gemma":0.0037097563,"teacher_disagreement_score":0.0029414014,"about_ca_system_score_codex":0.0002783044,"about_ca_system_score_gemma":0.00054151897,"threshold_uncertainty_score":0.0058485866},"labels":[],"label_agreement":null},{"id":"W1972278020","doi":"10.1006/csla.2000.0143","title":"Tree-structured vector quantization for speech recognition","year":2000,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Smoothing; Hidden Markov model; Computer science; Vector quantization; Pattern recognition (psychology); Speech recognition; Gaussian; Tree (set theory); Entropy (arrow of time); Artificial intelligence; Feature vector; Mixture model; Curse of dimensionality; Mathematics","score_opus":0.019873500248218698,"score_gpt":0.2541196303712127,"score_spread":0.234246130122994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972278020","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043886728,0.0019612678,0.98891836,0.00022964722,0.00028201388,0.00005080829,0.00068634516,0.002240837,0.0012419645],"genre_scores_gemma":[0.15709428,0.0023374767,0.8267862,0.00033130028,0.00026411976,0.00029257746,0.0038958986,0.00028378953,0.0087143155],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993616,0.00016133173,0.000076097625,0.000117040145,0.00022258198,0.000061340645],"domain_scores_gemma":[0.9991405,0.0002772054,0.000045041354,0.00019456037,0.00032085137,0.000021812235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061191915,0.0006180851,0.0010408241,0.000634757,0.00041668274,0.0008671399,0.0010243284,0.0008200989,0.007481222],"category_scores_gemma":[0.0021795845,0.00028629808,0.000464,0.0019035772,0.0004436638,0.0013994616,0.0005682086,0.0011171747,0.0029135593],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002138356,0.00007949204,0.00019111024,0.00017568498,0.000032776654,0.000037741167,0.000058780683,0.040383775,0.015856097,0.049676728,0.028595285,0.8646987],"study_design_scores_gemma":[0.0000625044,0.0001190756,0.00043452656,0.00005619404,0.000023122946,0.00008430851,0.000047316244,0.8943922,0.012811526,0.07708989,0.014840768,0.000038600498],"about_ca_topic_score_codex":0.009400433,"about_ca_topic_score_gemma":0.010892937,"teacher_disagreement_score":0.009400433,"about_ca_system_score_codex":0.0006722113,"about_ca_system_score_gemma":0.0014197979,"threshold_uncertainty_score":0.025027156},"labels":[],"label_agreement":null},{"id":"W1972404024","doi":"10.1109/dsp-spe.2013.6642556","title":"Diacritization, automatic segmentation and labeling for Levantine Arabic speech","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Arabic; Pronunciation; Transcription (linguistics); Segmentation; Speech recognition; Phonetic transcription; Artificial intelligence; Natural language processing; Speech processing; Speech corpus; Reliability (semiconductor); Speech synthesis; Linguistics","score_opus":0.015979757172952688,"score_gpt":0.24563861917994184,"score_spread":0.22965886200698915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972404024","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21543628,0.001186022,0.757274,0.00041650177,0.0005291236,0.00045342848,0.0017042733,0.015748084,0.007252292],"genre_scores_gemma":[0.23049295,0.00049261726,0.75173193,0.0001292405,0.00016290079,0.00046293842,0.004885535,0.001682971,0.009958866],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99900144,0.00027806728,0.0001036007,0.0003071359,0.00024181146,0.00006802805],"domain_scores_gemma":[0.99769396,0.00069735956,0.00017072621,0.00044251775,0.00091436127,0.00008105872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011049496,0.0009341697,0.0007134247,0.0015854759,0.0010105295,0.0011349813,0.00096302974,0.00062009186,0.005728128],"category_scores_gemma":[0.0030185478,0.00045885213,0.00033212264,0.00066996884,0.00064204907,0.00086130644,0.0007738737,0.0008219715,0.0044304216],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007441225,0.00009832056,0.0013185567,0.0004767314,0.000026317404,0.00044488112,0.00082581973,0.0048260153,0.52253336,0.0014726251,0.005308835,0.46192443],"study_design_scores_gemma":[0.000086447006,0.00037591538,0.010342373,0.000079098885,0.00007841046,0.000983572,0.00072948576,0.117599584,0.8099213,0.0017434312,0.057912596,0.00014786485],"about_ca_topic_score_codex":0.0038712,"about_ca_topic_score_gemma":0.007895648,"teacher_disagreement_score":0.005728128,"about_ca_system_score_codex":0.0005763079,"about_ca_system_score_gemma":0.0009301522,"threshold_uncertainty_score":0.019162476},"labels":[],"label_agreement":null},{"id":"W1976677479","doi":"10.1007/s10772-015-9276-6","title":"Feature selection for robust automatic speech recognition: a temporal offset approach","year":2015,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Speech recognition; Offset (computer science); Pattern recognition (psychology); Mel-frequency cepstrum; Feature selection; Artificial intelligence; Noise (video); Selection (genetic algorithm); Feature (linguistics); Feature extraction","score_opus":0.05480987488323085,"score_gpt":0.28389007859278653,"score_spread":0.22908020370955567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976677479","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017404208,0.00048125253,0.9807582,0.000070952265,0.00006628854,0.000027692426,0.000088199675,0.00048756567,0.00061569427],"genre_scores_gemma":[0.40232277,0.00097241206,0.58792436,0.00013667146,0.00023277005,0.00019019085,0.00096170005,0.00042422808,0.006834802],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99963045,0.00006847889,0.000028622902,0.00007928431,0.00013844452,0.00005469796],"domain_scores_gemma":[0.9995184,0.00018397071,0.000040842067,0.00006587406,0.00016902995,0.000021802782],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005744324,0.0005721557,0.00080063957,0.00066037383,0.00037885885,0.0005704214,0.0005883424,0.00042034374,0.0022933423],"category_scores_gemma":[0.0013396824,0.00023630136,0.0007345921,0.00086358935,0.00024765634,0.00062280486,0.0005830406,0.00064505544,0.0008628293],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005947057,0.00016501015,0.0011062326,0.00011531347,0.00009550109,0.00014316684,0.00004367608,0.022265632,0.1478152,0.0040229307,0.0019631982,0.8216694],"study_design_scores_gemma":[0.000054145316,0.00046250754,0.00831192,0.000024519308,0.00018550122,0.00038776503,0.00006756776,0.8821193,0.095848516,0.0048027085,0.0076823076,0.000053233787],"about_ca_topic_score_codex":0.0015460118,"about_ca_topic_score_gemma":0.002119605,"teacher_disagreement_score":0.0022933423,"about_ca_system_score_codex":0.00020767389,"about_ca_system_score_gemma":0.00065173546,"threshold_uncertainty_score":0.007672012},"labels":[],"label_agreement":null},{"id":"W1976874961","doi":"10.1121/1.2935778","title":"Adaptive threshold estimation for speaker verification systems","year":2008,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Speaker verification; Speech recognition; Authentication (law); Speaker recognition; Outlier; Artificial intelligence","score_opus":0.03994724399412187,"score_gpt":0.2565891544558379,"score_spread":0.21664191046171605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976874961","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040420345,0.0005494716,0.9938291,0.00003899439,0.000067318586,0.000036445203,0.000026796695,0.0008808452,0.0005289687],"genre_scores_gemma":[0.34648827,0.00090210687,0.64793944,0.0001434372,0.00017752277,0.00015046174,0.00025910678,0.00022141293,0.0037182164],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980762,0.00030797897,0.00014940831,0.0005005218,0.0008471244,0.00011866311],"domain_scores_gemma":[0.99834037,0.0006552216,0.00017385693,0.0002502802,0.0005373177,0.00004289698],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013155299,0.0007735747,0.00088213896,0.00096256513,0.0006020878,0.0011429377,0.00167658,0.0011783055,0.00225498],"category_scores_gemma":[0.0053919097,0.0004186346,0.0006252144,0.0007630934,0.00044299097,0.0013643593,0.0010460722,0.0012694817,0.0016695195],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005580412,0.00007610726,0.001362618,0.00027407386,0.00014302635,0.00018918842,0.000184519,0.06273978,0.12802002,0.015311712,0.0035331051,0.78760785],"study_design_scores_gemma":[0.000036611204,0.00024037126,0.00166195,0.00004349849,0.000099504956,0.0007418205,0.0000487822,0.8709143,0.10248706,0.010133949,0.013496375,0.000095783194],"about_ca_topic_score_codex":0.001302542,"about_ca_topic_score_gemma":0.00092043896,"teacher_disagreement_score":0.00225498,"about_ca_system_score_codex":0.0007334418,"about_ca_system_score_gemma":0.0005434202,"threshold_uncertainty_score":0.007543683},"labels":[],"label_agreement":null},{"id":"W1977321041","doi":"10.1121/1.4778589","title":"Speaker adaptation of HMMs using evolutionary strategy-based linear regression","year":2002,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; TIMIT; Hidden Markov model; Robustness (evolution); Transformation (genetics); Speech recognition; Regression; Artificial intelligence; Pattern recognition (psychology); Linear map; Mathematics; Statistics","score_opus":0.05762203781710408,"score_gpt":0.27280874767060403,"score_spread":0.21518670985349997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977321041","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0075904154,0.00011714944,0.9912164,0.00002648657,0.00002295411,0.00001731009,0.000011424653,0.0005768915,0.00042099436],"genre_scores_gemma":[0.24103445,0.00031251498,0.75480646,0.00006425648,0.000058803776,0.0001509858,0.00017940442,0.0002546665,0.003138435],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99954754,0.0001444082,0.000022645583,0.00010892263,0.00013867086,0.000037786736],"domain_scores_gemma":[0.9995648,0.00025596248,0.000031295134,0.00004877262,0.00008458418,0.000014482562],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078419165,0.000496285,0.0006345417,0.00036781354,0.00021927724,0.00041797428,0.00072976167,0.00057431526,0.0010032582],"category_scores_gemma":[0.0017541117,0.00036688903,0.0007360094,0.00030927785,0.0003024193,0.0005597048,0.0005947897,0.0008453767,0.00053393585],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011399717,0.000104548344,0.0008303043,0.000098094264,0.00017431963,0.00019770775,0.00021901791,0.46343443,0.06961936,0.010488712,0.0012240391,0.45349553],"study_design_scores_gemma":[0.000008458114,0.000032343738,0.0003377284,0.0000040023356,0.000015683308,0.000057675286,0.0000074345494,0.9910948,0.0060010804,0.0013900003,0.0010379305,0.000012769265],"about_ca_topic_score_codex":0.0015181509,"about_ca_topic_score_gemma":0.0017413526,"teacher_disagreement_score":0.0015181509,"about_ca_system_score_codex":0.00029782014,"about_ca_system_score_gemma":0.00026333547,"threshold_uncertainty_score":0.0041472316},"labels":[],"label_agreement":null},{"id":"W1977413534","doi":"10.1121/1.4788442","title":"The tube resonance model speech synthesizer","year":2005,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Acoustics; RADIUS; Resonance (particle physics); Vocal tract; Physics; Tube (container); Acoustic resonance; Scattering; Range (aeronautics); Optics; Materials science; Computer science; Atomic physics","score_opus":0.017115047730919007,"score_gpt":0.24677283586155804,"score_spread":0.22965778813063903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977413534","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021857629,0.00026378545,0.93279994,0.00014940681,0.00017336074,0.00020952517,0.0011169678,0.024491305,0.01893802],"genre_scores_gemma":[0.3399074,0.00036483177,0.607344,0.0002803863,0.00011459744,0.0009299507,0.003987859,0.002976878,0.04409409],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996561,0.00006337822,0.000016319555,0.00008922722,0.00015146336,0.000023507624],"domain_scores_gemma":[0.9997919,0.000083337116,0.000012174381,0.00003613182,0.00006158181,0.000014801653],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033926475,0.0005529694,0.00046864647,0.00034292988,0.00031420152,0.000722792,0.000711802,0.00096003176,0.018589968],"category_scores_gemma":[0.0011287546,0.00031411406,0.00041468954,0.00018080988,0.00024401632,0.00059213827,0.00050073495,0.00057581783,0.007870553],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011812914,0.00015914421,0.0011934888,0.0004741405,0.00010335682,0.0010303025,0.00046422053,0.09069196,0.3777205,0.046130374,0.039896194,0.4409551],"study_design_scores_gemma":[0.0001385931,0.00042590417,0.0007502389,0.000039684644,0.00006051382,0.0010845485,0.00005133048,0.74594027,0.13286926,0.006626599,0.11192153,0.00009151765],"about_ca_topic_score_codex":0.00058243686,"about_ca_topic_score_gemma":0.00075013563,"teacher_disagreement_score":0.018589968,"about_ca_system_score_codex":0.0002739052,"about_ca_system_score_gemma":0.00041513945,"threshold_uncertainty_score":0.06218964},"labels":[],"label_agreement":null},{"id":"W1978513628","doi":"10.2316/journal.201.2011.4.201-2300","title":"cROVER: THE CONTEXT-AUGMENTED ROVER","year":2011,"lang":"en","type":"article","venue":"Control and Intelligent Systems","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Vocabulary; Word error rate; Speech recognition; Context (archaeology); Word (group theory); Artificial intelligence; Natural language processing; Linguistics; History","score_opus":0.034877992398342265,"score_gpt":0.2140671539285279,"score_spread":0.17918916153018563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978513628","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10133076,0.00679715,0.7501013,0.0009325964,0.0017633459,0.00059974083,0.0040351087,0.07497263,0.05946741],"genre_scores_gemma":[0.4067067,0.0017800053,0.52992564,0.00095824106,0.00035369108,0.0003373414,0.0071699917,0.0024460643,0.05032232],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.999723,0.00004677771,0.00000917408,0.00009464518,0.000092188326,0.000034077657],"domain_scores_gemma":[0.99985766,0.000017973052,0.0000117822165,0.000054909386,0.000040003626,0.000017560458],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022728051,0.0009227616,0.0005953341,0.00040997996,0.00042323873,0.00071079435,0.0009183174,0.000706098,0.007124187],"category_scores_gemma":[0.00050397456,0.00022785965,0.00026412072,0.0003247648,0.00045727275,0.00074653176,0.0010234275,0.00085337536,0.0038770388],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015377685,0.00019307547,0.0034021009,0.00044940354,0.00015403482,0.00078629743,0.00033164097,0.025457125,0.121788464,0.0150634805,0.05816807,0.77266854],"study_design_scores_gemma":[0.0003700906,0.0010616949,0.005881336,0.00014579821,0.00018454173,0.0019231817,0.00029282583,0.24847952,0.091603525,0.012365908,0.63744247,0.0002490502],"about_ca_topic_score_codex":0.0041056084,"about_ca_topic_score_gemma":0.01198711,"teacher_disagreement_score":0.007124187,"about_ca_system_score_codex":0.00015145383,"about_ca_system_score_gemma":0.0005086816,"threshold_uncertainty_score":0.023832798},"labels":[],"label_agreement":null},{"id":"W1979346920","doi":"10.1121/1.4779372","title":"Evaluation of a strategy for automatic formant tracking","year":2002,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Formant; Speech recognition; Computer science; Spectrogram; Utterance; Autocorrelation; Vowel; Set (abstract data type); Sampling (signal processing); Intelligibility (philosophy); Mathematics; Statistics; Detector; Telecommunications","score_opus":0.0884424278516014,"score_gpt":0.31017590874627304,"score_spread":0.22173348089467165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979346920","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40980595,0.0003479583,0.56837136,0.00022579233,0.00019175396,0.0011286205,0.0004547258,0.013530384,0.0059434604],"genre_scores_gemma":[0.52056766,0.00012857413,0.4725322,0.00015294291,0.000040044073,0.00046808072,0.001070127,0.00057879195,0.0044616577],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978903,0.00046194717,0.00015416305,0.00046437455,0.0008667988,0.00016241655],"domain_scores_gemma":[0.994218,0.002410918,0.0001473553,0.0006977979,0.0023214424,0.00020456483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026881706,0.0009309727,0.00066603895,0.0010538754,0.0005567375,0.0008805844,0.001975711,0.001035988,0.0030128704],"category_scores_gemma":[0.009020424,0.00033030225,0.00033724122,0.00091391813,0.00043792266,0.00097320805,0.00080063427,0.00048690243,0.0011449482],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002041043,0.0011255366,0.004192412,0.00021147258,0.000121427845,0.0002394293,0.00034739313,0.031295642,0.14236815,0.001962662,0.0022664592,0.81382835],"study_design_scores_gemma":[0.00081043557,0.004387694,0.017846,0.000028780069,0.00019643763,0.000781584,0.0003830469,0.7587307,0.2060427,0.0009513605,0.009691901,0.00014944487],"about_ca_topic_score_codex":0.025606424,"about_ca_topic_score_gemma":0.016263051,"teacher_disagreement_score":0.025606424,"about_ca_system_score_codex":0.0010008438,"about_ca_system_score_gemma":0.0015594444,"threshold_uncertainty_score":0.050914764},"labels":[],"label_agreement":null},{"id":"W1980921678","doi":"10.1075/pc.14.2.16kan","title":"Speech transformation solutions","year":2006,"lang":"en","type":"article","venue":"Pragmatics & Cognition","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cape Breton University","funders":"","keywords":"Dictation; Computer science; Spotting; Speech recognition; Keyword spotting; Perception; Interface (matter); Distributive property; Transformation (genetics); Human–computer interaction; Multimedia; Artificial intelligence; Natural language processing","score_opus":0.022333147322471096,"score_gpt":0.23427528483208632,"score_spread":0.2119421375096152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980921678","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0065292795,0.0014998786,0.851301,0.0017619919,0.0011347111,0.00043946746,0.00087493856,0.019573608,0.116885014],"genre_scores_gemma":[0.14153454,0.002994813,0.500022,0.0026262326,0.00096922345,0.00090558245,0.008598472,0.0042142705,0.3381349],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99845874,0.00015780148,0.00010683229,0.00039049945,0.0007080364,0.0001779731],"domain_scores_gemma":[0.99888915,0.00017268176,0.00005286867,0.00032196284,0.00049555494,0.000067714784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009917837,0.0011486346,0.00059314794,0.0012602649,0.0011572967,0.002744611,0.0024603724,0.00205877,0.079508625],"category_scores_gemma":[0.0023658087,0.00045181077,0.00075966807,0.0009490824,0.00061423687,0.002737671,0.0030629698,0.001915085,0.056739055],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031606774,0.00024502003,0.0003795194,0.00035606982,0.000041592488,0.0003497347,0.00056525203,0.0041223047,0.047142256,0.07480525,0.047624514,0.82405233],"study_design_scores_gemma":[0.00008992062,0.00018758824,0.00050646946,0.00014269479,0.000048076316,0.001166925,0.000552991,0.03968579,0.07019388,0.04277687,0.8445781,0.00007074934],"about_ca_topic_score_codex":0.0011105884,"about_ca_topic_score_gemma":0.0010220775,"teacher_disagreement_score":0.079508625,"about_ca_system_score_codex":0.00090198114,"about_ca_system_score_gemma":0.0012715334,"threshold_uncertainty_score":0.26598287},"labels":[],"label_agreement":null},{"id":"W1981185131","doi":"10.1109/iscslp.2014.6936584","title":"Speaker adaptive bottleneck features extraction for LVCSR based on discriminative learning of speaker codes","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Speech recognition; Discriminative model; Speaker recognition; Hidden Markov model; Bottleneck; Speaker diarisation; Adaptation (eye); Word error rate; Pattern recognition (psychology); Feature extraction; Artificial intelligence; Task (project management); Engineering","score_opus":0.027343633529193816,"score_gpt":0.27562299606117074,"score_spread":0.24827936253197694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981185131","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022040498,0.0005774953,0.9750906,0.00004505641,0.00003699981,0.000058518788,0.00013359745,0.0014723799,0.00054491096],"genre_scores_gemma":[0.30720097,0.00066697714,0.68749607,0.00010222501,0.00009088388,0.0002417143,0.0014081574,0.0002942232,0.002498704],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995926,0.00007869166,0.000024343457,0.00010346822,0.00016116003,0.000039866365],"domain_scores_gemma":[0.99940073,0.00022286513,0.000044862078,0.00008499049,0.00021676894,0.000029739986],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007058534,0.0008859767,0.0007827746,0.0011932832,0.00022958593,0.0002897915,0.000754121,0.000451853,0.0016660936],"category_scores_gemma":[0.0011623645,0.00030350563,0.000523351,0.0007038524,0.00028640428,0.00067712064,0.00056413165,0.0008050101,0.0010710495],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030877124,0.00011164146,0.0012950876,0.00016143308,0.00007443112,0.00011438197,0.00008814443,0.02064836,0.2453285,0.0015426303,0.0023316948,0.7279949],"study_design_scores_gemma":[0.000032670923,0.00018106298,0.0058630123,0.000021761534,0.000072583774,0.00031314307,0.000036206035,0.8346443,0.1522575,0.0015090071,0.005007958,0.00006083729],"about_ca_topic_score_codex":0.0022358033,"about_ca_topic_score_gemma":0.0038170514,"teacher_disagreement_score":0.0022358033,"about_ca_system_score_codex":0.00035041285,"about_ca_system_score_gemma":0.00059586886,"threshold_uncertainty_score":0.0055736303},"labels":[],"label_agreement":null},{"id":"W1981517541","doi":"10.1121/1.4877151","title":"Using criterio voice familiarity to augment the accuracy of speaker identification in voice lineups","year":2014,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Psychology; Speaker identification; Identification (biology); Syllable; Speech recognition; Semitone; Duration (music); Audiology; Speaker recognition; Computer science; Acoustics","score_opus":0.03805159423408117,"score_gpt":0.3033150911949351,"score_spread":0.26526349696085394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981517541","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98743165,0.00008441906,0.011853971,0.000013271214,0.000009104807,0.000042931293,0.000026949036,0.00010675162,0.0004309517],"genre_scores_gemma":[0.9887582,0.000042074902,0.010836525,0.000021195263,0.000015220788,0.000046716756,0.00008151161,0.000040860476,0.00015770787],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.996822,0.0016889058,0.00036478572,0.00049235485,0.0005023665,0.00012951742],"domain_scores_gemma":[0.9698492,0.022248708,0.0034612808,0.0024001729,0.0014793023,0.00056133745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028286253,0.00047559608,0.0006388138,0.0004706238,0.00021071102,0.00081092457,0.00045718797,0.00064309296,0.0018138316],"category_scores_gemma":[0.02317947,0.00027475602,0.00026903735,0.00029125923,0.0005094252,0.0012832889,0.0010193061,0.0003859168,0.00037411947],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009265846,0.0005628792,0.07867941,0.00039219655,0.00016664165,0.0003562162,0.001070818,0.0020373645,0.7599595,0.00018757192,0.00010193149,0.1472196],"study_design_scores_gemma":[0.00028366758,0.023978572,0.49255982,0.000074976284,0.00048605743,0.0025362032,0.00092998333,0.024072193,0.4525709,0.0007829434,0.0015274077,0.00019731928],"about_ca_topic_score_codex":0.00029012488,"about_ca_topic_score_gemma":0.0004950433,"teacher_disagreement_score":0.0028286253,"about_ca_system_score_codex":0.00019161776,"about_ca_system_score_gemma":0.00012497327,"threshold_uncertainty_score":0.014959395},"labels":[],"label_agreement":null},{"id":"W1981932308","doi":"10.1109/icassp.2010.5495109","title":"I-smooth for improved minimum classification error training","year":2010,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Hidden Markov model; TIMIT; Discriminative model; Computer science; Boundary (topology); Interpolation (computer graphics); Generalization; Speech recognition; Word error rate; Pattern recognition (psychology); Confusion; Artificial intelligence; Training (meteorology); Training set; Task (project management); Mathematics; Engineering","score_opus":0.0834741312720563,"score_gpt":0.29785911738937093,"score_spread":0.21438498611731463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981932308","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027759854,0.00024216349,0.96559805,0.00016665428,0.00006371193,0.000047750258,0.0001117272,0.0040142564,0.0019957826],"genre_scores_gemma":[0.3477462,0.00017011836,0.64222807,0.00021060895,0.000053557695,0.00020228855,0.0009617117,0.0008524983,0.007574956],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910164,0.00021471849,0.00004950063,0.00025324934,0.00027904677,0.0001018363],"domain_scores_gemma":[0.9975358,0.0012593531,0.000104491395,0.0005872366,0.00042903982,0.00008398842],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017653385,0.0008110969,0.0008574782,0.00068819476,0.00045521828,0.00071860105,0.0015263392,0.0013441036,0.005049818],"category_scores_gemma":[0.008513427,0.0005455493,0.00056999153,0.0006700203,0.00059225986,0.0011391692,0.0017180812,0.0021478157,0.0021091627],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00075117516,0.00024178077,0.0028136421,0.00016143902,0.0000625221,0.00013598289,0.00023970689,0.2194401,0.03870609,0.010720781,0.0063381526,0.72038865],"study_design_scores_gemma":[0.000015224327,0.0000481454,0.0007248122,0.000011257653,0.000008090455,0.00004773562,0.000016610718,0.98626906,0.0090294,0.0019936655,0.0018243289,0.000011660914],"about_ca_topic_score_codex":0.0029967541,"about_ca_topic_score_gemma":0.004206562,"teacher_disagreement_score":0.005049818,"about_ca_system_score_codex":0.00043658237,"about_ca_system_score_gemma":0.00087460806,"threshold_uncertainty_score":0.016893327},"labels":[],"label_agreement":null},{"id":"W1988809937","doi":"10.5539/mas.v4n10p97","title":"Concatenative Synthesis of Persian Language Based on Word, Diphone and Triphone Databases","year":2010,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Speech synthesis; Speech recognition; Word (group theory); Persian; Set (abstract data type); Vocabulary; Natural language processing; Artificial intelligence; Speech corpus; Part of speech; Database; Linguistics","score_opus":0.015493047792780346,"score_gpt":0.2480546913990974,"score_spread":0.23256164360631704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988809937","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.071972676,0.0011986191,0.9156928,0.000118909455,0.00022188576,0.00011983843,0.000267654,0.0039612036,0.0064463876],"genre_scores_gemma":[0.50006205,0.00066781393,0.49086803,0.00011068256,0.00011109404,0.00019629256,0.00078498037,0.0001895298,0.0070094676],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99975437,0.000056411067,0.000026345955,0.00007254641,0.00007319772,0.000017158638],"domain_scores_gemma":[0.99978834,0.00007678042,0.000018724793,0.000030119278,0.000074346994,0.000011702544],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032205402,0.00060437754,0.00044073857,0.00039961783,0.0003378744,0.0004495151,0.00036671606,0.00029504122,0.003076835],"category_scores_gemma":[0.0005446806,0.00016380672,0.00039258614,0.0002739159,0.00022017663,0.00058122905,0.00036218777,0.00023370581,0.0010910747],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00092749466,0.00007867698,0.0009378667,0.0005175229,0.000099238256,0.00075986254,0.00037850763,0.04167377,0.34746116,0.007838232,0.0025128573,0.5968148],"study_design_scores_gemma":[0.00013762488,0.000780879,0.001940339,0.000054172426,0.00023797914,0.001660894,0.0002678094,0.5133974,0.4440449,0.005519249,0.03189137,0.00006736847],"about_ca_topic_score_codex":0.0008933333,"about_ca_topic_score_gemma":0.0010941743,"teacher_disagreement_score":0.003076835,"about_ca_system_score_codex":0.00019472455,"about_ca_system_score_gemma":0.00030270172,"threshold_uncertainty_score":0.010293007},"labels":[],"label_agreement":null},{"id":"W1990505856","doi":"10.1109/icassp.2014.6854321","title":"Deep mixture density networks for acoustic modeling in statistical parametric speech synthesis","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":193,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Naturalness; Parametric statistics; Computer science; Speech synthesis; Artificial neural network; Speech recognition; Probability density function; Layer (electronics); Deep neural networks; Mixture model; Statistical model; Artificial intelligence; Mathematics; Statistics","score_opus":0.027659185034576744,"score_gpt":0.24981290520688473,"score_spread":0.222153720172308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1990505856","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0076023247,0.0006257988,0.9906545,0.00009169773,0.000024496223,0.000010956464,0.000038526246,0.00036349637,0.0005882285],"genre_scores_gemma":[0.6542566,0.0017399407,0.33815458,0.000120100456,0.00007810704,0.0001332498,0.0002959969,0.00017302351,0.005048403],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99970406,0.000110106055,0.000016661335,0.00005279471,0.00009408695,0.000022277007],"domain_scores_gemma":[0.99939287,0.00041869516,0.0000367294,0.000034486773,0.00010175422,0.00001553073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009763904,0.0005984272,0.00050537346,0.00043320266,0.00022541375,0.00062724005,0.00067458866,0.00065292855,0.0013479532],"category_scores_gemma":[0.0022515066,0.000584069,0.000564087,0.00043285175,0.00040817328,0.001059804,0.00072880357,0.0013474379,0.00044754366],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010682618,0.000034310266,0.00047339883,0.00009396895,0.00006007013,0.000049838138,0.00006703641,0.85167,0.007836065,0.014794386,0.0006794318,0.124134615],"study_design_scores_gemma":[0.0000011382127,0.000004683503,0.000051674688,0.0000031023387,0.0000034999955,0.000005706825,0.0000018057373,0.99710995,0.0007094508,0.0018717137,0.00023423803,0.0000031346215],"about_ca_topic_score_codex":0.0066255946,"about_ca_topic_score_gemma":0.0067946925,"teacher_disagreement_score":0.0066255946,"about_ca_system_score_codex":0.0007021373,"about_ca_system_score_gemma":0.00074491114,"threshold_uncertainty_score":0.013174057},"labels":[],"label_agreement":null},{"id":"W1993282646","doi":"10.1121/1.4784179","title":"The nonaccommodation of speech errors.","year":2009,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Voice; Vowel; Accommodation; Coda; Perception; Plural; Consonant; Speech recognition; Computer science; Speech error; Acoustics; Psychology; Audiology; Linguistics; Speech production","score_opus":0.015970871322222482,"score_gpt":0.25634350632712977,"score_spread":0.2403726350049073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993282646","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9828681,0.0006647833,0.0066787223,0.00009481363,0.000057246147,0.000080913676,0.00034102894,0.00010159008,0.0091128005],"genre_scores_gemma":[0.99597,0.00023115333,0.0014931991,0.00005396656,0.000019190744,0.000037544465,0.00034361382,0.000043658176,0.0018076397],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9975975,0.0006080475,0.00034932885,0.00041419867,0.00092337886,0.00010750408],"domain_scores_gemma":[0.98163855,0.0076384447,0.0055042845,0.0029575326,0.0018386851,0.00042240057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016545469,0.00037911287,0.0001938047,0.0009225405,0.00024082005,0.0003667554,0.00051176205,0.00030757207,0.0023521842],"category_scores_gemma":[0.016727142,0.00012957373,0.00018362972,0.00051452435,0.00056699786,0.000607031,0.0009992007,0.00026713163,0.0006343676],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0035902632,0.00020959252,0.48507407,0.0008167416,0.00020991157,0.0034019644,0.0060085324,0.00039212685,0.14432694,0.001593982,0.0019494203,0.35242644],"study_design_scores_gemma":[0.000022319742,0.00034564268,0.9617697,0.00005856817,0.000070146474,0.008319485,0.0006380264,0.00072183565,0.023328569,0.00067860517,0.0040167226,0.000030325475],"about_ca_topic_score_codex":0.0013976124,"about_ca_topic_score_gemma":0.0019157068,"teacher_disagreement_score":0.0023521842,"about_ca_system_score_codex":0.00016418546,"about_ca_system_score_gemma":0.00033085412,"threshold_uncertainty_score":0.0087502},"labels":[],"label_agreement":null},{"id":"W1993409002","doi":"10.1109/icassp.2013.6639211","title":"Fast speaker adaptation of hybrid NN/HMM model for speech recognition based on discriminative learning of speaker code","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":224,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Speech recognition; Computer science; TIMIT; Hidden Markov model; Speaker diarisation; Adaptation (eye); Speaker recognition; Discriminative model; Artificial intelligence; Artificial neural network; Pattern recognition (psychology)","score_opus":0.06434906411656907,"score_gpt":0.2616561921307978,"score_spread":0.19730712801422876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993409002","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0090738665,0.0002911855,0.9887938,0.000033654967,0.00006507297,0.000021833435,0.00003584774,0.0010516633,0.00063311495],"genre_scores_gemma":[0.40509444,0.0006824751,0.5842597,0.00020891515,0.000148785,0.00021514625,0.00058553054,0.000392595,0.008412408],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994611,0.00012080902,0.000025090347,0.0001831385,0.00016736735,0.000042357547],"domain_scores_gemma":[0.99958974,0.00017024619,0.000023894569,0.000084799365,0.00011217528,0.000019085672],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007173984,0.0005572086,0.00067567837,0.00035467718,0.00025268953,0.00033840808,0.0008831628,0.00054605,0.001618434],"category_scores_gemma":[0.001032961,0.00039770358,0.0007522022,0.00033153867,0.00027879144,0.00075452134,0.0006465073,0.0012302048,0.0012939243],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032754976,0.00013292162,0.002054015,0.00015366463,0.00024598782,0.00015130508,0.00018317207,0.1888481,0.091315635,0.0038547618,0.0031964856,0.7095364],"study_design_scores_gemma":[0.0000068538634,0.000038037768,0.0009376568,0.0000050437984,0.000029843717,0.00012970025,0.000009536596,0.9847551,0.010959199,0.0010804113,0.0020255065,0.00002307743],"about_ca_topic_score_codex":0.0039188587,"about_ca_topic_score_gemma":0.005495124,"teacher_disagreement_score":0.0039188587,"about_ca_system_score_codex":0.00029100085,"about_ca_system_score_gemma":0.00038380513,"threshold_uncertainty_score":0.007792115},"labels":[],"label_agreement":null},{"id":"W1993882792","doi":"10.1109/tasl.2011.2109382","title":"Acoustic Modeling Using Deep Belief Networks","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1746,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"University of Pennsylvania","keywords":"TIMIT; Hidden Markov model; Discriminative model; Computer science; Artificial intelligence; Pattern recognition (psychology); Deep belief network; Mixture model; Artificial neural network; Speech recognition; Feature (linguistics); Backpropagation; Feature extraction; Markov model; Generative model; Gaussian; Generative grammar; Machine learning; Markov chain","score_opus":0.03523967748347272,"score_gpt":0.24992323005654898,"score_spread":0.21468355257307625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993882792","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040717954,0.00043997623,0.99265385,0.00018387524,0.00004359268,0.000015938796,0.00019362214,0.00086615025,0.0015312091],"genre_scores_gemma":[0.647759,0.0017914055,0.33825406,0.00024498094,0.00016630787,0.00024249007,0.0011307307,0.0003693275,0.010041603],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996896,0.00007965523,0.000017673387,0.00007048782,0.00011057409,0.00003201232],"domain_scores_gemma":[0.99930274,0.00038581566,0.00006012429,0.00006559764,0.0001549583,0.000030641433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005778009,0.0008502359,0.00074394775,0.00075473136,0.00032511243,0.0013165722,0.0015279083,0.0011277545,0.0035883663],"category_scores_gemma":[0.0025656268,0.0008324791,0.0007777965,0.00082604587,0.00056309055,0.0015694496,0.0010627345,0.0018878145,0.0014926078],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023855602,0.000013093226,0.00020742488,0.000031318235,0.000026382735,0.000026415315,0.000020369936,0.9595362,0.00074216066,0.007592321,0.00075043936,0.031030033],"study_design_scores_gemma":[0.0000012724406,0.0000017557051,0.000019704534,0.0000022268355,0.0000013003145,0.0000032770092,0.0000011873714,0.99552566,0.00010484485,0.004118285,0.00021860962,0.0000019391855],"about_ca_topic_score_codex":0.012579582,"about_ca_topic_score_gemma":0.01330214,"teacher_disagreement_score":0.012579582,"about_ca_system_score_codex":0.00087141263,"about_ca_system_score_gemma":0.0008337053,"threshold_uncertainty_score":0.025012732},"labels":[],"label_agreement":null},{"id":"W1995014979","doi":"10.1121/1.4783360","title":"Measuring articulatory similarity with algorithmically reweighted principal component analysis.","year":2009,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Principal component analysis; Similarity (geometry); Context (archaeology); Pattern recognition (psychology); Mathematics; Variance (accounting); Cross-validation; Interpolation (computer graphics); Variation (astronomy); Vocal tract; Computer science; Speech recognition; Artificial intelligence; Statistics; Image (mathematics)","score_opus":0.02139409261340762,"score_gpt":0.23111114208511416,"score_spread":0.20971704947170655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995014979","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4415111,0.000582099,0.5525742,0.00010192522,0.00009307661,0.00064101524,0.00083817943,0.001389959,0.002268562],"genre_scores_gemma":[0.5323369,0.00023162534,0.46385407,0.00002628955,0.00004250628,0.0005324401,0.0020248455,0.0002463689,0.0007049052],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99837023,0.00037699874,0.00017175335,0.00046472574,0.0005280511,0.00008824401],"domain_scores_gemma":[0.9961832,0.0015112997,0.00046634267,0.0005199881,0.0012328953,0.00008616675],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025224653,0.0006917429,0.00058648916,0.0028353594,0.00055989955,0.0011805873,0.00063824456,0.0006217495,0.0016576018],"category_scores_gemma":[0.01246939,0.00024420532,0.00069475657,0.0029570353,0.0005524484,0.0014272233,0.0012139347,0.00059664575,0.00064802606],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010434613,0.00037362738,0.021661812,0.0007490696,0.0005296195,0.00028812082,0.0011899275,0.021259362,0.21736708,0.003728484,0.002193132,0.7296163],"study_design_scores_gemma":[0.00017681977,0.0014482285,0.3427206,0.000079272366,0.00046618338,0.0018771824,0.0010113354,0.55199623,0.08185628,0.008662047,0.009300972,0.0004049265],"about_ca_topic_score_codex":0.001967797,"about_ca_topic_score_gemma":0.003361369,"teacher_disagreement_score":0.0028353594,"about_ca_system_score_codex":0.0003628854,"about_ca_system_score_gemma":0.00061828457,"threshold_uncertainty_score":0.013340235},"labels":[],"label_agreement":null},{"id":"W1996861904","doi":"10.1121/1.2942936","title":"Effects of frequency shifts on the identification of vowels and words in sentences","year":2007,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Vowel; Envelope (radar); Context (archaeology); Mathematics; Sentence; Acoustics; Set (abstract data type); Identification (biology); Speech recognition; Physics; Computer science; Telecommunications; Natural language processing; Geology","score_opus":0.011600546567526362,"score_gpt":0.24777718816970928,"score_spread":0.23617664160218294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996861904","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9994382,0.000053770986,0.00026425844,0.0000078644725,0.000007458299,0.0000061056935,0.000017270708,0.000014677588,0.0001903268],"genre_scores_gemma":[0.9984503,0.000055607,0.0010687158,0.000026741769,0.000010205268,0.00001221321,0.00007684501,0.000019244886,0.00028007376],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99897623,0.0003621426,0.00015310556,0.00015660502,0.0002784339,0.000073482785],"domain_scores_gemma":[0.9865969,0.010895502,0.0010977982,0.0004753265,0.0005298829,0.00040464502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009521196,0.00044227706,0.0002875145,0.0002792796,0.00017901295,0.0004509898,0.00017497157,0.00036334942,0.0021709856],"category_scores_gemma":[0.015410373,0.00029982807,0.00017991458,0.00014822932,0.00033024652,0.00050181674,0.0006058819,0.00034581352,0.00038847714],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0114792865,0.00035670708,0.035205014,0.00018726637,0.0001438521,0.00058214454,0.000930598,0.0012103972,0.91208756,0.00005380623,0.0001080713,0.03765518],"study_design_scores_gemma":[0.00015159264,0.011590889,0.63495034,0.000044067154,0.0002468809,0.0016036014,0.00073567097,0.003594018,0.34606674,0.00031336283,0.000626598,0.00007615901],"about_ca_topic_score_codex":0.00052456564,"about_ca_topic_score_gemma":0.00080480915,"teacher_disagreement_score":0.0021709856,"about_ca_system_score_codex":0.00015879679,"about_ca_system_score_gemma":0.0001225732,"threshold_uncertainty_score":0.007262647},"labels":[],"label_agreement":null},{"id":"W1996941879","doi":"10.1121/1.4781999","title":"Efficient spectral measures for automatic speech recognition","year":2007,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Spectrogram; Computer science; Speech recognition; Spectral envelope; Mel-frequency cepstrum; Linear prediction; Cepstrum; Wideband; Wavelet; Acoustics; Bandwidth (computing); Pattern recognition (psychology); Artificial intelligence; Feature extraction; Telecommunications","score_opus":0.02682802096998669,"score_gpt":0.2669700108464535,"score_spread":0.24014198987646682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996941879","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009073778,0.0026517047,0.9898357,0.00024762496,0.00018409894,0.000085487656,0.0003402258,0.0017909901,0.0039567696],"genre_scores_gemma":[0.036583297,0.0034232663,0.9501913,0.00020666822,0.0005980582,0.0003830881,0.0015245236,0.00057638576,0.006513374],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983584,0.0004923496,0.00012956386,0.00030829615,0.00064589403,0.0000654044],"domain_scores_gemma":[0.9979948,0.00079599436,0.00017665136,0.00047963942,0.00051188347,0.000041019608],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014795166,0.0013713764,0.001216238,0.0024095431,0.00049275643,0.0017112707,0.001239669,0.0010779143,0.017671388],"category_scores_gemma":[0.006112242,0.00054639654,0.0006845976,0.00320382,0.0007408589,0.0021484115,0.0011465007,0.0015582935,0.01619449],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000104795385,0.00008224645,0.00029884436,0.00047292208,0.00005794569,0.00009384763,0.000085313666,0.019950897,0.026120514,0.0958533,0.025835527,0.8310438],"study_design_scores_gemma":[0.000064894455,0.0001823911,0.0023263893,0.00039426656,0.00007422872,0.00069300644,0.00017181657,0.42206985,0.027209494,0.2959467,0.25069824,0.00016873551],"about_ca_topic_score_codex":0.00089362875,"about_ca_topic_score_gemma":0.00086172344,"teacher_disagreement_score":0.017671388,"about_ca_system_score_codex":0.0005665619,"about_ca_system_score_gemma":0.00054521766,"threshold_uncertainty_score":0.05911666},"labels":[],"label_agreement":null},{"id":"W1997539970","doi":"10.1109/icassp.2010.5494926","title":"Large margin estimation of n-gram language models for speech recognition via linear programming","year":2010,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Discriminative model; Computer science; Margin (machine learning); Speech recognition; Language model; Viterbi algorithm; Vocabulary; Word error rate; Viterbi decoder; n-gram; Artificial intelligence; Pattern recognition (psychology); Decoding methods; Hidden Markov model; Algorithm; Machine learning","score_opus":0.02641845991397187,"score_gpt":0.28234568494186885,"score_spread":0.255927225027897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997539970","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017021989,0.000066639295,0.99745756,0.000045566387,0.0000074138343,0.000009313596,0.00001648578,0.0005092879,0.00018548538],"genre_scores_gemma":[0.15698887,0.00025383977,0.8382972,0.00015941827,0.00007715996,0.00024144692,0.0004989253,0.00043446792,0.0030486013],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992238,0.00034198238,0.00003557613,0.00018858058,0.00015955401,0.00005049106],"domain_scores_gemma":[0.99819297,0.0012493222,0.00014924035,0.00018243282,0.00017602564,0.000050087372],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011633951,0.0011612251,0.00092376536,0.00039508485,0.0004102122,0.0007148699,0.0015871223,0.0008998322,0.0028725155],"category_scores_gemma":[0.0055108913,0.0007371156,0.00059646554,0.00060335506,0.0006508305,0.0016039448,0.0015032258,0.0024952271,0.0021326747],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019714389,0.0001276439,0.00041475196,0.00014757525,0.00006257185,0.00011285653,0.00010956115,0.503159,0.01920726,0.01464225,0.0035255363,0.45829386],"study_design_scores_gemma":[0.000004701118,0.000017815217,0.000049969058,0.0000036500508,0.0000033017375,0.000017193419,0.0000043446075,0.9933462,0.0021987197,0.0038972842,0.00045187928,0.000004971483],"about_ca_topic_score_codex":0.00237606,"about_ca_topic_score_gemma":0.004271543,"teacher_disagreement_score":0.0028725155,"about_ca_system_score_codex":0.0005897288,"about_ca_system_score_gemma":0.00090513384,"threshold_uncertainty_score":0.00960958},"labels":[],"label_agreement":null},{"id":"W1997805633","doi":"10.1145/1640377.1640388","title":"Avoiding speaker variability in pronunciation verification of children's disordered speech","year":2009,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Shanghai Ocean University; Universität Wien; McGill University","keywords":"Normalization (sociology); Pronunciation; Speech recognition; Computer science; Word error rate; Speaker recognition; Adaptation (eye); Artificial intelligence; Speaker verification; Test set; Pattern recognition (psychology); Natural language processing; Linguistics; Psychology","score_opus":0.011219972688645814,"score_gpt":0.22778042803402457,"score_spread":0.21656045534537877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997805633","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6122419,0.0008307935,0.38244176,0.00012518876,0.000057544916,0.00007080015,0.00022565764,0.0022830248,0.0017232607],"genre_scores_gemma":[0.880312,0.0002758032,0.117596984,0.000055767487,0.000024804585,0.00005717874,0.00044387602,0.0002306682,0.0010028016],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99765354,0.00093741645,0.00013717526,0.00053381186,0.00062795676,0.000110153735],"domain_scores_gemma":[0.9956682,0.0027258522,0.0003259785,0.00053433585,0.0006454707,0.00010022529],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002945681,0.00052015495,0.0008780194,0.0005622523,0.00034351757,0.00068552926,0.0006552341,0.0007240253,0.0007777509],"category_scores_gemma":[0.011549622,0.00020119245,0.00035644745,0.00034547035,0.00048179642,0.00080046756,0.0008682714,0.00052606326,0.00069046154],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012769005,0.000100858706,0.023521569,0.00028945532,0.00014301119,0.00044730585,0.0010276322,0.01858276,0.2505467,0.0008176653,0.00086633896,0.7023798],"study_design_scores_gemma":[0.00008052139,0.0013676638,0.14924248,0.00010515178,0.00032210827,0.006938142,0.0009663466,0.27119714,0.5597634,0.0035538634,0.0062354254,0.00022774297],"about_ca_topic_score_codex":0.0015480622,"about_ca_topic_score_gemma":0.0027246536,"teacher_disagreement_score":0.002945681,"about_ca_system_score_codex":0.00024429383,"about_ca_system_score_gemma":0.000681945,"threshold_uncertainty_score":0.015578389},"labels":[],"label_agreement":null},{"id":"W1998280908","doi":"10.1109/asru.2007.4430198","title":"Multiple feature combination to improve speaker diarization of telephone conversations","year":2007,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Speaker diarisation; Viterbi algorithm; Computer science; Mixture model; Cluster analysis; Speech recognition; Pattern recognition (psychology); Segmentation; Feature (linguistics); Bayesian information criterion; Artificial intelligence; Hierarchical clustering; Test set; Speaker recognition; Word error rate; Hidden Markov model","score_opus":0.010190349140749892,"score_gpt":0.2296411357601296,"score_spread":0.2194507866193797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998280908","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22773442,0.0015402103,0.75004727,0.000260738,0.00043957884,0.0002499902,0.0009110227,0.014207768,0.0046090013],"genre_scores_gemma":[0.39477193,0.0004934483,0.58990914,0.00018467008,0.00018378039,0.0002645668,0.0043349825,0.0014253026,0.008432182],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979559,0.00047494707,0.000113822505,0.0006141754,0.00061217666,0.00022885279],"domain_scores_gemma":[0.9979505,0.00066703104,0.000097209966,0.00036630788,0.0008368898,0.00008209229],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018690252,0.0018863729,0.0016183764,0.0012672462,0.0005245576,0.000730226,0.00085747853,0.00082142145,0.004536655],"category_scores_gemma":[0.0035471488,0.00039918206,0.0013050677,0.0010673337,0.00022485502,0.0010475038,0.0010571313,0.0011081325,0.0033347574],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009995874,0.00029851744,0.0022229836,0.00019618557,0.0002905976,0.00016309538,0.00021831277,0.018946007,0.16431262,0.00035420372,0.0042243493,0.80777365],"study_design_scores_gemma":[0.00032696614,0.001483631,0.028330978,0.00003575733,0.0009034405,0.0014649058,0.00022363383,0.47422168,0.46841976,0.0014045002,0.022910083,0.0002745842],"about_ca_topic_score_codex":0.002493495,"about_ca_topic_score_gemma":0.0038036956,"teacher_disagreement_score":0.004536655,"about_ca_system_score_codex":0.00038146626,"about_ca_system_score_gemma":0.00048154415,"threshold_uncertainty_score":0.015176654},"labels":[],"label_agreement":null},{"id":"W1998948935","doi":"10.1109/iciet.2007.4381302","title":"Speaker Accent Classification System Using a Fuzzy Gaussian Classifier","year":2007,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Mixture model; Stress (linguistics); Hidden Markov model; Computer science; Pattern recognition (psychology); Artificial intelligence; Speech recognition; Vector quantization; Fuzzy logic; Gaussian; Classifier (UML); Cluster analysis; Phonetic transcription; Speaker recognition; Fuzzy clustering; Feature vector; Speaker diarisation","score_opus":0.08100266918697686,"score_gpt":0.29624603515127984,"score_spread":0.215243365964303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998948935","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051349074,0.00036876413,0.9393408,0.0001666229,0.00023880425,0.00012713473,0.00014620673,0.0054901224,0.0027724996],"genre_scores_gemma":[0.59895396,0.00028931673,0.39114177,0.00019625068,0.000117024014,0.00015161531,0.00035192567,0.00010247777,0.008695649],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99926907,0.00008746955,0.000044919692,0.00022343735,0.00028890104,0.00008624733],"domain_scores_gemma":[0.99922264,0.00011173185,0.00004046791,0.000055544606,0.00052025594,0.000049298338],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014723599,0.0005239829,0.0010251367,0.00092057016,0.00079083146,0.00077256805,0.0009601201,0.00095097005,0.00226344],"category_scores_gemma":[0.0015347134,0.00030524764,0.00061856187,0.00046736165,0.00029444855,0.0008094504,0.0005636662,0.0007795852,0.0018478658],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009340814,0.0003199929,0.004274306,0.00010044163,0.00017397462,0.0001762693,0.00027973563,0.027659848,0.081370905,0.0026526712,0.0061714076,0.87588644],"study_design_scores_gemma":[0.000049478327,0.00014412473,0.004001949,0.000012719854,0.00008644172,0.00023405958,0.00006132127,0.96128076,0.029285414,0.0011841388,0.0035942567,0.00006530585],"about_ca_topic_score_codex":0.008518267,"about_ca_topic_score_gemma":0.006210938,"teacher_disagreement_score":0.008518267,"about_ca_system_score_codex":0.00076445955,"about_ca_system_score_gemma":0.0007443917,"threshold_uncertainty_score":0.016937375},"labels":[],"label_agreement":null},{"id":"W1999102959","doi":"10.1121/1.3248416","title":"Listener voice identification in foreign and accented English.","year":2009,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Mandarin Chinese; Formant; Salient; Speech recognition; Voice; Perception; Identification (biology); Variation (astronomy); Computer science; Acoustics; Vowel; Linguistics; Psychology; Artificial intelligence","score_opus":0.014998237736868186,"score_gpt":0.24662990598075027,"score_spread":0.2316316682438821,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999102959","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9906557,0.00025977625,0.003105911,0.000023663171,0.00003995802,0.000025173824,0.0001421362,0.000049674763,0.005697995],"genre_scores_gemma":[0.9966311,0.000095100084,0.0010641247,0.000049374696,0.000012975053,0.000013668545,0.00018865407,0.000017648747,0.0019273056],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99931145,0.00016624584,0.000060918133,0.00020999576,0.00019712663,0.000054280954],"domain_scores_gemma":[0.99723417,0.0015196529,0.0002929544,0.00022752886,0.00050155434,0.00022421166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010575973,0.00024349388,0.00025330074,0.00053522445,0.00028024332,0.0007322238,0.0001828151,0.00034330753,0.0036566365],"category_scores_gemma":[0.006581087,0.00008634463,0.00014770728,0.00013152149,0.00025905203,0.000846354,0.0006626858,0.00023470934,0.0011208554],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003947311,0.00041435752,0.3791107,0.00067271135,0.0001935094,0.001740668,0.029382166,0.00050508766,0.41800728,0.00086165126,0.0011392458,0.1640253],"study_design_scores_gemma":[0.000037702644,0.0014578673,0.9369296,0.00004421864,0.000111062225,0.003821673,0.012526326,0.0017129044,0.038936935,0.0006159056,0.003743233,0.00006254797],"about_ca_topic_score_codex":0.0005444818,"about_ca_topic_score_gemma":0.0011271551,"teacher_disagreement_score":0.0036566365,"about_ca_system_score_codex":0.00010387432,"about_ca_system_score_gemma":0.000086124004,"threshold_uncertainty_score":0.012232661},"labels":[],"label_agreement":null},{"id":"W2001936727","doi":"10.1109/lsp.2007.905088","title":"Combining Gaussianized/Non-Gaussianized Features to Improve Speaker Diarization of Telephone Conversations","year":2007,"lang":"en","type":"article","venue":"IEEE Signal Processing Letters","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Speaker diarisation; Viterbi algorithm; Computer science; Cluster analysis; Speech recognition; Mixture model; Pattern recognition (psychology); Segmentation; Bayesian information criterion; Mel-frequency cepstrum; Feature (linguistics); Artificial intelligence; Speaker recognition; Word error rate; Test set; Hierarchical clustering; Feature extraction; Hidden Markov model","score_opus":0.010488642288494734,"score_gpt":0.23965041366761372,"score_spread":0.22916177137911897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001936727","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42100483,0.0018578353,0.55633134,0.00041483017,0.00052808714,0.00025051803,0.0011283911,0.012799383,0.005684873],"genre_scores_gemma":[0.5103622,0.0005093376,0.47566497,0.00020772146,0.00016601734,0.00011969338,0.0046015717,0.0010861781,0.0072823665],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99822587,0.000404059,0.00008204378,0.0005288808,0.00047423723,0.00028500578],"domain_scores_gemma":[0.9977894,0.00082044984,0.00008715813,0.0003185443,0.000881544,0.000102956845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025713376,0.0016832832,0.0013813924,0.0014384517,0.0005034486,0.00086831144,0.0007453482,0.00077781134,0.0027964476],"category_scores_gemma":[0.003909823,0.00035502884,0.0012569855,0.0010903255,0.00032160454,0.0011614071,0.0010631011,0.00096314895,0.002641727],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015778615,0.0004636273,0.0039891014,0.00022794509,0.0003140681,0.00019916585,0.0002724604,0.025355158,0.11958639,0.000465259,0.0045161094,0.8430328],"study_design_scores_gemma":[0.00035106947,0.0015301376,0.035325654,0.000038228438,0.0008766636,0.0009208083,0.0003017982,0.5734382,0.3676856,0.0014717912,0.0177698,0.0002901788],"about_ca_topic_score_codex":0.004744414,"about_ca_topic_score_gemma":0.0066714836,"teacher_disagreement_score":0.004744414,"about_ca_system_score_codex":0.0003748898,"about_ca_system_score_gemma":0.0005937288,"threshold_uncertainty_score":0.01359874},"labels":[],"label_agreement":null},{"id":"W2002840771","doi":"10.1115/fmd2013-16131","title":"Implementation of Agent Based Model of Tissue Inflammation on a Graphics Processing Unit Platform","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Graphics processing unit; Inflammation; Computer science; Process (computing); Wound healing; Medicine; Surgery; Immunology; Operating system","score_opus":0.06734610164530011,"score_gpt":0.3046940250340357,"score_spread":0.2373479233887356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002840771","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030949086,0.00019827423,0.9416397,0.0004047277,0.00024018105,0.0002771975,0.0005033016,0.011027259,0.0147601925],"genre_scores_gemma":[0.47672227,0.00036842964,0.49977985,0.0002702661,0.00004847072,0.0007494367,0.0010801747,0.00091250794,0.02006863],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99981683,0.000031849082,0.000014309991,0.000036433896,0.0000712464,0.000029374181],"domain_scores_gemma":[0.9997955,0.00006937092,0.000015978594,0.00003110334,0.00005828785,0.000029743675],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029159596,0.00076211523,0.00063850614,0.00029554038,0.0004194955,0.0012616244,0.002043591,0.0014989874,0.01358732],"category_scores_gemma":[0.000725771,0.0004554123,0.00088280154,0.00017422126,0.00039224178,0.00056263054,0.00092518167,0.00087509037,0.0019046465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025710225,0.00012737564,0.0013766916,0.00015058968,0.00008100666,0.00049270084,0.00012996547,0.9277033,0.016218793,0.011319272,0.0054206992,0.036722433],"study_design_scores_gemma":[0.000035301677,0.0000329804,0.0000927787,0.000005953358,0.000011950223,0.00003144644,0.00001011683,0.9908772,0.0024834538,0.0016751712,0.0047346475,0.000009106766],"about_ca_topic_score_codex":0.007974456,"about_ca_topic_score_gemma":0.0048271734,"teacher_disagreement_score":0.01358732,"about_ca_system_score_codex":0.000594606,"about_ca_system_score_gemma":0.0010100439,"threshold_uncertainty_score":0.045454144},"labels":[],"label_agreement":null},{"id":"W2005604008","doi":"10.1109/isie.2006.295643","title":"Incorporation of State-Level Variable Stime-Varying Property into the HMM","year":2006,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Hidden Markov model; Property (philosophy); TIMIT; Computer science; Process (computing); Speech recognition; Variable (mathematics); State (computer science); Task (project management); Pattern recognition (psychology); Artificial intelligence; State variable; Mathematics; Algorithm; Engineering","score_opus":0.029661954659008713,"score_gpt":0.22242534827765117,"score_spread":0.19276339361864248,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005604008","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015008323,0.00007878824,0.9838674,0.000043474534,0.000019582692,0.000012256055,0.00003247564,0.00046299922,0.0004746588],"genre_scores_gemma":[0.7377866,0.00020468069,0.26030302,0.000057090714,0.00005795035,0.00006588822,0.00022367592,0.00019550133,0.0011056011],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993754,0.00021094277,0.000039308004,0.00019475704,0.00012759525,0.000052037612],"domain_scores_gemma":[0.9963588,0.0024648837,0.00018342624,0.00059818075,0.00032372717,0.00007097278],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013215609,0.00036901206,0.00055010256,0.00042496703,0.00032055427,0.0007200763,0.0007341246,0.00058208226,0.0014008264],"category_scores_gemma":[0.0067430064,0.0003322677,0.0005076,0.0005442454,0.0005358086,0.001829224,0.0006955068,0.0010566849,0.0005120741],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00066824176,0.00014289655,0.01849798,0.0001841773,0.00017217055,0.00041751273,0.00050002313,0.46911326,0.0564342,0.047737144,0.0012697169,0.4048627],"study_design_scores_gemma":[0.0000036695308,0.00003498712,0.0014051358,0.0000054622114,0.000016296486,0.00006135905,0.000010539286,0.990569,0.0035863626,0.0036151009,0.00067911745,0.000013003972],"about_ca_topic_score_codex":0.0020795106,"about_ca_topic_score_gemma":0.002223132,"teacher_disagreement_score":0.0020795106,"about_ca_system_score_codex":0.00045427348,"about_ca_system_score_gemma":0.00058770034,"threshold_uncertainty_score":0.0069891214},"labels":[],"label_agreement":null},{"id":"W2005708641","doi":"10.1109/asru.2013.6707742","title":"Hybrid speech recognition with Deep Bidirectional LSTM","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1794,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"TIMIT; Computer science; Word error rate; Speech recognition; Leverage (statistics); Hidden Markov model; Artificial neural network; Recurrent neural network; Artificial intelligence; Deep neural networks; Word (group theory); Vocabulary; Acoustic model; Deep learning; Speech processing","score_opus":0.01839249538427433,"score_gpt":0.20616813503791803,"score_spread":0.1877756396536437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005708641","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05921132,0.0012283779,0.91474813,0.00031458458,0.00029544032,0.000084700216,0.0009966131,0.016266095,0.0068547567],"genre_scores_gemma":[0.64569825,0.0004218286,0.3378663,0.00032985152,0.000102265025,0.00016570654,0.0019255937,0.00045168612,0.0130386045],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995766,0.0000819097,0.000026135782,0.00013988843,0.00012092823,0.000054540884],"domain_scores_gemma":[0.99961555,0.00013817311,0.0000241463,0.00007070456,0.00013036137,0.000020970667],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070871983,0.0007244415,0.0006105091,0.00050020043,0.00023826848,0.00087198155,0.000997686,0.00077658484,0.0047409814],"category_scores_gemma":[0.0010326068,0.00040561997,0.00051331095,0.00052872073,0.00022917367,0.0013967993,0.0008795346,0.00089872384,0.0031711995],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054923835,0.00018796154,0.0008769353,0.00020669324,0.00021519644,0.00020844035,0.00014645622,0.11563293,0.10649735,0.0041520116,0.008426363,0.76290035],"study_design_scores_gemma":[0.000017370228,0.000071198985,0.000511224,0.000013418757,0.000031292544,0.000081840975,0.000029602474,0.96713156,0.026290517,0.0028374016,0.0029588179,0.0000258189],"about_ca_topic_score_codex":0.0051128953,"about_ca_topic_score_gemma":0.01006185,"teacher_disagreement_score":0.0051128953,"about_ca_system_score_codex":0.00050231925,"about_ca_system_score_gemma":0.00046064125,"threshold_uncertainty_score":0.01586014},"labels":[],"label_agreement":null},{"id":"W2006577961","doi":"10.1109/icassp.2014.6854925","title":"Improvements to filterbank and delta learning within a deep neural network framework","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Filter bank; Speech recognition; Filter (signal processing); Word error rate; Artificial neural network; Artificial intelligence; Deep learning; Computer vision","score_opus":0.013459571748814604,"score_gpt":0.2353835797920289,"score_spread":0.2219240080432143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006577961","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019753667,0.0010070779,0.97368324,0.0002844519,0.00013828126,0.00004610754,0.0001274338,0.002511746,0.0024479977],"genre_scores_gemma":[0.4124428,0.0013256347,0.5701661,0.000423426,0.0002133972,0.00019815244,0.001013684,0.00048596333,0.013730823],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993575,0.00014634914,0.000044661214,0.00018214504,0.00021192338,0.00005737721],"domain_scores_gemma":[0.9988827,0.00041589772,0.00004588805,0.00028115683,0.00033254796,0.00004179382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017743204,0.0012459221,0.00076035893,0.00064029836,0.0003049239,0.0007378088,0.0014582152,0.0011424577,0.004518497],"category_scores_gemma":[0.0030072837,0.00041737285,0.0006746456,0.00051853794,0.00040621433,0.0024085464,0.0010600116,0.00207819,0.0018909753],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003970198,0.00040249157,0.0016518165,0.00016104584,0.00014873767,0.00013380156,0.00010403863,0.1436455,0.04815297,0.013968368,0.00494105,0.78629315],"study_design_scores_gemma":[0.0000344676,0.00021110804,0.0008438083,0.00002500517,0.000047056437,0.00011735676,0.000018660847,0.96310776,0.020387566,0.008069116,0.0071086287,0.000029520445],"about_ca_topic_score_codex":0.0063649667,"about_ca_topic_score_gemma":0.0076711616,"teacher_disagreement_score":0.0063649667,"about_ca_system_score_codex":0.0008317759,"about_ca_system_score_gemma":0.0010477927,"threshold_uncertainty_score":0.015115917},"labels":[],"label_agreement":null},{"id":"W2007243334","doi":"10.1109/taslp.2014.2332043","title":"Linear Regression Based Acoustic Adaptation for the Subspace Gaussian Mixture Model","year":2014,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Hidden Markov model; Computer science; Mixture model; Subspace topology; Feature vector; Pattern recognition (psychology); Adaptation (eye); Speech recognition; Context (archaeology); Linear subspace; Artificial intelligence; Gaussian; Projection (relational algebra); Gaussian process; Algorithm; Mathematics","score_opus":0.02573889994601482,"score_gpt":0.2738997070314438,"score_spread":0.24816080708542895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007243334","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029291036,0.00017811172,0.99538726,0.00003445948,0.000026799014,0.000013566917,0.00002465603,0.0005440719,0.00086197193],"genre_scores_gemma":[0.25956413,0.0012858697,0.7292032,0.00016741108,0.00016384537,0.00020675307,0.0005421427,0.00066856976,0.00819794],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99934906,0.0002433213,0.000023867226,0.00015956761,0.00019567905,0.000028491057],"domain_scores_gemma":[0.9993098,0.0003699578,0.000044174412,0.00011134886,0.00015302133,0.000011649151],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007658219,0.00067789096,0.0005570679,0.00029863673,0.00021291028,0.00043619383,0.0006816413,0.0005081657,0.0018977572],"category_scores_gemma":[0.0022836255,0.00025080462,0.0007376247,0.00051079394,0.00034727677,0.0006329637,0.00053507293,0.0011795145,0.0018856057],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016272646,0.0000798666,0.0008582744,0.00017635291,0.00017533953,0.00011905503,0.0001972629,0.34912667,0.073025465,0.017698716,0.0029088608,0.5554715],"study_design_scores_gemma":[0.000004808873,0.00005092921,0.0006539487,0.00001011809,0.000026266538,0.0001167311,0.000013937858,0.9782566,0.011566529,0.0032501204,0.006023243,0.00002672706],"about_ca_topic_score_codex":0.0025537943,"about_ca_topic_score_gemma":0.002746325,"teacher_disagreement_score":0.0025537943,"about_ca_system_score_codex":0.00026649618,"about_ca_system_score_gemma":0.0004247194,"threshold_uncertainty_score":0.00634861},"labels":[],"label_agreement":null},{"id":"W2008066109","doi":"10.1016/j.specom.2009.04.006","title":"Tools and Technologies for Computer-Aided Speech and Language Therapy","year":2009,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":133,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Pronunciation; Speech recognition; Population; Dysarthria; Set (abstract data type); Speech technology; Articulation (sociology); Domain (mathematical analysis); Speech processing; Speech corpus; Natural language processing; Speech synthesis; Linguistics; Audiology; Medicine","score_opus":0.03613621209312245,"score_gpt":0.28753021798531103,"score_spread":0.2513940058921886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2008066109","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005773862,0.008962193,0.9373915,0.0008067717,0.00057063217,0.00023100403,0.0003532348,0.005323655,0.04058713],"genre_scores_gemma":[0.08684479,0.011291994,0.84644425,0.0006710762,0.00031452527,0.00080019014,0.0007326561,0.00066395116,0.052236546],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99929535,0.00016481972,0.00005784988,0.00006253238,0.00037942786,0.00003991217],"domain_scores_gemma":[0.99912804,0.00045620074,0.00004260218,0.00013781931,0.00018806466,0.00004720401],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009782535,0.00060742314,0.0004801459,0.0013704684,0.00039535481,0.0018581979,0.00083554076,0.0009736389,0.02341073],"category_scores_gemma":[0.0021080761,0.00025062126,0.0003735719,0.00073612196,0.00062890834,0.0017834014,0.0016144218,0.00074417784,0.006454371],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012256771,0.000075272634,0.00034225214,0.0004883637,0.000027144162,0.00028269764,0.00034210563,0.0012392158,0.03165745,0.041527335,0.01785597,0.90603954],"study_design_scores_gemma":[0.00012599585,0.00053690776,0.0030761345,0.0011498363,0.00017047743,0.0048237033,0.0006327901,0.020682124,0.0695498,0.09418691,0.8049407,0.00012454066],"about_ca_topic_score_codex":0.00058091886,"about_ca_topic_score_gemma":0.00085417344,"teacher_disagreement_score":0.02341073,"about_ca_system_score_codex":0.0002983957,"about_ca_system_score_gemma":0.00073120825,"threshold_uncertainty_score":0.07831675},"labels":[],"label_agreement":null},{"id":"W2009049512","doi":"10.1016/s0167-6393(00)00089-3","title":"Speaker clustering for speech recognition using vocal tract parameters","year":2002,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Vocal tract; Speech recognition; Formant; Speaker recognition; Cluster analysis; Computer science; Speaker diarisation; Hidden Markov model; Pattern recognition (psychology); Artificial intelligence; Vowel","score_opus":0.14078547902367666,"score_gpt":0.2975063171245893,"score_spread":0.15672083810091264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009049512","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011234586,0.00036377605,0.9824827,0.000051473955,0.00004803926,0.000060941216,0.00024901947,0.0048165186,0.0006930136],"genre_scores_gemma":[0.11279451,0.00033829056,0.8767862,0.00006745394,0.00007768249,0.00025022702,0.0020693976,0.0010199146,0.0065962616],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992099,0.00018451792,0.00005026949,0.00027653258,0.00018534577,0.00009343542],"domain_scores_gemma":[0.99921465,0.00031542455,0.0000475292,0.00014365338,0.00024384813,0.00003491513],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083100743,0.0011792117,0.0014187666,0.0012620685,0.0012651278,0.0008288899,0.0012692895,0.0012843668,0.0058675855],"category_scores_gemma":[0.001698829,0.0006961348,0.0014999927,0.00092837075,0.00037022383,0.000802178,0.0007985948,0.0011861654,0.006847717],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005016603,0.00012097873,0.0006718698,0.0001123543,0.00018924789,0.000077970115,0.00015304919,0.03235062,0.12008293,0.0017986463,0.0049715363,0.8389693],"study_design_scores_gemma":[0.000041612697,0.000121396966,0.004535404,0.000020924577,0.00014970766,0.00027677463,0.00013036457,0.87411547,0.10937501,0.0045604995,0.0066001327,0.00007262154],"about_ca_topic_score_codex":0.00961568,"about_ca_topic_score_gemma":0.016390836,"teacher_disagreement_score":0.00961568,"about_ca_system_score_codex":0.0006452082,"about_ca_system_score_gemma":0.0010146797,"threshold_uncertainty_score":0.019629002},"labels":[],"label_agreement":null},{"id":"W2014517133","doi":"10.1109/icassp.2014.6854820","title":"Regularized constrained maximum likelihood linear regression for speech recognition","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Hidden Markov model; Embedding; Regularization (linguistics); Pattern recognition (psychology); Computer science; Feature vector; Feature (linguistics); Artificial intelligence; Graph; Speech recognition; Maximization; Mathematics; Mathematical optimization; Theoretical computer science","score_opus":0.02884976113153596,"score_gpt":0.2597818766113098,"score_spread":0.23093211547977385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014517133","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00095142424,0.0008062048,0.996789,0.00012337198,0.000025832784,0.000017091681,0.000069784386,0.00073358015,0.0004838433],"genre_scores_gemma":[0.14227767,0.0029145202,0.84428847,0.00021537361,0.0002522515,0.00043649276,0.0012672726,0.00070479716,0.0076431795],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986199,0.0007368087,0.000056439236,0.00023664156,0.00029687787,0.0000532934],"domain_scores_gemma":[0.9978404,0.0015725299,0.00015735687,0.00018966495,0.00021631205,0.000023780161],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014734273,0.0011996484,0.0012768212,0.0008118852,0.00026176494,0.00090534345,0.0011197692,0.0012787064,0.002779648],"category_scores_gemma":[0.0055270256,0.0006625771,0.0009903183,0.0016253741,0.00066360686,0.00094824814,0.00092318153,0.0018998671,0.003023803],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010911407,0.000068315,0.00023342848,0.0002913467,0.00013359453,0.00009824168,0.00009707843,0.681996,0.0086125005,0.037506726,0.0073624835,0.26349118],"study_design_scores_gemma":[0.000005822252,0.000011268425,0.00008321143,0.000010495657,0.0000059864133,0.000015779005,0.0000044320695,0.98398316,0.00067493756,0.013289795,0.0019054554,0.000009658362],"about_ca_topic_score_codex":0.005374301,"about_ca_topic_score_gemma":0.0046031657,"teacher_disagreement_score":0.005374301,"about_ca_system_score_codex":0.00077217096,"about_ca_system_score_gemma":0.00094480405,"threshold_uncertainty_score":0.01068604},"labels":[],"label_agreement":null},{"id":"W2015633636","doi":"10.1109/icassp.2014.6854823","title":"I-vector-based speaker adaptation of deep neural networks for French broadcast audio transcription","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":119,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Speech recognition; Computer science; Speaker diarisation; Word error rate; Transcription (linguistics); Feature vector; Hidden Markov model; Artificial neural network; Artificial intelligence; Speaker recognition; Acoustic model; Vector quantization; Pattern recognition (psychology); Speech processing","score_opus":0.027729139316015762,"score_gpt":0.22933402300871766,"score_spread":0.2016048836927019,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015633636","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15855567,0.0009357904,0.8246348,0.00022735455,0.00023020331,0.00010337989,0.00051589677,0.009869349,0.0049275546],"genre_scores_gemma":[0.7556191,0.0003755632,0.23118116,0.00017233392,0.000078785786,0.00017109852,0.0017616677,0.00057849876,0.010061799],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996284,0.00013916912,0.000018926232,0.000095405565,0.00007044574,0.00004757124],"domain_scores_gemma":[0.9996321,0.00015822682,0.000020982578,0.0000477787,0.0001226398,0.000018294733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068595307,0.0006102549,0.0002904318,0.0002654243,0.00018172506,0.00028829183,0.00050728273,0.00043170352,0.0032159567],"category_scores_gemma":[0.0014317272,0.00022713908,0.00036600028,0.00024928575,0.00019311334,0.00044973023,0.00050682045,0.0009486963,0.0014100468],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000586083,0.00013541381,0.0011065785,0.0001143654,0.00010999956,0.00013402791,0.00020677995,0.14515859,0.15259942,0.0010750688,0.004083545,0.69469017],"study_design_scores_gemma":[0.000021425902,0.00013740663,0.0020349445,0.000013773324,0.00004035027,0.000098060744,0.00004934699,0.91981035,0.07425089,0.0008726233,0.002638055,0.000032692606],"about_ca_topic_score_codex":0.0064460495,"about_ca_topic_score_gemma":0.00905784,"teacher_disagreement_score":0.0064460495,"about_ca_system_score_codex":0.00043783768,"about_ca_system_score_gemma":0.00035331395,"threshold_uncertainty_score":0.012817085},"labels":[],"label_agreement":null},{"id":"W2016084804","doi":"10.1109/icassp.2013.6639015","title":"Incoherent training of deep neural networks to de-correlate bottleneck features for speech recognition","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Hidden Markov model; Computer science; Speech recognition; Artificial neural network; Artificial intelligence; Bottleneck; Pattern recognition (psychology); Feature extraction; Context (archaeology); Feature (linguistics)","score_opus":0.032801787651130274,"score_gpt":0.2504833423333723,"score_spread":0.21768155468224204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016084804","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05376101,0.00043515168,0.9443686,0.000072881376,0.000042368014,0.000025598121,0.000046403118,0.00059853104,0.00064943195],"genre_scores_gemma":[0.56318676,0.00038650373,0.4321698,0.00018514285,0.000053252836,0.00012258219,0.00050947943,0.00019952767,0.0031870448],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99943763,0.00019573522,0.000035859615,0.0001351973,0.00014450472,0.000051085717],"domain_scores_gemma":[0.9992151,0.00036289654,0.00008446634,0.00013145022,0.00016651287,0.000039480372],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011825906,0.0011196054,0.00050811586,0.00037773748,0.0002478446,0.0003065498,0.0011028611,0.00048536746,0.0011102564],"category_scores_gemma":[0.0022751703,0.0005855614,0.00041534056,0.00044004485,0.0003948648,0.0011967015,0.0010029471,0.0011906264,0.00040556776],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004106298,0.00037314286,0.0032865785,0.00016374305,0.0001908426,0.0001693097,0.00019485327,0.36679965,0.13339789,0.006393531,0.0022400187,0.48637986],"study_design_scores_gemma":[0.000007674501,0.00010133941,0.0009217379,0.0000069028656,0.000025147285,0.000034160603,0.000011423975,0.9738777,0.023151793,0.0009683112,0.00088306813,0.000010613661],"about_ca_topic_score_codex":0.0028290313,"about_ca_topic_score_gemma":0.010017782,"teacher_disagreement_score":0.0028290313,"about_ca_system_score_codex":0.0005007595,"about_ca_system_score_gemma":0.0008334721,"threshold_uncertainty_score":0.006254196},"labels":[],"label_agreement":null},{"id":"W2016489207","doi":"10.1080/07434610310001605801","title":"Research Issues of Speech Recognition Accuracy Measurements: Response to Bruce Wisenburn","year":2004,"lang":"en","type":"article","venue":"Augmentative and Alternative Communication","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Speech recognition; Psychology; Computer science; Natural language processing; Audiology; Linguistics; Medicine","score_opus":0.24923239326747362,"score_gpt":0.4405365790829401,"score_spread":0.19130418581546646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016489207","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023344504,0.011037179,0.0007152907,0.9648179,0.02159542,0.000056532506,0.00008115921,0.000054542357,0.0014086703],"genre_scores_gemma":[0.005863094,0.011981226,0.0018794762,0.93865716,0.028029563,0.0002854848,0.00009242631,0.00011069874,0.013101003],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97093874,0.008544818,0.0031742125,0.0031975724,0.013313922,0.0008306965],"domain_scores_gemma":[0.84164727,0.06882383,0.0041541955,0.0025944356,0.0768482,0.0059321444],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0267618,0.0015891206,0.0020031016,0.0017807573,0.004787961,0.006316456,0.004095613,0.028505495,0.0054248436],"category_scores_gemma":[0.10539452,0.0011920054,0.0014045434,0.0020757015,0.005842514,0.006780395,0.0039046009,0.039098334,0.006846456],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007703094,0.000028346181,0.00039710847,0.0001320377,0.000011645104,0.000096413096,0.00030333316,0.00007142953,0.000248708,0.0011538339,0.9776754,0.019804718],"study_design_scores_gemma":[0.00006202526,0.00013364317,0.0022949907,0.0010964776,0.000047299236,0.0007770275,0.0022051986,0.0003681419,0.0008490459,0.0041603786,0.9878535,0.00015239141],"about_ca_topic_score_codex":0.020028561,"about_ca_topic_score_gemma":0.023160806,"teacher_disagreement_score":0.9732382,"about_ca_system_score_codex":0.0061095143,"about_ca_system_score_gemma":0.009424508,"threshold_uncertainty_score":0.14153165},"labels":[],"label_agreement":null},{"id":"W2017183468","doi":"10.1121/1.4805645","title":"Pitch affects voice onset time: A cross-linguistic study","year":2013,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Voice-onset time; Audiology; Duration (music); Psychology; Variation (astronomy); Acoustics; Speech recognition; Linguistics; Mathematics; Voice; Computer science; Physics; Medicine","score_opus":0.013919449524999374,"score_gpt":0.27194627925465964,"score_spread":0.2580268297296603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017183468","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9990976,0.000086187065,0.00018587419,0.000005395519,0.0000064868173,0.0000092678465,0.00003140156,0.0000023491657,0.0005756549],"genre_scores_gemma":[0.9991042,0.000081338825,0.00030603004,0.00002423959,0.000010654882,0.000021008209,0.000077141325,0.000009377978,0.000366042],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9995353,0.00012349723,0.000053910542,0.00015838949,0.00008981847,0.00003915341],"domain_scores_gemma":[0.9956885,0.002754243,0.00059281365,0.00026768917,0.00040920018,0.0002876968],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010761592,0.00019851289,0.00029154596,0.00046154516,0.00023906425,0.0005796609,0.00020317982,0.0003495062,0.0020305386],"category_scores_gemma":[0.0052592754,0.00022238371,0.00020778598,0.00020345724,0.000367065,0.00040127346,0.00051259616,0.00036286048,0.0003023859],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007165596,0.001299575,0.30267158,0.00038451355,0.0003156275,0.0015850065,0.009700826,0.00022729287,0.6457327,0.00030545576,0.00018298767,0.03042886],"study_design_scores_gemma":[0.00003964027,0.0019058429,0.98792934,0.000011701014,0.000092205686,0.0007485547,0.0009560533,0.00034809098,0.007424408,0.00006965648,0.00045816106,0.000016337224],"about_ca_topic_score_codex":0.0005388552,"about_ca_topic_score_gemma":0.0006437669,"teacher_disagreement_score":0.0020305386,"about_ca_system_score_codex":0.00013302607,"about_ca_system_score_gemma":0.000099321645,"threshold_uncertainty_score":0.0067928433},"labels":[],"label_agreement":null},{"id":"W2019393631","doi":"10.1109/icassp.2007.366866","title":"Bias Estimation and Correction in a Classifier using Product of Likelihood-Gaussians","year":2007,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Classifier (UML); Computer science; Artificial intelligence; Pattern recognition (psychology); Feature vector; Gaussian; Linear discriminant analysis; Mixture model; Machine learning","score_opus":0.05380874776208271,"score_gpt":0.2863807500740105,"score_spread":0.23257200231192776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019393631","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011919105,0.00016470668,0.9871171,0.000093051036,0.000029157283,0.00002295618,0.000016141126,0.0004875851,0.00015016852],"genre_scores_gemma":[0.32338473,0.00038642576,0.6735419,0.00017609415,0.00016258516,0.00016638362,0.0002188369,0.00035224282,0.0016108892],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99476045,0.0018076514,0.00040428273,0.00092792173,0.001772209,0.00032750398],"domain_scores_gemma":[0.98610306,0.00866509,0.00093531,0.00135668,0.0027033472,0.00023640718],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01305294,0.0009501043,0.0020932974,0.0019248163,0.00087097345,0.0025831354,0.0020085138,0.0021589438,0.00088113756],"category_scores_gemma":[0.037097402,0.0007641791,0.0012812299,0.0015270545,0.0016596619,0.0033892454,0.0020971557,0.0025817978,0.0009754642],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00095053617,0.0002018625,0.013217198,0.00027000933,0.00037376775,0.00030204994,0.0005320768,0.2519675,0.02566761,0.031763267,0.002531743,0.6722225],"study_design_scores_gemma":[0.000019903004,0.000067035886,0.0013713128,0.000015898155,0.000032277338,0.00015970011,0.000022118931,0.9790636,0.006499572,0.011891419,0.0008163489,0.000040834766],"about_ca_topic_score_codex":0.0025835717,"about_ca_topic_score_gemma":0.0016645818,"teacher_disagreement_score":0.01305294,"about_ca_system_score_codex":0.001223006,"about_ca_system_score_gemma":0.001524393,"threshold_uncertainty_score":0.06903136},"labels":[],"label_agreement":null},{"id":"W2020639336","doi":"10.1109/ccece.2008.4564576","title":"A preliminary study of factors affecting the performance of a Playback Attack Detector","year":2008,"lang":"en","type":"article","venue":"Conference proceedings - Canadian Conference on Electrical and Computer Engineering","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Utterance; Phrase; Process (computing); Channel (broadcasting); Detector; Speaker verification; Speech recognition; Speaker recognition; Artificial intelligence; Computer network; Telecommunications","score_opus":0.03531933933036837,"score_gpt":0.21073675545623322,"score_spread":0.17541741612586484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020639336","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92635727,0.0010476115,0.0680468,0.00016503331,0.00012234725,0.00061012123,0.00040202908,0.00085831573,0.002390501],"genre_scores_gemma":[0.9634521,0.00060820585,0.032814454,0.00007609098,0.000046118515,0.0002135639,0.0007129983,0.00013656766,0.00193979],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9970566,0.0007293991,0.0004467082,0.00058386335,0.0007454049,0.00043808398],"domain_scores_gemma":[0.9531317,0.035139687,0.0015446674,0.0017218613,0.007836883,0.00062526943],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030964732,0.0010594351,0.00087387924,0.00092327694,0.00077737233,0.0019136601,0.0008530339,0.00096888805,0.0028780785],"category_scores_gemma":[0.043623075,0.0004802549,0.00037689327,0.0007756567,0.0005703717,0.0023047896,0.0006286471,0.000735577,0.0012962044],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007973376,0.0017119823,0.0683639,0.0018769071,0.00022093413,0.0011156864,0.0013670393,0.011955661,0.64913195,0.00068294845,0.0013320437,0.2542677],"study_design_scores_gemma":[0.00017294014,0.022700552,0.15603216,0.00013963284,0.00061161583,0.0029278712,0.0019905528,0.1029308,0.70710146,0.00049504335,0.004670979,0.00022627802],"about_ca_topic_score_codex":0.0031397538,"about_ca_topic_score_gemma":0.0022919811,"teacher_disagreement_score":0.0031397538,"about_ca_system_score_codex":0.0006876493,"about_ca_system_score_gemma":0.0006783298,"threshold_uncertainty_score":0.0163759},"labels":[],"label_agreement":null},{"id":"W2020683423","doi":"10.1109/asru.2013.6707749","title":"Improvements to Deep Convolutional Neural Networks for LVCSR","year":2013,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Dropout (neural networks); Pooling; Convolutional neural network; Word error rate; Speech recognition; Task (project management); Artificial intelligence; Deep neural networks; Baseline (sea); Deep learning; Adaptation (eye); Machine learning; Pattern recognition (psychology)","score_opus":0.033450896165499386,"score_gpt":0.26621165720297973,"score_spread":0.23276076103748033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020683423","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056140438,0.008303492,0.89048356,0.0018109271,0.00086773635,0.00019791067,0.0025456029,0.016661596,0.022988833],"genre_scores_gemma":[0.47314602,0.00382232,0.48192033,0.0009163507,0.00051555963,0.00030565963,0.009061891,0.0011755762,0.029136207],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99881244,0.00019675893,0.00008566775,0.00028895802,0.00048103416,0.00013517152],"domain_scores_gemma":[0.9987746,0.00039117452,0.00006105851,0.00030566895,0.00041764634,0.000049779024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022073416,0.0021467765,0.0007412459,0.0008162549,0.00046831777,0.0010150577,0.0013740218,0.0010330688,0.011282435],"category_scores_gemma":[0.0050534345,0.0005645458,0.00088088994,0.00083725626,0.0003394705,0.0021843684,0.0013304125,0.0023648457,0.005451932],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005685511,0.00021584965,0.0021065574,0.00039324648,0.00019476711,0.00021054185,0.00010104423,0.123625174,0.06066368,0.010638499,0.025504937,0.77577716],"study_design_scores_gemma":[0.00010621626,0.00042245435,0.0040693157,0.0001304713,0.00014649934,0.0003783126,0.00006459358,0.85873705,0.07052094,0.010814378,0.054521296,0.00008845339],"about_ca_topic_score_codex":0.014068086,"about_ca_topic_score_gemma":0.027553169,"teacher_disagreement_score":0.014068086,"about_ca_system_score_codex":0.0013391159,"about_ca_system_score_gemma":0.0012355484,"threshold_uncertainty_score":0.03774351},"labels":[],"label_agreement":null},{"id":"W2021552769","doi":"10.1121/1.4743145","title":"Acoustic and perceptual speaker normalization","year":2000,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Normalization (sociology); Formant; Vowel; Perception; Speech recognition; Weighting; Acoustics; Computer science; Rounding; Mathematics; Psychology; Physics","score_opus":0.01212370106382214,"score_gpt":0.22852819087477924,"score_spread":0.2164044898109571,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021552769","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11404257,0.00107523,0.8560408,0.00020077387,0.0004786259,0.0016790476,0.00128119,0.0028225186,0.0223793],"genre_scores_gemma":[0.51759714,0.0012241781,0.46093053,0.00029584736,0.00029592472,0.0028851149,0.0020569786,0.0015128913,0.013201413],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9925006,0.0017640876,0.00049353123,0.0014642202,0.0035400372,0.00023758129],"domain_scores_gemma":[0.9929125,0.0022459705,0.00022991448,0.0012550611,0.0032475295,0.00010903469],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0071633486,0.0010203108,0.0011506173,0.0016973126,0.0008534498,0.0013340787,0.0011556982,0.0007129493,0.007941757],"category_scores_gemma":[0.021205226,0.00043601572,0.00085722574,0.0018283126,0.0012670537,0.0017875386,0.0014911246,0.00095291605,0.0026287655],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002184024,0.00031533226,0.009393935,0.0015706277,0.0003279734,0.0003282178,0.0019653311,0.021271616,0.29560247,0.010701673,0.002638177,0.65370065],"study_design_scores_gemma":[0.0005261027,0.004230682,0.2340936,0.00025845587,0.0009998116,0.0064932723,0.0020991995,0.1759792,0.48846507,0.023024902,0.06313197,0.00069773843],"about_ca_topic_score_codex":0.0016291257,"about_ca_topic_score_gemma":0.001981586,"teacher_disagreement_score":0.007941757,"about_ca_system_score_codex":0.0006530209,"about_ca_system_score_gemma":0.00077002967,"threshold_uncertainty_score":0.03788382},"labels":[],"label_agreement":null},{"id":"W2022164734","doi":"10.1121/1.4778214","title":"Glottal-wave and vocal-tract-area-function estimations from vowel sounds based on realistic assumptions and models","year":2005,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Vocal tract; Vowel; Acoustics; Glottis; Mathematics; Inverse filter; Speech recognition; Inverse; Computer science; Physics; Medicine; Larynx; Anatomy; Geometry","score_opus":0.033551128964869295,"score_gpt":0.2502150606801642,"score_spread":0.2166639317152949,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022164734","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35211614,0.0002834316,0.64591825,0.000040410734,0.000014605763,0.000059672406,0.00023329085,0.00027294928,0.001061235],"genre_scores_gemma":[0.9023433,0.00022625293,0.09611754,0.000017261935,0.000010685601,0.00010513764,0.0004335861,0.00005713422,0.0006892153],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996778,0.00007404302,0.00002590108,0.00009156732,0.00010692274,0.000023818971],"domain_scores_gemma":[0.9988206,0.0008478791,0.0000859616,0.00012058764,0.00010794397,0.000016913513],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000879137,0.00041113864,0.00034312136,0.0004056639,0.00018468277,0.0007126086,0.00028999048,0.0005590168,0.0006635009],"category_scores_gemma":[0.005564648,0.00031990337,0.00055182975,0.0001716987,0.00030073014,0.00089210673,0.00029291896,0.00039704292,0.00030772138],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00066974194,0.00012776058,0.029285526,0.0006423333,0.00028817827,0.0003236317,0.0007245575,0.41192788,0.31136638,0.0076321764,0.0005059365,0.23650582],"study_design_scores_gemma":[0.000022555632,0.00028060324,0.061815023,0.00006503773,0.000101034995,0.00062550686,0.00011801198,0.8876814,0.04406192,0.0035296003,0.0016065226,0.000092689195],"about_ca_topic_score_codex":0.0025765281,"about_ca_topic_score_gemma":0.0034242477,"teacher_disagreement_score":0.0025765281,"about_ca_system_score_codex":0.00032074994,"about_ca_system_score_gemma":0.00038924895,"threshold_uncertainty_score":0.005123079},"labels":[],"label_agreement":null},{"id":"W2022663094","doi":"10.1145/1979742.1979700","title":"Ubiquitous voice synthesis","year":2011,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Speech synthesis; Interactivity; Ubiquitous computing; Human–computer interaction; Embodied cognition; Phone; Production (economics); Multimedia; Speech recognition; Artificial intelligence; Linguistics","score_opus":0.0597872934221393,"score_gpt":0.22510852878167537,"score_spread":0.16532123535953608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022663094","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02196124,0.004370156,0.8645521,0.00054181763,0.0009606984,0.0002699125,0.0005008018,0.008838577,0.098004796],"genre_scores_gemma":[0.606441,0.0040234807,0.29581162,0.0008066947,0.000641944,0.0004986233,0.0015643105,0.0014515935,0.088760644],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990281,0.00016026353,0.00006297294,0.0002804214,0.00036595511,0.000102214384],"domain_scores_gemma":[0.9995028,0.00013629385,0.000023048728,0.00015059345,0.0001385815,0.000048734495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005874713,0.0007355974,0.00077664334,0.00062456523,0.00074262987,0.0025517582,0.00097372837,0.0012295798,0.018452192],"category_scores_gemma":[0.0019530032,0.000286389,0.0005887056,0.0004087022,0.0006743306,0.0020602609,0.0033877674,0.00064895063,0.0064228815],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005166397,0.00010556233,0.0009428428,0.0009712827,0.00008809109,0.001089499,0.0012440737,0.0067271153,0.20463236,0.053451303,0.016011018,0.71422017],"study_design_scores_gemma":[0.00018333335,0.00051330886,0.0019940336,0.00035667804,0.00014452206,0.003246471,0.0011765679,0.06638923,0.13431391,0.04837325,0.74317294,0.00013566145],"about_ca_topic_score_codex":0.0005006684,"about_ca_topic_score_gemma":0.0005704304,"teacher_disagreement_score":0.018452192,"about_ca_system_score_codex":0.00036282727,"about_ca_system_score_gemma":0.00042795154,"threshold_uncertainty_score":0.061728776},"labels":[],"label_agreement":null},{"id":"W2023289124","doi":"10.1109/isspa.2012.6310464","title":"Developing a hybrid language model for open vocabulary automatic speech recognition in a lecture speech task","year":2012,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Vocabulary; Task (project management); Lexicon; Speech recognition; Natural language processing; Artificial intelligence; Language model; Word (group theory); Domain (mathematical analysis); Linguistics","score_opus":0.06461673165344403,"score_gpt":0.3074663054317703,"score_spread":0.24284957377832625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2023289124","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020991778,0.00015849482,0.975872,0.000119110155,0.000054157168,0.00005174134,0.00011675691,0.0016447419,0.0009912149],"genre_scores_gemma":[0.52121305,0.00034582516,0.46917418,0.00022942231,0.000109552915,0.00041528157,0.0008413098,0.00043497194,0.0072364425],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99967015,0.00009134342,0.000024144025,0.00010212948,0.000080332014,0.0000319309],"domain_scores_gemma":[0.99944276,0.00030788817,0.00003100451,0.000038806753,0.00015564624,0.000024003004],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078742986,0.0005485009,0.0005154683,0.00042775885,0.00026895912,0.00078349473,0.0010405236,0.0006388401,0.0019482967],"category_scores_gemma":[0.0013522067,0.00034317613,0.0006308029,0.0002782577,0.00026271128,0.0011454222,0.0006215655,0.0009962232,0.0018535084],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043396006,0.0002493543,0.002139742,0.0001895945,0.00020811537,0.00023706094,0.00029408315,0.46070814,0.06644357,0.0127703445,0.0034276461,0.45289832],"study_design_scores_gemma":[0.0000080238415,0.00004413601,0.00013731365,0.0000035490314,0.000015851654,0.00003073032,0.000015986056,0.9946794,0.0032082067,0.0011309776,0.00071668415,0.000009155243],"about_ca_topic_score_codex":0.004717097,"about_ca_topic_score_gemma":0.0067233173,"teacher_disagreement_score":0.004717097,"about_ca_system_score_codex":0.00043201205,"about_ca_system_score_gemma":0.0007489649,"threshold_uncertainty_score":0.009379327},"labels":[],"label_agreement":null},{"id":"W2024218073","doi":"10.1145/1066078.1066081","title":"A speech synthesizer for Persian text using a neural network with a smooth ergodic HMM","year":2005,"lang":"en","type":"article","venue":"ACM Transactions on Asian Language Information Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Preprocessor; Speech recognition; Speech synthesis; Hidden Markov model; Artificial neural network; Intelligibility (philosophy); Natural language processing; Artificial intelligence; Active listening; Language model; Time delay neural network","score_opus":0.015612561096692375,"score_gpt":0.2520033667490014,"score_spread":0.23639080565230905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024218073","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048257492,0.0003738667,0.9390619,0.00011905158,0.00013234346,0.000119829114,0.00022176887,0.0077335034,0.003980236],"genre_scores_gemma":[0.43938503,0.00021270156,0.5507238,0.00007555175,0.000054590455,0.00014995497,0.0004314309,0.00021027004,0.008756616],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99986017,0.000028612665,0.000011180501,0.000054245233,0.00003551401,0.0000102511585],"domain_scores_gemma":[0.9998646,0.000053999785,0.000008399937,0.000021397358,0.000040505573,0.000011173696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034959553,0.00050685863,0.00033428433,0.00023046015,0.00028200852,0.00029790789,0.00037649806,0.00037571267,0.0031995985],"category_scores_gemma":[0.0004937756,0.00017685337,0.00034441374,0.00018208669,0.0001973003,0.00029798175,0.00023236159,0.00049076544,0.0010081673],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006035802,0.00009878544,0.00088262896,0.00029491234,0.00014507188,0.00072116405,0.00024339171,0.096055925,0.38201004,0.0059301797,0.0033247198,0.50968957],"study_design_scores_gemma":[0.00007208055,0.0003220079,0.0012897771,0.000020455433,0.00009903763,0.00046148163,0.000044207965,0.8405184,0.14095454,0.0017575679,0.014418744,0.000041803043],"about_ca_topic_score_codex":0.002199576,"about_ca_topic_score_gemma":0.0039235577,"teacher_disagreement_score":0.0031995985,"about_ca_system_score_codex":0.00025617197,"about_ca_system_score_gemma":0.0003117111,"threshold_uncertainty_score":0.0107037425},"labels":[],"label_agreement":null},{"id":"W2026159472","doi":"10.1016/j.engappai.2009.09.006","title":"An efficient speech recognition system in adverse conditions using the nonparametric regression","year":2009,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Speech recognition; Robustness (evolution); Hidden Markov model; Artificial neural network; Artificial intelligence; Noise (video); Pattern recognition (psychology)","score_opus":0.03786793650265436,"score_gpt":0.2989782076400465,"score_spread":0.26111027113739216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026159472","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.073455244,0.00024977312,0.91861457,0.00015517378,0.000111516,0.000068317786,0.00024857858,0.005168591,0.0019282586],"genre_scores_gemma":[0.56583536,0.00023623779,0.42720136,0.0001768791,0.00014693594,0.00015555759,0.0005892161,0.0002573502,0.0054010074],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99964714,0.00008322244,0.000022416538,0.00009747623,0.00010860496,0.000041186664],"domain_scores_gemma":[0.9995432,0.00018226456,0.000034271947,0.000051085946,0.00016575542,0.000023394607],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067823246,0.0005072443,0.0009287255,0.00037401286,0.0003822666,0.00051164255,0.0006024523,0.00084671535,0.0020765124],"category_scores_gemma":[0.0011216288,0.00027512718,0.00031423898,0.0002647972,0.0001933348,0.0005724042,0.00056582416,0.00057869236,0.0021904255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014100185,0.00022013142,0.0040108818,0.00015168781,0.000107387685,0.00045399362,0.000111876376,0.024068598,0.31344923,0.0013383368,0.0045753075,0.6501026],"study_design_scores_gemma":[0.00016274698,0.0004603556,0.009636914,0.000027332648,0.00021829207,0.0011007177,0.00006613155,0.82544154,0.15392041,0.00129497,0.007580696,0.000089823945],"about_ca_topic_score_codex":0.0012882996,"about_ca_topic_score_gemma":0.0022322214,"teacher_disagreement_score":0.0020765124,"about_ca_system_score_codex":0.00016499574,"about_ca_system_score_gemma":0.00050672406,"threshold_uncertainty_score":0.0069466233},"labels":[],"label_agreement":null},{"id":"W2029459011","doi":"10.1155/2008/258184","title":"On the Use of Complementary Spectral Features for Speaker Recognition","year":2007,"lang":"en","type":"article","venue":"EURASIP Journal on Advances in Signal Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Additive white Gaussian noise; Mel-frequency cepstrum; Speech recognition; Computer science; Cepstrum; Vocal tract; Pattern recognition (psychology); Crest factor; Linear prediction; Speaker recognition; Noise (video); White noise; Artificial intelligence; Mathematics; Bandwidth (computing); Feature extraction; Telecommunications","score_opus":0.08896500203753117,"score_gpt":0.3259021926772365,"score_spread":0.23693719063970536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029459011","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034114327,0.0034621248,0.9529112,0.00023061845,0.00027697315,0.00014006364,0.00029471578,0.0019858999,0.006584106],"genre_scores_gemma":[0.4519403,0.0036949976,0.5365376,0.00029605886,0.00036172048,0.00021008315,0.0012924501,0.00018464867,0.005482111],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99896705,0.00024664446,0.000052216554,0.00020522095,0.00047031196,0.00005866438],"domain_scores_gemma":[0.9988201,0.0004747096,0.000079466416,0.00013976204,0.00046308388,0.000022872015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011555215,0.0008551413,0.0006931964,0.0015928418,0.00030767708,0.0008632799,0.0005252308,0.00078366505,0.001772239],"category_scores_gemma":[0.0030516651,0.0002196384,0.0006413773,0.0011283482,0.00041900974,0.0011847973,0.0007592229,0.00064583815,0.0018815276],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022947174,0.00008550749,0.0011072791,0.00023576076,0.000095346295,0.00020310748,0.000106571686,0.015498372,0.08414946,0.0050192703,0.0023789145,0.89089096],"study_design_scores_gemma":[0.0000359091,0.0006632887,0.010541743,0.00018633349,0.0002716517,0.0017833337,0.00016038198,0.79437274,0.15056689,0.011040658,0.03015,0.0002270289],"about_ca_topic_score_codex":0.0014524028,"about_ca_topic_score_gemma":0.0012919251,"teacher_disagreement_score":0.001772239,"about_ca_system_score_codex":0.00023224842,"about_ca_system_score_gemma":0.00036696947,"threshold_uncertainty_score":0.0061110854},"labels":[],"label_agreement":null},{"id":"W2032491068","doi":"10.1121/1.4788447","title":"ArtiSynth designing a modular 3D articulatory speech synthesizer","year":2005,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Modular design; Component (thermodynamics); Vocal tract; Interface (matter); Rendering (computer graphics); Scripting language; Speech synthesis; Parametric statistics; Parametric model; Speech recognition; Computer vision","score_opus":0.015587821268608273,"score_gpt":0.23411663528967858,"score_spread":0.2185288140210703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032491068","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0076191733,0.00010561975,0.9783055,0.000044726905,0.00007275821,0.00014058794,0.00015988539,0.00976241,0.0037892452],"genre_scores_gemma":[0.09317587,0.00012840044,0.89516324,0.00008449393,0.000030706065,0.0002730787,0.0006817085,0.0015324742,0.008930008],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995877,0.000056560453,0.00002917005,0.00009301545,0.00019997385,0.000033580927],"domain_scores_gemma":[0.9997583,0.00008273115,0.000013863498,0.00005188616,0.0000646512,0.000028684826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007720352,0.0006694308,0.00051254116,0.00056448474,0.0004009125,0.0008132128,0.0011288847,0.0007641937,0.009487685],"category_scores_gemma":[0.0009888493,0.00069152407,0.0010295837,0.0002578869,0.00046810176,0.00075531815,0.0011101586,0.00074401236,0.0034475927],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038021698,0.00012625661,0.0009830593,0.0004886636,0.00011873388,0.0007654577,0.0007763782,0.17524602,0.37971544,0.029443065,0.015568333,0.39638838],"study_design_scores_gemma":[0.00015590557,0.00036848037,0.00086525746,0.000059274094,0.0000687804,0.0011346164,0.00009000373,0.7584484,0.11062599,0.006074844,0.12198835,0.000120051845],"about_ca_topic_score_codex":0.0012296635,"about_ca_topic_score_gemma":0.0015621128,"teacher_disagreement_score":0.009487685,"about_ca_system_score_codex":0.00036854745,"about_ca_system_score_gemma":0.00055988005,"threshold_uncertainty_score":0.031739473},"labels":[],"label_agreement":null},{"id":"W2034785571","doi":"10.1109/wosspa.2013.6602390","title":"Crim's French speech transcription system for ETAPE 2011","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Discriminative model; Speech recognition; Language model; Decoding methods; Artificial intelligence; Confusion; Transcription (linguistics); Algorithm","score_opus":0.029538230472533733,"score_gpt":0.22587332114791253,"score_spread":0.1963350906753788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034785571","genre_codex":"empirical","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25326952,0.002594391,0.22644423,0.0025591853,0.0032412326,0.0041893516,0.14940017,0.17732312,0.18097873],"genre_scores_gemma":[0.35590717,0.00088135037,0.17121953,0.0010141718,0.0006823547,0.0023258121,0.34134263,0.0075895335,0.11903749],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99814796,0.0005434026,0.0001022995,0.00035865547,0.00066536997,0.00018231833],"domain_scores_gemma":[0.99763954,0.00026492868,0.00007328976,0.00030953757,0.0015288166,0.00018396195],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016636763,0.0012688593,0.00077260926,0.0013672216,0.0010490032,0.0013000693,0.00091401214,0.000997657,0.031020788],"category_scores_gemma":[0.003315456,0.00023664089,0.0003766763,0.0008858412,0.0002458247,0.000771057,0.0006993115,0.0008623806,0.021704298],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015593818,0.00035643307,0.004638937,0.0005167646,0.00013106332,0.0009229265,0.0005850806,0.0052407268,0.06057026,0.0019736867,0.44463116,0.4788736],"study_design_scores_gemma":[0.00061553135,0.0012959001,0.03555741,0.00014563208,0.00017186314,0.0027149841,0.001248355,0.054121453,0.10468715,0.0009821455,0.7981397,0.00031986836],"about_ca_topic_score_codex":0.04266411,"about_ca_topic_score_gemma":0.045725618,"teacher_disagreement_score":0.04266411,"about_ca_system_score_codex":0.0015667232,"about_ca_system_score_gemma":0.0015769792,"threshold_uncertainty_score":0.103774905},"labels":[],"label_agreement":null},{"id":"W2035327776","doi":"10.1016/j.engappai.2012.06.006","title":"Adaptation to non-native speech using evolutionary-based discriminative linear transforms","year":2012,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Hidden Markov model; Speech recognition; Discriminative model; Adaptation (eye); Maximum a posteriori estimation; Artificial intelligence; Word error rate; Pattern recognition (psychology); Vocabulary; Genetic algorithm; Machine learning; Maximum likelihood; Statistics; Mathematics","score_opus":0.05886253252009006,"score_gpt":0.30295699338179793,"score_spread":0.24409446086170788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035327776","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1666396,0.0001841894,0.82914186,0.00009945013,0.00006995609,0.000028469336,0.000026308924,0.00052234496,0.0032879151],"genre_scores_gemma":[0.8407299,0.00016253222,0.15531062,0.00006258501,0.000024061526,0.00003887385,0.000101735386,0.00011729531,0.0034523953],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999882,0.000024560053,0.0000057157745,0.000036329784,0.00003459802,0.000016809514],"domain_scores_gemma":[0.99966466,0.00015188009,0.000022649336,0.000048790334,0.00009253518,0.000019386922],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035459636,0.00030055473,0.0003237663,0.00023782547,0.00014614324,0.0003324898,0.00038582867,0.0003838633,0.0010408162],"category_scores_gemma":[0.0013008676,0.00022956908,0.00034554888,0.00026982158,0.00025790138,0.00041848878,0.00047542452,0.00045050148,0.0004004477],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002174073,0.00018084339,0.0020979983,0.00009011115,0.00008527315,0.00022893648,0.00018647459,0.36975613,0.21715175,0.004705679,0.0007751782,0.4045242],"study_design_scores_gemma":[0.0000083699115,0.000037206828,0.00067774375,0.0000026947625,0.000011692071,0.00007352648,0.000015075168,0.98843,0.0097694695,0.0005331828,0.00043514336,0.000005834225],"about_ca_topic_score_codex":0.0010278994,"about_ca_topic_score_gemma":0.0017878168,"teacher_disagreement_score":0.0010408162,"about_ca_system_score_codex":0.00019258709,"about_ca_system_score_gemma":0.00022553308,"threshold_uncertainty_score":0.003481865},"labels":[],"label_agreement":null},{"id":"W2035647012","doi":"10.1121/1.3508941","title":"An acoustic study of [liquid + stop] sequences by native and second-language speakers of English.","year":2010,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Percept; Context (archaeology); Variation (astronomy); Perception; Speech production; First language; Variety (cybernetics); Linguistics; Formant; Computer science; Sample (material); Acoustics; Psychology; Speech recognition; Geography; Artificial intelligence; Physics; Vowel","score_opus":0.009730380559663037,"score_gpt":0.25841855956011117,"score_spread":0.24868817900044812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035647012","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9989507,0.00004699173,0.00026082143,0.000008645076,0.00000431858,0.000007964255,0.00007049634,0.0000045882357,0.0006453921],"genre_scores_gemma":[0.99773276,0.00009719543,0.00082410657,0.000016484022,0.000009151242,0.000017814033,0.00027140666,0.000014928135,0.0010161074],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99966943,0.00007964594,0.000014662695,0.0000789003,0.00011645051,0.000040947696],"domain_scores_gemma":[0.9988457,0.0005410081,0.00007857573,0.00006368927,0.00031835012,0.00015254531],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005210698,0.00025075392,0.00022631868,0.00041473558,0.00046208923,0.00041029725,0.00022962643,0.00021697972,0.0012501708],"category_scores_gemma":[0.0021511938,0.00015660515,0.00014904697,0.0003973642,0.00049914524,0.00019985715,0.00040600455,0.00028252226,0.00032875504],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019097014,0.00029348847,0.2658522,0.0003082584,0.00014603774,0.0017882163,0.11392269,0.00020869823,0.55975246,0.00030859897,0.00085308874,0.054656576],"study_design_scores_gemma":[0.00002030213,0.0005583496,0.96896344,0.000009057171,0.00004185622,0.0021563063,0.015920766,0.0004954654,0.009599444,0.0000481605,0.0021535668,0.00003329706],"about_ca_topic_score_codex":0.022438668,"about_ca_topic_score_gemma":0.045943435,"teacher_disagreement_score":0.022438668,"about_ca_system_score_codex":0.00024008233,"about_ca_system_score_gemma":0.00034018912,"threshold_uncertainty_score":0.044616163},"labels":[],"label_agreement":null},{"id":"W2036242736","doi":"10.1109/icassp.2013.6638952","title":"A deep convolutional neural network using heterogeneous pooling for trading acoustic invariance with phonetic confusion","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":188,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Word error rate; Speech recognition; Pooling; Convolutional neural network; TIMIT; Artificial intelligence; Dropout (neural networks); Deep learning; Artificial neural network; Hidden Markov model; Pattern recognition (psychology); Machine learning","score_opus":0.032079038474955385,"score_gpt":0.23135305306931908,"score_spread":0.1992740145943637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036242736","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032729223,0.0003933572,0.96196324,0.00014390363,0.00008299365,0.000050187344,0.00018830855,0.0018291351,0.0026196954],"genre_scores_gemma":[0.5793263,0.0003583436,0.4114891,0.0002608399,0.000059161495,0.00013648947,0.0008739488,0.00021113691,0.007284734],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99968255,0.00003155014,0.0000150648175,0.000104521205,0.00010471756,0.000061675695],"domain_scores_gemma":[0.99979323,0.00005366368,0.000024005058,0.00004902461,0.00005773256,0.000022491857],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058889244,0.0009642357,0.00051298155,0.00039371388,0.00034472893,0.000567027,0.0013414288,0.0007245412,0.0020025289],"category_scores_gemma":[0.0010254649,0.00041288135,0.0004938471,0.0005160319,0.00045721393,0.0012211581,0.0010660634,0.0008218795,0.0006409706],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003174313,0.00021717093,0.002570908,0.00015493222,0.00023587939,0.00029065256,0.000084698855,0.30763075,0.15951353,0.011925515,0.0064282115,0.5106303],"study_design_scores_gemma":[0.000013988223,0.00006746922,0.0005862334,0.000009980908,0.000039623978,0.00008659593,0.000005395121,0.96844876,0.025790261,0.0024351475,0.0025009117,0.000015615053],"about_ca_topic_score_codex":0.0069800806,"about_ca_topic_score_gemma":0.01408261,"teacher_disagreement_score":0.0069800806,"about_ca_system_score_codex":0.0009042357,"about_ca_system_score_gemma":0.001027798,"threshold_uncertainty_score":0.013878942},"labels":[],"label_agreement":null},{"id":"W2038598237","doi":"10.1109/asru.2013.6707717","title":"Cross-lingual context sharing and parameter-tying for multi-lingual speech recognition","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Speech recognition; Context (archaeology); Tying; Natural language processing; Artificial intelligence; Subspace topology; Covariance; Language model; Task (project management); Dialog box","score_opus":0.12312297462305719,"score_gpt":0.3351410842406935,"score_spread":0.2120181096176363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038598237","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022436967,0.00045011513,0.9738705,0.000094092626,0.00006896455,0.00003603719,0.00013957873,0.0015304482,0.001373319],"genre_scores_gemma":[0.49519286,0.00062556774,0.4988311,0.00020305038,0.00017657666,0.00020097148,0.0011017666,0.0006748217,0.00299339],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980217,0.0008105338,0.00010792122,0.00066646887,0.00027206115,0.00012133134],"domain_scores_gemma":[0.99743325,0.00075419695,0.0001622103,0.0012889985,0.000297447,0.000063865424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022235254,0.0008607428,0.0010161012,0.00080287695,0.00086365064,0.0012600044,0.0012075761,0.00091145834,0.0026066704],"category_scores_gemma":[0.006014921,0.0005613463,0.0010441844,0.0012998377,0.0008101533,0.002470568,0.0032745635,0.0014243543,0.0021364144],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032184544,0.00016531828,0.0037949614,0.00015266771,0.00018367814,0.0003297723,0.00063984544,0.09554506,0.047954086,0.0122249825,0.002660766,0.836027],"study_design_scores_gemma":[0.00002454294,0.00019596894,0.003746012,0.000040959927,0.00010582262,0.0006179479,0.00040720397,0.9046036,0.05018561,0.027846461,0.012115962,0.000109907014],"about_ca_topic_score_codex":0.002171437,"about_ca_topic_score_gemma":0.0043956577,"teacher_disagreement_score":0.0026066704,"about_ca_system_score_codex":0.000360774,"about_ca_system_score_gemma":0.0011557137,"threshold_uncertainty_score":0.011759222},"labels":[],"label_agreement":null},{"id":"W2041644614","doi":"10.1121/1.4783150","title":"Experimental and numerical determination of the surface deformation of a synthetic model of the human vocal folds.","year":2008,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"von Mises yield criterion; Materials science; Synthetic data; Mechanics; Deformation (meteorology); Vocal folds; Stress (linguistics); Displacement (psychology); Acoustics; Oscillation (cell signaling); Experimental data; Amplitude; Surface (topology); Finite element method; Computer science; Optics; Mathematics; Geometry; Physics; Algorithm; Composite material; Thermodynamics","score_opus":0.02363772537464647,"score_gpt":0.2537168821655702,"score_spread":0.23007915679092372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041644614","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9135119,0.00030910893,0.080415264,0.00013001487,0.000075430326,0.00012382463,0.0007492606,0.00022207874,0.0044629644],"genre_scores_gemma":[0.97666293,0.00009404134,0.022244707,0.000014072066,0.000006813807,0.000059412636,0.00023674233,0.000012140137,0.0006690564],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9997961,0.000028402425,0.000014662708,0.000047414025,0.000097896875,0.000015621712],"domain_scores_gemma":[0.9996265,0.00014719067,0.000036149,0.00010477473,0.00006080353,0.000024650115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004684785,0.00023088988,0.00020682793,0.00020892892,0.00020336181,0.00018421811,0.00025620373,0.00050609244,0.0019973922],"category_scores_gemma":[0.0008633873,0.00015442874,0.0002083695,0.00019989183,0.0005111831,0.00018957583,0.00022459125,0.00019662423,0.00020059674],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002256377,0.00013294988,0.0026004992,0.00019920016,0.000014487235,0.00030435345,0.00019685725,0.09723518,0.88436294,0.001202344,0.00043429222,0.013091279],"study_design_scores_gemma":[0.00006364912,0.0013593672,0.022344138,0.00002880078,0.000040926316,0.0015125838,0.00019718886,0.65031457,0.3185696,0.0009781251,0.004527185,0.00006382095],"about_ca_topic_score_codex":0.00078128086,"about_ca_topic_score_gemma":0.0007371633,"teacher_disagreement_score":0.0019973922,"about_ca_system_score_codex":0.00017558997,"about_ca_system_score_gemma":0.00018124277,"threshold_uncertainty_score":0.006681919},"labels":[],"label_agreement":null},{"id":"W2044054970","doi":"10.1109/asru.2011.6163886","title":"Multi-taper MFCC features for speaker verification using I-vectors","year":2011,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Computer Research Institute of Montréal","funders":"National Institute of Standards and Technology","keywords":"NIST; Mel-frequency cepstrum; Computer science; Speech recognition; Speaker recognition; Pattern recognition (psychology); Classifier (UML); Speaker verification; Hamming distance; Hamming code; Microphone; Variance (accounting); Artificial intelligence; Feature extraction; Algorithm; Decoding methods; Telecommunications","score_opus":0.16905148776932388,"score_gpt":0.2935253001225161,"score_spread":0.12447381235319221,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044054970","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.059862196,0.00317132,0.92857397,0.0001682848,0.00016374655,0.00013803168,0.0004919053,0.0039602374,0.0034702686],"genre_scores_gemma":[0.4230063,0.0014685105,0.5689708,0.00009728693,0.00025645652,0.0001827027,0.0018254066,0.00037223002,0.0038203206],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990876,0.00014672209,0.0000720024,0.00019636392,0.00042543677,0.0000718265],"domain_scores_gemma":[0.9988393,0.00038170922,0.0001612911,0.00021919467,0.00035795296,0.000040558072],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007181998,0.00077126233,0.0007225778,0.0018180825,0.00045640944,0.0007322804,0.0007149551,0.00068436767,0.0031623815],"category_scores_gemma":[0.0031894753,0.00020705623,0.0005333671,0.0010741231,0.00026500432,0.0012737516,0.0006114941,0.0006688107,0.002620162],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002938324,0.00008072827,0.0009631765,0.00016767727,0.00003769356,0.00010310788,0.00007670326,0.008604009,0.10258624,0.001489053,0.0020780521,0.8835197],"study_design_scores_gemma":[0.000080968595,0.0011231299,0.021417636,0.0002113666,0.000270188,0.0022065693,0.00023951055,0.625065,0.31205812,0.0051318435,0.03188342,0.0003122231],"about_ca_topic_score_codex":0.0013145887,"about_ca_topic_score_gemma":0.0016365905,"teacher_disagreement_score":0.0031623815,"about_ca_system_score_codex":0.00025780898,"about_ca_system_score_gemma":0.000340393,"threshold_uncertainty_score":0.010579228},"labels":[],"label_agreement":null},{"id":"W2048311555","doi":"10.1121/1.2918787","title":"Suppressing aliasing noise in the speech feature domain for automatic speech recognition","year":2008,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Computer science; Speech recognition; Noise (video); Aliasing; Feature (linguistics); Baseband; Voice activity detection; Speech processing; Linear predictive coding; Artificial intelligence; Pattern recognition (psychology); Telecommunications","score_opus":0.030908986815525338,"score_gpt":0.2663822704639665,"score_spread":0.23547328364844117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048311555","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036138196,0.002067749,0.95766795,0.00030942916,0.00019263585,0.0000434929,0.000039879294,0.00071145635,0.0028292534],"genre_scores_gemma":[0.363379,0.0021435698,0.6283376,0.00027204084,0.00033887746,0.00010265749,0.00024183723,0.0001805541,0.0050037922],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996288,0.00008883753,0.000028979315,0.000048460362,0.00018286465,0.000022054082],"domain_scores_gemma":[0.9993698,0.00029965208,0.000050861367,0.00009165057,0.00017116392,0.000016902877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044374965,0.0003839925,0.0003577593,0.00046640038,0.00037171415,0.00064470136,0.00038542706,0.00068465015,0.0018496546],"category_scores_gemma":[0.0015988727,0.0001646382,0.00028130523,0.000533832,0.00036701703,0.0006445884,0.00023415926,0.000512831,0.0013497891],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035037516,0.00009580194,0.0005814426,0.00022847798,0.00003354393,0.0002819234,0.00019744161,0.0066464674,0.3824748,0.014072061,0.002609282,0.59242827],"study_design_scores_gemma":[0.000045933386,0.00055854407,0.0030985174,0.000068850946,0.0001160941,0.0017940267,0.00010574622,0.41570255,0.521017,0.011717034,0.045716103,0.000059618782],"about_ca_topic_score_codex":0.0005068784,"about_ca_topic_score_gemma":0.0013000928,"teacher_disagreement_score":0.0018496546,"about_ca_system_score_codex":0.00023413714,"about_ca_system_score_gemma":0.000391467,"threshold_uncertainty_score":0.0061876774},"labels":[],"label_agreement":null},{"id":"W2052003572","doi":"10.1007/s10772-005-2166-6","title":"Aligning Text and Phonemes for Speech Technology Applications Using an EM-Like Algorithm","year":2005,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; National Research Council Institute for Biodiagnostics","funders":"","keywords":"Computer science; Speech recognition; Speech synthesis; Speech technology; Algorithm; Artificial intelligence; Natural language processing","score_opus":0.021730622613951044,"score_gpt":0.3048551054452593,"score_spread":0.28312448283130826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052003572","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004090573,0.000048673908,0.99410003,0.000053979657,0.00007383529,0.000029509354,0.000046293557,0.0009597861,0.0005973086],"genre_scores_gemma":[0.045578364,0.000116056566,0.9501069,0.00011079921,0.00006088551,0.00011712106,0.0004496025,0.00043915774,0.0030210703],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994305,0.00016010119,0.00004898547,0.00020350516,0.00011210715,0.000044793556],"domain_scores_gemma":[0.9989512,0.0004890775,0.00006472386,0.00015769753,0.0002967943,0.000040404324],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010521736,0.0011897915,0.0007895868,0.0007732836,0.0006378596,0.0010163336,0.0010118252,0.0018465547,0.0074474276],"category_scores_gemma":[0.0047006225,0.0005945097,0.0010384277,0.0012026167,0.0004879997,0.0015636873,0.0010940806,0.0016474976,0.005624262],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006241585,0.00015596673,0.00079536386,0.00020474005,0.00015424774,0.00019187108,0.00014600513,0.08807941,0.07523761,0.009647713,0.004805758,0.8199572],"study_design_scores_gemma":[0.00007546267,0.00017077333,0.0009964156,0.000032702534,0.000085718115,0.0003565903,0.00010558551,0.9047321,0.07089716,0.010464537,0.012036175,0.000046741134],"about_ca_topic_score_codex":0.0014419524,"about_ca_topic_score_gemma":0.0021153348,"teacher_disagreement_score":0.0074474276,"about_ca_system_score_codex":0.00027579296,"about_ca_system_score_gemma":0.0008490049,"threshold_uncertainty_score":0.024914086},"labels":[],"label_agreement":null},{"id":"W2052793700","doi":"10.1186/1743-0003-6-26","title":"Development of an automated speech recognition interface for personal emergency response systems","year":2009,"lang":"en","type":"article","venue":"Journal of NeuroEngineering and Rehabilitation","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":74,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Microphone; Phone; Computer science; Dialog box; Interface (matter); Speech recognition; Telecommunications; World Wide Web; Operating system","score_opus":0.02038812681467578,"score_gpt":0.28212500849185024,"score_spread":0.26173688167717446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052793700","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1273676,0.00027052386,0.83673984,0.00022434253,0.00021092723,0.0017244316,0.00052186125,0.027741257,0.005199222],"genre_scores_gemma":[0.33506712,0.00015584452,0.65164113,0.0003007711,0.00006997758,0.0010462003,0.0010307514,0.0004937084,0.0101944795],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991591,0.00013589633,0.00008168674,0.00021008954,0.00036491643,0.000048271908],"domain_scores_gemma":[0.99828416,0.0005157684,0.00006341051,0.00009371546,0.0009577304,0.000085182786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012289183,0.00074132433,0.000461912,0.0003211027,0.00021740778,0.0005719463,0.0016630144,0.00069046946,0.008406988],"category_scores_gemma":[0.0024975887,0.0003208181,0.00037408617,0.0001148799,0.00024422255,0.0008728227,0.00050331256,0.00058759336,0.0028700393],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014388912,0.0008470618,0.0039040332,0.0008508976,0.00014702076,0.0012165313,0.00087222527,0.0074256817,0.46418586,0.0012643375,0.012131221,0.50571626],"study_design_scores_gemma":[0.0005695211,0.004755753,0.013845505,0.00017103355,0.0003194285,0.00367677,0.00033106963,0.33081648,0.57772326,0.00092076336,0.06668034,0.00019000257],"about_ca_topic_score_codex":0.00085030636,"about_ca_topic_score_gemma":0.0006161744,"teacher_disagreement_score":0.008406988,"about_ca_system_score_codex":0.00031169294,"about_ca_system_score_gemma":0.0005181457,"threshold_uncertainty_score":0.028124213},"labels":[],"label_agreement":null},{"id":"W2053878040","doi":"10.1109/ccece.2010.5575245","title":"An approach to recognize and pronounce words with alternative pronunciations in Farsi","year":2010,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Pronunciation; Computer science; Vowel; Orthography; Word (group theory); Layer (electronics); Artificial intelligence; Speech recognition; Set (abstract data type); Artificial neural network; Perceptron; Natural language processing; Speech synthesis; Index (typography); Mathematics; Linguistics; Reading (process)","score_opus":0.016614110171937292,"score_gpt":0.2418820508242266,"score_spread":0.2252679406522893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053878040","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16112393,0.002299329,0.8199638,0.000584936,0.00044159286,0.00021669854,0.00036974417,0.0029530914,0.012046755],"genre_scores_gemma":[0.5286019,0.00089465745,0.4540758,0.00024368936,0.000077560544,0.000098850505,0.0006016525,0.00009198051,0.015313914],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99966073,0.000054938326,0.000037344038,0.00014193618,0.0000679457,0.000037175294],"domain_scores_gemma":[0.99980265,0.000047098372,0.000016897928,0.000015372643,0.00010798798,0.0000099863555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003951804,0.0004990016,0.00037477328,0.0006945192,0.0005666064,0.0007736281,0.00053959765,0.00065867393,0.0023069945],"category_scores_gemma":[0.00067585055,0.00025859452,0.00037642254,0.00054382,0.0003503165,0.0009760039,0.0005281732,0.00056463276,0.0014301069],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022632834,0.000094884934,0.0036236804,0.00030065555,0.00007638593,0.0004993068,0.0012708765,0.0072450596,0.12849373,0.004933342,0.0032885121,0.8499473],"study_design_scores_gemma":[0.0001039972,0.00066299195,0.026469063,0.00019425084,0.00029409764,0.003289727,0.0033419344,0.7077495,0.18001238,0.012317017,0.06536034,0.00020473958],"about_ca_topic_score_codex":0.0053409375,"about_ca_topic_score_gemma":0.008304634,"teacher_disagreement_score":0.0053409375,"about_ca_system_score_codex":0.00036229033,"about_ca_system_score_gemma":0.0006953259,"threshold_uncertainty_score":0.0106197},"labels":[],"label_agreement":null},{"id":"W2054060258","doi":"10.1109/icassp.2014.6853889","title":"JFA-based front ends for speaker recognition","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"National Institute of Standards and Technology; Johns Hopkins University","keywords":"NIST; Computer science; Speaker recognition; Normalization (sociology); Speech recognition; Adaptation (eye); Diagonal; Feature extraction; Artificial intelligence; Pattern recognition (psychology); Mathematics","score_opus":0.03535858043039168,"score_gpt":0.2393011804715223,"score_spread":0.20394260004113063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054060258","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017270176,0.00013866763,0.99165404,0.000053280495,0.00010060269,0.000038023092,0.00017647316,0.00510842,0.0010034265],"genre_scores_gemma":[0.0905002,0.00023505933,0.8966304,0.0003221772,0.00021782081,0.00033035158,0.0017307271,0.0010053823,0.009027832],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99841166,0.00031641033,0.00010581089,0.0003933095,0.00059623696,0.00017653026],"domain_scores_gemma":[0.99732435,0.0009572472,0.00009494831,0.00054859323,0.0009770399,0.00009778551],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023875954,0.0016938129,0.0010182991,0.0014822008,0.0011518811,0.00203277,0.0019392945,0.002006775,0.015693363],"category_scores_gemma":[0.0062918933,0.0008038327,0.0019950457,0.0009958679,0.0006854662,0.0020810508,0.0017628344,0.0030438893,0.021765957],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006085512,0.0001835554,0.0008276051,0.00018463442,0.00020766114,0.00014807565,0.00021424177,0.0425776,0.070562,0.017398115,0.01300119,0.85408676],"study_design_scores_gemma":[0.000027395574,0.00012483091,0.0010836349,0.000046057554,0.000048332386,0.00027693866,0.000046570476,0.91264623,0.047500335,0.021216795,0.01689073,0.000092088616],"about_ca_topic_score_codex":0.005602665,"about_ca_topic_score_gemma":0.007493586,"teacher_disagreement_score":0.015693363,"about_ca_system_score_codex":0.00090234604,"about_ca_system_score_gemma":0.0011618742,"threshold_uncertainty_score":0.052499533},"labels":[],"label_agreement":null},{"id":"W2055696218","doi":"10.1109/odyssey.2006.248137","title":"The Geometry of the Channel Space in GMM-Based Speaker Recognition","year":2006,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Channel (broadcasting); Mixture model; Joint (building); Range (aeronautics); Rank (graph theory); Pattern recognition (psychology); Computer science; Gaussian; Factor (programming language); Artificial intelligence; Feature (linguistics); Factor analysis; Feature vector; Space (punctuation); Limiting; Mathematics; Machine learning; Combinatorics; Telecommunications; Physics; Engineering","score_opus":0.015656382955508016,"score_gpt":0.20454701128938582,"score_spread":0.18889062833387782,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055696218","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012822882,0.0006300974,0.983491,0.00023120423,0.00008594815,0.000024632918,0.00017983295,0.00053041056,0.0020039184],"genre_scores_gemma":[0.5321747,0.0016247251,0.46216157,0.00021471665,0.00033387542,0.00012852425,0.0005322601,0.00038172683,0.0024478654],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981744,0.00097639294,0.00004072197,0.0003312519,0.00035476693,0.00012247183],"domain_scores_gemma":[0.99812716,0.001051291,0.00012885398,0.0003255077,0.00029388163,0.00007332768],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015430005,0.0006565993,0.00057043775,0.0006669165,0.0005182175,0.0012725403,0.0008549979,0.000831047,0.001890996],"category_scores_gemma":[0.006968176,0.00058179465,0.000573863,0.0008353629,0.0020189409,0.0022671118,0.0012275892,0.0010651352,0.0011430886],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046540765,0.00004365844,0.0033004216,0.00025727623,0.00011237491,0.0004094435,0.00076319935,0.24403346,0.034322575,0.38200554,0.007259893,0.3270268],"study_design_scores_gemma":[0.000017571008,0.00018162801,0.003498919,0.00004565734,0.0000617029,0.0006923465,0.00019835593,0.71326005,0.020349175,0.2446889,0.01686585,0.00013984436],"about_ca_topic_score_codex":0.004944857,"about_ca_topic_score_gemma":0.0033106143,"teacher_disagreement_score":0.004944857,"about_ca_system_score_codex":0.0008228104,"about_ca_system_score_gemma":0.0008436088,"threshold_uncertainty_score":0.009832144},"labels":[],"label_agreement":null},{"id":"W2055842011","doi":"10.1109/icassp.2014.6854822","title":"Deep neural network trained with speaker representation for speaker normalization","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Hidden Markov model; Normalization (sociology); Speech recognition; Computer science; Discriminative model; Speaker recognition; Pattern recognition (psychology); Feature extraction; Word error rate; Artificial neural network; Artificial intelligence; Speaker diarisation","score_opus":0.02168773414574742,"score_gpt":0.2424845208748048,"score_spread":0.22079678672905736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055842011","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02125194,0.0004289433,0.97296077,0.0001234365,0.00012251995,0.000034789515,0.00013840855,0.0019632922,0.0029760245],"genre_scores_gemma":[0.45026404,0.00044782492,0.530647,0.00027116184,0.00008260987,0.00016225084,0.0007841271,0.00018613783,0.01715492],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99977607,0.000038695358,0.000010364508,0.00007357206,0.000072786934,0.000028445334],"domain_scores_gemma":[0.9998599,0.00003873959,0.000012226371,0.000025816224,0.00005529855,0.000007879722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046827496,0.0004543088,0.0003635161,0.00021767868,0.00025138684,0.00035037327,0.00061531493,0.0005287547,0.0020978614],"category_scores_gemma":[0.0007453351,0.00025729477,0.00032246418,0.00028313408,0.00020552536,0.00058076944,0.0005651437,0.001159925,0.0009045303],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002668066,0.00011790265,0.00088034966,0.00010375522,0.00012151357,0.00011203688,0.000088647925,0.14919962,0.14060703,0.008031055,0.0058206907,0.69465065],"study_design_scores_gemma":[0.000008280792,0.000047933296,0.0004990336,0.000007929192,0.000026089205,0.000068060064,0.000008001868,0.96632284,0.027798621,0.0014816135,0.0037191126,0.000012502121],"about_ca_topic_score_codex":0.0041043162,"about_ca_topic_score_gemma":0.00884912,"teacher_disagreement_score":0.0041043162,"about_ca_system_score_codex":0.00056744413,"about_ca_system_score_gemma":0.00060634,"threshold_uncertainty_score":0.00816083},"labels":[],"label_agreement":null},{"id":"W2056986748","doi":"10.1139/p07-102","title":"SIMCV un simulateur analogue de la propagation du son dans le conduit vocal","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Physics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formant; Physics; Vocal tract; Transfer function; Acoustics; Speech recognition; Computer science","score_opus":0.012028217570712731,"score_gpt":0.22079727505460972,"score_spread":0.20876905748389699,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056986748","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52248067,0.00014250957,0.44355878,0.00013710451,0.00016117893,0.0001154364,0.0004455929,0.0038304448,0.029128235],"genre_scores_gemma":[0.93433136,0.000078540324,0.05613971,0.000034737313,0.000018547764,0.00009566579,0.00021254765,0.0002542327,0.008834634],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998839,0.000028056327,0.0000030669999,0.000015393389,0.000053347827,0.000016147573],"domain_scores_gemma":[0.99947184,0.00035112692,0.000024813937,0.0000399271,0.000087634755,0.000024697452],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003684999,0.00048843666,0.0003493773,0.00028661516,0.00030960678,0.00048000473,0.0006818641,0.0006771975,0.0047399555],"category_scores_gemma":[0.001033428,0.00019086829,0.000337776,0.00022822146,0.0003971082,0.00024739603,0.00025633592,0.00036990512,0.00037495035],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006960348,0.00011283907,0.002957554,0.00018945707,0.000052133848,0.0006708451,0.00034785212,0.89592266,0.05672306,0.009464863,0.0015187806,0.031343963],"study_design_scores_gemma":[0.000017883132,0.000052307172,0.00021263669,0.0000039223123,0.000004364661,0.00003537512,0.000012639928,0.991787,0.0066438136,0.00021648736,0.0010102241,0.0000032730914],"about_ca_topic_score_codex":0.006508921,"about_ca_topic_score_gemma":0.0038124814,"teacher_disagreement_score":0.006508921,"about_ca_system_score_codex":0.0005324099,"about_ca_system_score_gemma":0.000391593,"threshold_uncertainty_score":0.015856802},"labels":[],"label_agreement":null},{"id":"W2058080055","doi":"10.1016/j.csl.2014.06.002","title":"Unsupervised language model adaptation using LDA-based mixture models and latent semantic marginals","year":2014,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Latent Dirichlet allocation; Artificial intelligence; Language model; Topic model; Probabilistic latent semantic analysis; Pattern recognition (psychology); Scaling; Mixture model; Cluster analysis; Machine learning; Mathematics","score_opus":0.03687698171248772,"score_gpt":0.25634630427735217,"score_spread":0.21946932256486446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058080055","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006576063,0.0002061521,0.9914766,0.00008261784,0.000061834595,0.000028249422,0.000091083,0.0010422092,0.00043508294],"genre_scores_gemma":[0.37648252,0.0008077711,0.61003554,0.00027312475,0.00025161286,0.00045055742,0.0025079057,0.0017552123,0.007435794],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985519,0.0006498906,0.000070834525,0.00036112932,0.0002453713,0.000120919976],"domain_scores_gemma":[0.9982084,0.00095000985,0.00008027991,0.00030821576,0.00038246406,0.00007055859],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00184013,0.0011116486,0.001268594,0.0011641285,0.00074379885,0.0012551544,0.0015421639,0.00101357,0.0024138256],"category_scores_gemma":[0.004931001,0.0010689262,0.0028795665,0.0012108248,0.0007716623,0.0019322571,0.0021239857,0.0027451026,0.0033646324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009079603,0.00038199857,0.0022620293,0.00023250288,0.00062801555,0.00019690079,0.0005612398,0.35975546,0.035798423,0.01854072,0.007999299,0.5727355],"study_design_scores_gemma":[0.000012616023,0.000018796403,0.00036956408,0.0000080785985,0.000031670916,0.000042911764,0.000021893033,0.99102026,0.0026775834,0.0047799316,0.0009929822,0.000023675693],"about_ca_topic_score_codex":0.005633029,"about_ca_topic_score_gemma":0.008635009,"teacher_disagreement_score":0.005633029,"about_ca_system_score_codex":0.000533251,"about_ca_system_score_gemma":0.0010558747,"threshold_uncertainty_score":0.011200488},"labels":[],"label_agreement":null},{"id":"W2058506073","doi":"10.1016/s1319-1578(09)80002-5","title":"Investigating Emphatic Consonants in Foreign Accented Arabic","year":2009,"lang":"en","type":"article","venue":"Journal of King Saud University - Computer and Information Sciences","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick; Université de Moncton","funders":"","keywords":"Pronunciation; Arabic; Speech recognition; Computer science; Hidden Markov model; Linguistics; Word error rate; Point (geometry); Natural language processing; First language; Artificial intelligence; Mathematics","score_opus":0.023722153588125638,"score_gpt":0.23345435003278556,"score_spread":0.20973219644465993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058506073","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9923085,0.00024272669,0.0062884265,0.000025592894,0.000013797762,0.000020334617,0.000050386054,0.00003261039,0.0010175405],"genre_scores_gemma":[0.99201125,0.0002528109,0.0067006554,0.000023876068,0.000010672867,0.000015135935,0.00011927951,0.000018946337,0.00084740215],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99946016,0.00017646507,0.00005429411,0.000117510834,0.00015644303,0.0000350988],"domain_scores_gemma":[0.99773204,0.0013664854,0.00021651229,0.0001725765,0.00046038115,0.00005202696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060436595,0.0003408439,0.0003215414,0.00041926923,0.00033763418,0.00048574418,0.00022725236,0.0005491051,0.0014497049],"category_scores_gemma":[0.0034226,0.00014929348,0.00017900339,0.00021858838,0.0003145813,0.0005428893,0.00037366952,0.00030409562,0.0008504518],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001516269,0.0001685817,0.025915537,0.0006167774,0.000057231635,0.0014922555,0.0036981667,0.0020156077,0.84715205,0.00036447798,0.00015064226,0.11685243],"study_design_scores_gemma":[0.000076673394,0.0028693464,0.29254556,0.00009264227,0.00028307768,0.010412537,0.007252406,0.02914478,0.6508888,0.0008459767,0.0054603983,0.00012788255],"about_ca_topic_score_codex":0.00092232425,"about_ca_topic_score_gemma":0.0009266523,"teacher_disagreement_score":0.0014497049,"about_ca_system_score_codex":0.00009804348,"about_ca_system_score_gemma":0.00019774232,"threshold_uncertainty_score":0.004849732},"labels":[],"label_agreement":null},{"id":"W2058877998","doi":"10.1121/1.4786938","title":"Better model and decoding methods for automatic speech recognition","year":2006,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Hidden Markov model; Speech recognition; Syllable; Decoding methods; Computer science; TIMIT; Task (project management); Artificial intelligence; Pattern recognition (psychology); Algorithm","score_opus":0.034629954055449885,"score_gpt":0.30929439296888855,"score_spread":0.27466443891343867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058877998","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011489292,0.00069824414,0.99543035,0.00012754422,0.0001047166,0.000029112072,0.00008125805,0.0018428812,0.00053683226],"genre_scores_gemma":[0.028860275,0.0014652183,0.9615468,0.00026506803,0.00023921518,0.00018018617,0.0012976709,0.0009851382,0.0051604295],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99664474,0.0012457801,0.00026191608,0.00062936486,0.0010970475,0.00012102997],"domain_scores_gemma":[0.9959811,0.0015622776,0.0001926099,0.0010400454,0.0011662472,0.000057649326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035226436,0.0018455347,0.001754739,0.0016160851,0.00052586297,0.0017677064,0.0020181437,0.0024843651,0.009257524],"category_scores_gemma":[0.009186265,0.000972815,0.0015020553,0.002110485,0.00056548126,0.0039538913,0.00080408016,0.0029065649,0.010010815],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023161576,0.00017856706,0.00052487635,0.00040062694,0.00017291658,0.00009153992,0.00014114089,0.13017079,0.03600947,0.023832774,0.0064709787,0.80177456],"study_design_scores_gemma":[0.000056376513,0.00009471229,0.0004498806,0.00008078089,0.000059219605,0.00024828908,0.000029333785,0.9462366,0.021256736,0.014927174,0.016464973,0.00009589804],"about_ca_topic_score_codex":0.0051582307,"about_ca_topic_score_gemma":0.006337495,"teacher_disagreement_score":0.009257524,"about_ca_system_score_codex":0.00096347206,"about_ca_system_score_gemma":0.0011866258,"threshold_uncertainty_score":0.0309695},"labels":[],"label_agreement":null},{"id":"W2062003163","doi":"10.1007/s12559-012-9197-5","title":"Low-variance Multitaper Mel-frequency Cepstral Coefficient Features for Speech and Speaker Recognition Systems","year":2012,"lang":"en","type":"article","venue":"Cognitive Computation","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec; Computer Research Institute of Montréal; Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Multitaper; Speech recognition; Window function; Computer science; Cepstrum; Mel-frequency cepstrum; Hamming code; NIST; Estimator; Pattern recognition (psychology); Spectral density; Artificial intelligence; Algorithm; Feature extraction; Mathematics; Statistics; Telecommunications","score_opus":0.03785654066309455,"score_gpt":0.2835100555252821,"score_spread":0.24565351486218753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062003163","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060259875,0.0029594025,0.9310749,0.0003420592,0.00017755838,0.00006946665,0.0007449329,0.0013823111,0.0029893734],"genre_scores_gemma":[0.52648574,0.0020915477,0.46089885,0.00012255479,0.00021126794,0.00014578218,0.0019126929,0.000316443,0.007815129],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99982786,0.00003228368,0.000014672336,0.0000265456,0.000079320096,0.000019320994],"domain_scores_gemma":[0.999451,0.00020565763,0.00004083067,0.00007649825,0.00020588683,0.000020152514],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027987562,0.00035637067,0.00043059775,0.00061384856,0.0002748886,0.00072758883,0.00042726938,0.00047436703,0.0038189392],"category_scores_gemma":[0.00171215,0.00017784872,0.00023327972,0.00077462924,0.00014065945,0.0007122444,0.00031654918,0.00053206086,0.0016516808],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040404187,0.00012288064,0.0005913353,0.00014927803,0.000026548405,0.000086692045,0.000054386477,0.016044883,0.13738626,0.0040323813,0.005321297,0.83578],"study_design_scores_gemma":[0.000051005616,0.00027335767,0.0075005977,0.000048482325,0.000094450064,0.00024975624,0.00008785229,0.8734456,0.09944722,0.0044365744,0.01430997,0.000055092973],"about_ca_topic_score_codex":0.0016891155,"about_ca_topic_score_gemma":0.0034052427,"teacher_disagreement_score":0.0038189392,"about_ca_system_score_codex":0.00024642263,"about_ca_system_score_gemma":0.0003675377,"threshold_uncertainty_score":0.0127756},"labels":[],"label_agreement":null},{"id":"W2062227835","doi":"10.1109/icassp.2013.6639346","title":"Improving deep neural networks for LVCSR using rectified linear units and dropout","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1281,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Dropout (neural networks); Artificial neural network; Speech recognition; Artificial intelligence; Sigmoid function; Discriminative model; Deep neural networks; Task (project management); Vocabulary; Deep learning; Mixture model; Hidden Markov model; Time delay neural network; Bayesian probability; Pattern recognition (psychology); Machine learning","score_opus":0.0442634602867148,"score_gpt":0.2510945759761163,"score_spread":0.2068311156894015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062227835","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03877688,0.002205609,0.9407361,0.00046629092,0.00022389328,0.00012623782,0.0004304609,0.013087563,0.0039469344],"genre_scores_gemma":[0.4202078,0.0010424873,0.56178564,0.000572659,0.00013029545,0.00027811844,0.002304496,0.00095717405,0.012721405],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908197,0.00019015628,0.00007255267,0.00023677183,0.00030190207,0.00011668225],"domain_scores_gemma":[0.99880636,0.00057760865,0.000068549656,0.00016789745,0.00033959394,0.00003999847],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025552877,0.0021965818,0.0010225056,0.00084574055,0.00060468714,0.00097310933,0.001693571,0.0015478845,0.006583173],"category_scores_gemma":[0.005527613,0.00072819786,0.0009515456,0.0007407653,0.00050777884,0.0023385333,0.0011903265,0.00333959,0.0033339255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034626867,0.00023087702,0.0011975212,0.00020647453,0.00015664364,0.00016893835,0.00012897633,0.38607737,0.023780223,0.0043530595,0.009505271,0.5738485],"study_design_scores_gemma":[0.000019701914,0.00007813721,0.00030802938,0.000017912436,0.000022752976,0.000035536716,0.000014405957,0.9854512,0.010796177,0.0012314292,0.0020086507,0.000016060801],"about_ca_topic_score_codex":0.023031173,"about_ca_topic_score_gemma":0.03374742,"teacher_disagreement_score":0.023031173,"about_ca_system_score_codex":0.0016668792,"about_ca_system_score_gemma":0.0014702512,"threshold_uncertainty_score":0.04579425},"labels":[],"label_agreement":null},{"id":"W2063689849","doi":"10.1109/iscslp.2012.6423452","title":"Investigation of deep neural networks (DNN) for large vocabulary continuous speech recognition: Why DNN surpasses GMMS in acoustic modeling","year":2012,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Speech recognition; Artificial neural network; Vocabulary; Context (archaeology); Mel-frequency cepstrum; Word error rate; Artificial intelligence; Task (project management); Reduction (mathematics); Deep neural networks; Hidden Markov model; Logarithm; Pattern recognition (psychology); Feature extraction; Mathematics","score_opus":0.05066265927163722,"score_gpt":0.2545038198180309,"score_spread":0.20384116054639367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063689849","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25811064,0.044167694,0.6469222,0.014923207,0.00069646916,0.00013041032,0.00034903473,0.0016290147,0.0330714],"genre_scores_gemma":[0.7712332,0.010983375,0.20967203,0.0011819338,0.00028768746,0.000058894086,0.00025474478,0.00015034113,0.006177748],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99948597,0.00013560569,0.000026772468,0.00013495164,0.00016567639,0.00005094539],"domain_scores_gemma":[0.99852824,0.0007938984,0.00007211812,0.00013290801,0.00041780408,0.000054944896],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023494142,0.0006890955,0.00040162765,0.00041247005,0.00027606552,0.0009836054,0.0006970619,0.00096002535,0.0015216208],"category_scores_gemma":[0.003884432,0.00035986525,0.0002350865,0.00052648963,0.00060250773,0.0029888889,0.000605821,0.0018173954,0.00056742685],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054842955,0.00020593202,0.007372536,0.00046487205,0.00013173756,0.00023018754,0.00024254195,0.09609335,0.056330297,0.060973108,0.0074480395,0.769959],"study_design_scores_gemma":[0.0000380538,0.00045180586,0.0032359737,0.00012635316,0.0000652071,0.00031345114,0.0001506276,0.8885039,0.04646576,0.04155431,0.019047383,0.000047157842],"about_ca_topic_score_codex":0.004489874,"about_ca_topic_score_gemma":0.008039345,"teacher_disagreement_score":0.004489874,"about_ca_system_score_codex":0.00087549567,"about_ca_system_score_gemma":0.00057061797,"threshold_uncertainty_score":0.012425065},"labels":[],"label_agreement":null},{"id":"W2064364374","doi":"10.1109/icassp.2013.6639151","title":"PLDA for speaker verification with utterances of arbitrary duration","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":205,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"NIST; Computer science; Speaker verification; Covariance; Speech recognition; Classifier (UML); Speaker recognition; Duration (music); Speech processing; Artificial intelligence; Pattern recognition (psychology); Mathematics; Statistics","score_opus":0.013820470872802554,"score_gpt":0.20593647213030436,"score_spread":0.1921160012575018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064364374","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009969063,0.00045807313,0.98621863,0.0000891985,0.00005691721,0.00006156942,0.00023444755,0.0019667463,0.0009452955],"genre_scores_gemma":[0.23732387,0.00038913058,0.7568973,0.0001235269,0.00006943261,0.00035518536,0.00094225624,0.00038492845,0.0035144144],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9979266,0.00079189235,0.00014300771,0.0005491551,0.0004834637,0.00010590795],"domain_scores_gemma":[0.99689746,0.0016536193,0.00025331118,0.00054961955,0.0005834692,0.000062476516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026213264,0.000799861,0.0007299178,0.0005750829,0.0006252391,0.0009247653,0.0008782249,0.00079427427,0.0035514762],"category_scores_gemma":[0.009210196,0.00042656148,0.00058258785,0.0005432915,0.00056979706,0.0011226946,0.0011356652,0.0017654024,0.002220932],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009078489,0.00011191332,0.0016176363,0.0003410684,0.00017031626,0.00040356285,0.00029188895,0.11853107,0.09448039,0.013329457,0.0060926466,0.76372224],"study_design_scores_gemma":[0.000023564564,0.00013582176,0.0021218143,0.00003442828,0.000021855561,0.00018129863,0.000042777727,0.96324104,0.02232606,0.005764553,0.0060654827,0.000041252322],"about_ca_topic_score_codex":0.0039464715,"about_ca_topic_score_gemma":0.005823688,"teacher_disagreement_score":0.0039464715,"about_ca_system_score_codex":0.0007093692,"about_ca_system_score_gemma":0.0009226816,"threshold_uncertainty_score":0.013863027},"labels":[],"label_agreement":null},{"id":"W2064505662","doi":"10.5539/mas.v3n8p106","title":"Design and Implementation of Speech Recognition System Based on Field Programmable Gate Array","year":2009,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Field-programmable gate array; Computer science; Hidden Markov model; Viterbi algorithm; Gate array; Speech recognition; Chip; Field (mathematics); Pattern recognition (psychology); Computer hardware; Artificial intelligence; Telecommunications; Mathematics","score_opus":0.028217468432939964,"score_gpt":0.26512092911509694,"score_spread":0.23690346068215698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064505662","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06615997,0.0013167697,0.9064812,0.0003067247,0.0005822713,0.00037640845,0.00031982863,0.013200138,0.01125659],"genre_scores_gemma":[0.67707616,0.00065071153,0.3091568,0.00031550217,0.00014829656,0.0003666955,0.0006104783,0.00012458429,0.01155076],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997819,0.000027613874,0.000015103402,0.00006216719,0.00007407906,0.000039069804],"domain_scores_gemma":[0.99987197,0.00002553862,0.000011691909,0.00001357499,0.00006340322,0.00001386309],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022612241,0.00040198426,0.00041108104,0.00038451378,0.00029851063,0.0004561004,0.00082896656,0.0004545474,0.0035096419],"category_scores_gemma":[0.00025702483,0.00021899247,0.00022092483,0.00018533846,0.00014372493,0.00042698093,0.00015478506,0.00030910567,0.0013351204],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00087922334,0.00015746253,0.004045384,0.0005954155,0.00014539741,0.0008704146,0.00028934568,0.017938003,0.4179066,0.0076385303,0.009614102,0.5399201],"study_design_scores_gemma":[0.00048885465,0.001770309,0.009781416,0.00013033893,0.00034226134,0.003348051,0.00014212623,0.3587747,0.5560089,0.0025003308,0.06655422,0.0001585008],"about_ca_topic_score_codex":0.0016844101,"about_ca_topic_score_gemma":0.0014647299,"teacher_disagreement_score":0.0035096419,"about_ca_system_score_codex":0.0002690112,"about_ca_system_score_gemma":0.00051443704,"threshold_uncertainty_score":0.011740923},"labels":[],"label_agreement":null},{"id":"W2067459736","doi":"10.1002/ecjb.10119","title":"Model‐based speaker normalization methods for speech recognition","year":2003,"lang":"en","type":"article","venue":"Electronics and Communications in Japan (Part II Electronics)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Vocal tract; Formant; Normalization (sociology); Speech recognition; Computer science; Speaker recognition; Smoothing; Speaker diarisation; Image warping; Pattern recognition (psychology); Artificial intelligence; Computer vision","score_opus":0.06666757292295987,"score_gpt":0.3387917852170029,"score_spread":0.27212421229404304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067459736","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015723109,0.00033478107,0.9960962,0.000032156626,0.00004045649,0.000026916387,0.000033272507,0.0014607186,0.00040321445],"genre_scores_gemma":[0.10041316,0.00082787796,0.8919452,0.00009849457,0.0001230688,0.0003803096,0.00047927315,0.00048826312,0.0052444893],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99903095,0.00030327172,0.000042600153,0.00020980953,0.00036911285,0.00004428752],"domain_scores_gemma":[0.999416,0.00022230812,0.000047215453,0.000103991995,0.0001978902,0.000012698781],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012007413,0.0008764463,0.000950336,0.00076650234,0.00035155623,0.0006423408,0.0010622583,0.00070023385,0.0037753722],"category_scores_gemma":[0.00207061,0.0004747106,0.00088824995,0.00056943635,0.00039258407,0.0007673473,0.00059861084,0.0009296773,0.0030549543],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019907592,0.000070810835,0.00031600642,0.00020982519,0.00016796999,0.000084607505,0.000092696224,0.0921498,0.060761854,0.0082207685,0.004998715,0.83272773],"study_design_scores_gemma":[0.000021389718,0.00005057457,0.0005991765,0.000018600324,0.000047483958,0.00017024114,0.000016919952,0.9525243,0.032613106,0.004983728,0.00891558,0.00003884942],"about_ca_topic_score_codex":0.0016620569,"about_ca_topic_score_gemma":0.0018812438,"teacher_disagreement_score":0.0037753722,"about_ca_system_score_codex":0.00049336464,"about_ca_system_score_gemma":0.00052984955,"threshold_uncertainty_score":0.012629807},"labels":[],"label_agreement":null},{"id":"W2068004116","doi":"10.1109/icassp.2013.6639168","title":"Compensation for inter-frame correlations in speaker diarization and recognition","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"NIST; Speaker diarisation; Computer science; Speech recognition; Speaker recognition; Cluster analysis; Sample (material); Sample size determination; Pattern recognition (psychology); Feature (linguistics); Set (abstract data type); Hierarchical clustering; Scaling; Inference; Artificial intelligence; Statistics; Mathematics","score_opus":0.030146364738411622,"score_gpt":0.23712867836759066,"score_spread":0.20698231362917904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068004116","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010362502,0.00044837382,0.9878714,0.000101325575,0.00012353007,0.000052766514,0.000045399163,0.00051871344,0.00047580872],"genre_scores_gemma":[0.25804666,0.00069499767,0.7377073,0.00033577552,0.00027007892,0.00033858,0.0005720434,0.00046398485,0.0015705338],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9941954,0.002121327,0.000373204,0.0011328378,0.0019014509,0.0002756967],"domain_scores_gemma":[0.985158,0.00825831,0.0009339174,0.0032994407,0.0021509302,0.0001993603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008315452,0.0011097647,0.001207394,0.0010222946,0.0007522363,0.001142854,0.0014695829,0.0009953395,0.0014920798],"category_scores_gemma":[0.0365311,0.0006192789,0.00060185225,0.0010272607,0.0010306936,0.0023495415,0.0018831562,0.002233103,0.0011959375],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001104382,0.00020446836,0.0064818566,0.0004239209,0.00028526463,0.0003107962,0.00075031206,0.05828585,0.14167617,0.02034542,0.0043930663,0.7657386],"study_design_scores_gemma":[0.00010444282,0.0006268506,0.023032876,0.00012259049,0.0001894609,0.001309219,0.00031086922,0.7320528,0.18890893,0.032843035,0.020326538,0.00017239347],"about_ca_topic_score_codex":0.0015783423,"about_ca_topic_score_gemma":0.0026057719,"teacher_disagreement_score":0.008315452,"about_ca_system_score_codex":0.0006773017,"about_ca_system_score_gemma":0.0012058428,"threshold_uncertainty_score":0.043976903},"labels":[],"label_agreement":null},{"id":"W2069483556","doi":"10.1109/ais.2010.5547038","title":"Systems combination in large vocabulary continuous speech recognition","year":2010,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Word error rate; Vocabulary; Speech recognition; Confusion; Word (group theory); Field (mathematics); Frame (networking); Reduction (mathematics); Artificial intelligence; Natural language processing; Linguistics; Telecommunications","score_opus":0.015475374975381833,"score_gpt":0.23333525023105964,"score_spread":0.2178598752556778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069483556","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01991277,0.008090479,0.9621837,0.00016513812,0.00025511853,0.00020868388,0.00009555847,0.0025787274,0.0065099383],"genre_scores_gemma":[0.39940187,0.0051211854,0.57795197,0.00033106774,0.0005210026,0.00045402846,0.0011479973,0.0006396505,0.014431266],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99673957,0.0010911728,0.00031284528,0.00065993203,0.0010214351,0.00017509643],"domain_scores_gemma":[0.9982962,0.0007829545,0.000086744876,0.00027498617,0.00051515107,0.000043970223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021804818,0.0014565791,0.0014748788,0.00110268,0.0006293413,0.0014822354,0.0011512543,0.00089642114,0.003939123],"category_scores_gemma":[0.002812744,0.0006588456,0.0011094977,0.0009097522,0.00060716324,0.0018049764,0.0016916334,0.0009769305,0.0031135282],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000416853,0.0001226839,0.0015007631,0.00082358805,0.00041086416,0.00037609428,0.00019949354,0.0394264,0.05670458,0.005317168,0.0029065986,0.8917949],"study_design_scores_gemma":[0.00011455179,0.002194005,0.005258607,0.00023375897,0.0012460351,0.0036262833,0.00026005626,0.62669086,0.2676287,0.025581507,0.06689838,0.00026732468],"about_ca_topic_score_codex":0.0008507177,"about_ca_topic_score_gemma":0.0013536164,"teacher_disagreement_score":0.003939123,"about_ca_system_score_codex":0.00038210902,"about_ca_system_score_gemma":0.0005450698,"threshold_uncertainty_score":0.013177693},"labels":[],"label_agreement":null},{"id":"W2069929513","doi":"10.1017/s0025100313000327","title":"A study of laryngeal gestures in Mandarin citation tones using simultaneous laryngoscopy and laryngeal ultrasound (SLLUS)","year":2014,"lang":"en","type":"article","venue":"Journal of the International Phonetic Association","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":76,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Larynx; Laryngoscopy; Tone (literature); Mandarin Chinese; Articulatory phonetics; Audiology; Speech production; Vocal folds; Phonation; Medicine; Acoustics; Speech recognition; Computer science; Anatomy; Surgery; Intubation; Linguistics; Physics","score_opus":0.01320693738831537,"score_gpt":0.2537196381902821,"score_spread":0.2405127008019667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069929513","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9962381,0.0001789127,0.002488725,0.000015717558,0.000007776023,0.000027077234,0.000028880851,0.00001530122,0.0009995388],"genre_scores_gemma":[0.9919546,0.00015636516,0.0066274656,0.000028461007,0.000022682503,0.000044694647,0.000062826344,0.000012506163,0.0010903287],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9996093,0.00010369518,0.00003399267,0.00010902964,0.000103872444,0.00004008525],"domain_scores_gemma":[0.99923444,0.00037769426,0.00012475297,0.00006471642,0.000119595075,0.00007882506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061458466,0.0002879858,0.00022375595,0.0007030345,0.0003353754,0.00032698148,0.00019069495,0.00040169005,0.0013142062],"category_scores_gemma":[0.0018154538,0.00019619011,0.00024421813,0.0003300432,0.0005854247,0.00048660891,0.00054277596,0.00021232177,0.00033317457],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009513217,0.00014368974,0.06646798,0.00030097773,0.000043879856,0.0021690622,0.0065712538,0.00022633161,0.849057,0.00039644854,0.00013755973,0.07353444],"study_design_scores_gemma":[0.000045312194,0.005226998,0.8682102,0.00003749648,0.00014283776,0.007623538,0.003908715,0.002523393,0.10857417,0.00021197303,0.0034155038,0.00007988011],"about_ca_topic_score_codex":0.00076143065,"about_ca_topic_score_gemma":0.0014281886,"teacher_disagreement_score":0.0013142062,"about_ca_system_score_codex":0.00014673822,"about_ca_system_score_gemma":0.00020851319,"threshold_uncertainty_score":0.0043964386},"labels":[],"label_agreement":null},{"id":"W2070080535","doi":"10.1121/1.2980456","title":"Identification of frequency-shifted vowels","year":2008,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Social Sciences and Humanities Research Council of Canada; National Science Foundation","keywords":"Acoustics; Identification (biology); Mathematics; Computer science; Physics; Biology","score_opus":0.020696442230777004,"score_gpt":0.24597708902980844,"score_spread":0.22528064679903143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070080535","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99673754,0.00011173569,0.001993871,0.000011871044,0.000007742145,0.0000064788674,0.000024901685,0.000028000866,0.0010779531],"genre_scores_gemma":[0.99639565,0.00006454986,0.0026789424,0.000022022536,0.0000048421816,0.000006413117,0.000088826426,0.000012736819,0.00072598894],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99946994,0.00008311609,0.00005936522,0.00015690163,0.00017098886,0.00005970981],"domain_scores_gemma":[0.9982659,0.00065856206,0.0003343164,0.00023289041,0.00041256295,0.00009580563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055382465,0.00019321262,0.0002665259,0.00036952973,0.00021528763,0.0005881108,0.00022766918,0.00040379015,0.0013290631],"category_scores_gemma":[0.0054033804,0.00018503828,0.0001712223,0.00012488525,0.00020343746,0.0005110898,0.0007051052,0.00023972114,0.0005370585],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006855132,0.000055722183,0.06717227,0.00012051015,0.000036242316,0.00040194497,0.0018954624,0.00080184406,0.8514628,0.00042022337,0.00014251783,0.076804966],"study_design_scores_gemma":[0.000015091499,0.0008538799,0.7737021,0.00004784602,0.000042881285,0.0029315713,0.0012272245,0.011574525,0.20650473,0.0009771014,0.0020685669,0.00005437416],"about_ca_topic_score_codex":0.0007462747,"about_ca_topic_score_gemma":0.00081707555,"teacher_disagreement_score":0.0013290631,"about_ca_system_score_codex":0.00015530516,"about_ca_system_score_gemma":0.00016266116,"threshold_uncertainty_score":0.004446149},"labels":[],"label_agreement":null},{"id":"W2071007762","doi":"10.1121/1.4806678","title":"Nonlinearities in block-type reduced-order vocal fold models with asymmetric tissue properties","year":2013,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Phonation; Vocal folds; Nonlinear system; Fold (higher-order function); Bifurcation; Sensitivity (control systems); Computer science; Mathematics; Speech recognition; Physics; Larynx","score_opus":0.02419412231878018,"score_gpt":0.23448301451663472,"score_spread":0.21028889219785454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071007762","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5120214,0.0011641894,0.4615696,0.0005196918,0.00008501671,0.00010125915,0.00039273768,0.00039200517,0.0237541],"genre_scores_gemma":[0.980785,0.0005396303,0.009881492,0.000042843963,0.00002568512,0.000101204176,0.00014958963,0.0000535404,0.008421032],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998859,0.000038348382,0.000006407802,0.00001717943,0.000033727014,0.000018330224],"domain_scores_gemma":[0.9996985,0.00012981797,0.000076510914,0.000031185562,0.00004218002,0.00002184274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025524772,0.00047583025,0.0005762208,0.0003969801,0.00023669528,0.0005963171,0.00070379,0.0008857293,0.0014320933],"category_scores_gemma":[0.0008609847,0.0003421018,0.00072552514,0.00019495492,0.00061574613,0.00062554516,0.00040315202,0.00044843205,0.00045478888],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040498337,0.000025930802,0.0006652853,0.000047336154,0.00001968511,0.00014853245,0.00009214316,0.97142327,0.010028317,0.014806989,0.00020877049,0.002493163],"study_design_scores_gemma":[0.0000023295113,0.000009390375,0.000121495636,0.0000021708236,0.0000029585938,0.000012455481,0.000005136328,0.99805593,0.00020605072,0.0014605285,0.00011854443,0.0000030704305],"about_ca_topic_score_codex":0.005067756,"about_ca_topic_score_gemma":0.0040525803,"teacher_disagreement_score":0.005067756,"about_ca_system_score_codex":0.0005061108,"about_ca_system_score_gemma":0.0003972294,"threshold_uncertainty_score":0.010076523},"labels":[],"label_agreement":null},{"id":"W2072245166","doi":"10.1007/s10772-005-2168-4","title":"Post Recognition Speech Localization","year":2005,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Phrase; Speech recognition; SIGNAL (programming language); Speech processing; Multilateration; Word (group theory); Artificial intelligence; Pattern recognition (psychology); Acoustics; Mathematics","score_opus":0.01544005197725855,"score_gpt":0.2639430521250483,"score_spread":0.24850300014778975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072245166","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.059196223,0.001329557,0.83592594,0.00068382773,0.0016162186,0.00046160351,0.0031160603,0.035329908,0.06234072],"genre_scores_gemma":[0.36234188,0.0011837651,0.35202426,0.0012952344,0.000779735,0.00053583604,0.010505081,0.003369854,0.26796436],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99937075,0.000050190105,0.000027193015,0.00021119301,0.00023692769,0.00010378558],"domain_scores_gemma":[0.99923646,0.000114053364,0.000041259595,0.00022465114,0.0003360207,0.00004765528],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004161278,0.0015734371,0.0008839445,0.0012626041,0.0009813055,0.0022204383,0.00083306833,0.001467887,0.0753638],"category_scores_gemma":[0.001022132,0.0004591483,0.0006218152,0.00071330776,0.00041455278,0.0013217378,0.001197927,0.00095684984,0.07170521],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007466071,0.00012984595,0.0008554319,0.00018883352,0.000032714528,0.0002793304,0.00007844881,0.000733297,0.44833794,0.002603237,0.01141822,0.5345961],"study_design_scores_gemma":[0.00005765078,0.00045539613,0.007499203,0.000051062852,0.00011199923,0.0015608046,0.00012006257,0.028237326,0.8710956,0.0016373972,0.089120194,0.000053335996],"about_ca_topic_score_codex":0.0016647856,"about_ca_topic_score_gemma":0.0034046345,"teacher_disagreement_score":0.0753638,"about_ca_system_score_codex":0.0004316439,"about_ca_system_score_gemma":0.00096853275,"threshold_uncertainty_score":0.25211704},"labels":[],"label_agreement":null},{"id":"W2072667706","doi":"10.1109/iccspa.2013.6487262","title":"Effect of characteristics of speakers on MSA ASR performance","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Pronunciation; Speech recognition; Stress (linguistics); Hidden Markov model; Arabic; Computer science; Word error rate; Word (group theory); Linguistics; Speech corpus; Natural language processing; Artificial intelligence; Speech synthesis","score_opus":0.008206595823481298,"score_gpt":0.21461453454020782,"score_spread":0.20640793871672652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072667706","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.994915,0.0002747192,0.0035852578,0.00003760996,0.0000335855,0.00002069034,0.00018919494,0.00013629124,0.0008076768],"genre_scores_gemma":[0.9977519,0.00017426723,0.0008965911,0.000019607962,0.000029555456,0.000027774635,0.00044240418,0.00008931796,0.0005687176],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99836296,0.0005429638,0.0002158235,0.0003929066,0.00033450485,0.00015087442],"domain_scores_gemma":[0.9836991,0.013272378,0.00084994826,0.0006587117,0.0011721005,0.00034786132],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011766881,0.0004477732,0.0006124746,0.00039140508,0.0002688276,0.0006424803,0.00017802246,0.00046239636,0.001857158],"category_scores_gemma":[0.012671695,0.00024176628,0.000258953,0.0003695537,0.0003271093,0.00044871683,0.00042448624,0.000302657,0.001036687],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012342553,0.00040883082,0.19204013,0.0006596786,0.0005123771,0.0040400405,0.0028983606,0.017453095,0.6372039,0.00026798155,0.0010206448,0.13115254],"study_design_scores_gemma":[0.00012593922,0.0050020185,0.7176178,0.000050294584,0.0007024094,0.008592396,0.0018966892,0.024284728,0.237986,0.00048143134,0.0030853169,0.00017499925],"about_ca_topic_score_codex":0.0006056793,"about_ca_topic_score_gemma":0.00057660375,"teacher_disagreement_score":0.001857158,"about_ca_system_score_codex":0.00016301549,"about_ca_system_score_gemma":0.00018127025,"threshold_uncertainty_score":0.0062229633},"labels":[],"label_agreement":null},{"id":"W2074176370","doi":"10.1109/icassp.2013.6639312","title":"Comparison of a bigram PLSA and a novel context-based PLSA language model for speech recognition","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Bigram; Probabilistic latent semantic analysis; Perplexity; Computer science; Context (archaeology); Artificial intelligence; Language model; Natural language processing; Topic model; Context model; Speech recognition; Word (group theory); Latent semantic analysis; Linguistics","score_opus":0.08940868257063371,"score_gpt":0.31921028913982696,"score_spread":0.22980160656919324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074176370","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06531155,0.0012921861,0.9282011,0.00037602536,0.00016539144,0.000078732424,0.00034466034,0.0027351899,0.0014951517],"genre_scores_gemma":[0.6009126,0.001248874,0.39001766,0.00032232158,0.00015315975,0.00027223534,0.0012785469,0.0006106529,0.005184067],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99916625,0.0003210219,0.00005744988,0.0001968951,0.00021029009,0.000048114558],"domain_scores_gemma":[0.9989818,0.0005343936,0.00004485422,0.00013816639,0.0002502655,0.000050416143],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010062002,0.000987944,0.0005910525,0.0006803031,0.00035447304,0.00086564396,0.0010378546,0.0007669996,0.0026463734],"category_scores_gemma":[0.0018518859,0.0004925745,0.0011136847,0.00055199704,0.00030808535,0.0021001957,0.000833799,0.0011943931,0.0018327833],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016034038,0.00036636516,0.0026028443,0.00043950486,0.00045555504,0.0003651053,0.0004253081,0.23807698,0.08203988,0.009808747,0.003180766,0.6606355],"study_design_scores_gemma":[0.00003241491,0.00015071839,0.00052898156,0.00000903837,0.00004162725,0.000101772,0.00003864716,0.98831123,0.0074237124,0.002170194,0.0011661543,0.000025449819],"about_ca_topic_score_codex":0.004089625,"about_ca_topic_score_gemma":0.0055101886,"teacher_disagreement_score":0.004089625,"about_ca_system_score_codex":0.00039142783,"about_ca_system_score_gemma":0.00096565514,"threshold_uncertainty_score":0.008853018},"labels":[],"label_agreement":null},{"id":"W2074517850","doi":"10.1007/s11042-014-1973-7","title":"Spectro-temporal directional derivative based automatic speech recognition for a serious game scenario","year":2014,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Speech recognition; Feature (linguistics); Discrete cosine transform; Arabic numerals; Feature vector; Artificial intelligence; Pattern recognition (psychology); Image (mathematics)","score_opus":0.030683642402534274,"score_gpt":0.2570780568454679,"score_spread":0.22639441444293365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074517850","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8562626,0.00012367063,0.13100623,0.00021775051,0.000086860186,0.00021394796,0.00094638485,0.0017179574,0.009424666],"genre_scores_gemma":[0.9729656,0.000041803083,0.023809087,0.00003185119,0.000009979815,0.000032811553,0.00035938286,0.000036647103,0.0027128665],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9998678,0.000030281584,0.000005898648,0.000028513348,0.00003997836,0.000027595028],"domain_scores_gemma":[0.99983346,0.00004943203,0.000006998127,0.000009963394,0.000058234837,0.000041753286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018942749,0.0005150727,0.0003430471,0.00042203852,0.00029365296,0.00032647562,0.0003929922,0.0006599388,0.0031549914],"category_scores_gemma":[0.00037331664,0.00014182877,0.00019478955,0.00015695901,0.00018056041,0.00021766558,0.0003319207,0.00037414534,0.00094234303],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034567744,0.0008939116,0.012927365,0.00039564515,0.00011085654,0.005130359,0.0011828488,0.035030164,0.69096935,0.003101466,0.005965552,0.2408358],"study_design_scores_gemma":[0.00017326024,0.0021288747,0.06814275,0.000054383378,0.000119331606,0.0042958455,0.0012080568,0.7623209,0.15105025,0.0021155705,0.008233684,0.00015706636],"about_ca_topic_score_codex":0.0037839059,"about_ca_topic_score_gemma":0.0063068625,"teacher_disagreement_score":0.0037839059,"about_ca_system_score_codex":0.00017520296,"about_ca_system_score_gemma":0.00023461448,"threshold_uncertainty_score":0.0105544925},"labels":[],"label_agreement":null},{"id":"W2075449699","doi":"10.1109/icassp.2014.6854638","title":"Phone sequence modeling with recurrent neural networks","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; TIMIT; Phone; Speech recognition; Artificial neural network; Word error rate; Decoding methods; Language model; Artificial intelligence; Recurrent neural network; Sequence (biology); Classifier (UML); Acoustic model; Context model; Complementarity (molecular biology); Hidden Markov model; Speech processing; Algorithm","score_opus":0.04426966286379785,"score_gpt":0.24659188787626132,"score_spread":0.20232222501246347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075449699","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018739045,0.00039802608,0.9776757,0.00016023887,0.000074040196,0.000019503987,0.00020295536,0.0015354437,0.0011950074],"genre_scores_gemma":[0.7430558,0.000822479,0.24710655,0.0002082467,0.0001296284,0.00011685916,0.0012630711,0.00033875677,0.0069586844],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996475,0.00009933163,0.000021233967,0.000117296026,0.00007860297,0.00003595351],"domain_scores_gemma":[0.99939525,0.00032651608,0.00007499313,0.00007246463,0.00011238837,0.000018485714],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006247896,0.00073690905,0.0006043798,0.00042438877,0.0002067881,0.00068452256,0.0012332269,0.0007155833,0.0017609769],"category_scores_gemma":[0.0022519287,0.0004472127,0.0006988465,0.0005003533,0.00027938507,0.0014067447,0.0005097822,0.0011649089,0.0012109322],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009541958,0.000039866496,0.000688261,0.000067862034,0.00006902715,0.00010960291,0.000053886615,0.8912254,0.0075361324,0.0056842,0.0010833134,0.09334714],"study_design_scores_gemma":[0.0000010054797,0.0000068470104,0.000043193213,0.0000020510554,0.0000034158004,0.000008505313,0.0000020063533,0.9976667,0.0007120308,0.0013608235,0.00019087968,0.000002557565],"about_ca_topic_score_codex":0.006847383,"about_ca_topic_score_gemma":0.010062638,"teacher_disagreement_score":0.006847383,"about_ca_system_score_codex":0.00054579455,"about_ca_system_score_gemma":0.0005135177,"threshold_uncertainty_score":0.013615072},"labels":[],"label_agreement":null},{"id":"W2076029080","doi":"10.1121/1.2942600","title":"Intelligibility of information in temporally desynchronized bands of speech","year":2007,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Intelligibility (philosophy); Mathematics; Maxima and minima; Syllable; Acoustics; Speech recognition; Computer science; Physics; Mathematical analysis","score_opus":0.014513416696958636,"score_gpt":0.2617047805084385,"score_spread":0.24719136381147985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076029080","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9951212,0.00013778413,0.00394273,0.00001812732,0.000017543098,0.0000142645185,0.000069694135,0.000034228007,0.00064433407],"genre_scores_gemma":[0.9964998,0.0000995844,0.0026036755,0.000020131234,0.000011627654,0.00002046037,0.00020232619,0.000029416045,0.00051293935],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999617,0.00009026738,0.000059148002,0.00009416735,0.00012060451,0.000018911402],"domain_scores_gemma":[0.99794036,0.0012672959,0.0003048067,0.00020077021,0.00019324645,0.00009353767],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009189726,0.00028206178,0.00030371462,0.00041003645,0.00012354963,0.0004886495,0.00018369645,0.0002666812,0.0012046167],"category_scores_gemma":[0.0057021426,0.00013769716,0.00020492991,0.00015875258,0.00026739485,0.00039091287,0.0005204096,0.00026542027,0.00022583798],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031663876,0.00010505272,0.011073643,0.00020929282,0.00008407264,0.00015244378,0.00078413665,0.0015974944,0.9402079,0.00032284568,0.00013145286,0.042165257],"study_design_scores_gemma":[0.00013545663,0.004626166,0.4983291,0.00007868945,0.00040024813,0.0009267177,0.00066849304,0.02290515,0.46804297,0.0019172039,0.0018645087,0.00010519927],"about_ca_topic_score_codex":0.00028763403,"about_ca_topic_score_gemma":0.00030328406,"teacher_disagreement_score":0.0012046167,"about_ca_system_score_codex":0.000118880555,"about_ca_system_score_gemma":0.00010324547,"threshold_uncertainty_score":0.0048600435},"labels":[],"label_agreement":null},{"id":"W2076794394","doi":"10.1109/asru.2011.6163900","title":"Making Deep Belief Networks effective for large vocabulary continuous speech recognition","year":2011,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":192,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Speech recognition; Vocabulary; Artificial intelligence; Natural language processing; Linguistics","score_opus":0.04830958816975836,"score_gpt":0.2643455917612188,"score_spread":0.21603600359146044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076794394","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031759404,0.0004652266,0.96165127,0.000697438,0.000096936536,0.000039241422,0.00010913085,0.001973194,0.0032081704],"genre_scores_gemma":[0.7083652,0.00046730053,0.28492847,0.00025587511,0.00009066411,0.00012374068,0.00029945647,0.00022028321,0.005249013],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99946266,0.00016609128,0.000026381229,0.00012614619,0.00014072385,0.00007811171],"domain_scores_gemma":[0.99833244,0.0010370312,0.00008503431,0.0001758301,0.00030770042,0.0000619816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012971584,0.00073587365,0.0005477016,0.0004273293,0.00032998313,0.001043908,0.0010359106,0.00095140055,0.0041284985],"category_scores_gemma":[0.006078931,0.00065561075,0.0003519813,0.0003917302,0.00070740667,0.002914418,0.0013756866,0.0022315364,0.0011899276],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004390316,0.0002063418,0.00091473554,0.00014708492,0.00007195662,0.000110688066,0.00013107655,0.57361555,0.014936592,0.02566428,0.005006709,0.378756],"study_design_scores_gemma":[0.0000137906845,0.00001905399,0.0000680776,0.0000059270133,0.000006261285,0.0000063343355,0.000010925426,0.98842293,0.002240978,0.008684427,0.00051738875,0.000003806087],"about_ca_topic_score_codex":0.005079719,"about_ca_topic_score_gemma":0.0072917244,"teacher_disagreement_score":0.005079719,"about_ca_system_score_codex":0.00080762594,"about_ca_system_score_gemma":0.0007873181,"threshold_uncertainty_score":0.013811171},"labels":[],"label_agreement":null},{"id":"W2078373756","doi":"10.1115/sbc2011-53952","title":"Nonlinear Vocal Fold Dynamics in a Two-Mass Model of Speech Arising From Asymmetric Intraglottal Flow","year":2011,"lang":"en","type":"article","venue":"ASME 2011 Summer Bioengineering Conference, Parts A and B","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Vocal folds; Nonlinear system; Vocal tract; Vocal fold paralysis; Speech recognition; Larynx; Phonation; Computer science; Acoustics; Audiology; Physics; Paralysis; Anatomy; Medicine","score_opus":0.04746612188469605,"score_gpt":0.24105739890266928,"score_spread":0.19359127701797324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078373756","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42428824,0.002230458,0.5177456,0.002315454,0.00047374383,0.00018136216,0.00048219785,0.0005095278,0.05177337],"genre_scores_gemma":[0.96851647,0.00056603015,0.007758027,0.0001535207,0.000090434885,0.00012591637,0.00008583647,0.000049541184,0.022654187],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99990785,0.00002339194,0.0000057885973,0.000024268807,0.000024750583,0.000013891287],"domain_scores_gemma":[0.9998318,0.000057594607,0.00003418064,0.0000142557465,0.000028146893,0.000033978195],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027599075,0.0007720388,0.0006830912,0.00041642837,0.00044251262,0.0009245063,0.0010281918,0.002325405,0.002380136],"category_scores_gemma":[0.000640382,0.0003951363,0.0006614686,0.0002142811,0.0011947601,0.0010563075,0.00076167233,0.0007060448,0.0008100303],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018424686,0.00005987653,0.0009723142,0.00011890076,0.00003730334,0.001027276,0.00043677058,0.91565377,0.026770754,0.0476792,0.0009382428,0.006121351],"study_design_scores_gemma":[0.000011483047,0.000022585415,0.00021288266,0.0000055448113,0.000007345436,0.000063182124,0.000019773566,0.99692994,0.00023151032,0.002214145,0.00027243252,0.000009323168],"about_ca_topic_score_codex":0.003943391,"about_ca_topic_score_gemma":0.0020170365,"teacher_disagreement_score":0.003943391,"about_ca_system_score_codex":0.0005515634,"about_ca_system_score_gemma":0.000384957,"threshold_uncertainty_score":0.007962346},"labels":[],"label_agreement":null},{"id":"W2080551551","doi":"10.1186/s13636-014-0042-5","title":"Homogenous ensemble phonotactic language recognition based on SVM supervector reconstruction","year":2014,"lang":"en","type":"article","venue":"EURASIP Journal on Audio Speech and Music Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"GLS Industries (Canada)","funders":"National Natural Science Foundation of China","keywords":"Computer science; Phonotactics; Support vector machine; Word error rate; NIST; Speech recognition; Language model; Artificial intelligence; Pattern recognition (psychology); Feature vector","score_opus":0.023246705929737776,"score_gpt":0.2328707149487062,"score_spread":0.20962400901896844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080551551","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11693739,0.00022415048,0.8736563,0.00010246964,0.00007461568,0.00005149653,0.0001609054,0.0072157895,0.0015768904],"genre_scores_gemma":[0.7355651,0.00010843548,0.25778675,0.000121556455,0.000035413763,0.00006114143,0.0010347686,0.00022348936,0.005063382],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995241,0.000097502256,0.000024598934,0.00017263753,0.00012560247,0.000055587177],"domain_scores_gemma":[0.9995096,0.00009227726,0.000045945406,0.00012331469,0.0001986079,0.00003024413],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047214777,0.00070337194,0.00071814196,0.00044312724,0.0002146809,0.00053753733,0.0008313586,0.0004606406,0.0018451826],"category_scores_gemma":[0.00093149877,0.00023380165,0.00067041157,0.00034130772,0.00018468327,0.00085927144,0.0007345508,0.0007763929,0.0014402947],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035737167,0.00017946724,0.0030516544,0.000048788046,0.00011850843,0.00014887298,0.000097270466,0.06618905,0.10369714,0.0014708518,0.0038287789,0.8208121],"study_design_scores_gemma":[0.000006587454,0.000076122866,0.00076476176,0.0000028585534,0.00001955765,0.00007154042,0.000021308777,0.9718398,0.02596434,0.00040850902,0.0008120396,0.00001256953],"about_ca_topic_score_codex":0.0026587143,"about_ca_topic_score_gemma":0.003312325,"teacher_disagreement_score":0.0026587143,"about_ca_system_score_codex":0.00022893061,"about_ca_system_score_gemma":0.00041787943,"threshold_uncertainty_score":0.0061727166},"labels":[],"label_agreement":null},{"id":"W2081811590","doi":"10.1109/tasl.2013.2271591","title":"Large Vocabulary Speech Recognition on Parallel Architectures","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Parallel computing; Graphics processing unit; Viterbi algorithm; CUDA; Speedup; Scalability; Massively parallel; Beam search; Heuristic; Multi-core processor; Computation; Search algorithm; Decoding methods; Algorithm; Artificial intelligence","score_opus":0.015379626009789192,"score_gpt":0.24419802523908518,"score_spread":0.22881839922929598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081811590","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10790347,0.0010792409,0.8537456,0.000659036,0.00036024224,0.00022884503,0.00066274515,0.018084792,0.017276043],"genre_scores_gemma":[0.5441841,0.00054145296,0.43741295,0.0002503349,0.0001349567,0.00032340764,0.0018447706,0.00046939807,0.01483856],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993012,0.00012821714,0.000053941672,0.00018648652,0.00023595292,0.00009412019],"domain_scores_gemma":[0.9989189,0.00028841943,0.00004933334,0.0002647046,0.0004299327,0.000048881033],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006399314,0.00079796155,0.0007963747,0.0007602253,0.00052128715,0.0011221819,0.0013000681,0.00063144177,0.0078093945],"category_scores_gemma":[0.0023610306,0.0004227688,0.0005613383,0.001253249,0.0003948339,0.0016562208,0.00080191926,0.0008918101,0.0035691692],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001329365,0.00025922176,0.0015368403,0.00032367342,0.00022614512,0.0005454985,0.0002358053,0.24289508,0.0818952,0.021707078,0.022652028,0.6263941],"study_design_scores_gemma":[0.00009765447,0.00012408182,0.00062833825,0.000016171802,0.000029436565,0.00011835646,0.00006915961,0.95242697,0.02446483,0.013177019,0.008825055,0.000022991933],"about_ca_topic_score_codex":0.011807661,"about_ca_topic_score_gemma":0.012502969,"teacher_disagreement_score":0.011807661,"about_ca_system_score_codex":0.00089757284,"about_ca_system_score_gemma":0.0012623852,"threshold_uncertainty_score":0.026125073},"labels":[],"label_agreement":null},{"id":"W2082488947","doi":"10.1155/2009/540409","title":"Alternative Speech Communication System for Persons with Severe Speech Disorders","year":2009,"lang":"en","type":"article","venue":"EURASIP Journal on Advances in Signal Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada; New Brunswick Innovation Foundation; Université de Moncton","keywords":"Intelligibility (philosophy); Computer science; Dysarthria; Speech recognition; PESQ; Speech synthesis; PSQM; Voice activity detection; Perception; Speech processing; Speech communication; Speech technology; Speech enhancement; Artificial intelligence; Audiology; Psychology; Linguistics; Medicine","score_opus":0.019855821837908207,"score_gpt":0.2904018645717373,"score_spread":0.2705460427338291,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082488947","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6885898,0.0024786014,0.28890544,0.00069638574,0.0005148502,0.0004835454,0.0012340095,0.0070430697,0.010054345],"genre_scores_gemma":[0.8794567,0.00067148654,0.105373606,0.00037371772,0.00012471876,0.0004668022,0.0014259865,0.00008181808,0.012025074],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9998381,0.00004882105,0.000015898804,0.00003917453,0.000040686304,0.00001738333],"domain_scores_gemma":[0.9997942,0.00005922352,0.000014835532,0.000023193854,0.000081729624,0.000026894773],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002786421,0.00038448925,0.000439731,0.00030637012,0.00027718954,0.00031257677,0.00036094963,0.00055345555,0.0069683343],"category_scores_gemma":[0.00048874755,0.0000889134,0.0002217428,0.00012242718,0.000127844,0.00027029536,0.0004157519,0.00024249718,0.0024573165],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027194417,0.00028684404,0.0058576623,0.0007514214,0.00010328463,0.002726886,0.00093888986,0.0013702905,0.38461438,0.0018721767,0.011211546,0.5875471],"study_design_scores_gemma":[0.0018491339,0.0110151,0.099142835,0.00037444447,0.0013168213,0.05428798,0.002757604,0.14753662,0.51842844,0.0031757208,0.15973544,0.0003798385],"about_ca_topic_score_codex":0.00050309504,"about_ca_topic_score_gemma":0.0008050078,"teacher_disagreement_score":0.0069683343,"about_ca_system_score_codex":0.00014594758,"about_ca_system_score_gemma":0.00019272888,"threshold_uncertainty_score":0.023311436},"labels":[],"label_agreement":null},{"id":"W2084215616","doi":"10.1109/icassp.2014.6854821","title":"Two-stage speaker adaptation in subspace Gaussian mixture models","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Subspace topology; Feature vector; Hidden Markov model; Pattern recognition (psychology); Context (archaeology); Mixture model; Artificial intelligence; Projection (relational algebra); Linear subspace; Feature (linguistics); Covariance; Gaussian; Adaptation (eye); Algorithm; Mathematics; Statistics","score_opus":0.033974109288578774,"score_gpt":0.2480830844242725,"score_spread":0.2141089751356937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084215616","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001346458,0.00013596792,0.997766,0.000027988302,0.00002374143,0.000016624705,0.000021731183,0.00035691046,0.00030454568],"genre_scores_gemma":[0.107689336,0.0005594589,0.88622326,0.0001252297,0.00011233592,0.00019765458,0.00037928604,0.00021506498,0.0044983462],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99912995,0.00032422287,0.00003729749,0.0001944904,0.0002597092,0.0000544377],"domain_scores_gemma":[0.99943787,0.0002422946,0.000033670454,0.00010424331,0.00016089385,0.000021073909],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011685387,0.00096874544,0.00095919793,0.00043323258,0.00033033974,0.0006026088,0.0013376749,0.0012781419,0.0017717455],"category_scores_gemma":[0.0017967852,0.00061270554,0.0011179971,0.00073197513,0.00045570105,0.0009069178,0.0011696522,0.0017327615,0.002104241],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003031671,0.00012930948,0.0008388433,0.0002374782,0.00023920706,0.00015442586,0.00022345466,0.26742053,0.060359836,0.021881754,0.003928643,0.64428335],"study_design_scores_gemma":[0.000010095665,0.00005674354,0.00034446167,0.0000059735144,0.000021135333,0.000089710666,0.0000071054574,0.98472023,0.008761164,0.0032606213,0.0026918412,0.00003087589],"about_ca_topic_score_codex":0.0021667401,"about_ca_topic_score_gemma":0.002970441,"teacher_disagreement_score":0.0021667401,"about_ca_system_score_codex":0.00029816505,"about_ca_system_score_gemma":0.000586281,"threshold_uncertainty_score":0.006179869},"labels":[],"label_agreement":null},{"id":"W2084514013","doi":"10.1109/msp.2009.932166","title":"Developments and directions in speech recognition and understanding, Part 1 [DSP Education]","year":2009,"lang":"en","type":"article","venue":"IEEE Signal Processing Magazine","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":227,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Set (abstract data type); Focus (optics); Field (mathematics); Data science; Speech processing; Digital signal processing; Speech recognition","score_opus":0.06475663745855617,"score_gpt":0.2729375041776006,"score_spread":0.20818086671904443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084514013","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005079667,0.5004536,0.1824945,0.081107534,0.019158427,0.00018317999,0.00029634,0.0012648404,0.20996194],"genre_scores_gemma":[0.0649402,0.6139265,0.13937984,0.009595611,0.019503566,0.00025134612,0.0007643567,0.0005240532,0.15111452],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985941,0.00047887367,0.00018044507,0.00021015925,0.00045190263,0.000084490195],"domain_scores_gemma":[0.9942631,0.0028730265,0.00020125158,0.00039615808,0.0019636652,0.00030280495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004625231,0.0007129897,0.00048731518,0.002981291,0.000976964,0.0050714477,0.0011009303,0.003010518,0.01695691],"category_scores_gemma":[0.006946479,0.00048135847,0.0003609601,0.0029324384,0.0028927443,0.006117096,0.001068062,0.002957051,0.009398795],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040944084,0.00010068062,0.0004214667,0.0009658958,0.00001192125,0.00009566929,0.00062819116,0.00085530215,0.0026149992,0.07902663,0.08620545,0.82903296],"study_design_scores_gemma":[0.000009140297,0.00016331702,0.0014719862,0.0011588254,0.000016135808,0.0006456958,0.0006135394,0.0027030539,0.0025367402,0.076082595,0.9145492,0.000049716007],"about_ca_topic_score_codex":0.0023306755,"about_ca_topic_score_gemma":0.0024975508,"teacher_disagreement_score":0.01695691,"about_ca_system_score_codex":0.0015504305,"about_ca_system_score_gemma":0.0033034633,"threshold_uncertainty_score":0.056726456},"labels":[],"label_agreement":null},{"id":"W2084716563","doi":"10.1109/isspa.2012.6310452","title":"The A* speech recognition system on parallel architectures","year":2012,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Viterbi algorithm; Parallel computing; Viterbi decoder; Speedup; Graphics processing unit; Scalability; Computation; Thread (computing); Speech recognition; Decoding methods; Hidden Markov model; Algorithm","score_opus":0.03562324010333636,"score_gpt":0.2451685944611037,"score_spread":0.20954535435776733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084716563","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10380333,0.000499734,0.80059314,0.0005664408,0.0004527997,0.0003145789,0.00073161174,0.0647234,0.028314924],"genre_scores_gemma":[0.5072958,0.00030073838,0.4645485,0.0004242215,0.00014073175,0.00035059496,0.0015089632,0.0009811542,0.024449317],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995617,0.00008225345,0.000039252245,0.00014397585,0.0001240404,0.000048796806],"domain_scores_gemma":[0.999401,0.00010404003,0.000025194695,0.00018815443,0.00023478271,0.000046920286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005068789,0.0005596149,0.000534224,0.00042059808,0.00061640993,0.0012797627,0.0010361722,0.00061368156,0.00926094],"category_scores_gemma":[0.0013785042,0.0003688823,0.0003802291,0.00048438617,0.00030126737,0.0011147509,0.0010701101,0.00079258555,0.005234728],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020720852,0.00027729044,0.0024391613,0.00024264783,0.00016363773,0.00057552406,0.00025578943,0.0743247,0.16140261,0.025989667,0.0521697,0.68008715],"study_design_scores_gemma":[0.00026806985,0.00038375953,0.0009051846,0.00003077215,0.000057538866,0.00036556463,0.00007686309,0.86257887,0.075170316,0.0145359915,0.04557414,0.00005290851],"about_ca_topic_score_codex":0.0044080685,"about_ca_topic_score_gemma":0.00234948,"teacher_disagreement_score":0.00926094,"about_ca_system_score_codex":0.0005142951,"about_ca_system_score_gemma":0.001194973,"threshold_uncertainty_score":0.030980945},"labels":[],"label_agreement":null},{"id":"W2085555790","doi":"10.1121/1.4785782","title":"Improving automatic speech recognition via better analysis and adaptation","year":2005,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Speech recognition; Mel-frequency cepstrum; Normalization (sociology); Hidden Markov model; Maximum a posteriori estimation; Feature (linguistics); Pattern recognition (psychology); Speech processing; Autoregressive model; Parametric statistics; Artificial intelligence; Feature extraction; Maximum likelihood","score_opus":0.016954566396927488,"score_gpt":0.2345133681408842,"score_spread":0.2175588017439567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2085555790","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007100784,0.00044839192,0.98654896,0.0001859202,0.00008309095,0.000034031516,0.000075016025,0.0034831907,0.002040691],"genre_scores_gemma":[0.12664104,0.0013511712,0.8615636,0.00035422217,0.00023914318,0.00015682344,0.00068084826,0.0007352365,0.008277954],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99879885,0.00033049766,0.00008660946,0.0002970849,0.00042710637,0.000059884525],"domain_scores_gemma":[0.9985501,0.0005956919,0.00006674831,0.00036264153,0.00040135856,0.000023343253],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011928055,0.00095226336,0.0009533777,0.0009882787,0.00024566398,0.001136123,0.00080450665,0.0011046245,0.005307775],"category_scores_gemma":[0.0038192442,0.00043412138,0.0007804727,0.0009765816,0.00043131603,0.0018601941,0.0007040567,0.0011412449,0.005287086],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011769209,0.000120148485,0.00047403664,0.00013726203,0.00008837862,0.00007113866,0.000094627605,0.06851336,0.14785002,0.005130703,0.004815138,0.77258754],"study_design_scores_gemma":[0.0000288822,0.00007989993,0.0022556272,0.000028701854,0.000059794704,0.00028383094,0.000028659404,0.8926175,0.07739709,0.005589366,0.02156116,0.00006940483],"about_ca_topic_score_codex":0.0016577013,"about_ca_topic_score_gemma":0.0018688954,"teacher_disagreement_score":0.005307775,"about_ca_system_score_codex":0.00038982398,"about_ca_system_score_gemma":0.00041197785,"threshold_uncertainty_score":0.017756224},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W2087119585","doi":"10.1109/icassp.2010.5495503","title":"Score normalization in playback attack detection","year":2010,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Phrase; Utterance; Computer science; Speech recognition; Similarity (geometry); Normalization (sociology); Set (abstract data type); Pattern recognition (psychology); Thresholding; Task (project management); Artificial intelligence; Natural language processing; Detector","score_opus":0.025001573441882915,"score_gpt":0.24846226710243866,"score_spread":0.22346069366055574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087119585","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10851027,0.0010930202,0.88219565,0.00014969743,0.00012236535,0.00018030526,0.00018080359,0.0036434687,0.0039244713],"genre_scores_gemma":[0.60806227,0.00058926863,0.38590214,0.00010825541,0.00012440694,0.00023583628,0.0006605937,0.0002935293,0.0040237415],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9964244,0.0007403882,0.0002584286,0.00059820357,0.0017127064,0.00026583122],"domain_scores_gemma":[0.99671906,0.0013107877,0.00038350202,0.0004306661,0.00095600233,0.00019988565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028247812,0.0011681992,0.0016020112,0.0024092991,0.0006427428,0.0016892981,0.0011818424,0.0008584392,0.0025321997],"category_scores_gemma":[0.010155288,0.00039930406,0.00064242276,0.0018628413,0.0012077304,0.0017283494,0.0014233054,0.0010375432,0.0017935794],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012507817,0.00017226176,0.0050139693,0.00017331076,0.00009437123,0.00021185125,0.00018917161,0.027052933,0.074182,0.0062698736,0.0021474152,0.88324213],"study_design_scores_gemma":[0.0000834981,0.0007990177,0.020657616,0.00006508422,0.00013050014,0.0012643846,0.00026011627,0.8336556,0.12445315,0.011859819,0.0066209785,0.00015018383],"about_ca_topic_score_codex":0.0029739975,"about_ca_topic_score_gemma":0.003267502,"teacher_disagreement_score":0.0029739975,"about_ca_system_score_codex":0.0007801296,"about_ca_system_score_gemma":0.0010754372,"threshold_uncertainty_score":0.01493907},"labels":[],"label_agreement":null},{"id":"W2088104516","doi":"10.1121/1.4806530","title":"Coarticulation in a whole event model of speech production","year":2013,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; University of British Columbia","funders":"","keywords":"Coarticulation; Speech production; Computer science; Event (particle physics); Variation (astronomy); Biomechanics; Speech recognition; Physics; Vowel","score_opus":0.01987518365265132,"score_gpt":0.24551915067460545,"score_spread":0.22564396702195413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2088104516","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04028365,0.00037327412,0.9486651,0.00040155364,0.000103421844,0.00004219144,0.00016761778,0.00033648103,0.009626705],"genre_scores_gemma":[0.8908363,0.0008363178,0.08708944,0.00014367244,0.00015466119,0.00020090221,0.00020835351,0.00020984613,0.020320648],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9997706,0.00007563912,0.000012920413,0.00006699779,0.00005281167,0.000021154876],"domain_scores_gemma":[0.99975246,0.00012673296,0.000031152707,0.000027185712,0.000037881666,0.000024574772],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040333654,0.00071018626,0.00040977917,0.0004296608,0.0002984389,0.00068256404,0.0011914065,0.0008796837,0.003942481],"category_scores_gemma":[0.0010659224,0.00038893867,0.0007764132,0.00029422744,0.0006120918,0.0011755067,0.0006170713,0.0007122654,0.0012500832],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016539624,0.00007589237,0.00090176397,0.0001233677,0.00010124924,0.00044479853,0.00042841057,0.8749734,0.015766088,0.07529496,0.0009068811,0.030817889],"study_design_scores_gemma":[0.0000065848126,0.000029907686,0.00023845723,0.0000036867418,0.000014215399,0.0000860867,0.0000120532495,0.98844916,0.00041062696,0.010037702,0.00070249155,0.000009019121],"about_ca_topic_score_codex":0.0023148167,"about_ca_topic_score_gemma":0.0019028435,"teacher_disagreement_score":0.003942481,"about_ca_system_score_codex":0.00030594482,"about_ca_system_score_gemma":0.00039779025,"threshold_uncertainty_score":0.013188958},"labels":[],"label_agreement":null},{"id":"W2092684968","doi":"10.1121/1.1315288","title":"Spontaneous speech recognition using a statistical coarticulatory model for the vocal-tract-resonance dynamics","year":2000,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":89,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Science Foundation","keywords":"Vocal tract; Computer science; Context (archaeology); Speech recognition; Benchmark (surveying); Hidden Markov model; Property (philosophy); Set (abstract data type); Artificial intelligence; Statistical model; Computation; Pattern recognition (psychology); Algorithm","score_opus":0.028178239125639517,"score_gpt":0.26690674222336963,"score_spread":0.2387285030977301,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2092684968","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01272254,0.000065638524,0.9860072,0.000042806278,0.00002902609,0.000028427023,0.000110122455,0.00053560466,0.00045860384],"genre_scores_gemma":[0.3719696,0.00030640286,0.62210715,0.00007797629,0.000061028324,0.00041064547,0.0011136058,0.00023517224,0.0037184234],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999655,0.00009064227,0.000020728534,0.00011399488,0.00010135231,0.000018317849],"domain_scores_gemma":[0.9993231,0.00035120256,0.00006285651,0.0001329229,0.000106572734,0.000023200755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000697909,0.0005469733,0.00048360074,0.00025663056,0.00017846076,0.0006325063,0.00088827877,0.0006180922,0.0013652407],"category_scores_gemma":[0.0021201093,0.00029457433,0.00057777937,0.00029858833,0.00032431743,0.0009307643,0.0004937619,0.00081223116,0.0009212032],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027371096,0.00020180506,0.0024357352,0.00035142034,0.00022533323,0.00040649704,0.0002341951,0.52647924,0.18795665,0.027422296,0.00262806,0.251385],"study_design_scores_gemma":[0.0000066743196,0.000054462547,0.0004718065,0.0000056610133,0.000011584471,0.00009601551,0.000008776289,0.9897142,0.006028374,0.002487703,0.0011016068,0.000013069489],"about_ca_topic_score_codex":0.0011110615,"about_ca_topic_score_gemma":0.0019403324,"teacher_disagreement_score":0.0013652407,"about_ca_system_score_codex":0.0003140024,"about_ca_system_score_gemma":0.0004630644,"threshold_uncertainty_score":0.004567206},"labels":[],"label_agreement":null},{"id":"W2095168634","doi":"10.1121/1.4781344","title":"Auditory priming releases Chinese speech from informational masking","year":2006,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Sentence; Masking (illustration); Speech recognition; Priming (agriculture); Noise (video); Computer science; Speech perception; Psychology; Perception; Natural language processing; Artificial intelligence","score_opus":0.008951168816919612,"score_gpt":0.22461454555542765,"score_spread":0.21566337673850802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095168634","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9892663,0.00032930597,0.004661343,0.00014052264,0.00009864587,0.000055249784,0.00005804613,0.0001734981,0.0052171047],"genre_scores_gemma":[0.99401504,0.00022041536,0.0035283358,0.00019375992,0.00004731751,0.000050789262,0.00007442797,0.00006317632,0.0018068155],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99974173,0.000057994122,0.000024320609,0.000062587176,0.00007102235,0.000042336243],"domain_scores_gemma":[0.9992323,0.00038200952,0.00013368909,0.000079968835,0.0000793674,0.000092733804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043473596,0.000652651,0.00040702432,0.0002165461,0.00021276783,0.00031236946,0.00026399156,0.0003481982,0.005070454],"category_scores_gemma":[0.0018516188,0.00025710717,0.00027388928,0.00007680463,0.0005040584,0.0005109023,0.00076838955,0.00050581055,0.00052329863],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007533394,0.000023928795,0.00021250635,0.00010287412,0.0000052506766,0.00013625149,0.00013044503,0.000036966827,0.99296063,0.00030720653,0.000056782097,0.00527384],"study_design_scores_gemma":[0.0002526443,0.001930293,0.034749717,0.000043899818,0.000113239046,0.00091582077,0.00025814303,0.0014835178,0.95714736,0.0012629604,0.0018140862,0.000028347882],"about_ca_topic_score_codex":0.00026905866,"about_ca_topic_score_gemma":0.0003129358,"teacher_disagreement_score":0.005070454,"about_ca_system_score_codex":0.00015247146,"about_ca_system_score_gemma":0.0003121292,"threshold_uncertainty_score":0.01696235},"labels":[],"label_agreement":null},{"id":"W2095504751","doi":"10.1558/ijsll.v14i1.145","title":"Forensic automatic speaker recognition using Bayesian interpretation and statistical compensation for mismatched conditions","year":2007,"lang":"en","type":"article","venue":"International Journal of Speech Language and the Law","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Bayesian probability; Interpretation (philosophy); Computer science; Speech recognition; Speaker recognition; Compensation (psychology); Artificial intelligence; Natural language processing; Pattern recognition (psychology); Psychology; Programming language","score_opus":0.018240739386723357,"score_gpt":0.30168284742505624,"score_spread":0.28344210803833286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095504751","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022951884,0.0001991427,0.97357464,0.00012996283,0.000085247804,0.000028443303,0.0001498869,0.0010988394,0.0017819842],"genre_scores_gemma":[0.37204367,0.0004258213,0.6214918,0.000104231054,0.00014455614,0.00007650283,0.0008777122,0.00045779708,0.0043779314],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989261,0.00027078987,0.000051518367,0.00019370428,0.00044057617,0.00011725007],"domain_scores_gemma":[0.99837935,0.000502537,0.000119749755,0.00030076015,0.0006389763,0.000058675116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016009872,0.00074068876,0.00089775934,0.001440822,0.0005646801,0.00095201074,0.0007714736,0.0010579606,0.0038040895],"category_scores_gemma":[0.0051047127,0.00059245835,0.00061530387,0.0006717895,0.0004673922,0.0012780556,0.0013100703,0.001032777,0.0023498745],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010032528,0.00012068419,0.0025288113,0.00015383546,0.0000961086,0.00032953147,0.00018513764,0.034080338,0.19773492,0.009412395,0.004429802,0.7499252],"study_design_scores_gemma":[0.00004837091,0.00014374027,0.0054114168,0.000040713436,0.00008429739,0.0010769941,0.000065968066,0.87972665,0.09576767,0.012765891,0.0047886106,0.0000797179],"about_ca_topic_score_codex":0.0008042721,"about_ca_topic_score_gemma":0.0025337576,"teacher_disagreement_score":0.0038040895,"about_ca_system_score_codex":0.00030289945,"about_ca_system_score_gemma":0.0010269852,"threshold_uncertainty_score":0.012725949},"labels":[],"label_agreement":null},{"id":"W2096698602","doi":"10.1109/sipnn.1994.344815","title":"HMMs with mixtures of trend functions for automatic speech recognition","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Hidden Markov model; Speech recognition; TIMIT; Computer science; Set (abstract data type); Task (project management); State (computer science); Mixture model; Trajectory; Pattern recognition (psychology); SIGNAL (programming language); Artificial intelligence; Maximum likelihood; Mathematics; Algorithm; Statistics; Engineering","score_opus":0.04627982596179582,"score_gpt":0.2315993290325417,"score_spread":0.1853195030707459,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096698602","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027858904,0.0009842743,0.9937313,0.000108080814,0.00007998839,0.000022012255,0.00022042853,0.0015387114,0.00052921235],"genre_scores_gemma":[0.14318828,0.0027405838,0.8452783,0.0001516124,0.0002971215,0.00026350794,0.00210498,0.0004608889,0.0055147214],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988807,0.00046863375,0.00008292406,0.00025663417,0.000256654,0.000054571672],"domain_scores_gemma":[0.9982766,0.0010782692,0.000114483184,0.00027538755,0.00022950144,0.000025705427],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001733618,0.0007085365,0.00074775785,0.0010780704,0.0003698679,0.00088812556,0.00094665936,0.00094268605,0.003398731],"category_scores_gemma":[0.0051633352,0.0007246583,0.0009349136,0.0017707666,0.0004614136,0.0021532062,0.0006445884,0.0013517309,0.0026078322],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028149257,0.00007767046,0.0013991495,0.0002952446,0.00020736671,0.0001692941,0.000242765,0.23210758,0.0142159965,0.069028236,0.008294824,0.6736805],"study_design_scores_gemma":[0.00001186144,0.000035694764,0.0006878007,0.00002752318,0.000032672993,0.000058119673,0.000017703082,0.95269424,0.0026660971,0.034856845,0.008876681,0.00003487621],"about_ca_topic_score_codex":0.0036969115,"about_ca_topic_score_gemma":0.0035674113,"teacher_disagreement_score":0.0036969115,"about_ca_system_score_codex":0.0006605835,"about_ca_system_score_gemma":0.0005781711,"threshold_uncertainty_score":0.011369824},"labels":[],"label_agreement":null},{"id":"W2096875330","doi":"10.1109/tasl.2008.916530","title":"Rapid Speaker Adaptation Using Clustered Maximum-Likelihood Linear Basis With Sparse Training Data","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Basis (linear algebra); Adaptation (eye); Computer science; Maximum likelihood; Pattern recognition (psychology); Speech recognition; Artificial intelligence; Statistics; Mathematics; Psychology","score_opus":0.09851490030450993,"score_gpt":0.2764646673115335,"score_spread":0.17794976700702358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096875330","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012461355,0.0000930593,0.9862375,0.00003545115,0.000019228375,0.00002920939,0.00002001241,0.00078369246,0.00032051877],"genre_scores_gemma":[0.20913957,0.000140614,0.78814465,0.000069924085,0.000047082725,0.00016966561,0.00032870533,0.00016215967,0.0017975513],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995059,0.00021066029,0.000018839819,0.00008530599,0.0001478473,0.000031470165],"domain_scores_gemma":[0.9989029,0.00068494893,0.00007228947,0.00014507664,0.00016766581,0.000027044434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077603373,0.00052319036,0.0004965244,0.00038431937,0.00024269518,0.00029199547,0.00072343525,0.00055545237,0.0010720902],"category_scores_gemma":[0.002695857,0.00041712148,0.0004864872,0.00059148873,0.00029457576,0.00060535263,0.0007486124,0.0009849238,0.0006904497],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046570468,0.00022360872,0.00070509175,0.00010742275,0.00014089461,0.00011051619,0.00022123619,0.27006474,0.10009699,0.005450068,0.0029721495,0.6194415],"study_design_scores_gemma":[0.000018982306,0.00005975444,0.0003783634,0.00000383242,0.000009736344,0.000046874204,0.000011059733,0.98529804,0.012325594,0.0009784804,0.0008523628,0.00001693614],"about_ca_topic_score_codex":0.0023265756,"about_ca_topic_score_gemma":0.0035868387,"teacher_disagreement_score":0.0023265756,"about_ca_system_score_codex":0.00019878756,"about_ca_system_score_gemma":0.00043509915,"threshold_uncertainty_score":0.0046260357},"labels":[],"label_agreement":null},{"id":"W2096958852","doi":"10.1109/itng.2009.332","title":"Feature Combination Using Multiple Spectral Cues for Robust Speech Recognition in Mobile Communications","year":2009,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Speech recognition; Mel-frequency cepstrum; GSM; Feature (linguistics); Front and back ends; Speech processing; Feature extraction; Task (project management); Cepstrum; Artificial intelligence; Mobile telephony; Voice activity detection; Pattern recognition (psychology); Mobile radio; Engineering; Telecommunications","score_opus":0.08309602341530054,"score_gpt":0.30263847420268214,"score_spread":0.2195424507873816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096958852","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12646441,0.0020502973,0.8686645,0.00014732407,0.00007704884,0.00005112939,0.000094648945,0.001104494,0.0013460792],"genre_scores_gemma":[0.5819882,0.0009597746,0.41413864,0.00008152398,0.00012211292,0.000057024612,0.0002955179,0.00009967107,0.0022574577],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996805,0.00007451344,0.0000161032,0.00005987917,0.00013964143,0.000029333116],"domain_scores_gemma":[0.9996884,0.00015030343,0.000028183626,0.000042547766,0.00007901671,0.000011618653],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004196889,0.0005176145,0.0005581974,0.00056993915,0.00018228611,0.0005106075,0.0003326198,0.0005207845,0.0016685305],"category_scores_gemma":[0.0011793998,0.0001899013,0.00032290193,0.0005102066,0.00023824871,0.0007541512,0.0003731969,0.0003825819,0.00086830906],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048576418,0.00011310157,0.0006174262,0.00017216548,0.000060012306,0.00016568856,0.00006949073,0.01579151,0.3228285,0.0015506365,0.00094618084,0.65719956],"study_design_scores_gemma":[0.00007039351,0.001064606,0.008993771,0.000049329752,0.00020699175,0.0011799615,0.00010714919,0.55514485,0.41760668,0.003738639,0.011724076,0.00011350912],"about_ca_topic_score_codex":0.00040849714,"about_ca_topic_score_gemma":0.00097390515,"teacher_disagreement_score":0.0016685305,"about_ca_system_score_codex":0.00012639633,"about_ca_system_score_gemma":0.00019379104,"threshold_uncertainty_score":0.005581856},"labels":[],"label_agreement":null},{"id":"W2098509485","doi":"10.1109/ccece.1997.614787","title":"Recent progress in automatic recognition of continuous speech","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Merge (version control); Speech recognition; Vocabulary; Artificial intelligence; Language model; Pruning; Word error rate; Phone; Graph; Natural language processing; Pattern recognition (psychology); Information retrieval; Theoretical computer science","score_opus":0.04223942686832255,"score_gpt":0.25127615110540286,"score_spread":0.2090367242370803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098509485","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03872047,0.108568214,0.83210546,0.001608506,0.0008758173,0.00013677203,0.0006043626,0.0060137496,0.011366651],"genre_scores_gemma":[0.17825325,0.051242854,0.7517091,0.00081563,0.0017663949,0.00017902743,0.0031949277,0.0009305034,0.011908388],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973181,0.00057799736,0.0002369919,0.00083125243,0.0008935327,0.0001420934],"domain_scores_gemma":[0.9877322,0.00669236,0.0004986552,0.0014888267,0.0033545278,0.00023349746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005331884,0.001097377,0.0013879793,0.002608379,0.00043233056,0.0025514548,0.0020541404,0.0012915467,0.008120794],"category_scores_gemma":[0.00781688,0.0006402267,0.0008079527,0.002596975,0.0010451518,0.0037859685,0.0012247978,0.0011634845,0.004621292],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024482099,0.00006963366,0.0010639166,0.0013860654,0.00006210752,0.00006569885,0.00020120555,0.0036814727,0.036533885,0.00413911,0.003353437,0.9491987],"study_design_scores_gemma":[0.00019555833,0.0014832633,0.017706774,0.0011596557,0.0007402774,0.0028050826,0.00086633733,0.29528952,0.20990619,0.017417684,0.45197934,0.0004503127],"about_ca_topic_score_codex":0.0025521915,"about_ca_topic_score_gemma":0.0019457883,"teacher_disagreement_score":0.008120794,"about_ca_system_score_codex":0.0005029852,"about_ca_system_score_gemma":0.0011080201,"threshold_uncertainty_score":0.028198063},"labels":[],"label_agreement":null},{"id":"W2099621636","doi":"","title":"Vocal Tract Length Perturbation (VTLP) improves speech recognition","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":335,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Speech recognition; Vocal tract; Normalization (sociology); Convolutional neural network; Spectrogram; Artificial neural network; Test set; Dynamic time warping; Word error rate; TIMIT; Image warping; Artificial intelligence; Pattern recognition (psychology); Hidden Markov model","score_opus":0.024196056855806596,"score_gpt":0.22428764260694675,"score_spread":0.20009158575114017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099621636","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21501744,0.0029913995,0.7426578,0.0005482757,0.00069028634,0.00014225321,0.0019153776,0.029468581,0.006568536],"genre_scores_gemma":[0.65976024,0.0009818404,0.32108644,0.00029458624,0.0002438601,0.00018369593,0.0073043737,0.0013906296,0.008754312],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991198,0.00020020838,0.00006063042,0.00029375113,0.00025811917,0.00006748896],"domain_scores_gemma":[0.9984262,0.00066356343,0.00012823564,0.00051101204,0.00021695653,0.000054076434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001178324,0.0013700717,0.00071088853,0.0006693693,0.00023908317,0.0007533395,0.00071334455,0.00064003933,0.003504599],"category_scores_gemma":[0.0040301536,0.0002854028,0.0006336476,0.00063861447,0.00041793066,0.0016088455,0.0012917159,0.0010578078,0.00349553],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00056058285,0.00016784784,0.0019574123,0.00021717459,0.000087435634,0.00016233005,0.00009865159,0.028887425,0.1667939,0.00092761195,0.0043265764,0.79581314],"study_design_scores_gemma":[0.000061643215,0.0013604715,0.018397417,0.000085048814,0.00018849892,0.0009634881,0.00015264846,0.637709,0.31284484,0.0043872646,0.023726067,0.0001236396],"about_ca_topic_score_codex":0.0017571428,"about_ca_topic_score_gemma":0.002692425,"teacher_disagreement_score":0.003504599,"about_ca_system_score_codex":0.0003566546,"about_ca_system_score_gemma":0.00035899304,"threshold_uncertainty_score":0.011724055},"labels":[],"label_agreement":null},{"id":"W2100220834","doi":"10.1109/icassp.2005.1415060","title":"Discriminative Training of CDHMMs for Maximum Relative Separation Margin","year":2006,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Discriminative model; Minimax; Computer science; Margin (machine learning); Hidden Markov model; Probabilistic logic; Pattern recognition (psychology); Artificial intelligence; Separation (statistics); Reduction (mathematics); Optimization problem; Mathematical optimization; Word error rate; Mathematics; Algorithm; Machine learning","score_opus":0.05021710298073339,"score_gpt":0.29499860457972443,"score_spread":0.24478150159899104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100220834","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0066227117,0.00009333928,0.99260485,0.000053593852,0.000012138779,0.0000126032555,0.000012168368,0.00027348727,0.0003149621],"genre_scores_gemma":[0.44370437,0.0001360856,0.5526703,0.00026429634,0.00006993298,0.000169852,0.00025932878,0.00021358725,0.0025123446],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898,0.00041448715,0.00004542149,0.00023405776,0.00025505587,0.0000709811],"domain_scores_gemma":[0.9980685,0.001241669,0.00015373467,0.00023911038,0.00023495362,0.000061964376],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016330307,0.0006890495,0.0008554445,0.00039114343,0.00035332053,0.0004393043,0.0013102632,0.0009841988,0.0018500799],"category_scores_gemma":[0.0061183167,0.00053509074,0.00032239623,0.00038964025,0.0007614212,0.0010976149,0.0012975328,0.001514092,0.00082094804],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033083497,0.00014456667,0.0012882274,0.00018298344,0.00007010851,0.00007072876,0.0001357559,0.35396108,0.037107762,0.016044807,0.0025789929,0.58808416],"study_design_scores_gemma":[0.000010413476,0.00003715514,0.0002591415,0.000006067087,0.0000050843855,0.00003568979,0.0000067658852,0.98924035,0.0068208473,0.0028643003,0.00070648233,0.000007592739],"about_ca_topic_score_codex":0.0010637003,"about_ca_topic_score_gemma":0.0016882288,"teacher_disagreement_score":0.0018500799,"about_ca_system_score_codex":0.0004626349,"about_ca_system_score_gemma":0.0007492726,"threshold_uncertainty_score":0.008636415},"labels":[],"label_agreement":null},{"id":"W2102113734","doi":"","title":"Towards End-To-End Speech Recognition with Recurrent Neural Networks","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1855,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Word error rate; Trigram; Speech recognition; Connectionism; Language model; Recurrent neural network; Artificial intelligence; Lexicon; Artificial neural network; Word (group theory); Time delay neural network; Natural language processing","score_opus":0.02874013249881295,"score_gpt":0.24337099036898666,"score_spread":0.21463085787017372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102113734","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010685102,0.00048986764,0.9807984,0.00017816282,0.00008990968,0.00003475433,0.0002285846,0.005884231,0.0016109422],"genre_scores_gemma":[0.20432341,0.0004793986,0.7818396,0.00031031715,0.00012791198,0.00012494688,0.0016093915,0.00043525593,0.010749761],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990326,0.00024818594,0.00006359205,0.00027259736,0.000295546,0.000087445005],"domain_scores_gemma":[0.9989994,0.0003741668,0.00006368425,0.00015623274,0.00036903995,0.00003742312],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012514836,0.0011570988,0.0007762556,0.000416249,0.0002819698,0.0012086504,0.001542653,0.0015433605,0.0034746067],"category_scores_gemma":[0.0027459373,0.0005863355,0.0005047832,0.00036781724,0.00040466082,0.0019644436,0.001144379,0.0019261222,0.004968637],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005490125,0.00021956321,0.0010046859,0.00033560142,0.00015730041,0.00033926542,0.00025348488,0.08600773,0.17802513,0.009024289,0.011805923,0.712278],"study_design_scores_gemma":[0.000022241531,0.000123102,0.0004567922,0.000035918387,0.000038764367,0.000119963064,0.00003743266,0.9391707,0.048251327,0.0062190634,0.0054959934,0.000028709155],"about_ca_topic_score_codex":0.0022847936,"about_ca_topic_score_gemma":0.005185778,"teacher_disagreement_score":0.0034746067,"about_ca_system_score_codex":0.00044754936,"about_ca_system_score_gemma":0.00046799652,"threshold_uncertainty_score":0.011623681},"labels":[],"label_agreement":null},{"id":"W2103359087","doi":"","title":"Phone Recognition with the Mean-Covariance Restricted Boltzmann Machine","year":2010,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":275,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"TIMIT; Boltzmann machine; Computer science; Covariance; Hidden Markov model; Restricted Boltzmann machine; Speech recognition; Mixture model; Artificial intelligence; Covariance matrix; Pattern recognition (psychology); Algorithm; Artificial neural network; Mathematics; Statistics","score_opus":0.01803519807988988,"score_gpt":0.2190759133437164,"score_spread":0.20104071526382652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103359087","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009584766,0.0002790526,0.9864442,0.00017673415,0.000067449306,0.00002227352,0.00013991263,0.0019934538,0.0012921598],"genre_scores_gemma":[0.46567383,0.00043217003,0.52611226,0.0002789912,0.000110197354,0.00022884709,0.00075882603,0.00027691503,0.006127978],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99950266,0.00014980318,0.000027435433,0.0001415114,0.00013493664,0.000043676482],"domain_scores_gemma":[0.999511,0.00024266778,0.00003762197,0.000101055804,0.00008655722,0.000021094875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068097346,0.00061423774,0.00079380773,0.00035260734,0.00025230867,0.00075899437,0.0010993226,0.0010869354,0.0022829312],"category_scores_gemma":[0.002781232,0.00058339967,0.000809923,0.00054481917,0.0003941318,0.0012480358,0.0009273969,0.0017874549,0.001751536],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022285832,0.000077445635,0.0012217365,0.00009529945,0.00014776706,0.00010227719,0.00008673325,0.62809694,0.012920707,0.014432247,0.0056771236,0.33691886],"study_design_scores_gemma":[0.0000048898823,0.00000939156,0.00012257954,0.0000033744577,0.000004234852,0.000021384378,0.00000325442,0.9909071,0.0016732832,0.0067260675,0.000517293,0.0000071700933],"about_ca_topic_score_codex":0.003424067,"about_ca_topic_score_gemma":0.004383217,"teacher_disagreement_score":0.003424067,"about_ca_system_score_codex":0.0005120158,"about_ca_system_score_gemma":0.00069799385,"threshold_uncertainty_score":0.007637143},"labels":[],"label_agreement":null},{"id":"W2103385917","doi":"10.1109/icassp.1994.389568","title":"Vowel classification using a neural predictive HMM: a discriminative training approach","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Hidden Markov model; Discriminative model; Speech recognition; Computer science; Perceptron; Artificial intelligence; Pattern recognition (psychology); Frame (networking); Multilayer perceptron; Vowel; Artificial neural network","score_opus":0.2575933512278999,"score_gpt":0.2855798959375007,"score_spread":0.027986544709600825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103385917","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01686235,0.00019618751,0.97914654,0.00011622506,0.000036709866,0.000022149197,0.00009020792,0.0017339372,0.0017957293],"genre_scores_gemma":[0.5511503,0.00039879032,0.43949422,0.00015495706,0.00006976613,0.00009975121,0.0005863258,0.00019015797,0.007855591],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997547,0.000049692204,0.0000129157115,0.00008816645,0.000062412866,0.000032095082],"domain_scores_gemma":[0.99969494,0.00013047358,0.000023898017,0.00007028487,0.00006049714,0.000019884632],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003630096,0.00033244546,0.00038473544,0.00034119777,0.00024591378,0.00045511956,0.0007912464,0.0005893551,0.001437884],"category_scores_gemma":[0.0013230754,0.00036562223,0.00030195978,0.00039400766,0.0002641731,0.00063531596,0.0004893962,0.0007544344,0.0010518143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025761162,0.00016187046,0.001740385,0.00012518774,0.00005173799,0.00014952077,0.00011120007,0.160241,0.07043275,0.007331513,0.002897335,0.7564999],"study_design_scores_gemma":[0.0000048998936,0.000025100891,0.00069883774,0.000006291462,0.000013620333,0.000045914214,0.000006814276,0.9885084,0.008001425,0.0016253275,0.0010543233,0.00000896936],"about_ca_topic_score_codex":0.0037841771,"about_ca_topic_score_gemma":0.005729147,"teacher_disagreement_score":0.0037841771,"about_ca_system_score_codex":0.00033322064,"about_ca_system_score_gemma":0.00037311812,"threshold_uncertainty_score":0.0075243115},"labels":[],"label_agreement":null},{"id":"W2103962059","doi":"10.1109/tasl.2006.881695","title":"Dialect/Accent Classification Using Unrestricted Audio","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Classifier (UML); Natural language processing; Speech recognition; Utterance","score_opus":0.03328024716986407,"score_gpt":0.2886593159864606,"score_spread":0.25537906881659656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103962059","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41794625,0.0013015218,0.561997,0.00020855085,0.00029175193,0.00018980316,0.001063483,0.0030094068,0.013992236],"genre_scores_gemma":[0.87502176,0.0005205652,0.11509826,0.0000935839,0.00017087397,0.000060174236,0.001751434,0.000112177586,0.007171168],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995746,0.00006800882,0.000023756265,0.00014586365,0.0001229582,0.000064864274],"domain_scores_gemma":[0.9994843,0.00015168365,0.000041251136,0.00007618721,0.00019070604,0.000055868226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041917793,0.0005718957,0.00042933022,0.0012401261,0.00029662237,0.0010245186,0.0004518205,0.0003465467,0.00249508],"category_scores_gemma":[0.0012327889,0.000162216,0.00057529565,0.0006327656,0.00021585124,0.00086657365,0.0007545167,0.00046326613,0.0022446346],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006989329,0.0001634421,0.009293213,0.00014397947,0.00007448643,0.00026614597,0.00018549779,0.011570616,0.0875137,0.0011295072,0.0020266045,0.88693386],"study_design_scores_gemma":[0.000079529105,0.0005130323,0.035193074,0.000054707267,0.00028734983,0.00067097985,0.0007050251,0.86380255,0.0801453,0.0047965003,0.013638688,0.00011322741],"about_ca_topic_score_codex":0.003218685,"about_ca_topic_score_gemma":0.003936058,"teacher_disagreement_score":0.003218685,"about_ca_system_score_codex":0.00023369133,"about_ca_system_score_gemma":0.00041112787,"threshold_uncertainty_score":0.008346856},"labels":[],"label_agreement":null},{"id":"W2104046483","doi":"10.1109/isspa.2001.950249","title":"Hybrid architectures for complex phonetic features classification: a unified approach","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Hidden Markov model; Speech recognition; Artificial intelligence; Artificial neural network; Classifier (UML); Pattern recognition (psychology); Boosting (machine learning); Backpropagation; Learning vector quantization; Vector quantization; Time delay neural network; Machine learning","score_opus":0.0997431855592085,"score_gpt":0.2613932056576351,"score_spread":0.16165002009842658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104046483","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011703223,0.00084824616,0.98439354,0.00012743662,0.000036976056,0.000028316264,0.00003807079,0.0006993738,0.0021249142],"genre_scores_gemma":[0.44260404,0.001785605,0.54295546,0.000174954,0.00021255817,0.0002543845,0.0002995682,0.00017410397,0.011539253],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99972814,0.00005851165,0.000017643653,0.000067866094,0.00009047298,0.000037322134],"domain_scores_gemma":[0.9997106,0.00007573202,0.00001941766,0.00005495202,0.0001237009,0.000015494918],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064948277,0.0005473457,0.0006765882,0.00068361795,0.00024255614,0.0012639402,0.001081959,0.0010026653,0.0025048591],"category_scores_gemma":[0.0009008826,0.00034541995,0.00057686045,0.0006728368,0.00040558793,0.0019011562,0.0009297521,0.0006376271,0.0010562883],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016440135,0.00009076438,0.0014185582,0.00017444028,0.00015743624,0.00010566867,0.00013315697,0.16574353,0.021360489,0.029296873,0.0023736653,0.77898115],"study_design_scores_gemma":[0.000011330601,0.000065871616,0.0005237753,0.000015564177,0.000041409232,0.000059242884,0.000039231316,0.97721237,0.003302093,0.01600942,0.00270143,0.000018298586],"about_ca_topic_score_codex":0.0019933707,"about_ca_topic_score_gemma":0.0030353118,"teacher_disagreement_score":0.0025048591,"about_ca_system_score_codex":0.0003922642,"about_ca_system_score_gemma":0.00042978823,"threshold_uncertainty_score":0.008379579},"labels":[],"label_agreement":null},{"id":"W2105626703","doi":"10.1142/s0218001410008329","title":"PHONETIC SEGMENTATION OF EMOTIONAL SPEECH WITH HMM-BASED METHODS","year":2010,"lang":"en","type":"article","venue":"International Journal of Pattern Recognition and Artificial Intelligence","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"European Commission; McMaster University","keywords":"Segmentation; Computer science; Hidden Markov model; Speech segmentation; Speech recognition; Artificial intelligence; Process (computing); Pattern recognition (psychology)","score_opus":0.07410581644215461,"score_gpt":0.3492316905540887,"score_spread":0.2751258741119341,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105626703","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036294716,0.00015648552,0.99429095,0.000026638674,0.00004671734,0.00002345214,0.000051675837,0.0009605195,0.0008140333],"genre_scores_gemma":[0.18383309,0.0005293626,0.80940837,0.000097903096,0.00010884737,0.00017071363,0.0006605775,0.00059612707,0.0045950194],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99939287,0.00020141517,0.000050481067,0.00018499278,0.000120184384,0.00005003017],"domain_scores_gemma":[0.9990615,0.0005464921,0.000056286503,0.00014207896,0.00016213367,0.000031516345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085954246,0.00065350626,0.0005787687,0.00088532397,0.0004270149,0.0012108312,0.00097061764,0.0010515888,0.003684144],"category_scores_gemma":[0.0028041531,0.0005696211,0.0009144999,0.0006570926,0.00046066826,0.0011251518,0.0007819963,0.001115266,0.0027996702],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000385162,0.000097716234,0.0013494482,0.00033268047,0.0001702119,0.00024218882,0.0005726391,0.17763896,0.06554989,0.013741675,0.0029174387,0.7370019],"study_design_scores_gemma":[0.000015382922,0.000036605146,0.0012049428,0.000038480954,0.00004612468,0.000101096375,0.000068919326,0.96955216,0.016321925,0.008085822,0.004493198,0.000035355573],"about_ca_topic_score_codex":0.0023167115,"about_ca_topic_score_gemma":0.003205008,"teacher_disagreement_score":0.003684144,"about_ca_system_score_codex":0.000406918,"about_ca_system_score_gemma":0.0005598056,"threshold_uncertainty_score":0.012324631},"labels":[],"label_agreement":null},{"id":"W2106901945","doi":"10.1109/slt.2012.6424216","title":"Topic n-gram count language model adaptation for speech recognition","year":2012,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"n-gram; Gram; Latent Dirichlet allocation; Topic model; Cluster analysis; Word (group theory); Set (abstract data type); Computer science; Artificial intelligence; Test set; Adaptation (eye); Natural language processing; Language model; Speech recognition; Mathematics; Statistics","score_opus":0.07775270899817129,"score_gpt":0.2867773065104716,"score_spread":0.20902459751230035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106901945","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008792207,0.00038621767,0.9849337,0.00010122059,0.00013684362,0.00005928152,0.00020522726,0.004435525,0.00094989117],"genre_scores_gemma":[0.23892577,0.000889677,0.74552375,0.00033847822,0.0003349321,0.00071451435,0.002740368,0.002164011,0.008368481],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985239,0.00062800164,0.000081926344,0.00038653085,0.0003087248,0.000070875656],"domain_scores_gemma":[0.9982692,0.0008580282,0.00009022024,0.00038535416,0.00033502732,0.0000622416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015563826,0.0013206229,0.0012369968,0.0009995946,0.00046173125,0.0009136599,0.0017169073,0.0008209192,0.0027208005],"category_scores_gemma":[0.0052695107,0.0005006257,0.0011531926,0.0013753584,0.000421008,0.0018562557,0.001310587,0.0023262769,0.0033761552],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000486811,0.00033900046,0.0023087782,0.00023016564,0.00038638938,0.00019977521,0.00035515492,0.21478295,0.038994685,0.010519151,0.012054579,0.7193425],"study_design_scores_gemma":[0.000013037614,0.00003435442,0.00054045004,0.000008208836,0.000023588895,0.000059994767,0.000023172697,0.9818534,0.008332991,0.0045199376,0.0045584193,0.000032379223],"about_ca_topic_score_codex":0.0042407354,"about_ca_topic_score_gemma":0.0074712187,"teacher_disagreement_score":0.0042407354,"about_ca_system_score_codex":0.0007130828,"about_ca_system_score_gemma":0.0008137801,"threshold_uncertainty_score":0.009101987},"labels":[],"label_agreement":null},{"id":"W2107638917","doi":"10.1109/tasl.2006.881693","title":"Joint Factor Analysis Versus Eigenchannels in Speaker Recognition","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":709,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Normalization (sociology); NIST; Speaker recognition; Speech recognition; Computer science; Speaker verification; Gaussian; Joint (building); Session (web analytics); Mixture model; Pattern recognition (psychology); Artificial intelligence; Engineering","score_opus":0.0407489263447483,"score_gpt":0.28112707873527615,"score_spread":0.24037815239052784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107638917","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034833767,0.0013139695,0.95670724,0.00063220214,0.00012577871,0.00010126566,0.00027092392,0.002097678,0.0039171767],"genre_scores_gemma":[0.29280677,0.0009367064,0.70065314,0.00020509645,0.00020742069,0.00021949105,0.0005457183,0.0008743763,0.0035512953],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9903499,0.006358341,0.00042760486,0.00086671574,0.0017222684,0.0002752601],"domain_scores_gemma":[0.9796061,0.0152248535,0.0006869588,0.0025455442,0.0017819962,0.00015448328],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006414473,0.0011316797,0.0010114122,0.0013509638,0.00042976366,0.0023419356,0.00093835377,0.001220211,0.0055994405],"category_scores_gemma":[0.02793589,0.00038965364,0.0007188842,0.0022236141,0.0013455573,0.0042674053,0.001442688,0.001141924,0.0032944635],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031892252,0.00016081403,0.0037512693,0.00032910705,0.00024193292,0.00010049118,0.00028081526,0.06640807,0.028418519,0.037307233,0.009731788,0.85008067],"study_design_scores_gemma":[0.00011231847,0.00049219525,0.0069026668,0.00006133983,0.00012517514,0.00035021364,0.00020155893,0.8896384,0.053128153,0.043228693,0.0056077866,0.0001513867],"about_ca_topic_score_codex":0.0020168128,"about_ca_topic_score_gemma":0.0038195185,"teacher_disagreement_score":0.006414473,"about_ca_system_score_codex":0.0004807131,"about_ca_system_score_gemma":0.0005285912,"threshold_uncertainty_score":0.033923388},"labels":[],"label_agreement":null},{"id":"W2107687614","doi":"10.1109/icassp.2013.6639210","title":"Phonetic subspace adaptation for automatic speech recognition","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Subspace topology; Computer science; Projection (relational algebra); Adaptation (eye); Speech recognition; Artificial intelligence; Random subspace method; Pattern recognition (psychology); Vocabulary; Linear subspace; Algorithm; Mathematics","score_opus":0.044783962692685975,"score_gpt":0.24030223560061933,"score_spread":0.19551827290793336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107687614","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021752354,0.00045927893,0.9939334,0.000060220795,0.000084414205,0.000033807326,0.00011440319,0.0022270351,0.0009120779],"genre_scores_gemma":[0.14825845,0.0015309716,0.8377685,0.00024634253,0.00029976555,0.00039345893,0.002383557,0.0006335107,0.008485459],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990036,0.0002973096,0.000040549934,0.0002640234,0.00033418302,0.000060488343],"domain_scores_gemma":[0.9993938,0.00019243985,0.000028709886,0.00015887443,0.0002065951,0.000019583595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008699644,0.00088466535,0.0009857923,0.0008509564,0.00041702547,0.00068155647,0.0009838687,0.0007936535,0.004368129],"category_scores_gemma":[0.0017519647,0.00041827044,0.0010114113,0.0015114428,0.00049183035,0.0009166499,0.0009132061,0.0011964189,0.0046833493],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012430489,0.00008112227,0.0003977696,0.00010747028,0.00009851874,0.00004980465,0.00006450735,0.046774898,0.053564098,0.0072447485,0.005888998,0.88560367],"study_design_scores_gemma":[0.000016222291,0.0001167879,0.0013342351,0.000017377028,0.00004106979,0.00016585524,0.00003217775,0.9320093,0.036672935,0.010341051,0.01919674,0.00005625922],"about_ca_topic_score_codex":0.0027371997,"about_ca_topic_score_gemma":0.0035411539,"teacher_disagreement_score":0.004368129,"about_ca_system_score_codex":0.0003696067,"about_ca_system_score_gemma":0.00075497635,"threshold_uncertainty_score":0.0146128535},"labels":[],"label_agreement":null},{"id":"W2109302000","doi":"10.1109/vecims.2005.1567572","title":"Accent adaptation in speech user interface","year":2006,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Defense Advanced Research Projects Agency","keywords":"Speech recognition; Computer science; Stress (linguistics); Utterance; Word error rate; Hidden Markov model; TIMIT; Adaptation (eye); Artificial intelligence; Natural language processing","score_opus":0.02355940262558318,"score_gpt":0.24947106186015072,"score_spread":0.22591165923456755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109302000","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54901403,0.004851837,0.4139814,0.00043101533,0.0006700693,0.00036693702,0.0002896573,0.007038807,0.023356292],"genre_scores_gemma":[0.9455968,0.0011350731,0.04435283,0.00031873587,0.00016537077,0.000099620345,0.00023257805,0.0003696198,0.0077293282],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999212,0.0002678501,0.00005534436,0.00013924667,0.0002732356,0.00005223743],"domain_scores_gemma":[0.99810934,0.0010667514,0.00011681459,0.00024417753,0.00040615958,0.00005662506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012122132,0.00050957286,0.00036387425,0.00028819125,0.00023532646,0.00086711714,0.00045931837,0.000507194,0.0029979611],"category_scores_gemma":[0.005362795,0.00025982797,0.00025334713,0.00023445257,0.000286543,0.0009335526,0.00061408,0.0005161495,0.0016773391],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013781096,0.00026407422,0.009280876,0.0005581009,0.00014881951,0.0007374267,0.0011930664,0.023409277,0.35237426,0.002252275,0.0028155642,0.6055882],"study_design_scores_gemma":[0.00011796567,0.003942774,0.11108096,0.00023321813,0.0005983106,0.005157922,0.00095251726,0.27345055,0.5476103,0.00605656,0.05048166,0.00031723984],"about_ca_topic_score_codex":0.0005085839,"about_ca_topic_score_gemma":0.00038141385,"teacher_disagreement_score":0.0029979611,"about_ca_system_score_codex":0.00016550295,"about_ca_system_score_gemma":0.0001224119,"threshold_uncertainty_score":0.010029197},"labels":[],"label_agreement":null},{"id":"W2109740207","doi":"10.1109/isccsp.2008.4537397","title":"A playback attack detector for speaker verification systems","year":2008,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Detector; Similarity (geometry); Frame (networking); Set (abstract data type); Speech recognition; Cosine similarity; Feature (linguistics); Speaker verification; Utterance; Fast Fourier transform; Artificial intelligence; Pattern recognition (psychology); Speaker recognition; Algorithm; Telecommunications","score_opus":0.09712723700519299,"score_gpt":0.26977739776514476,"score_spread":0.17265016075995177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109740207","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022371588,0.00055914593,0.9633911,0.0001421352,0.00014043387,0.0002677421,0.00021796423,0.011425194,0.0014847018],"genre_scores_gemma":[0.43599653,0.00045915612,0.55478567,0.00028361072,0.00013860509,0.00032382415,0.0006638245,0.00035311142,0.006995709],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998108,0.00025836017,0.00014127271,0.0002937051,0.0010492465,0.0001494229],"domain_scores_gemma":[0.9980205,0.0007426747,0.00019602911,0.0003183979,0.0005909357,0.00013144803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016264367,0.0009796376,0.0011181526,0.0015392473,0.00071182434,0.0013641722,0.0012523219,0.0013436287,0.005043265],"category_scores_gemma":[0.004241813,0.0005940169,0.00041018266,0.00043907567,0.00041095528,0.0014942752,0.0010589649,0.0014686371,0.0034726008],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014543097,0.00029734962,0.0033634175,0.00026654196,0.00013069964,0.0005658596,0.00016319704,0.008086451,0.33878478,0.0054074987,0.00689806,0.6345819],"study_design_scores_gemma":[0.000090748516,0.00093329255,0.0040157815,0.00005729057,0.000111296686,0.0016526984,0.00005715779,0.6013531,0.3712145,0.0021639483,0.018237565,0.000112517155],"about_ca_topic_score_codex":0.0009185572,"about_ca_topic_score_gemma":0.00105722,"teacher_disagreement_score":0.005043265,"about_ca_system_score_codex":0.0006439105,"about_ca_system_score_gemma":0.0006800208,"threshold_uncertainty_score":0.016871393},"labels":[],"label_agreement":null},{"id":"W2109848220","doi":"10.1109/icassp.2011.5947460","title":"Adapting acoustic and lexical models to dysarthric speech","year":2011,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":80,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Dysarthria; Pronunciation; Speech recognition; Computer science; Vocabulary; Word error rate; Speech production; Lexicon; Artificial intelligence; Audiology; Linguistics","score_opus":0.1228450209147413,"score_gpt":0.24206564249048945,"score_spread":0.11922062157574816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109848220","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79909754,0.00039741507,0.1943751,0.0001783256,0.00019019011,0.00014761763,0.00035095293,0.0025181912,0.002744652],"genre_scores_gemma":[0.9585331,0.00017045689,0.037544087,0.00011648352,0.000043452306,0.00014049161,0.0012340121,0.00028987037,0.0019281257],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993668,0.00022939367,0.00004573837,0.00022358006,0.00008369881,0.000050672053],"domain_scores_gemma":[0.99873096,0.000713855,0.00006143246,0.00017693566,0.00028004116,0.000036755195],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093382166,0.0009012097,0.00055119337,0.00044069826,0.0002804256,0.00063169515,0.0005891479,0.0005659822,0.0011062962],"category_scores_gemma":[0.0039027839,0.00034536922,0.0005868834,0.0002866936,0.00036321318,0.00056228426,0.0008334764,0.00095505826,0.0011514407],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007197828,0.0004973836,0.0073874523,0.00020955424,0.0003657372,0.00063463236,0.0008534289,0.35196298,0.27459908,0.00072908105,0.0021284856,0.3599124],"study_design_scores_gemma":[0.00003055711,0.00017750243,0.006224739,0.000009497111,0.00009208029,0.00020124002,0.00013902423,0.95876294,0.032019384,0.0011796054,0.0011052886,0.00005817253],"about_ca_topic_score_codex":0.0034781646,"about_ca_topic_score_gemma":0.004815181,"teacher_disagreement_score":0.0034781646,"about_ca_system_score_codex":0.00034177824,"about_ca_system_score_gemma":0.0003826372,"threshold_uncertainty_score":0.0069158673},"labels":[],"label_agreement":null},{"id":"W2109886035","doi":"10.1109/icassp.2016.7472618","title":"End-to-end attention-based large vocabulary speech recognition","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":124,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Computer science; Hidden Markov model; Recurrent neural network; Speech recognition; Decoding methods; Vocabulary; Sequence (biology); Pooling; Artificial intelligence; Character (mathematics); Language model; Process (computing); Pattern recognition (psychology); Artificial neural network; Algorithm","score_opus":0.035201277585039846,"score_gpt":0.26630435358302523,"score_spread":0.23110307599798538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109886035","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02080865,0.00061377895,0.9488205,0.00015650624,0.00025923908,0.00017417756,0.0013428577,0.021110795,0.0067135748],"genre_scores_gemma":[0.34304577,0.0004651333,0.62169677,0.00043428104,0.00024002658,0.00035785555,0.008018047,0.0011593404,0.024582813],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898905,0.00016905891,0.000047206893,0.00037189753,0.00028452196,0.0001382888],"domain_scores_gemma":[0.9986934,0.0004593465,0.00005155659,0.00028107033,0.00045147413,0.00006322409],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000829407,0.0014772149,0.0012385695,0.00089227245,0.00046189965,0.0010433572,0.0019356608,0.0013022934,0.013657825],"category_scores_gemma":[0.002630598,0.00037799595,0.0005585971,0.00063900807,0.00041601097,0.0014410027,0.0015756732,0.0013602996,0.016015744],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005154727,0.00021087217,0.0006257042,0.00020392465,0.00007738172,0.00021726244,0.00010291556,0.014841105,0.101744674,0.0024636898,0.015889429,0.86310756],"study_design_scores_gemma":[0.000051528652,0.0001883794,0.002096532,0.00003157803,0.00006381438,0.0003936842,0.000073729636,0.80049425,0.17667626,0.008429196,0.011451004,0.000049977873],"about_ca_topic_score_codex":0.0041640094,"about_ca_topic_score_gemma":0.008928131,"teacher_disagreement_score":0.013657825,"about_ca_system_score_codex":0.00058381463,"about_ca_system_score_gemma":0.0008332974,"threshold_uncertainty_score":0.04569},"labels":[],"label_agreement":null},{"id":"W2112021726","doi":"10.1109/taslp.2014.2346313","title":"Fast Adaptation of Deep Neural Network Based on Discriminant Codes for Speech Recognition","year":2014,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":139,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"University of Science and Technology of China","keywords":"Computer science; Speech recognition; TIMIT; Normalization (sociology); Adaptation (eye); Artificial neural network; Artificial intelligence; Speaker recognition; Pattern recognition (psychology); Word error rate; Hidden Markov model","score_opus":0.02681299895984912,"score_gpt":0.26100173092852763,"score_spread":0.2341887319686785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112021726","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044239093,0.00078180275,0.95134974,0.00011363079,0.00013824481,0.000044514076,0.00009790861,0.0018068427,0.0014282825],"genre_scores_gemma":[0.64463246,0.000726824,0.3482639,0.00019007118,0.00006517684,0.00014047259,0.00058206887,0.00023186476,0.0051672244],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99969685,0.00006472963,0.000015408705,0.00008597549,0.000105455976,0.00003157762],"domain_scores_gemma":[0.99961406,0.00013638547,0.000029825187,0.000069512695,0.00013170239,0.000018645178],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005802385,0.0006734337,0.00038816396,0.0003923998,0.00016273672,0.0002543833,0.00055124174,0.00044507414,0.001259639],"category_scores_gemma":[0.0013443526,0.00025524115,0.0004215731,0.0004057263,0.00034352543,0.0007422698,0.0006124825,0.0013534372,0.0005576932],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025542645,0.00012479717,0.0019831583,0.00012368908,0.00009517022,0.00010945034,0.00010919427,0.2647353,0.14553303,0.0042316616,0.003361296,0.57933784],"study_design_scores_gemma":[0.000006799437,0.00003743316,0.00087149657,0.0000069867247,0.000013009288,0.00004494863,0.000010680858,0.96540993,0.030273166,0.0014123295,0.0018972753,0.000015932657],"about_ca_topic_score_codex":0.0037171587,"about_ca_topic_score_gemma":0.0061745257,"teacher_disagreement_score":0.0037171587,"about_ca_system_score_codex":0.00046796375,"about_ca_system_score_gemma":0.00047401624,"threshold_uncertainty_score":0.0073910356},"labels":[],"label_agreement":null},{"id":"W2112582577","doi":"10.1109/tasl.2007.894527","title":"Speaker and Session Variability in GMM-Based Speaker Verification","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":227,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"NIST; Computer science; Speaker recognition; Speech recognition; Session (web analytics); Set (abstract data type); Statistic; Pattern recognition (psychology); Artificial intelligence; Speaker diarisation; Factor (programming language); Feature (linguistics); Statistics; Mathematics; Linguistics","score_opus":0.012953082206222183,"score_gpt":0.2605477096187157,"score_spread":0.24759462741249352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112582577","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10924545,0.0010125028,0.8849971,0.00014019395,0.000095006275,0.000074725685,0.0002906504,0.001854645,0.0022896752],"genre_scores_gemma":[0.8162435,0.00036505758,0.18047851,0.000071327486,0.00010175028,0.00011065447,0.0004947974,0.00026831363,0.0018660661],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9967769,0.0017484244,0.00012520587,0.0004892467,0.0006760841,0.00018413289],"domain_scores_gemma":[0.99564075,0.0031918827,0.00018735733,0.0005092053,0.00040798684,0.00006278576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045011416,0.00054788095,0.0008487874,0.000860945,0.0004222172,0.00064674794,0.0006530439,0.0008323531,0.0012602948],"category_scores_gemma":[0.009684813,0.00038278094,0.00063259463,0.00069059816,0.0005319506,0.0013197165,0.000940619,0.00077736337,0.00088704523],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022749288,0.00013675677,0.017212825,0.000288425,0.00030217084,0.00027540085,0.00068596937,0.17721447,0.073184535,0.01450597,0.004049864,0.7098687],"study_design_scores_gemma":[0.000030112169,0.00024885152,0.018494466,0.000043838274,0.0001463443,0.0005832875,0.00012976806,0.9142366,0.055218197,0.007438916,0.0033439673,0.00008575443],"about_ca_topic_score_codex":0.0033721016,"about_ca_topic_score_gemma":0.0050527416,"teacher_disagreement_score":0.0045011416,"about_ca_system_score_codex":0.00049242354,"about_ca_system_score_gemma":0.0005930165,"threshold_uncertainty_score":0.023804665},"labels":[],"label_agreement":null},{"id":"W2113395503","doi":"10.1109/tasl.2008.2001105","title":"Transforming Perceived Vocal Effort and Breathiness Using Adaptive Pre-Emphasis Linear Prediction","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"University of Victoria","keywords":"Emphasis (telecommunications); Formant; Vocal tract; Spectral envelope; Speech recognition; Filter (signal processing); Active listening; Computer science; Breathy voice; Envelope (radar); Linear prediction; Acoustics; Phonation; Vowel; Psychology; Audiology; Telecommunications; Radar; Communication","score_opus":0.024238213379658247,"score_gpt":0.2607480318921048,"score_spread":0.23650981851244657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113395503","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25621185,0.00031011488,0.73995435,0.00011325689,0.00006939317,0.0000903245,0.00009516071,0.0007673177,0.0023882051],"genre_scores_gemma":[0.7850618,0.0003479641,0.21179684,0.00007470193,0.0000452745,0.00007163545,0.00013497198,0.00015129919,0.0023155278],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998273,0.000037909584,0.000008759201,0.000045615314,0.0000666784,0.000013894885],"domain_scores_gemma":[0.999423,0.0003767831,0.00004735666,0.000042921554,0.00009511155,0.000014955793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003338394,0.00040234483,0.00016850232,0.00025090005,0.00010570923,0.00041651595,0.00021961746,0.00031775862,0.0014091603],"category_scores_gemma":[0.0024454321,0.00017541542,0.0002239504,0.00016129753,0.00022087997,0.00050174334,0.00029018935,0.00043428427,0.00036488145],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00063088373,0.00014362107,0.0043578334,0.00019759333,0.000063889805,0.00020984473,0.0005431128,0.027810466,0.33448103,0.0012986144,0.0005510362,0.62971205],"study_design_scores_gemma":[0.00011353263,0.0015489248,0.060985837,0.00008255077,0.0002054501,0.0010674817,0.00045933362,0.636719,0.28846928,0.004422026,0.0057418514,0.00018467661],"about_ca_topic_score_codex":0.00084505783,"about_ca_topic_score_gemma":0.0011506994,"teacher_disagreement_score":0.0014091603,"about_ca_system_score_codex":0.00012372731,"about_ca_system_score_gemma":0.00017134626,"threshold_uncertainty_score":0.0047141314},"labels":[],"label_agreement":null},{"id":"W2114948162","doi":"10.1109/icassp.1996.540277","title":"HMM-based speech recognition using state-dependent, linear transforms on Mel-warped DFT features","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"TIMIT; Hidden Markov model; Computer science; Speech recognition; Word error rate; Pattern recognition (psychology); Mel-frequency cepstrum; Transformation (genetics); Feature extraction; Artificial intelligence; Feature (linguistics)","score_opus":0.0734056754320572,"score_gpt":0.2641613885171936,"score_spread":0.19075571308513642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114948162","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.108466975,0.00025610573,0.88830304,0.000065046675,0.000024414796,0.00003779127,0.00008176284,0.0016571635,0.0011077239],"genre_scores_gemma":[0.64266616,0.00033433188,0.35288924,0.00003511706,0.000023736888,0.00007539511,0.00030120145,0.00009683509,0.003578098],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998313,0.0000489018,0.000010315922,0.000040985626,0.000052286254,0.000016023452],"domain_scores_gemma":[0.9997179,0.00016282873,0.000022004026,0.00004160899,0.000048339036,0.000007277267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004018969,0.00021941464,0.00033166417,0.00019686941,0.000099804136,0.000320294,0.00023250586,0.00021618325,0.0011058473],"category_scores_gemma":[0.0009040513,0.00017588573,0.00021828429,0.00022953692,0.00018919409,0.0005698734,0.00018103069,0.00032234396,0.0007387819],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031213692,0.00014224411,0.0020581204,0.00011851257,0.00006974088,0.00010884705,0.000121273166,0.14565639,0.2315457,0.0033512805,0.0010879459,0.6154278],"study_design_scores_gemma":[0.00001080763,0.00010373955,0.0019731494,0.0000080899645,0.000026210488,0.000072741874,0.000014165736,0.930202,0.065732785,0.0007330461,0.0011098854,0.000013439043],"about_ca_topic_score_codex":0.0015368586,"about_ca_topic_score_gemma":0.0028210282,"teacher_disagreement_score":0.0015368586,"about_ca_system_score_codex":0.00014782479,"about_ca_system_score_gemma":0.00024337227,"threshold_uncertainty_score":0.0036994219},"labels":[],"label_agreement":null},{"id":"W2115230584","doi":"","title":"A Critical Reassessment of Evaluation Baselines for Speech Summarization","year":2008,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Automatic summarization; Computer science; Speech recognition; Speech analytics; Voice activity detection; Natural language processing; Speech processing; Surprise; Speech synthesis; Artificial intelligence; Information retrieval","score_opus":0.08207451475019102,"score_gpt":0.35184597856050354,"score_spread":0.26977146381031253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115230584","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2383964,0.13406721,0.41403314,0.09764188,0.019358328,0.002639306,0.016027302,0.016281644,0.06155479],"genre_scores_gemma":[0.68240935,0.012003046,0.25730324,0.0073803207,0.004713912,0.001952776,0.02259174,0.003406215,0.008239485],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8993386,0.054397866,0.008725158,0.008597849,0.027432984,0.0015074764],"domain_scores_gemma":[0.70245534,0.1489957,0.007950052,0.024030333,0.113036044,0.0035325743],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.14521343,0.001954155,0.002401266,0.006977695,0.004076047,0.009848238,0.004370946,0.0030036317,0.0038955589],"category_scores_gemma":[0.28906232,0.00070428016,0.0014227931,0.0059534926,0.002429885,0.009657215,0.0035635468,0.005429569,0.003204941],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0038167357,0.0010527727,0.021567032,0.0041390704,0.001050716,0.00021831293,0.0031267547,0.0073752715,0.024502574,0.02840547,0.17166041,0.7330849],"study_design_scores_gemma":[0.0017372117,0.010521995,0.15573782,0.0095426105,0.0023241981,0.0018108885,0.011455018,0.13591194,0.1131149,0.1372344,0.41938758,0.0012213851],"about_ca_topic_score_codex":0.004965792,"about_ca_topic_score_gemma":0.00769225,"teacher_disagreement_score":0.8547866,"about_ca_system_score_codex":0.005254144,"about_ca_system_score_gemma":0.0025003965,"threshold_uncertainty_score":0.76797116},"labels":[],"label_agreement":null},{"id":"W2115328154","doi":"10.1109/icassp.2004.1325916","title":"Disentangling speaker and channel effects in speaker verification","year":2004,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Speaker recognition; Speaker diarisation; NIST; Computer science; Speaker verification; Speech recognition; Variation (astronomy); Task (project management); Channel (broadcasting); Factor (programming language); Construct (python library); Joint (building); Artificial intelligence; Telecommunications; Engineering","score_opus":0.011520597261380609,"score_gpt":0.21973349414653406,"score_spread":0.20821289688515346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115328154","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055589724,0.0004192398,0.94241357,0.00009325022,0.000036495585,0.00003388859,0.00007965063,0.00048536155,0.0008488093],"genre_scores_gemma":[0.5847018,0.0007573883,0.41122243,0.00008704771,0.00010912836,0.000093972485,0.0003543587,0.00034902312,0.0023248687],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99734205,0.0011722014,0.00011209321,0.00049863313,0.00062344864,0.0002515338],"domain_scores_gemma":[0.9939713,0.0045805876,0.00025162668,0.00069287245,0.0004045631,0.00009900771],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037907173,0.0011109102,0.0009880315,0.00067747757,0.0004965658,0.0012816559,0.00052026974,0.0010365824,0.002105575],"category_scores_gemma":[0.013125928,0.00052286935,0.0011042572,0.00076690206,0.00088451785,0.0029766383,0.0014343179,0.0014205999,0.001421355],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017844898,0.00016650057,0.0056396103,0.00022648134,0.00025696406,0.00022513737,0.00057462644,0.07529811,0.17510828,0.010776948,0.00092009694,0.72902274],"study_design_scores_gemma":[0.00007879489,0.00063484156,0.014601969,0.00004274283,0.00027986304,0.0006752812,0.00013932811,0.84180456,0.10583175,0.032374326,0.0033590407,0.00017745935],"about_ca_topic_score_codex":0.0022648855,"about_ca_topic_score_gemma":0.0039686565,"teacher_disagreement_score":0.0037907173,"about_ca_system_score_codex":0.0001958466,"about_ca_system_score_gemma":0.0007928643,"threshold_uncertainty_score":0.020047486},"labels":[],"label_agreement":null},{"id":"W2115599677","doi":"10.1109/jstsp.2010.2081790","title":"Diarization of Telephone Conversations Using Factor Analysis","year":2010,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Signal Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":141,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"Johns Hopkins University","keywords":"Speaker diarisation; Computer science; Cluster analysis; Speech recognition; Word error rate; Speaker recognition; NIST; Channel (broadcasting); Hierarchical clustering; Bayes' theorem; Exploit; Artificial intelligence; Pattern recognition (psychology); Telecommunications; Bayesian probability","score_opus":0.025827002893712158,"score_gpt":0.2748875302374324,"score_spread":0.24906052734372025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115599677","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027955059,0.0006165972,0.9674878,0.00010775065,0.00008765247,0.00014182966,0.00034275104,0.0017122474,0.0015483293],"genre_scores_gemma":[0.2561314,0.0007354892,0.7362862,0.0000881409,0.00014919102,0.00015758585,0.0017304309,0.0004989171,0.004222651],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976221,0.0007538295,0.00014311822,0.00074100774,0.0005730254,0.00016699407],"domain_scores_gemma":[0.9971411,0.0011782652,0.00022093464,0.000434671,0.00094387913,0.00008107131],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002230769,0.0013096712,0.00094086624,0.0019644017,0.00059732795,0.001185256,0.000859348,0.00046620079,0.0032405404],"category_scores_gemma":[0.0071229595,0.00032818885,0.0013147646,0.0019612992,0.0004325826,0.0013184965,0.00076766504,0.0011820215,0.0018558529],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047265575,0.000120178454,0.0032415881,0.00018998237,0.00022270111,0.00007489498,0.00068316894,0.015906952,0.040163293,0.0023575344,0.0025047234,0.9340624],"study_design_scores_gemma":[0.000111436515,0.0005990315,0.024007075,0.0000890391,0.00038296593,0.0007825692,0.00078221026,0.8252556,0.09609282,0.016429571,0.035130765,0.0003369859],"about_ca_topic_score_codex":0.006423189,"about_ca_topic_score_gemma":0.009112255,"teacher_disagreement_score":0.006423189,"about_ca_system_score_codex":0.0006763722,"about_ca_system_score_gemma":0.0006505211,"threshold_uncertainty_score":0.012771547},"labels":[],"label_agreement":null},{"id":"W2115695999","doi":"10.1080/02699200500113590","title":"Techniques for field application of lingual ultrasound imaging","year":2005,"lang":"en","type":"article","venue":"Clinical Linguistics & Phonetics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria; University of British Columbia","funders":"National Institute on Deafness and Other Communication Disorders; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Tongue; Transducer; Ultrasound; Field (mathematics); Head (geology); Computer science; Ultrasound imaging; Acoustics; Presentation (obstetrics); Computer vision; Radiology; Medicine; Mathematics; Physics; Geology; Pathology","score_opus":0.028728005045375735,"score_gpt":0.36518292966211335,"score_spread":0.3364549246167376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115695999","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02325192,0.0055108904,0.94271606,0.0012788983,0.0006962858,0.0012709909,0.00017430303,0.0024411206,0.022659585],"genre_scores_gemma":[0.101826444,0.0036541298,0.88026965,0.00065622735,0.00034348672,0.0013021182,0.00011586117,0.00038778372,0.011444263],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99931264,0.00022308787,0.00005192212,0.0001586243,0.0001957029,0.00005797736],"domain_scores_gemma":[0.997693,0.000951805,0.00016809764,0.0006138087,0.00045484025,0.000118467535],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016190521,0.0007180342,0.0005819926,0.0015336367,0.0011422819,0.00082770485,0.0010612721,0.0010004843,0.016452558],"category_scores_gemma":[0.0028955003,0.00064082735,0.00060705503,0.00068357046,0.0010162396,0.0012686043,0.0012836227,0.0017307164,0.0052806553],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037073987,0.00017913914,0.0012015614,0.0008676861,0.000027373908,0.0006468211,0.00060277997,0.00044566006,0.6107192,0.011034469,0.005676598,0.368228],"study_design_scores_gemma":[0.00044239347,0.0058073634,0.015433524,0.0009524529,0.00035837325,0.03646566,0.0015856541,0.010940359,0.55068636,0.033011407,0.34371722,0.00059923227],"about_ca_topic_score_codex":0.00037722578,"about_ca_topic_score_gemma":0.0006938094,"teacher_disagreement_score":0.016452558,"about_ca_system_score_codex":0.0002692424,"about_ca_system_score_gemma":0.0005833469,"threshold_uncertainty_score":0.055039287},"labels":[],"label_agreement":null},{"id":"W2115900223","doi":"10.1109/icassp.1994.389284","title":"Correcting complex false starts in spontaneous speech","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Utterance; Computer science; Speech recognition; Word (group theory); Identification (biology); Artificial intelligence; Natural language processing; Linguistics","score_opus":0.0633903589158387,"score_gpt":0.244796490937937,"score_spread":0.18140613202209832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115900223","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57507193,0.0009667352,0.41236043,0.0002778468,0.00039826543,0.00013900298,0.00086154265,0.0049780877,0.004946166],"genre_scores_gemma":[0.90049964,0.00025390275,0.093136884,0.00012645456,0.00010390913,0.000070425194,0.0014459873,0.00088590675,0.0034768656],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99447316,0.0018396304,0.00045361198,0.0012095292,0.0017322922,0.00029177772],"domain_scores_gemma":[0.9527111,0.029613784,0.0036942444,0.008699154,0.0048487345,0.00043293997],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032178543,0.000886216,0.0010074874,0.0009012604,0.0006439992,0.0018719166,0.0009766011,0.0013555062,0.002681937],"category_scores_gemma":[0.037198897,0.0004844769,0.00041030627,0.00061918155,0.00089107413,0.0017914975,0.0015919313,0.001070178,0.0017455651],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0057442747,0.00029450498,0.037704475,0.00090398086,0.00025703904,0.010396976,0.0056536817,0.03268062,0.25405887,0.009780832,0.008387046,0.63413775],"study_design_scores_gemma":[0.00023741428,0.0017408571,0.06462639,0.0003474147,0.0003959005,0.016599346,0.0026161103,0.32914594,0.52990365,0.023530897,0.030403668,0.00045252297],"about_ca_topic_score_codex":0.0012866884,"about_ca_topic_score_gemma":0.0016556563,"teacher_disagreement_score":0.0032178543,"about_ca_system_score_codex":0.00038374166,"about_ca_system_score_gemma":0.0005356404,"threshold_uncertainty_score":0.017017901},"labels":[],"label_agreement":null},{"id":"W2116168363","doi":"10.1109/ivtta.1998.727683","title":"Automation of locality recognition in ADAS Plus","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Nortel (Canada)","funders":"","keywords":"Directory; Phone; Computer science; Automation; Listing (finance); Service (business); Product (mathematics); Advanced driver assistance systems; Speech recognition; Database; World Wide Web; Operating system; Artificial intelligence; Engineering; Business","score_opus":0.06646115400023518,"score_gpt":0.24317356398463297,"score_spread":0.1767124099843978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116168363","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15441377,0.0005158207,0.6203362,0.00055467506,0.000447484,0.00042868388,0.0018221235,0.16348179,0.057999488],"genre_scores_gemma":[0.5024686,0.00016961014,0.4507095,0.0005964432,0.0001045458,0.00020221942,0.0031398667,0.0020383198,0.04057097],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985763,0.00018002247,0.00009278347,0.00040064895,0.00060257,0.0001477181],"domain_scores_gemma":[0.9986518,0.00027661334,0.000077211254,0.00027388288,0.00065686106,0.00006351268],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006627802,0.00062493735,0.0006735852,0.00088437967,0.0005924453,0.0012685934,0.00088553573,0.00066248997,0.010903383],"category_scores_gemma":[0.0016657781,0.00046669543,0.00034042334,0.00046063136,0.00040729094,0.0008317778,0.00074815063,0.00068840367,0.015562704],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00097567897,0.00026774747,0.0039598863,0.00016171919,0.000042373576,0.00055926753,0.00076740753,0.0054845475,0.17621148,0.003198893,0.048262686,0.7601083],"study_design_scores_gemma":[0.00025857828,0.000606255,0.012081107,0.000061257386,0.00010342938,0.0027612643,0.00075511093,0.260236,0.50157726,0.004794516,0.21651797,0.00024723375],"about_ca_topic_score_codex":0.014593238,"about_ca_topic_score_gemma":0.02175908,"teacher_disagreement_score":0.014593238,"about_ca_system_score_codex":0.00077210035,"about_ca_system_score_gemma":0.0008212713,"threshold_uncertainty_score":0.03647548},"labels":[],"label_agreement":null},{"id":"W2116375618","doi":"10.1109/chinsl.2004.1409573","title":"A comparative study on various confidence measures in large vocabulary speech recognition","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Dictation; Vocabulary; Word error rate; Computer science; Speech recognition; Mandarin Chinese; Word (group theory); Task (project management); Artificial intelligence; A priori and a posteriori; Language model; Interpolation (computer graphics); Natural language processing; Pattern recognition (psychology); Mathematics","score_opus":0.0777816752275478,"score_gpt":0.3098407658864848,"score_spread":0.23205909065893698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116375618","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2087779,0.012588321,0.77032083,0.0004521592,0.00015231897,0.00018976373,0.00029972612,0.0020915607,0.005127367],"genre_scores_gemma":[0.7877798,0.0012550042,0.20913564,0.00010320918,0.00018720127,0.00012233271,0.0005641216,0.00019344746,0.0006592417],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9820801,0.0087271435,0.0013028119,0.0016346129,0.005773276,0.00048207908],"domain_scores_gemma":[0.76655656,0.20755515,0.0054114102,0.007826791,0.0114299,0.0012202438],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022284444,0.0011859733,0.0013077094,0.0043469775,0.0005513243,0.0017607539,0.0021280574,0.0019198266,0.0020709508],"category_scores_gemma":[0.1312225,0.00043543437,0.00086467044,0.0030439342,0.0010155612,0.0050237738,0.0015526541,0.0014720843,0.00042218738],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002251853,0.00040202102,0.023518734,0.0013186879,0.00062638597,0.0001702126,0.0004903025,0.08972869,0.021767737,0.0115689,0.0014652263,0.84669125],"study_design_scores_gemma":[0.00013313987,0.0035033636,0.02899516,0.00026978637,0.0003675377,0.0013309016,0.00044311586,0.8703278,0.08327291,0.007142814,0.003857936,0.00035564147],"about_ca_topic_score_codex":0.0013161084,"about_ca_topic_score_gemma":0.0010993766,"teacher_disagreement_score":0.022284444,"about_ca_system_score_codex":0.0009792933,"about_ca_system_score_gemma":0.0005472831,"threshold_uncertainty_score":0.11785281},"labels":[],"label_agreement":null},{"id":"W2117817230","doi":"10.1109/issse.2007.4294413","title":"A Processing Method for Pitch Smoothing Based on Autocorrelation and Cepstral F0 Detection Approaches","year":2007,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Speech recognition; Pitch detection algorithm; Smoothing; Computer science; Discriminative model; Cepstrum; Autocorrelation; Intonation (linguistics); Mel-frequency cepstrum; Tone (literature); Artificial intelligence; Pattern recognition (psychology); Feature extraction; Speech processing; Mathematics; Computer vision","score_opus":0.06618200486706205,"score_gpt":0.2972780613994062,"score_spread":0.23109605653234416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117817230","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034946788,0.00023999569,0.9939804,0.000038325663,0.00010742683,0.000058614358,0.0000598963,0.0014256038,0.0005951214],"genre_scores_gemma":[0.033321347,0.00026709703,0.9630858,0.00004973821,0.000090937785,0.00009184456,0.0001925441,0.00014214328,0.0027585092],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993777,0.00006128083,0.000044809607,0.00018878057,0.00029312976,0.000034290755],"domain_scores_gemma":[0.999164,0.00017252646,0.00005127514,0.00014319255,0.00043464903,0.000034424105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006415075,0.00086423056,0.0006869095,0.0017005071,0.0006533023,0.0005600605,0.0009513964,0.0008354508,0.0039899144],"category_scores_gemma":[0.0015310614,0.00041562153,0.00076010614,0.0011764416,0.00040268208,0.00088605937,0.00047155112,0.0008163821,0.0029949124],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022497331,0.00007630207,0.000508592,0.00015554893,0.00004910423,0.0001359989,0.00008450978,0.004927095,0.19314052,0.00410858,0.0032989052,0.79328984],"study_design_scores_gemma":[0.00010239322,0.0005162598,0.0066315727,0.00005358882,0.00027398838,0.0016676837,0.00007887818,0.6338634,0.295608,0.0039912495,0.057018597,0.00019440142],"about_ca_topic_score_codex":0.0029094273,"about_ca_topic_score_gemma":0.0035670905,"teacher_disagreement_score":0.0039899144,"about_ca_system_score_codex":0.00038899615,"about_ca_system_score_gemma":0.0007517604,"threshold_uncertainty_score":0.013347566},"labels":[],"label_agreement":null},{"id":"W2121415728","doi":"10.1109/tsa.2004.840940","title":"Eigenvoice modeling with sparse training data","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Speech and Audio Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":472,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Speech recognition; Training set; Set (abstract data type); Adaptation (eye); Limit (mathematics); Training (meteorology); Maximum likelihood; Covariance matrix; Pattern recognition (psychology); Estimation theory; Artificial intelligence; Covariance; Speaker recognition; Algorithm; Mathematics; Statistics","score_opus":0.095794255220844,"score_gpt":0.2797844726229301,"score_spread":0.1839902174020861,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121415728","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005680046,0.00006269001,0.99351764,0.000043627537,0.000013688858,0.000009312174,0.000045552093,0.00014377378,0.00048372726],"genre_scores_gemma":[0.47542048,0.00054984255,0.51559895,0.00018576637,0.0001511257,0.00022798829,0.00079956354,0.0002749555,0.006791252],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995765,0.000118992095,0.000016325788,0.000101235,0.00012877234,0.000058186564],"domain_scores_gemma":[0.99912506,0.00044245063,0.00008881113,0.00015130657,0.00016274443,0.000029627281],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007939901,0.00053049513,0.0007143595,0.00049459544,0.00026938258,0.0007678655,0.0013526723,0.00080754247,0.0014852852],"category_scores_gemma":[0.003208085,0.0005329204,0.00067358714,0.00056437205,0.00056212745,0.0012259965,0.0010610936,0.0012674484,0.00069066195],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001051985,0.000052041392,0.000860624,0.00009482021,0.0000609196,0.00010855857,0.00023275295,0.80146766,0.012447549,0.033431843,0.0022378552,0.14890021],"study_design_scores_gemma":[0.0000026325647,0.000007831561,0.00010531008,0.0000035166584,0.0000029667224,0.00002115068,0.000006456563,0.99129045,0.0010478433,0.006963778,0.0005419836,0.000006088376],"about_ca_topic_score_codex":0.00244556,"about_ca_topic_score_gemma":0.0042363885,"teacher_disagreement_score":0.00244556,"about_ca_system_score_codex":0.000251907,"about_ca_system_score_gemma":0.0004872123,"threshold_uncertainty_score":0.0049687624},"labels":[],"label_agreement":null},{"id":"W2123545720","doi":"10.1109/icassp.2009.4960580","title":"Unsupervised pronunciation validation","year":2009,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada)","funders":"","keywords":"Computer science; Pronunciation; Vocabulary; Word error rate; Speech recognition; Lexicon; Artificial intelligence; Search engine indexing; Phone; Natural language processing; Word (group theory); Speech processing; Pattern recognition (psychology)","score_opus":0.018767538752516116,"score_gpt":0.233102594424234,"score_spread":0.2143350556717179,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123545720","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20443627,0.0009847694,0.7629334,0.00019094304,0.00065938587,0.00065921457,0.0054758927,0.015243596,0.0094165625],"genre_scores_gemma":[0.6454763,0.00032996116,0.308745,0.00036326514,0.00018017758,0.00082121964,0.028854635,0.002655384,0.012574028],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99144673,0.0030798027,0.00069501187,0.0026755645,0.0015894263,0.00051355746],"domain_scores_gemma":[0.9773515,0.010816385,0.000878595,0.0034297626,0.007150765,0.0003729413],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052851755,0.0021261435,0.0013983459,0.0032079176,0.0012533797,0.0022630824,0.002302922,0.0016380138,0.007322768],"category_scores_gemma":[0.029968953,0.0004072123,0.0010330377,0.0015154716,0.0009161247,0.0020408856,0.0022634487,0.0018473363,0.008477785],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00095221365,0.00027076429,0.016307184,0.00046427807,0.00025183934,0.0005215053,0.0006228478,0.023666957,0.07794127,0.0026966468,0.010493451,0.86581105],"study_design_scores_gemma":[0.00024625522,0.0008350788,0.035755686,0.00023687782,0.00025553117,0.0038588142,0.0013377899,0.6619975,0.24104862,0.009411464,0.044706684,0.00030972634],"about_ca_topic_score_codex":0.0024847372,"about_ca_topic_score_gemma":0.0032656284,"teacher_disagreement_score":0.007322768,"about_ca_system_score_codex":0.00054258615,"about_ca_system_score_gemma":0.002032178,"threshold_uncertainty_score":0.027951002},"labels":[],"label_agreement":null},{"id":"W2123781188","doi":"10.1109/icassp.1998.674432","title":"Specific language modelling for new-word detection in continuous-speech recognition","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Keyword spotting; Vocabulary; Spotting; Word (group theory); Natural language processing; Speech recognition; Language model; Artificial intelligence; Transcription (linguistics); Process (computing); Linguistics","score_opus":0.06618264797328118,"score_gpt":0.24173339912606753,"score_spread":0.17555075115278634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123781188","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016393151,0.00014512283,0.9814636,0.0000490885,0.000031912718,0.00003535847,0.00005686898,0.0012041725,0.000620762],"genre_scores_gemma":[0.44661587,0.0004057043,0.5483234,0.00014491267,0.000070202674,0.00029033475,0.0006726555,0.00040970033,0.0030672424],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998803,0.0004483807,0.00011801615,0.0002987402,0.00025247733,0.00007940953],"domain_scores_gemma":[0.9980787,0.0010493068,0.00012291582,0.00043369006,0.00026038534,0.000055052624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001263599,0.0009959086,0.0007912107,0.0006048901,0.00027624928,0.0010937554,0.0011231599,0.00085774704,0.0015821123],"category_scores_gemma":[0.0040439465,0.0005052945,0.001238336,0.0003432352,0.00070152164,0.0026774434,0.0006700168,0.0011283192,0.0017492683],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011086252,0.00038883253,0.00347799,0.0007422004,0.00030034888,0.00042446866,0.0009702568,0.33132812,0.22491196,0.034717906,0.0023618052,0.39926746],"study_design_scores_gemma":[0.000016300399,0.00011372554,0.000494765,0.000015040565,0.000047836857,0.00021036557,0.000052268737,0.95185965,0.03899403,0.005891468,0.0022679174,0.0000366028],"about_ca_topic_score_codex":0.0013951269,"about_ca_topic_score_gemma":0.002433936,"teacher_disagreement_score":0.0015821123,"about_ca_system_score_codex":0.00044825126,"about_ca_system_score_gemma":0.00081562245,"threshold_uncertainty_score":0.0066826344},"labels":[],"label_agreement":null},{"id":"W2123798005","doi":"10.1109/icassp.2010.5495646","title":"Multilingual acoustic modeling for speech recognition based on subspace Gaussian Mixture Models","year":2010,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":160,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Subspace topology; Computer science; Phone; Gaussian; Mixture model; Speech recognition; Set (abstract data type); Language model; Artificial intelligence; Acoustic model; Space (punctuation); Hidden Markov model; Natural language processing; Pattern recognition (psychology); Speech processing; Linguistics","score_opus":0.04797919133278814,"score_gpt":0.2764242881821557,"score_spread":0.22844509684936756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123798005","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052024904,0.0002095788,0.9915658,0.00007213752,0.000029632973,0.000017936922,0.00011751395,0.002158677,0.0006262511],"genre_scores_gemma":[0.22372411,0.00074761803,0.767534,0.00015194838,0.00008857189,0.00024763966,0.0020205574,0.001034991,0.004450514],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990221,0.0003802624,0.000046816247,0.00023396431,0.00025012103,0.00006669248],"domain_scores_gemma":[0.99939156,0.00023974542,0.000034714645,0.00013672363,0.00017165135,0.00002555809],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000914791,0.0010583915,0.0010154088,0.0007152215,0.00043511137,0.0009027064,0.0008956591,0.0006008152,0.0031969792],"category_scores_gemma":[0.002110029,0.0004283795,0.0011589961,0.00093513494,0.00031951995,0.0016068592,0.0009907188,0.0015816672,0.003416391],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030876277,0.00013918168,0.0010997528,0.00013466121,0.00026574844,0.00011855127,0.00022439823,0.3819588,0.03483895,0.015312813,0.005258772,0.5603396],"study_design_scores_gemma":[0.000005460306,0.000021743732,0.00019338087,0.0000056399513,0.000016599615,0.000043596112,0.000016482489,0.98628587,0.004917082,0.0063887457,0.002088604,0.000016711167],"about_ca_topic_score_codex":0.0061872257,"about_ca_topic_score_gemma":0.010946781,"teacher_disagreement_score":0.0061872257,"about_ca_system_score_codex":0.00053347874,"about_ca_system_score_gemma":0.00072698307,"threshold_uncertainty_score":0.012302458},"labels":[],"label_agreement":null},{"id":"W2125226720","doi":"10.1109/asru.2009.5373248","title":"Discriminative training of n-gram language models for speech recognition via linear programming","year":2009,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Discriminative model; Computer science; Speech recognition; Word error rate; Viterbi algorithm; Artificial intelligence; n-gram; Vocabulary; Language model; Metric (unit); Pattern recognition (psychology); Viterbi decoder; Hidden Markov model; Decoding methods; Algorithm","score_opus":0.0839183369757153,"score_gpt":0.30859773701399074,"score_spread":0.22467940003827544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125226720","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002610827,0.000103212005,0.99608046,0.000053767,0.000010903777,0.000013877182,0.000021470863,0.0008387437,0.0002667864],"genre_scores_gemma":[0.1728109,0.00028486244,0.8218299,0.00021227098,0.00007781559,0.0002678601,0.0006222617,0.00046243402,0.003431579],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991341,0.00035625405,0.000040489107,0.00022818008,0.00017484883,0.00006610337],"domain_scores_gemma":[0.9983463,0.0011709505,0.00011698494,0.0001558438,0.00016085,0.000049022805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011046045,0.0012999814,0.0010879786,0.00048662795,0.0004851706,0.0006610577,0.0017368202,0.00090143253,0.0027977778],"category_scores_gemma":[0.004908013,0.00083772955,0.0007247736,0.0007587615,0.00064140296,0.0014006196,0.0013142932,0.0024775725,0.0020450456],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019491995,0.00013936465,0.0004398634,0.000139345,0.000064577864,0.00009900037,0.00010388357,0.4211625,0.014146518,0.010722053,0.0032247452,0.5495633],"study_design_scores_gemma":[0.000005651324,0.000024601737,0.000060064787,0.0000035467015,0.0000045198217,0.00002132336,0.0000059798754,0.9944066,0.001977139,0.0029635853,0.00052155665,0.000005499524],"about_ca_topic_score_codex":0.004193316,"about_ca_topic_score_gemma":0.0074557513,"teacher_disagreement_score":0.004193316,"about_ca_system_score_codex":0.00071143237,"about_ca_system_score_gemma":0.0010017772,"threshold_uncertainty_score":0.009359539},"labels":[],"label_agreement":null},{"id":"W2125964738","doi":"10.1109/icassp.2011.5947401","title":"Large vocabulary continuous speech recognition with context-dependent DBN-HMMS","year":2011,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":182,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Hidden Markov model; Computer science; Speech recognition; Word error rate; Mixture model; Artificial intelligence; Context (archaeology); Vocabulary; Phone; Pattern recognition (psychology); Sentence","score_opus":0.038738701807049386,"score_gpt":0.21732816535304594,"score_spread":0.17858946354599656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125964738","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054224335,0.0014217334,0.931773,0.00019495262,0.00019107253,0.000064467946,0.0009603416,0.008815613,0.0023543793],"genre_scores_gemma":[0.5825779,0.00065671356,0.4079395,0.00024807546,0.00010046688,0.0001695161,0.003026702,0.00031420446,0.0049670693],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999471,0.00012152943,0.000036390327,0.00020419229,0.0001263782,0.000040555402],"domain_scores_gemma":[0.9992557,0.0003143018,0.000041882457,0.0001583627,0.0001925434,0.000037163525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007801307,0.0006699357,0.0006722596,0.00042684277,0.00028335012,0.0006114172,0.0010480408,0.0006916414,0.0026151154],"category_scores_gemma":[0.0021249813,0.00043686252,0.00047843016,0.0004892323,0.00025524868,0.0012087558,0.0008559671,0.0011470688,0.0020229926],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005226141,0.00025076818,0.0019452976,0.00023410798,0.00019805676,0.00018868654,0.00015292941,0.09592252,0.09592044,0.0029083143,0.007149784,0.79460657],"study_design_scores_gemma":[0.000022187163,0.000060274393,0.0014140925,0.000014696124,0.00003764695,0.000096874894,0.000030363268,0.9710551,0.023162602,0.0019816272,0.002100313,0.000024161835],"about_ca_topic_score_codex":0.007610193,"about_ca_topic_score_gemma":0.015817078,"teacher_disagreement_score":0.007610193,"about_ca_system_score_codex":0.00040302586,"about_ca_system_score_gemma":0.00059656275,"threshold_uncertainty_score":0.015131831},"labels":[],"label_agreement":null},{"id":"W2126853534","doi":"10.1109/icalip.2008.4590005","title":"Comparison of frame margin probability training to other discriminative methods for multi-condition speech recognition","year":2008,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Discriminative model; Margin (machine learning); Computer science; Speech recognition; Pattern recognition (psychology); Frame (networking); Interpolation (computer graphics); Artificial intelligence; Maximum likelihood; Linear interpolation; Machine learning; Mathematics; Statistics","score_opus":0.40090993485312554,"score_gpt":0.46378618075651784,"score_spread":0.0628762459033923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126853534","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061217923,0.001611818,0.930123,0.00019611913,0.00013558396,0.00012205332,0.00013916414,0.0028491563,0.003605252],"genre_scores_gemma":[0.5112123,0.0008613972,0.48182112,0.0002109031,0.00013491017,0.00014184543,0.0008351098,0.00045145242,0.0043310532],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980683,0.0006243892,0.00012524286,0.0004378492,0.0006328459,0.00011142476],"domain_scores_gemma":[0.99525404,0.0030259104,0.00017075741,0.000720912,0.0006699499,0.00015839555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002609054,0.00090595044,0.0010953017,0.0011575111,0.00042921465,0.0007176114,0.001373174,0.000973623,0.0034496202],"category_scores_gemma":[0.010691125,0.0004097803,0.00045196782,0.0010818596,0.00049117376,0.0018921413,0.0010441964,0.001111009,0.0011259747],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00081057905,0.00025059757,0.002282816,0.00016740154,0.000099757664,0.00009133715,0.00006299899,0.048490208,0.016051019,0.0014619045,0.0013217193,0.92890966],"study_design_scores_gemma":[0.00005543441,0.00030761072,0.0054662046,0.000024458166,0.000069047754,0.00052618637,0.000040414172,0.95027375,0.039517015,0.0011016651,0.0025747002,0.000043502547],"about_ca_topic_score_codex":0.0028287664,"about_ca_topic_score_gemma":0.0034355791,"teacher_disagreement_score":0.0034496202,"about_ca_system_score_codex":0.00044494178,"about_ca_system_score_gemma":0.0006121312,"threshold_uncertainty_score":0.013798177},"labels":[],"label_agreement":null},{"id":"W2128176957","doi":"10.1109/icassp.1982.1171437","title":"A composite scheme for text-independent speaker recognition","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Speech recognition; Speaker recognition; Computer science; Cepstrum; Mel-frequency cepstrum; Inverse filter; Filter (signal processing); Pattern recognition (psychology); Feature (linguistics); Scheme (mathematics); Feature extraction; Linear prediction; Population; Inverse; Artificial intelligence; Mathematics","score_opus":0.037567609274671517,"score_gpt":0.2611128798612824,"score_spread":0.2235452705866109,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128176957","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0088996785,0.00017668195,0.98642564,0.000048871385,0.00009981159,0.00022452211,0.00008455113,0.0023600936,0.0016801849],"genre_scores_gemma":[0.06943673,0.00010724811,0.92417437,0.00007158922,0.000111304485,0.00032545126,0.00029399336,0.00016969172,0.005309534],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9975083,0.00045369173,0.00019325934,0.0006415697,0.001073726,0.00012935653],"domain_scores_gemma":[0.9964561,0.00073844776,0.00017501225,0.0012834043,0.0011462286,0.0002009279],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028180652,0.000663964,0.0009531599,0.00097407907,0.000712859,0.0009938229,0.0018823633,0.0009469836,0.008362213],"category_scores_gemma":[0.0051115947,0.00037037546,0.00055021263,0.0006232422,0.0005345015,0.0014027234,0.0016429472,0.0013788785,0.00765783],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001761561,0.00019189055,0.0007640038,0.00019594732,0.00006569093,0.00011235109,0.0002662536,0.004831527,0.19110751,0.011287379,0.0035474594,0.78586835],"study_design_scores_gemma":[0.00025326316,0.0022964617,0.0042624352,0.000085666994,0.00022924451,0.0019975184,0.000108912995,0.5125397,0.39023414,0.018014729,0.069706574,0.00027147468],"about_ca_topic_score_codex":0.00039929227,"about_ca_topic_score_gemma":0.00072490104,"teacher_disagreement_score":0.008362213,"about_ca_system_score_codex":0.00030941173,"about_ca_system_score_gemma":0.00057030894,"threshold_uncertainty_score":0.027974367},"labels":[],"label_agreement":null},{"id":"W2129269533","doi":"","title":"VARIABLE PRE-EMPHASIS LPC FOR MODELING VOCAL EFFORT IN THE SINGING VOICE","year":2006,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Formant; Spectral envelope; Speech recognition; Computer science; Envelope (radar); Singing; Phonation; Filter (signal processing); Linear predictive coding; Voice analysis; Breathy voice; Acoustics; Speech processing; Vowel; Telecommunications; Audiology; Physics","score_opus":0.023448755611974098,"score_gpt":0.2564090423091711,"score_spread":0.232960286697197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129269533","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011155248,0.00056029577,0.9853349,0.00009142095,0.00007500278,0.000055110257,0.00012832241,0.00095043756,0.00164937],"genre_scores_gemma":[0.3137877,0.0010981909,0.6787866,0.00008748885,0.00009341818,0.00021797344,0.00055491884,0.00043303616,0.004940712],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997008,0.00009852497,0.000011920106,0.000056306195,0.00011357536,0.000018919554],"domain_scores_gemma":[0.9994019,0.00031971186,0.00004034353,0.00006411065,0.00016199984,0.000011884425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006246295,0.000795493,0.00028406936,0.0005416852,0.00036459023,0.0004801359,0.0007902559,0.00093089737,0.0023582221],"category_scores_gemma":[0.0020296413,0.00023053527,0.00035018343,0.0009573596,0.0003312657,0.00041109262,0.00023828098,0.0009522394,0.0012024748],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035575012,0.000096191194,0.001849019,0.00035282804,0.00006610814,0.0003536323,0.0001888128,0.38918027,0.07156781,0.01244956,0.0051497603,0.5183903],"study_design_scores_gemma":[0.0000058705396,0.000043413707,0.00078541297,0.000016686794,0.000017762779,0.00006499077,0.000007537649,0.9879885,0.007229008,0.0009812847,0.0028444293,0.00001510302],"about_ca_topic_score_codex":0.0072987033,"about_ca_topic_score_gemma":0.007497764,"teacher_disagreement_score":0.0072987033,"about_ca_system_score_codex":0.00044822993,"about_ca_system_score_gemma":0.00053719117,"threshold_uncertainty_score":0.014512479},"labels":[],"label_agreement":null},{"id":"W2130509597","doi":"10.1109/tasl.2007.894523","title":"Environmental Independent ASR Model Adaptation/Compensation by Bayesian Parametric Representation","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Hidden Markov model; Normalization (sociology); Speech recognition; Adaptation (eye); Parametric statistics; Maximization; Parametric model; Bayesian probability; Artificial intelligence; Mathematics","score_opus":0.018098051288397823,"score_gpt":0.25645668791932236,"score_spread":0.23835863663092455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130509597","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008054406,0.00012354064,0.9904323,0.000040271818,0.000019752162,0.00001865697,0.000017964458,0.0007296257,0.00056348933],"genre_scores_gemma":[0.48662856,0.0006574981,0.50678635,0.00018127574,0.00007678642,0.00019673769,0.00043974983,0.0004652757,0.0045677368],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981927,0.00057146634,0.00006582993,0.00031224903,0.00075431896,0.00010346847],"domain_scores_gemma":[0.99925905,0.0002250306,0.00011002923,0.00018612544,0.00020261844,0.000017103555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011077521,0.0010638984,0.000773183,0.00040725834,0.00026167935,0.0005470648,0.0014647571,0.0009668257,0.0010662581],"category_scores_gemma":[0.0032115027,0.00051196624,0.00072209595,0.00050120364,0.00047337284,0.0013097922,0.00084511336,0.0010275117,0.0011418103],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003037011,0.00015852455,0.0010570938,0.00015023281,0.0001285643,0.00015890157,0.00016919535,0.3359988,0.12935156,0.0061022923,0.001706076,0.524715],"study_design_scores_gemma":[0.000015982525,0.000079081336,0.0008896481,0.000009137216,0.000035777262,0.00018816104,0.000021763552,0.9547396,0.039504964,0.001601194,0.0028710235,0.00004368498],"about_ca_topic_score_codex":0.0019221379,"about_ca_topic_score_gemma":0.0022592226,"teacher_disagreement_score":0.0019221379,"about_ca_system_score_codex":0.00030184723,"about_ca_system_score_gemma":0.00059478736,"threshold_uncertainty_score":0.0058584213},"labels":[],"label_agreement":null},{"id":"W2131525232","doi":"10.1109/asru.2005.1566525","title":"A constrained joint optimization method for large margin HMM estimation","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Minimax; Margin (machine learning); Hidden Markov model; Computer science; Mathematical optimization; Optimization problem; Algorithm; Mathematics; Artificial intelligence; Machine learning","score_opus":0.03204761856645677,"score_gpt":0.29603580166454196,"score_spread":0.2639881830980852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131525232","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003315069,0.00004381518,0.9993192,0.00001917988,0.0000074421146,0.000006254183,0.000005106833,0.00008730741,0.00018017358],"genre_scores_gemma":[0.09283586,0.00022117521,0.9034817,0.00012381155,0.00007039073,0.0002712168,0.00014945382,0.000291663,0.0025547429],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893254,0.00048008232,0.0000506102,0.00021884477,0.00027453422,0.000043489308],"domain_scores_gemma":[0.99878806,0.00081260374,0.00008440045,0.000123517,0.00016270505,0.00002865562],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015458359,0.0010101089,0.0010888163,0.000511865,0.00042134186,0.0007041519,0.0012474641,0.0010818574,0.0035358558],"category_scores_gemma":[0.004339466,0.0006936352,0.0007031233,0.0005975358,0.0007493793,0.0015335607,0.0013444057,0.0016596462,0.0011156221],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013096193,0.000074147974,0.0004145241,0.00021460748,0.00011219814,0.000090403424,0.00012936756,0.6573347,0.012216823,0.047478743,0.0039631156,0.2778405],"study_design_scores_gemma":[0.0000074674194,0.000014887507,0.00006572361,0.0000070038286,0.0000055538844,0.000021778622,0.000003781674,0.9920176,0.0013303461,0.0052233734,0.0012931568,0.0000094640955],"about_ca_topic_score_codex":0.0014951441,"about_ca_topic_score_gemma":0.0014757758,"teacher_disagreement_score":0.0035358558,"about_ca_system_score_codex":0.00043704893,"about_ca_system_score_gemma":0.00092303863,"threshold_uncertainty_score":0.011828661},"labels":[],"label_agreement":null},{"id":"W2131706900","doi":"10.1109/pacrim.2001.953719","title":"Pitch-excited ARMA lattice model for speech synthesis","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Vocal tract; Speech synthesis; Computer science; Speech recognition; Autoregressive–moving-average model; Lattice (music); Representation (politics); Pole–zero plot; Speech production; Speech processing; Autoregressive model; Acoustics; Transfer function; Mathematics; Physics; Engineering","score_opus":0.07871584020366355,"score_gpt":0.257007547745181,"score_spread":0.1782917075415174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131706900","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024009976,0.00034126095,0.9924833,0.000081049315,0.00007877535,0.000021901007,0.00006596524,0.00044284205,0.004083878],"genre_scores_gemma":[0.50200385,0.0015186629,0.46595109,0.0002297544,0.0002038569,0.00057365,0.00055198086,0.00029955793,0.028667662],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997483,0.000077038756,0.000014451911,0.000043145104,0.00009789835,0.000019255722],"domain_scores_gemma":[0.9998342,0.0000665001,0.000019176556,0.000019600708,0.000047435824,0.000013014147],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003245785,0.0006653271,0.00065450347,0.00025523678,0.00034503176,0.0007822094,0.0009668542,0.0009435963,0.0045562824],"category_scores_gemma":[0.0006475334,0.0003039652,0.00073023816,0.00034372113,0.00032994253,0.0006255729,0.0005224877,0.0011870482,0.0031993387],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013037816,0.000058962414,0.00016284561,0.00017431674,0.000053317803,0.00016645828,0.00009113223,0.83273345,0.033798885,0.050132103,0.0022129372,0.08028514],"study_design_scores_gemma":[0.0000057394823,0.00001856872,0.000016740889,0.0000049024784,0.000005203628,0.000020290969,0.0000028305424,0.9930448,0.0009848394,0.003852147,0.0020362404,0.000007632938],"about_ca_topic_score_codex":0.001931005,"about_ca_topic_score_gemma":0.0019075595,"teacher_disagreement_score":0.0045562824,"about_ca_system_score_codex":0.00043979136,"about_ca_system_score_gemma":0.0005353752,"threshold_uncertainty_score":0.015242219},"labels":[],"label_agreement":null},{"id":"W2132037657","doi":"10.1109/icassp.2011.5947700","title":"Learning a better representation of speech soundwaves using restricted boltzmann machines","year":2011,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":229,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Cepstrum; Speech recognition; Computer science; Mel-frequency cepstrum; Linear predictive coding; Boltzmann machine; Restricted Boltzmann machine; Representation (politics); Artificial intelligence; Speech coding; Pattern recognition (psychology); Artificial neural network; Feature extraction","score_opus":0.07598615674813156,"score_gpt":0.2849837548539779,"score_spread":0.20899759810584637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132037657","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04029168,0.00020200408,0.95814836,0.00026510426,0.00004375783,0.000022541062,0.000055237277,0.0004590312,0.0005121914],"genre_scores_gemma":[0.7289907,0.00034380524,0.26653183,0.00026025777,0.00007845676,0.00018085928,0.0002836749,0.00017580495,0.0031546855],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996507,0.00015260493,0.000022892693,0.000089022666,0.00005119025,0.00003354511],"domain_scores_gemma":[0.99922204,0.0004759167,0.00005761803,0.00012677387,0.00008960974,0.000028075508],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089400087,0.0005685542,0.0010371068,0.00029445617,0.00020584228,0.0008745331,0.000932127,0.0010568242,0.0015060367],"category_scores_gemma":[0.003733619,0.0005379779,0.00087427895,0.0003112698,0.0005227129,0.0020746617,0.00066839234,0.0014863195,0.00061354117],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000977109,0.00007390131,0.0007083044,0.000076476885,0.00007514495,0.000058624388,0.00008421391,0.90893686,0.014572942,0.013071124,0.00075503445,0.061489664],"study_design_scores_gemma":[0.000004070934,0.00000823611,0.000040521194,0.0000018652072,0.000002651707,0.000005100698,0.0000027017543,0.99631643,0.0005059255,0.0030239394,0.00008406675,0.0000044352755],"about_ca_topic_score_codex":0.0016333488,"about_ca_topic_score_gemma":0.0019886778,"teacher_disagreement_score":0.0016333488,"about_ca_system_score_codex":0.0004668699,"about_ca_system_score_gemma":0.0004740619,"threshold_uncertainty_score":0.005038202},"labels":[],"label_agreement":null},{"id":"W2135433537","doi":"10.1109/89.928919","title":"A maximum a posteriori approach to speaker adaptation using the trended hidden Markov model","year":2001,"lang":"en","type":"article","venue":"IEEE Transactions on Speech and Audio Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Hidden Markov model; Maximum a posteriori estimation; Polynomial; Computer science; Speech recognition; Adaptation (eye); Security token; A priori and a posteriori; Gaussian; Pattern recognition (psychology); Mathematics; Algorithm; Artificial intelligence; Statistics; Maximum likelihood","score_opus":0.05320708971129079,"score_gpt":0.2664378542114752,"score_spread":0.2132307645001844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135433537","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017952505,0.00007611202,0.9975604,0.000032405624,0.000012419389,0.000013621066,0.000022273058,0.00024645063,0.000241023],"genre_scores_gemma":[0.12157443,0.00044514058,0.8738481,0.00008404018,0.000112339316,0.0002177667,0.0003144291,0.00026678867,0.0031370774],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991116,0.00037455797,0.000043666638,0.00021390778,0.00021036302,0.000045847642],"domain_scores_gemma":[0.99854904,0.0009732594,0.0000692964,0.00014755146,0.00023882044,0.000022109354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001832936,0.00082522415,0.0007835683,0.0006302447,0.0004692294,0.0006953855,0.0011948369,0.0009646951,0.0017788529],"category_scores_gemma":[0.0053097066,0.0007137236,0.0011845253,0.0006449051,0.00048532026,0.0010826988,0.0009029773,0.0018183213,0.001095833],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002645403,0.00008555743,0.00085790013,0.00019237523,0.00028357303,0.00017030958,0.00028817632,0.5486665,0.02383363,0.019499479,0.002393232,0.40346482],"study_design_scores_gemma":[0.000007903114,0.000039630522,0.000298491,0.000008579917,0.000025467878,0.000050061284,0.000012846285,0.986062,0.0032990212,0.008931574,0.0012445427,0.00001992438],"about_ca_topic_score_codex":0.003462002,"about_ca_topic_score_gemma":0.0041118856,"teacher_disagreement_score":0.003462002,"about_ca_system_score_codex":0.00039859972,"about_ca_system_score_gemma":0.0009808929,"threshold_uncertainty_score":0.009693563},"labels":[],"label_agreement":null},{"id":"W2135474356","doi":"10.1109/icassp.2002.5743869","title":"Auditory-based acoustic distinctive features and spectral cues for automatic speech recognition using a multi-stream paradigm","year":2002,"lang":"en","type":"article","venue":"IEEE International Conference on Acoustics Speech and Signal Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Speech recognition; Bigram; Hidden Markov model; TIMIT; Word error rate; Artificial intelligence; Feature extraction; Pattern recognition (psychology)","score_opus":0.09560722869828778,"score_gpt":0.3126416919736763,"score_spread":0.21703446327538853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135474356","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036383267,0.001239535,0.96014243,0.00018827342,0.00016721638,0.00008365641,0.000073751995,0.00067572005,0.0010461829],"genre_scores_gemma":[0.2615249,0.0014569641,0.7338485,0.00017219808,0.00026663314,0.00017523054,0.00027987984,0.00011616899,0.0021594947],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996817,0.00010007202,0.000026727248,0.00006692217,0.000107327214,0.000017288958],"domain_scores_gemma":[0.9995018,0.00020962073,0.00002951367,0.000082689665,0.00014757145,0.000028676237],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006648242,0.0003961456,0.0005209722,0.00049967814,0.00020376573,0.0005796228,0.00050210167,0.0005934742,0.0020100982],"category_scores_gemma":[0.0011466492,0.00019321428,0.00047561756,0.00043597975,0.00033708182,0.0012632477,0.00039418216,0.00063404813,0.0010699257],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042958456,0.00019318322,0.00064307696,0.00046536888,0.000061023442,0.00022656121,0.00012460529,0.010755825,0.4202891,0.00621764,0.0013014431,0.5592926],"study_design_scores_gemma":[0.00012252823,0.0012994759,0.0046804496,0.0000961372,0.00025704585,0.0017104828,0.00012889667,0.72542995,0.23615207,0.010125325,0.01985999,0.00013759217],"about_ca_topic_score_codex":0.00036432146,"about_ca_topic_score_gemma":0.00095430197,"teacher_disagreement_score":0.0020100982,"about_ca_system_score_codex":0.00012958054,"about_ca_system_score_gemma":0.000379754,"threshold_uncertainty_score":0.006724477},"labels":[],"label_agreement":null},{"id":"W2136652457","doi":"10.1109/icassp.2004.1326116","title":"A Viterbi algorithm for a trajectory model derived from HMM with explicit relationship between static and dynamic features","year":2004,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Pratt and Whitney Canada","keywords":"Viterbi algorithm; Hidden Markov model; Soft output Viterbi algorithm; Forward algorithm; Computer science; Iterative Viterbi decoding; Trajectory; Speech recognition; Sequence (biology); Algorithm; State (computer science); Pattern recognition (psychology); Artificial intelligence; Markov model; Machine learning; Markov chain; Decoding methods; Variable-order Markov model","score_opus":0.03367362737486818,"score_gpt":0.2606226382829699,"score_spread":0.2269490109081017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136652457","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010269496,0.00013491983,0.99757665,0.00006107794,0.00003369633,0.000022927983,0.000073167816,0.0005321991,0.0005385082],"genre_scores_gemma":[0.06235536,0.00045573272,0.9306489,0.00009907441,0.000053933672,0.00020422468,0.0009068934,0.00034483644,0.004931024],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995363,0.00009584022,0.000030035222,0.00019081621,0.00010793327,0.000039144445],"domain_scores_gemma":[0.99963677,0.00016675463,0.000030279956,0.00004902269,0.000104687504,0.000012389263],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007297498,0.00065584225,0.00076079316,0.00064864516,0.00064759416,0.0005919749,0.001218144,0.0011410508,0.0045665842],"category_scores_gemma":[0.002914877,0.0007586205,0.000608766,0.00087767193,0.0003931513,0.0013237358,0.0007217292,0.0021172834,0.0027084192],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002307599,0.00008246537,0.0010037059,0.00036804937,0.00014329507,0.00014638827,0.0002543336,0.31197286,0.03151508,0.08552112,0.009558111,0.55920386],"study_design_scores_gemma":[0.000014013895,0.000032882897,0.00026582507,0.000020455032,0.000019690293,0.000095432086,0.000013526632,0.97222316,0.0062263403,0.013118904,0.007947978,0.000021705291],"about_ca_topic_score_codex":0.010558128,"about_ca_topic_score_gemma":0.009498674,"teacher_disagreement_score":0.010558128,"about_ca_system_score_codex":0.00093094655,"about_ca_system_score_gemma":0.0016980682,"threshold_uncertainty_score":0.020993352},"labels":[],"label_agreement":null},{"id":"W2136836257","doi":"10.1109/89.979381","title":"A robust compensation strategy for extraneous acoustic variations in spontaneous speech recognition","year":2002,"lang":"en","type":"article","venue":"IEEE Transactions on Speech and Audio Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Hidden Markov model; Speech recognition; Computer science; Word error rate; Pattern recognition (psychology); Pronunciation; Bayesian probability; Artificial intelligence","score_opus":0.07417596438202625,"score_gpt":0.2557498206924044,"score_spread":0.18157385631037812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136836257","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02829794,0.000222077,0.9698738,0.00005421996,0.00004176222,0.00003644418,0.000046987814,0.0010216312,0.00040522622],"genre_scores_gemma":[0.47212312,0.00029438292,0.52360886,0.0001648824,0.00008954896,0.0002146589,0.00048849825,0.00019485917,0.002821241],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993579,0.00012852876,0.000046691195,0.00016814578,0.0002495802,0.000049187176],"domain_scores_gemma":[0.999342,0.0001654252,0.000092217284,0.00017236295,0.00019410028,0.00003385319],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062812126,0.0007484098,0.0006161236,0.0002981406,0.00021130533,0.0003997089,0.0009519604,0.0006276482,0.0009952143],"category_scores_gemma":[0.0020170875,0.00028591402,0.0003636464,0.00026058836,0.000331465,0.0006888742,0.00053277693,0.0005069792,0.0008416689],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030059216,0.00015763464,0.0009156337,0.0001176882,0.00008503897,0.0002106334,0.00012162557,0.030743632,0.3855463,0.0023944415,0.0014215958,0.5779852],"study_design_scores_gemma":[0.00005522085,0.0004662129,0.004329623,0.000014672537,0.00008455502,0.0011128393,0.000049068567,0.75903577,0.22741462,0.0021390002,0.005210404,0.00008802263],"about_ca_topic_score_codex":0.0010156455,"about_ca_topic_score_gemma":0.0013481709,"teacher_disagreement_score":0.0010156455,"about_ca_system_score_codex":0.00015328327,"about_ca_system_score_gemma":0.00043741113,"threshold_uncertainty_score":0.0033293366},"labels":[],"label_agreement":null},{"id":"W2136879537","doi":"10.1109/tasl.2008.925147","title":"A Study of Interspeaker Variability in Speaker Verification","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":591,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"NIST; Hyperparameter; Channel (broadcasting); Computer science; Word error rate; Task (project management); Joint (building); Speech recognition; Statistics; Function (biology); Error analysis; Pattern recognition (psychology); Artificial intelligence; Mathematics; Engineering; Applied mathematics","score_opus":0.02538206399158666,"score_gpt":0.2646189760404997,"score_spread":0.23923691204891306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136879537","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34020296,0.0010393449,0.65707743,0.000116687814,0.000020677036,0.000026996453,0.000062633015,0.00029628986,0.00115698],"genre_scores_gemma":[0.94543123,0.00021512216,0.05337868,0.000028676279,0.00003387855,0.000019857474,0.00018420881,0.000077553814,0.00063080573],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.996472,0.0018804625,0.000118824864,0.00063068274,0.0007826362,0.00011552761],"domain_scores_gemma":[0.9732256,0.023330767,0.0008104208,0.0014340298,0.0010571356,0.00014202665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0054822997,0.00041546865,0.0006011832,0.00044123107,0.0003061552,0.000638011,0.0006007081,0.0006918638,0.0007250534],"category_scores_gemma":[0.023874212,0.0002645716,0.00034394077,0.00053537346,0.0005702113,0.0014352212,0.00067679706,0.00087111496,0.00018444605],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013596399,0.0002005469,0.028623555,0.0003395361,0.0005164976,0.0005300751,0.0012939844,0.40703055,0.12003325,0.016274642,0.0012383499,0.42255938],"study_design_scores_gemma":[0.000009915346,0.00022521193,0.017096482,0.000017374332,0.000040180294,0.00045494823,0.00006745176,0.9520519,0.026128052,0.0030754786,0.00079674786,0.000036270456],"about_ca_topic_score_codex":0.001822116,"about_ca_topic_score_gemma":0.0015544603,"teacher_disagreement_score":0.0054822997,"about_ca_system_score_codex":0.00031392518,"about_ca_system_score_gemma":0.00034162693,"threshold_uncertainty_score":0.028993547},"labels":[],"label_agreement":null},{"id":"W2137137149","doi":"10.1109/icassp.1984.1172800","title":"Modelling of the laryngeal acoustic source by labile nonlinear oscillators","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Phonation; Nonlinear system; Speech production; Dynamics (music); Acoustics; Computer science; Speech recognition; Physics; Audiology; Quantum mechanics","score_opus":0.017951610414642265,"score_gpt":0.2089034662436795,"score_spread":0.19095185582903723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137137149","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035147198,0.00017212136,0.9612753,0.000106351,0.000025247738,0.00003214833,0.000053549877,0.00018770824,0.0030003546],"genre_scores_gemma":[0.9071784,0.00063950155,0.08389284,0.00003810996,0.00005146899,0.00018655139,0.00010397121,0.00008620304,0.007822954],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999268,0.000021541648,0.0000045445354,0.000013850226,0.000027278136,0.000005966437],"domain_scores_gemma":[0.9998802,0.00005937401,0.000022433014,0.000013793232,0.000016648193,0.0000075216326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018870873,0.00041708213,0.00026741804,0.00017635156,0.00013368235,0.00042450163,0.00059554126,0.0005916672,0.0010588111],"category_scores_gemma":[0.0006289033,0.0002747927,0.00030515977,0.000098292294,0.00030430793,0.0005858503,0.00040606392,0.00045516467,0.00039691408],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010458749,0.000025701815,0.0010573535,0.00016422021,0.000036353515,0.00030825534,0.00031882664,0.8205826,0.10695049,0.029995829,0.00049602654,0.039959595],"study_design_scores_gemma":[0.000003703727,0.000019089923,0.00013556077,0.000003958605,0.0000034878842,0.00003904355,0.000006809741,0.99492633,0.0021900162,0.001974062,0.0006915145,0.0000064960473],"about_ca_topic_score_codex":0.00069144764,"about_ca_topic_score_gemma":0.0008647108,"teacher_disagreement_score":0.0010588111,"about_ca_system_score_codex":0.00015896025,"about_ca_system_score_gemma":0.00024066376,"threshold_uncertainty_score":0.0035421252},"labels":[],"label_agreement":null},{"id":"W2137587425","doi":"10.1109/asru.2001.1034628","title":"Out-of-vocabulary word modeling using multiple lexical fillers","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Vocabulary; Word error rate; Computer science; Word (group theory); Natural language processing; Task (project management); Speech recognition; Artificial intelligence; Linguistics; Engineering","score_opus":0.09530444043216925,"score_gpt":0.28768958386833093,"score_spread":0.1923851434361617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137587425","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06386911,0.0002990898,0.93080866,0.0000810797,0.00007989876,0.00007577067,0.00020775573,0.0035600725,0.0010186096],"genre_scores_gemma":[0.5749273,0.00031416866,0.41788042,0.00013608622,0.000068000845,0.00025911714,0.001549389,0.00095766195,0.0039078626],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994326,0.00018520508,0.000043512988,0.0001878753,0.000113559734,0.000037299644],"domain_scores_gemma":[0.9982272,0.0010518457,0.00009546501,0.0003329058,0.0002481472,0.000044534107],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068902655,0.0009176426,0.0008017558,0.0009524585,0.0005036382,0.0007359939,0.0011701253,0.00084584847,0.0019213815],"category_scores_gemma":[0.0032657785,0.00054916163,0.0010269715,0.0007179302,0.0005885619,0.0021500946,0.0006885572,0.001026063,0.0013374379],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007446318,0.00036771796,0.0030042995,0.0003226366,0.00018502466,0.000697232,0.00064681313,0.28258404,0.09284187,0.012864969,0.0043094773,0.6014313],"study_design_scores_gemma":[0.000015769914,0.00008766768,0.00049222837,0.000008969878,0.000032543197,0.00013527118,0.000043863467,0.9734341,0.015926687,0.007979326,0.0018164509,0.000027202583],"about_ca_topic_score_codex":0.0055356896,"about_ca_topic_score_gemma":0.008794114,"teacher_disagreement_score":0.0055356896,"about_ca_system_score_codex":0.00035710816,"about_ca_system_score_gemma":0.0007039359,"threshold_uncertainty_score":0.011006951},"labels":[],"label_agreement":null},{"id":"W2137743578","doi":"10.1109/34.845379","title":"Training hidden Markov models with multiple observations-a combinatorial method","year":2000,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":150,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; Université Laval; SNC-Lavalin (Canada)","funders":"Natural Sciences and Engineering Research Council of Canada; Guangxi University; East China Institute of Technology","keywords":"Hidden Markov model; Computer science; Artificial intelligence; Markov chain; Lagrange multiplier; Generality; Handwriting; Independence (probability theory); Machine learning; Function (biology); Maximization; Pattern recognition (psychology); Algorithm; Mathematics; Mathematical optimization; Statistics","score_opus":0.06005585691777636,"score_gpt":0.2821406138225669,"score_spread":0.22208475690479051,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137743578","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011256838,0.00006791747,0.9981633,0.00004881928,0.0000095015985,0.000011554917,0.000016929063,0.00009085086,0.00046549982],"genre_scores_gemma":[0.1695746,0.0005944196,0.8248267,0.00017489794,0.0001359559,0.0003662375,0.0003998993,0.00022015812,0.0037070836],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.99852115,0.0008071142,0.00007730305,0.00023389359,0.00026658678,0.000093931085],"domain_scores_gemma":[0.9948959,0.004256693,0.00021793527,0.0002743042,0.00028064635,0.00007452447],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025533014,0.0008974107,0.0012556028,0.0008685568,0.000397183,0.001058027,0.0020726505,0.001226868,0.0038409412],"category_scores_gemma":[0.008834982,0.0012002238,0.0012190093,0.0012857248,0.00087334233,0.0022384685,0.0017041658,0.0021019992,0.00087233935],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004020291,0.000049735667,0.00038542986,0.00010007607,0.00005290594,0.0000826396,0.00006786096,0.8498776,0.0008439886,0.06863876,0.0008896872,0.07897114],"study_design_scores_gemma":[0.0000061522787,0.000010043506,0.000035633002,0.000008704389,0.000007766403,0.000012595745,0.000003488957,0.9812428,0.00024526537,0.017902669,0.00051911833,0.000005743021],"about_ca_topic_score_codex":0.0018896358,"about_ca_topic_score_gemma":0.0028069413,"teacher_disagreement_score":0.0038409412,"about_ca_system_score_codex":0.00088935095,"about_ca_system_score_gemma":0.0013158777,"threshold_uncertainty_score":0.013503313},"labels":[],"label_agreement":null},{"id":"W2137997377","doi":"10.1109/icassp.2013.6639126","title":"Multiple windowed spectral features for emotion recognition","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Institut National de la Recherche Scientifique; Computer Research Institute of Montréal","funders":"","keywords":"Multitaper; Mel-frequency cepstrum; Speech recognition; Computer science; Pattern recognition (psychology); Mixture model; Dynamic time warping; Feature (linguistics); Set (abstract data type); Artificial intelligence; Cepstrum; Feature extraction","score_opus":0.028112341929656913,"score_gpt":0.2315257983846509,"score_spread":0.20341345645499398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137997377","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19073537,0.004816265,0.7953279,0.00021642333,0.00029610746,0.00015263645,0.0013145473,0.004006322,0.0031343799],"genre_scores_gemma":[0.60988414,0.0016663105,0.3817199,0.00006599634,0.00014631334,0.0001808223,0.0017981555,0.00029962743,0.0042388784],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999686,0.000067699686,0.000024502793,0.000085954634,0.000109197535,0.000026683658],"domain_scores_gemma":[0.9995534,0.00019332914,0.00003961535,0.00006582167,0.00013223781,0.000015613514],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045339638,0.0005252608,0.00049373484,0.0009194726,0.00014612165,0.00051405473,0.0003348821,0.00043314378,0.0035501232],"category_scores_gemma":[0.0011547634,0.00017872795,0.00042812905,0.0008536433,0.00011938095,0.00089193333,0.00034113385,0.00036326196,0.0013788424],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004516691,0.000094500254,0.00086887466,0.0001772429,0.00006461361,0.000102698476,0.000057677284,0.009884548,0.16972886,0.0010721387,0.0023122502,0.81518495],"study_design_scores_gemma":[0.000081561666,0.00066438963,0.023136469,0.00008405447,0.00023418842,0.0006945566,0.00016383779,0.7449187,0.20147869,0.004315915,0.02410487,0.00012279698],"about_ca_topic_score_codex":0.0008645641,"about_ca_topic_score_gemma":0.0011319768,"teacher_disagreement_score":0.0035501232,"about_ca_system_score_codex":0.00017902232,"about_ca_system_score_gemma":0.00016554398,"threshold_uncertainty_score":0.011876285},"labels":[],"label_agreement":null},{"id":"W2138632432","doi":"10.1109/icassp.2012.6289016","title":"Dealing with acoustic mismatch for training multilingual subspace Gaussian mixture models for speech recognition","year":2012,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Pronunciation; Subspace topology; Speech recognition; Acoustic model; Variation (astronomy); Mixture model; Similarity (geometry); Artificial intelligence; Gaussian; Speech corpus; Training set; Natural language processing; Language model; Hidden Markov model; Parametrization (atmospheric modeling); Speech processing; Speech synthesis; Linguistics","score_opus":0.09074219761707655,"score_gpt":0.2908651392679138,"score_spread":0.20012294165083724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138632432","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015951,0.00015826807,0.98293865,0.000050727835,0.000019877907,0.000025140784,0.000045950266,0.00058799353,0.00022244894],"genre_scores_gemma":[0.3622739,0.00029912998,0.6347181,0.00010087095,0.000059542024,0.00023335747,0.00084224634,0.0002896183,0.0011832208],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990332,0.00042452686,0.00005762978,0.00020751778,0.00021832294,0.000058782123],"domain_scores_gemma":[0.9988844,0.00060917623,0.00006313301,0.00018262239,0.00022197404,0.000038737242],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019452957,0.0010209987,0.000771652,0.0004890514,0.00043302387,0.0006413944,0.0009741571,0.0010336018,0.0015344664],"category_scores_gemma":[0.005888308,0.00045396676,0.00060560915,0.0008539679,0.0003484843,0.0010350425,0.0009961164,0.0013721375,0.0012079661],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038451128,0.00018414398,0.0026637877,0.00015741435,0.00014074205,0.00012398938,0.00038599726,0.39492258,0.0349189,0.0054953382,0.0017793762,0.55884326],"study_design_scores_gemma":[0.000009503299,0.00006439887,0.00054183014,0.000007762303,0.000019940519,0.00005916271,0.000036347243,0.98563784,0.009322561,0.002921458,0.0013592042,0.000020004516],"about_ca_topic_score_codex":0.0034718404,"about_ca_topic_score_gemma":0.005904194,"teacher_disagreement_score":0.0034718404,"about_ca_system_score_codex":0.0003491184,"about_ca_system_score_gemma":0.00076860486,"threshold_uncertainty_score":0.010287881},"labels":[],"label_agreement":null},{"id":"W2139753501","doi":"10.1109/ispa.2003.1296424","title":"Online identification of hidden Semi-Markov models","year":2004,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Hidden Markov model; Hidden semi-Markov model; Algorithm; Computer science; Forward algorithm; Estimation theory; SIGNAL (programming language); Maximum-entropy Markov model; Parametric model; Exponential function; Parametric statistics; Constant (computer programming); Exponential distribution; Markov model; Markov chain; State (computer science); Pattern recognition (psychology); Mathematics; Artificial intelligence; Variable-order Markov model; Statistics; Machine learning","score_opus":0.032438083842129754,"score_gpt":0.2582246811897791,"score_spread":0.22578659734764933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139753501","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011342809,0.00009031376,0.9876439,0.00004615658,0.000012895431,0.000012568797,0.00002866668,0.0003901017,0.0004326437],"genre_scores_gemma":[0.6355975,0.00027431257,0.36103526,0.00006574165,0.00003567943,0.00011443613,0.00034903674,0.00011753743,0.0024104663],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925345,0.00022759268,0.000049472237,0.00017186956,0.00022556174,0.00007203009],"domain_scores_gemma":[0.9963019,0.0027017049,0.00031142996,0.00029727767,0.00033107723,0.00005656782],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011550825,0.00054015085,0.00090027985,0.00052206335,0.000328202,0.0007112087,0.0011758461,0.000832221,0.0015012409],"category_scores_gemma":[0.00727419,0.00050151,0.00049654476,0.00041718033,0.00040442633,0.0013161133,0.00075850484,0.0014118166,0.0006363959],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014658176,0.000060022485,0.002098671,0.00010755677,0.00004816796,0.00017727127,0.00014980533,0.7981699,0.0076078298,0.0221902,0.00087155227,0.1683724],"study_design_scores_gemma":[0.0000022538095,0.0000048672023,0.00011200803,0.0000027162782,0.000002180739,0.000015587128,0.000003486932,0.9955165,0.0008313191,0.0033201966,0.0001850755,0.0000037705315],"about_ca_topic_score_codex":0.0035155837,"about_ca_topic_score_gemma":0.0038053489,"teacher_disagreement_score":0.0035155837,"about_ca_system_score_codex":0.000515676,"about_ca_system_score_gemma":0.0009329955,"threshold_uncertainty_score":0.0069901943},"labels":[],"label_agreement":null},{"id":"W2140046090","doi":"10.1109/icassp.2008.4518622","title":"Speaker diarization of French broadcast news","year":2008,"lang":"en","type":"article","venue":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Speaker diarisation; Computer science; Mel-frequency cepstrum; Cluster analysis; Speech recognition; Feature (linguistics); Test set; Word error rate; Set (abstract data type); Hierarchical clustering; Pattern recognition (psychology); Speaker recognition; Artificial intelligence; Segmentation; Feature extraction","score_opus":0.05214884939631418,"score_gpt":0.2664301578707716,"score_spread":0.21428130847445745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140046090","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90437716,0.0039562657,0.06497737,0.00030665396,0.00050469575,0.00037730348,0.0059487824,0.007906181,0.011645675],"genre_scores_gemma":[0.9093568,0.0009070985,0.050937027,0.00014133933,0.0002280924,0.0001593753,0.024573585,0.0006093978,0.013087356],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977126,0.0006956104,0.0001300751,0.0005820552,0.0005751061,0.00030455057],"domain_scores_gemma":[0.99669904,0.0011621444,0.00012553661,0.0002979361,0.001530887,0.0001842782],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024564397,0.001419349,0.0009699423,0.0027471308,0.0008668148,0.0008544376,0.0005403007,0.00059590576,0.0029110196],"category_scores_gemma":[0.0041409233,0.00017062319,0.0008912117,0.0012454487,0.00030597957,0.00047652042,0.00059358735,0.0005568808,0.0017453117],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032366393,0.00038566702,0.018934187,0.0008484105,0.0006388583,0.0006208992,0.001367217,0.0145741105,0.1384622,0.0004945425,0.011421909,0.80901533],"study_design_scores_gemma":[0.00040480404,0.0031069105,0.32855827,0.000086974054,0.0013615286,0.0026383703,0.0019795583,0.16219907,0.4451111,0.0006392823,0.05347812,0.00043603705],"about_ca_topic_score_codex":0.02408714,"about_ca_topic_score_gemma":0.02202058,"teacher_disagreement_score":0.02408714,"about_ca_system_score_codex":0.00082288217,"about_ca_system_score_gemma":0.00038035997,"threshold_uncertainty_score":0.04789388},"labels":[],"label_agreement":null},{"id":"W2141401351","doi":"10.1109/mmsp.2007.4412892","title":"Combining Vocal Source and MFCC Features for Enhanced Speaker Recognition Performance Using GMMs","year":2007,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Mel-frequency cepstrum; Speech recognition; Crest factor; Computer science; Cepstrum; Vocal tract; Mixture model; Pattern recognition (psychology); Artificial intelligence; Speaker recognition; Centroid; Feature extraction; Bandwidth (computing)","score_opus":0.039143575831901284,"score_gpt":0.2683018335022468,"score_spread":0.2291582576703455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141401351","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14233997,0.00217456,0.8439554,0.00019969934,0.00025135127,0.000089341054,0.00028724034,0.007593943,0.0031084619],"genre_scores_gemma":[0.6278091,0.00091976573,0.36675316,0.00009401978,0.00029116985,0.00010405274,0.00065360573,0.00039541002,0.0029796606],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99930525,0.00016852301,0.000037874182,0.00013901976,0.00027270167,0.00007662303],"domain_scores_gemma":[0.9993824,0.00023262893,0.00004299486,0.000059747585,0.00025681744,0.000025318897],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010943052,0.0010214297,0.00088333496,0.0015134268,0.00030098888,0.0006288871,0.00048842805,0.00054564135,0.0018814265],"category_scores_gemma":[0.0019373989,0.0003343382,0.0005460121,0.000607437,0.00022039338,0.0010435355,0.00057302346,0.0005111551,0.0016496056],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040130957,0.00012643768,0.0025018218,0.00017845814,0.00013513432,0.00010550198,0.00011430833,0.014279273,0.19807437,0.00087459,0.0023363119,0.7808724],"study_design_scores_gemma":[0.00006503174,0.0005956291,0.032114208,0.00007059263,0.00049253384,0.00109383,0.00015399084,0.67652124,0.26895374,0.002136556,0.017549139,0.0002534919],"about_ca_topic_score_codex":0.0019323952,"about_ca_topic_score_gemma":0.003740488,"teacher_disagreement_score":0.0019323952,"about_ca_system_score_codex":0.00025341572,"about_ca_system_score_gemma":0.00031085403,"threshold_uncertainty_score":0.0062939525},"labels":[],"label_agreement":null},{"id":"W2141778357","doi":"10.21437/interspeech.2010-304","title":"Investigation of full-sequence training of deep belief networks for speech recognition","year":2010,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":213,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Training (meteorology); Speech recognition; Sequence (biology); Artificial intelligence; Natural language processing","score_opus":0.08245940770069941,"score_gpt":0.2678514967899197,"score_spread":0.18539208908922028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141778357","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07590638,0.0013654953,0.91825145,0.00054091646,0.000032928638,0.000059707545,0.00004095839,0.00044016913,0.0033620668],"genre_scores_gemma":[0.7606762,0.0008768535,0.23565365,0.00016083835,0.00004367312,0.00012075613,0.00012351488,0.0000793568,0.0022650578],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99930084,0.00033621196,0.00003115105,0.00010217562,0.00017377459,0.000055868357],"domain_scores_gemma":[0.9963666,0.0027223795,0.000111189605,0.00023103399,0.0004962926,0.000072542316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034248533,0.0008575534,0.000715826,0.0003372819,0.00024347486,0.0006367402,0.0010681282,0.0010090638,0.0017281413],"category_scores_gemma":[0.0111438045,0.0007569243,0.00032807438,0.00039165103,0.0005965377,0.0022943004,0.00086665957,0.0015415055,0.00024091305],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015409102,0.00012964706,0.00096726057,0.000092712646,0.000044771892,0.00004481435,0.00006575132,0.84460455,0.005295548,0.014464651,0.00041899463,0.1337172],"study_design_scores_gemma":[0.00000259554,0.000020519245,0.000044542634,0.0000030632202,0.00000189997,0.0000050846857,0.0000024481399,0.9981186,0.00075895846,0.00095588766,0.00008505267,0.0000013002146],"about_ca_topic_score_codex":0.0043262057,"about_ca_topic_score_gemma":0.005410181,"teacher_disagreement_score":0.0043262057,"about_ca_system_score_codex":0.00088907307,"about_ca_system_score_gemma":0.001300156,"threshold_uncertainty_score":0.0181126},"labels":[],"label_agreement":null},{"id":"W2142799607","doi":"10.1109/icassp.2006.1659970","title":"Improvements in Factor Analysis Based Speaker Verification","year":2006,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Speaker verification; Factor (programming language); Speech recognition; Speaker recognition; Programming language","score_opus":0.015071807643092246,"score_gpt":0.23138557314759944,"score_spread":0.2163137655045072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142799607","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031126358,0.0030125717,0.9487461,0.0003806619,0.00027216147,0.00022556246,0.0006174017,0.012435828,0.0031832985],"genre_scores_gemma":[0.17117128,0.0010150381,0.8205795,0.00020931699,0.00020298942,0.00017221608,0.0015538016,0.0007435631,0.004352324],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98385024,0.0064696963,0.0009563739,0.0027901575,0.0054595037,0.00047419558],"domain_scores_gemma":[0.9749536,0.011265721,0.000608815,0.0046990043,0.008318539,0.00015433412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010562378,0.002528071,0.0017616769,0.0019830237,0.0007633418,0.0015301511,0.0019186393,0.0014835035,0.008866263],"category_scores_gemma":[0.030616447,0.00069387286,0.0015791038,0.0017499079,0.00063941965,0.003065918,0.0016336684,0.0016911275,0.008355723],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009690301,0.00022940878,0.0022054245,0.00031477326,0.00022629065,0.0000753641,0.00017730819,0.017075298,0.08217885,0.0035936222,0.006351274,0.8866033],"study_design_scores_gemma":[0.00027921185,0.0014771583,0.017625572,0.00013194734,0.0005909943,0.0018724753,0.00019877678,0.72459126,0.2077057,0.008923774,0.03622391,0.00037923612],"about_ca_topic_score_codex":0.007104678,"about_ca_topic_score_gemma":0.0058084745,"teacher_disagreement_score":0.010562378,"about_ca_system_score_codex":0.0008056977,"about_ca_system_score_gemma":0.000954392,"threshold_uncertainty_score":0.055859864},"labels":[],"label_agreement":null},{"id":"W2143612262","doi":"10.1109/icassp.2013.6638947","title":"Speech recognition with deep recurrent neural networks","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8837,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Recurrent neural network; Computer science; Connectionism; TIMIT; Speech recognition; Artificial intelligence; Deep learning; Context (archaeology); Benchmark (surveying); Time delay neural network; Artificial neural network; Hidden Markov model; Pattern recognition (psychology)","score_opus":0.021275216449558917,"score_gpt":0.21530829898896017,"score_spread":0.19403308253940127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143612262","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040532917,0.0019041743,0.944698,0.00036786008,0.0001987479,0.0000498676,0.0005830534,0.0069643236,0.0047010756],"genre_scores_gemma":[0.6135056,0.001254581,0.37002498,0.00027036236,0.000158336,0.00010851226,0.002838765,0.00028471794,0.011554211],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99931836,0.00014932857,0.00004834553,0.0001720516,0.0002531724,0.00005869945],"domain_scores_gemma":[0.99933904,0.00024444316,0.00005612234,0.00014548312,0.00019305629,0.000021752454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007586823,0.00064364605,0.0005179227,0.0005044773,0.0001809325,0.00092214195,0.00072647823,0.0007082384,0.00331165],"category_scores_gemma":[0.0023128649,0.0003498581,0.0005151977,0.00057185366,0.0002620846,0.0011903838,0.00070502824,0.00088245707,0.002779167],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025556906,0.000100000805,0.00097141665,0.00018580281,0.00017415635,0.00016939237,0.000073719304,0.2257454,0.067141674,0.006321207,0.007350397,0.6915113],"study_design_scores_gemma":[0.000008188331,0.000050604962,0.00047095073,0.000014974914,0.000018133787,0.000052184507,0.000011735665,0.9773127,0.016265344,0.0030133433,0.0027673044,0.000014501594],"about_ca_topic_score_codex":0.00426619,"about_ca_topic_score_gemma":0.0073109027,"teacher_disagreement_score":0.00426619,"about_ca_system_score_codex":0.0005063308,"about_ca_system_score_gemma":0.00038953553,"threshold_uncertainty_score":0.011078596},"labels":[],"label_agreement":null},{"id":"W2144015346","doi":"10.5281/zenodo.43376","title":"Plsa Enhanced With A Long-Distance Bigram Language Model For Speech Recognition","year":2013,"lang":"en","type":"article","venue":"INFM-OAR (INFN Catania)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Perplexity; Bigram; Language model; Computer science; Probabilistic latent semantic analysis; Topic model; Natural language processing; Word error rate; Artificial intelligence; Speech recognition; Word (group theory); Hidden Markov model; Event (particle physics); Trigram; Linguistics","score_opus":0.02486412488034375,"score_gpt":0.24656600029035372,"score_spread":0.22170187541000996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144015346","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019149382,0.0013833944,0.95392615,0.0003316485,0.00059725944,0.00009380929,0.0016565985,0.019929258,0.0029325224],"genre_scores_gemma":[0.2550547,0.0011212958,0.7112362,0.0004973346,0.00036800146,0.0004667726,0.008863678,0.002771444,0.019620575],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992924,0.00027074892,0.00006259198,0.00016715328,0.0001360879,0.000071144554],"domain_scores_gemma":[0.9986596,0.00055745867,0.000034964556,0.00022662879,0.00045827014,0.000063010724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010897991,0.0012392954,0.0009922624,0.00095901923,0.00069618225,0.0013538529,0.0012256813,0.0011427597,0.017300347],"category_scores_gemma":[0.0022127072,0.00063323707,0.0013544493,0.0010414157,0.0002639279,0.0020146375,0.001351879,0.0024039836,0.019462707],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001366466,0.0003680346,0.00075973297,0.00032840628,0.00027758395,0.0003235563,0.00012733931,0.035344247,0.077721864,0.004383154,0.014867157,0.8641325],"study_design_scores_gemma":[0.00006720103,0.000239661,0.0007816014,0.000031467094,0.00011115116,0.00018780897,0.00007439186,0.9427828,0.04171956,0.00338973,0.01056084,0.000053877848],"about_ca_topic_score_codex":0.0054426063,"about_ca_topic_score_gemma":0.009763727,"teacher_disagreement_score":0.017300347,"about_ca_system_score_codex":0.00037089366,"about_ca_system_score_gemma":0.0012671382,"threshold_uncertainty_score":0.057875395},"labels":[],"label_agreement":null},{"id":"W2144325519","doi":"10.1109/ccece.2006.277694","title":"Robust Self-Training System for Spoken Query Information Retrieval using Pitch Range Variations","year":2006,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Speech recognition; Variation (astronomy); Session (web analytics); Quality (philosophy); Range (aeronautics); Artificial intelligence; Natural language processing; World Wide Web; Engineering","score_opus":0.05296486172370055,"score_gpt":0.23293315386927527,"score_spread":0.17996829214557472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144325519","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.094491616,0.00073647825,0.8584649,0.00015971805,0.00012758133,0.00025433188,0.0004071152,0.041415013,0.0039432757],"genre_scores_gemma":[0.5480532,0.0002848602,0.43394524,0.00038866734,0.00018081,0.0004188955,0.001790405,0.0007881619,0.01414978],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994609,0.000076854674,0.00005319731,0.0001804211,0.00017988903,0.000048764898],"domain_scores_gemma":[0.9993849,0.00021183946,0.000051523013,0.00011080446,0.00019719564,0.00004378773],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006995538,0.00043684358,0.0009849215,0.0007113009,0.0003410176,0.0005924033,0.0012530144,0.000600131,0.0051493607],"category_scores_gemma":[0.0015046987,0.00025819908,0.0003540456,0.00030507482,0.0002328311,0.0011246675,0.0005895304,0.00041786573,0.0035990088],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009382964,0.00028937083,0.0012991651,0.00026816272,0.0000873521,0.0002824683,0.000381598,0.004649629,0.39539412,0.0018525042,0.0107418895,0.58381546],"study_design_scores_gemma":[0.0003018751,0.0010148415,0.0068913237,0.000029309245,0.00022323066,0.0014810311,0.00025997104,0.57521105,0.3841004,0.0020867807,0.028241176,0.00015900574],"about_ca_topic_score_codex":0.001870619,"about_ca_topic_score_gemma":0.0014370703,"teacher_disagreement_score":0.0051493607,"about_ca_system_score_codex":0.00036628093,"about_ca_system_score_gemma":0.00040009452,"threshold_uncertainty_score":0.017226338},"labels":[],"label_agreement":null},{"id":"W2144421128","doi":"10.1109/isspa.2010.5605556","title":"Text-independent distributed speaker identification and verification using GMM-UBM speaker models for mobile communications","year":2010,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec; Institut National de la Recherche Scientifique; Université de Moncton; Université du Québec à Montréal","funders":"","keywords":"Computer science; Speech recognition; Speaker recognition; Speaker diarisation; Mixture model; Maximum a posteriori estimation; Hidden Markov model; Speaker identification; Identification (biology); Artificial intelligence; Channel (broadcasting); Pattern recognition (psychology); Maximum likelihood","score_opus":0.053831147825318525,"score_gpt":0.29645053132652527,"score_spread":0.24261938350120674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144421128","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49241206,0.00042773274,0.5000682,0.0002943422,0.000094398536,0.00012887355,0.00017767647,0.0015285157,0.004868247],"genre_scores_gemma":[0.9689303,0.0000618458,0.029828547,0.000023234526,0.0000066472558,0.000036779944,0.000082257204,0.00002699991,0.0010032258],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995326,0.00018688598,0.000015681711,0.00006565128,0.00015066213,0.000048512156],"domain_scores_gemma":[0.9989022,0.00068909186,0.000058587495,0.00010722604,0.00021107083,0.000031769374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010460733,0.0004649635,0.00063594326,0.00029562772,0.00044390344,0.00042841566,0.00046372364,0.000632474,0.001444328],"category_scores_gemma":[0.003012498,0.00020639117,0.00037480364,0.00020907319,0.000344774,0.0007060799,0.0004448826,0.0005697555,0.0004279169],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00082519045,0.000115437084,0.004262205,0.00009956796,0.00008592009,0.00021319906,0.00014862404,0.90314144,0.02845585,0.003881559,0.0009515291,0.057819486],"study_design_scores_gemma":[0.000020360783,0.000113373324,0.0005447971,0.0000023201987,0.0000102736285,0.00006643469,0.0000144483165,0.9903869,0.008021482,0.0005608756,0.0002487271,0.0000099004055],"about_ca_topic_score_codex":0.005162309,"about_ca_topic_score_gemma":0.0046074875,"teacher_disagreement_score":0.005162309,"about_ca_system_score_codex":0.00076810294,"about_ca_system_score_gemma":0.00055518065,"threshold_uncertainty_score":0.010264516},"labels":[],"label_agreement":null},{"id":"W2147094156","doi":"10.1109/asru.2007.4430179","title":"Interpolative variable frame rate transmission of speech features for distributed speech recognition","year":2007,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Computer science; Speech recognition; Voice activity detection; Speech coding; Word error rate; Linear predictive coding; Codec2; Frame (networking); Speech processing; Artificial intelligence; Computer network","score_opus":0.024571848015133235,"score_gpt":0.2716059338041716,"score_spread":0.24703408578903835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147094156","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.072396204,0.00087467267,0.9235836,0.00010468686,0.00012100027,0.00006978718,0.000080074606,0.0012459896,0.0015239592],"genre_scores_gemma":[0.64316416,0.00076928036,0.35217506,0.00007107563,0.00014566217,0.000097658834,0.00029247458,0.00020908963,0.0030755755],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995326,0.00012932789,0.00003197212,0.00006671847,0.00019827239,0.000041203864],"domain_scores_gemma":[0.9982217,0.0009530398,0.00016547518,0.00032349778,0.00030677093,0.000029506864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010882637,0.00045902666,0.0005248269,0.00047483842,0.00036024148,0.00046659802,0.00089534593,0.00045706533,0.0025918297],"category_scores_gemma":[0.0033716129,0.00022337312,0.0002693425,0.0005086137,0.00040438608,0.00080585975,0.00046431992,0.00067363394,0.0006903259],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023234545,0.00021095148,0.0016298555,0.00041142016,0.00006665928,0.0005249848,0.00053352327,0.042384703,0.3375125,0.010817909,0.002609529,0.60097444],"study_design_scores_gemma":[0.00014879888,0.0012519497,0.0023773585,0.00010338539,0.00012989526,0.0012875248,0.00016649386,0.5069382,0.4644002,0.006171199,0.016894436,0.00013051077],"about_ca_topic_score_codex":0.0006999743,"about_ca_topic_score_gemma":0.0010281634,"teacher_disagreement_score":0.0025918297,"about_ca_system_score_codex":0.00033614683,"about_ca_system_score_gemma":0.00022865269,"threshold_uncertainty_score":0.008670509},"labels":[],"label_agreement":null},{"id":"W2147768505","doi":"10.1109/tasl.2011.2134090","title":"Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3077,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Microsoft Research; University of Toronto; Microsoft","keywords":"Hidden Markov model; Computer science; Speech recognition; Word error rate; Artificial intelligence; Artificial neural network; Context (archaeology); Mixture model; Deep neural networks; Sentence; Generalization; Phone; Deep learning; Pattern recognition (psychology); Vocabulary; Mathematics","score_opus":0.026434426717621164,"score_gpt":0.25310468969957234,"score_spread":0.22667026298195117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147768505","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015915472,0.00051938527,0.9801224,0.00013492948,0.000078147445,0.000034354376,0.00023956301,0.0016725296,0.0012832703],"genre_scores_gemma":[0.5965258,0.0007011815,0.39344493,0.00030934613,0.00009234325,0.00026609533,0.0013867998,0.00021398148,0.00705944],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996786,0.000078654906,0.000019413648,0.00011150219,0.000076427634,0.00003542179],"domain_scores_gemma":[0.9995771,0.00018318056,0.00003111435,0.00007630474,0.00011084205,0.000021459982],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005402551,0.0007394771,0.0005086479,0.00031330326,0.00025369882,0.00049176335,0.0016873722,0.00077693607,0.002501511],"category_scores_gemma":[0.0015338705,0.0004941287,0.0005412256,0.0003877989,0.0003055956,0.0011914184,0.00073056185,0.0019333408,0.0010725504],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021690095,0.00015777141,0.0015607177,0.00012418863,0.000093063754,0.00012807241,0.000089884816,0.6963683,0.0251768,0.010866624,0.0046751946,0.26054257],"study_design_scores_gemma":[0.0000029489227,0.000014104715,0.00014259746,0.0000035939743,0.000005418377,0.000014794941,0.0000029663768,0.9952232,0.002444667,0.0016643889,0.0004769564,0.000004298496],"about_ca_topic_score_codex":0.0075184763,"about_ca_topic_score_gemma":0.02138541,"teacher_disagreement_score":0.0075184763,"about_ca_system_score_codex":0.0007601764,"about_ca_system_score_gemma":0.0009559336,"threshold_uncertainty_score":0.014949441},"labels":[],"label_agreement":null},{"id":"W2148177126","doi":"10.1109/icassp.2005.1416353","title":"Large Margin HMMs for Speech Recognition","year":2006,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Hidden Markov model; Margin (machine learning); Minimax; Computer science; Pattern recognition (psychology); Optimization problem; Artificial intelligence; Speech recognition; Mathematics; Algorithm; Mathematical optimization; Machine learning","score_opus":0.025622888386847717,"score_gpt":0.24311999577670307,"score_spread":0.21749710738985534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148177126","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012926129,0.00028147188,0.99750936,0.00006487376,0.000027730515,0.000009898007,0.000040959872,0.00045738101,0.00031572126],"genre_scores_gemma":[0.24040736,0.0010174115,0.7526424,0.00024175034,0.0002321558,0.0002668552,0.00078356994,0.00032468827,0.0040838267],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889886,0.00049107254,0.000059493177,0.00024702825,0.00025242017,0.00005103218],"domain_scores_gemma":[0.9974529,0.0016985877,0.00016689111,0.0003991154,0.00024018204,0.000042227275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015446933,0.0007209703,0.0009446258,0.0005138475,0.0003788045,0.000909124,0.0011649089,0.001235732,0.0029254616],"category_scores_gemma":[0.005617314,0.000570806,0.0006303432,0.00074073323,0.00075776863,0.0020766666,0.0012109857,0.0023442307,0.0020394828],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028887333,0.00009169853,0.00076591276,0.0001925633,0.00010129969,0.00015930492,0.00017216627,0.459289,0.018950794,0.08120819,0.0060246265,0.43275553],"study_design_scores_gemma":[0.0000061883707,0.000016942437,0.00017024824,0.000010562493,0.0000068501895,0.000027115644,0.000005872681,0.972258,0.0024750133,0.023254128,0.0017583115,0.000010814542],"about_ca_topic_score_codex":0.0013905481,"about_ca_topic_score_gemma":0.0014204497,"teacher_disagreement_score":0.0029254616,"about_ca_system_score_codex":0.0005590474,"about_ca_system_score_gemma":0.00054966804,"threshold_uncertainty_score":0.009786606},"labels":[],"label_agreement":null},{"id":"W2148424003","doi":"10.1109/icassp.2004.1326309","title":"A new signal model and identification algorithm for hidden semi-Markov signals","year":2004,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Hidden Markov model; Hidden semi-Markov model; SIGNAL (programming language); Algorithm; Identification (biology); Computer science; Markov model; Markov chain; Maximum-entropy Markov model; Estimation theory; Forward algorithm; Markov process; State (computer science); Constant (computer programming); Pattern recognition (psychology); Mathematics; Artificial intelligence; Variable-order Markov model; Machine learning; Statistics","score_opus":0.026753284819732943,"score_gpt":0.2586929159079327,"score_spread":0.23193963108819976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148424003","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00034427474,0.00002766663,0.9993037,0.000024110652,0.000011062288,0.000009718627,0.000013602708,0.00015377557,0.0001120552],"genre_scores_gemma":[0.04162908,0.00015568332,0.95559394,0.00008208121,0.000061954845,0.00018677847,0.0002505907,0.00015232674,0.0018875358],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999161,0.00018407988,0.00005814785,0.000205151,0.00033505043,0.00005664965],"domain_scores_gemma":[0.9988702,0.0005884089,0.00011219625,0.00013403452,0.00025511952,0.000040022012],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013808452,0.0010174579,0.00096872746,0.0008277104,0.0005608358,0.00094045803,0.0017202654,0.001674204,0.0029681185],"category_scores_gemma":[0.0039735814,0.0006146743,0.0010732618,0.0009153316,0.00070428115,0.0027661645,0.0012839645,0.0023887723,0.0015973556],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001740944,0.00009759679,0.00089326815,0.00022609094,0.00012383929,0.00026651268,0.0002502811,0.428094,0.019585041,0.123749495,0.004604434,0.42193547],"study_design_scores_gemma":[0.000012381149,0.000027335815,0.000074676,0.000010164427,0.000011490422,0.00008855081,0.0000073006577,0.97788835,0.0018895597,0.016524378,0.0034502875,0.000015460062],"about_ca_topic_score_codex":0.0018564404,"about_ca_topic_score_gemma":0.0017713635,"teacher_disagreement_score":0.0029681185,"about_ca_system_score_codex":0.0006870624,"about_ca_system_score_gemma":0.0011163657,"threshold_uncertainty_score":0.009929419},"labels":[],"label_agreement":null},{"id":"W2148725087","doi":"10.5281/zenodo.43036","title":"Robust Speech Recognition Under Noisy Environments Using Asymmetric Tapers","year":2012,"lang":"en","type":"article","venue":"INFM-OAR (INFN Catania)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Mel-frequency cepstrum; Computer science; Speech recognition; Feature extraction; Feature (linguistics); Constraint (computer-aided design); Pattern recognition (psychology); Distortion (music); Cepstrum; Hamming code; Artificial intelligence; Mathematics; Algorithm; Amplifier; Bandwidth (computing); Telecommunications","score_opus":0.10667732456096098,"score_gpt":0.25804151493059035,"score_spread":0.1513641903696294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148725087","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.087672584,0.0022680846,0.8996704,0.00024107809,0.00048408136,0.00009741225,0.00046620387,0.0024521959,0.0066479486],"genre_scores_gemma":[0.5867528,0.0028854671,0.3845885,0.0001964681,0.0007796563,0.00020311297,0.002584499,0.00069218664,0.021317381],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987618,0.00034493668,0.00009807308,0.00022250228,0.00044154548,0.00013107131],"domain_scores_gemma":[0.99822575,0.00084053935,0.00009604209,0.00036087868,0.00042036004,0.000056405337],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009737984,0.0012120641,0.0011115506,0.0006710773,0.00054420804,0.0015354845,0.00078960747,0.0011962634,0.005468836],"category_scores_gemma":[0.0029734063,0.00041123078,0.00057584146,0.00055853213,0.00060062425,0.0012969997,0.0013138828,0.0011375714,0.0041552056],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019279232,0.00012634786,0.00063156645,0.00047221957,0.00010726799,0.0006407907,0.00025733688,0.023136789,0.456005,0.0029277836,0.002837064,0.51093],"study_design_scores_gemma":[0.00007725749,0.0006726387,0.0027498766,0.00012939269,0.00025787743,0.0015803688,0.00027411248,0.40518636,0.5705523,0.00296934,0.015455851,0.0000946928],"about_ca_topic_score_codex":0.00082319346,"about_ca_topic_score_gemma":0.0013259168,"teacher_disagreement_score":0.005468836,"about_ca_system_score_codex":0.0001812604,"about_ca_system_score_gemma":0.00045608566,"threshold_uncertainty_score":0.01829511},"labels":[],"label_agreement":null},{"id":"W2148812765","doi":"10.1006/csla.1999.0136","title":"A path-stack algorithm for optimizing dynamic regimes in a statistical hidden dynamic model of speech","year":2000,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Hidden Markov model; Utterance; Speech recognition; Stack (abstract data type); Path (computing); Phone; Reduction (mathematics); Set (abstract data type); Segmentation; Algorithm; Artificial intelligence; Pattern recognition (psychology)","score_opus":0.013258436234086577,"score_gpt":0.2679317228246664,"score_spread":0.2546732865905798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148812765","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005868726,0.0001124156,0.99234915,0.00006651079,0.000018447905,0.00005023884,0.000045892906,0.0008689514,0.00061959354],"genre_scores_gemma":[0.124701545,0.00019685595,0.871011,0.000100643476,0.000036357815,0.00042443405,0.0003638718,0.00058310817,0.0025821282],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99963784,0.00012241486,0.000022537484,0.00009269724,0.00007798621,0.00004657844],"domain_scores_gemma":[0.9989518,0.00078838965,0.00004380521,0.000057349156,0.0001164475,0.000042194486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001977727,0.0016751288,0.0016877683,0.0012574274,0.0010481616,0.00094597635,0.0018026943,0.0025240844,0.006168039],"category_scores_gemma":[0.0042053037,0.0018574471,0.0013140804,0.0012191166,0.001102629,0.0021296893,0.0019004245,0.0023988388,0.0011336115],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014223286,0.00007141579,0.00036173832,0.000050805844,0.000074924654,0.0000523985,0.0000738671,0.83392304,0.0016104189,0.013500993,0.0015830412,0.1485551],"study_design_scores_gemma":[0.000011601376,0.000013844581,0.000023926652,0.0000032619553,0.000006643299,0.0000042506,0.0000040890136,0.99614775,0.00022348286,0.0033316254,0.00022501474,0.00000455433],"about_ca_topic_score_codex":0.017531916,"about_ca_topic_score_gemma":0.017948803,"teacher_disagreement_score":0.017531916,"about_ca_system_score_codex":0.0011641075,"about_ca_system_score_gemma":0.0030905043,"threshold_uncertainty_score":0.034859776},"labels":[],"label_agreement":null},{"id":"W2150722744","doi":"10.1109/cihsps.2005.1500624","title":"Speech accent identification with vocal tract variation trajectory tracking using neural networks","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Stress (linguistics); Computer science; Speech recognition; Vocal tract; Artificial neural network; Identification (biology); Variation (astronomy); Speech processing; Trajectory; Speaker recognition; Artificial intelligence","score_opus":0.04051435498512875,"score_gpt":0.26696526079216515,"score_spread":0.2264509058070364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150722744","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10768776,0.0004416367,0.88884133,0.00012306115,0.00006893546,0.00004784971,0.000056423825,0.001051256,0.0016817256],"genre_scores_gemma":[0.7443155,0.00026180994,0.25088888,0.0000629595,0.000060913833,0.00006569737,0.0001367578,0.000056959347,0.0041504228],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99979764,0.000047947706,0.00001094499,0.00007212529,0.00004913857,0.000022275033],"domain_scores_gemma":[0.99963176,0.00015386712,0.000056700454,0.000036535774,0.00010493868,0.0000160888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006686192,0.0004716918,0.00031178063,0.00052165147,0.00025144868,0.0004520122,0.00040067828,0.0005431807,0.00067988504],"category_scores_gemma":[0.0013065303,0.00031194923,0.00037838623,0.0004050464,0.00026575933,0.00063050265,0.00035198044,0.00051612884,0.0003984126],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043060636,0.00016013843,0.004358252,0.00005375421,0.00010502956,0.0001084232,0.00008341151,0.21877056,0.059818193,0.0011075282,0.0010791391,0.71392494],"study_design_scores_gemma":[0.0000058868195,0.000031301348,0.0017952794,0.0000033207762,0.000012699933,0.00003176151,0.000006161808,0.9892442,0.008111506,0.0005079854,0.00024184772,0.000008088706],"about_ca_topic_score_codex":0.003405759,"about_ca_topic_score_gemma":0.005040586,"teacher_disagreement_score":0.003405759,"about_ca_system_score_codex":0.00037030148,"about_ca_system_score_gemma":0.0002836726,"threshold_uncertainty_score":0.0067718625},"labels":[],"label_agreement":null},{"id":"W2151120341","doi":"","title":"Automatic Syllabification with Structured SVMs for Letter-to-Phoneme Conversion","year":2008,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Syllabification; Computer science; Discriminative model; Artificial intelligence; Word error rate; Speech recognition; Natural language processing; German; Syllable; Linguistics","score_opus":0.024311775966838128,"score_gpt":0.22514287289706725,"score_spread":0.20083109693022913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151120341","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09069035,0.00029247964,0.9014755,0.0001224346,0.00013457151,0.00007652954,0.00034322508,0.004715665,0.0021493025],"genre_scores_gemma":[0.5219102,0.0001625876,0.472064,0.00012881355,0.00010251045,0.00011556642,0.0015432931,0.00026112073,0.0037118793],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995983,0.00009637752,0.000032506494,0.00009807877,0.000113986454,0.000060713686],"domain_scores_gemma":[0.9991154,0.00036525298,0.00005567844,0.000123734,0.00027777004,0.0000621976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045716597,0.00044832885,0.00045726492,0.0005814457,0.00033482333,0.00058888824,0.0005799629,0.00043787214,0.003141956],"category_scores_gemma":[0.0018660325,0.00021449123,0.00029879963,0.0004229669,0.00020820682,0.0006234073,0.0005995867,0.00086309365,0.0019551206],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031978957,0.00020045691,0.002559078,0.00011080327,0.000046468733,0.00011834088,0.00007818782,0.015686166,0.13922437,0.0023509157,0.005797562,0.83350784],"study_design_scores_gemma":[0.000029360624,0.00010096861,0.0032723066,0.000014830338,0.000027988706,0.00014852497,0.000031346102,0.90693116,0.083144784,0.0027170384,0.0035533868,0.000028351327],"about_ca_topic_score_codex":0.0018517096,"about_ca_topic_score_gemma":0.0037806216,"teacher_disagreement_score":0.003141956,"about_ca_system_score_codex":0.0002030433,"about_ca_system_score_gemma":0.0007420693,"threshold_uncertainty_score":0.0105109215},"labels":[],"label_agreement":null},{"id":"W2151936436","doi":"10.1109/tasl.2010.2072499","title":"Articulatory Knowledge in the Recognition of Dysarthric Speech","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":105,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Vocal tract; Discriminative model; Dysarthria; Speech recognition; Computer science; Speech production; Manner of articulation; Generative grammar; Artificial intelligence; Natural language processing; Psychology","score_opus":0.017474742947774666,"score_gpt":0.2601078714734097,"score_spread":0.242633128525635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151936436","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8443563,0.0017560599,0.15009534,0.00023244822,0.00003659681,0.00002708584,0.00016038919,0.0007009214,0.0026348939],"genre_scores_gemma":[0.9870064,0.00031946052,0.011687693,0.000024935087,0.000014215349,0.0000064816763,0.00014833246,0.00001667897,0.00077568257],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9994499,0.00017523165,0.000035430985,0.00016693491,0.0001347496,0.000037774687],"domain_scores_gemma":[0.99828017,0.001171418,0.00013957928,0.0002107309,0.00015708488,0.00004103181],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013533848,0.00039307537,0.00034611055,0.00061929453,0.00028321834,0.0008444682,0.0005168959,0.0005674831,0.0007896985],"category_scores_gemma":[0.005975587,0.00019294916,0.00020675379,0.00035016407,0.0005143932,0.001180177,0.0005633093,0.0005282744,0.00054603204],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061141717,0.00014604931,0.013628264,0.00022625434,0.00008011524,0.00032055678,0.00033876146,0.092064224,0.06257381,0.0015523955,0.0005102729,0.827948],"study_design_scores_gemma":[0.00002153705,0.00032950082,0.04262976,0.0000693729,0.000087006636,0.0011416724,0.0003293359,0.908073,0.0396208,0.0062397486,0.001400118,0.000058130627],"about_ca_topic_score_codex":0.0037282722,"about_ca_topic_score_gemma":0.0070201005,"teacher_disagreement_score":0.0037282722,"about_ca_system_score_codex":0.0002863988,"about_ca_system_score_gemma":0.00046299997,"threshold_uncertainty_score":0.007413149},"labels":[],"label_agreement":null},{"id":"W2154037907","doi":"10.1109/icassp.1995.479399","title":"Analysis of acoustic-phonetic variations in fluent speech using TIMIT","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"TIMIT; Speech recognition; Computer science; Mel-frequency cepstrum; Context (archaeology); Phonetics; Variance (accounting); Cepstrum; Artificial intelligence; Hidden Markov model; Feature extraction; Linguistics; Biology","score_opus":0.04996774319873785,"score_gpt":0.26251441654567603,"score_spread":0.2125466733469382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154037907","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8283743,0.00023603137,0.1663592,0.00007522627,0.00005987828,0.00013629944,0.0011580084,0.0006960828,0.0029050244],"genre_scores_gemma":[0.9497404,0.0001316577,0.047822457,0.000036417732,0.00004649555,0.0002572769,0.0011626676,0.00017481478,0.0006277707],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99907863,0.00023136853,0.00007333531,0.00018490305,0.00034633104,0.000085360894],"domain_scores_gemma":[0.9974458,0.0016489872,0.00019504059,0.00024136493,0.00039806875,0.00007069037],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012613265,0.00057042635,0.0005664987,0.0012949291,0.00044716324,0.0007775053,0.00028558,0.0002789983,0.0016331333],"category_scores_gemma":[0.0049024737,0.00018682885,0.0005680299,0.0008189876,0.0006161283,0.00060125225,0.00048106702,0.00043228088,0.0003614908],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022652436,0.00031257735,0.035561085,0.00042755154,0.00039139562,0.0002830075,0.0020124477,0.0066371937,0.68508476,0.0014158785,0.00058721943,0.26502168],"study_design_scores_gemma":[0.000048930146,0.0021433574,0.81003225,0.000038848902,0.0004092784,0.00071774144,0.0011458707,0.046612196,0.13364743,0.0022287052,0.0027730241,0.00020238088],"about_ca_topic_score_codex":0.0016895818,"about_ca_topic_score_gemma":0.0022395945,"teacher_disagreement_score":0.0016895818,"about_ca_system_score_codex":0.00025959697,"about_ca_system_score_gemma":0.00027528463,"threshold_uncertainty_score":0.006670594},"labels":[],"label_agreement":null},{"id":"W2154162514","doi":"10.1109/asru.2007.4430082","title":"Exploiting complementary aspects of phonological features in automatic speech recognition","year":2007,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"University of Edinburgh","keywords":"Computer science; Mel-frequency cepstrum; Speech recognition; Feature (linguistics); Phone; Pattern recognition (psychology); Decoding methods; Artificial intelligence; Feature extraction; Frame (networking); Algorithm","score_opus":0.05129818448945806,"score_gpt":0.28484618720485627,"score_spread":0.23354800271539822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154162514","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05236106,0.0011002156,0.94406444,0.00008884239,0.000046285695,0.000049383765,0.000036392405,0.00057473977,0.0016787334],"genre_scores_gemma":[0.43642437,0.0007462301,0.5608064,0.00008143856,0.000100442994,0.0000955557,0.00015766136,0.00009968672,0.0014882509],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99906284,0.00020273712,0.000061465355,0.00017959939,0.00044035332,0.00005309702],"domain_scores_gemma":[0.9978523,0.0014496975,0.00011809579,0.00026704645,0.00027487965,0.000037929967],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009943651,0.0006148337,0.0005592353,0.0009598964,0.00032321856,0.0010039977,0.00055330526,0.000703627,0.0010061805],"category_scores_gemma":[0.0036768175,0.00043873428,0.00047526433,0.0007218798,0.0007645221,0.0022432564,0.0008479273,0.0009204284,0.00048671608],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022186489,0.000082785315,0.0008613924,0.00019781383,0.000059767623,0.00015459048,0.00015209192,0.009530255,0.16665798,0.0064669033,0.00024918144,0.8153654],"study_design_scores_gemma":[0.000099997436,0.0012202804,0.009845563,0.00011698871,0.00037718704,0.0029488814,0.00018810111,0.6063227,0.32359123,0.040577672,0.014428221,0.00028324893],"about_ca_topic_score_codex":0.0006043435,"about_ca_topic_score_gemma":0.0012793568,"teacher_disagreement_score":0.0010061805,"about_ca_system_score_codex":0.00020459955,"about_ca_system_score_gemma":0.00034971253,"threshold_uncertainty_score":0.0052587986},"labels":[],"label_agreement":null},{"id":"W2154909174","doi":"10.1109/icassp.2004.1326054","title":"Estimating vocal-tract area functions from vowel sound signals over closed glottal phases","year":2004,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Vocal tract; Speech recognition; Vowel; Computer science; Acoustics; Glottis; Ideal (ethics); Mathematics; Larynx; Medicine; Physics; Anatomy","score_opus":0.041037723420219954,"score_gpt":0.27744566829149025,"score_spread":0.23640794487127031,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154909174","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17655219,0.00057329854,0.8208878,0.000040301733,0.00001945162,0.000050396768,0.00013301798,0.00080525177,0.00093837356],"genre_scores_gemma":[0.5418545,0.00069325324,0.45382893,0.00003643567,0.000083159364,0.00013113658,0.000635972,0.00027374199,0.0024629382],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99977034,0.00004415332,0.000015888812,0.00006487982,0.000079213474,0.000025464748],"domain_scores_gemma":[0.9989635,0.0006454336,0.00010811292,0.000057060843,0.0001856542,0.00004021488],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047051033,0.00069666974,0.00076837715,0.0011477333,0.00027973746,0.00064276694,0.0002856086,0.0007942614,0.001130107],"category_scores_gemma":[0.002622381,0.00036881285,0.0003911296,0.0004817321,0.00030132942,0.0008620901,0.00040733034,0.00043083876,0.00065368536],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035951464,0.00007206329,0.005038252,0.00020818127,0.00011002528,0.00012254252,0.00021742581,0.03323017,0.44956058,0.0008431668,0.0004791794,0.50975883],"study_design_scores_gemma":[0.000053290372,0.00033387198,0.06734102,0.000043756278,0.00018606112,0.00086933863,0.00015778052,0.7109204,0.21289755,0.0032580646,0.0038438053,0.000095168485],"about_ca_topic_score_codex":0.0018394784,"about_ca_topic_score_gemma":0.0031521807,"teacher_disagreement_score":0.0018394784,"about_ca_system_score_codex":0.00016873544,"about_ca_system_score_gemma":0.00044222563,"threshold_uncertainty_score":0.0037806034},"labels":[],"label_agreement":null},{"id":"W2155973539","doi":"10.1109/icassp.2006.1660066","title":"Speech Feature Estimation Under the Presence of Noise with a Switching Linear Dynamic Model","year":2006,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Feature (linguistics); Computer science; Speech recognition; Feature vector; Parametric statistics; Noise (video); Linear model; Compensation (psychology); Speech processing; Pattern recognition (psychology); Artificial intelligence; Algorithm; Mathematics; Machine learning","score_opus":0.011837635991456565,"score_gpt":0.23982426095168966,"score_spread":0.2279866249602331,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155973539","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1057562,0.000121476405,0.8929119,0.00006310039,0.000023102953,0.0000140250295,0.000025213296,0.0005044703,0.00058053475],"genre_scores_gemma":[0.87131083,0.00016196063,0.12700355,0.0000519131,0.000039458315,0.000026232443,0.00014470259,0.000068368696,0.0011928814],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994141,0.00013280309,0.000030590767,0.00014203195,0.00021854202,0.00006200012],"domain_scores_gemma":[0.99892175,0.0006865353,0.00009712379,0.00012654459,0.00013400847,0.00003409265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007162812,0.0005408803,0.0007884319,0.00033126978,0.00019730652,0.00053916295,0.0006218383,0.00069516053,0.0005037668],"category_scores_gemma":[0.002943571,0.00031243943,0.00041225814,0.0003030456,0.00037329245,0.0010738954,0.0006487157,0.000678396,0.0003032676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012472253,0.00020477992,0.003813908,0.00023543516,0.00014091685,0.000711599,0.00037558688,0.36138025,0.22848621,0.0056591313,0.00065936666,0.39708555],"study_design_scores_gemma":[0.000010959497,0.0001010838,0.0012208015,0.0000038247567,0.000022019614,0.00015135987,0.000023181768,0.96669334,0.029877527,0.0014517562,0.0004251763,0.000018979776],"about_ca_topic_score_codex":0.001592659,"about_ca_topic_score_gemma":0.0015281228,"teacher_disagreement_score":0.001592659,"about_ca_system_score_codex":0.00023424502,"about_ca_system_score_gemma":0.0003729076,"threshold_uncertainty_score":0.0037881136},"labels":[],"label_agreement":null},{"id":"W2157458051","doi":"10.1109/icassp.1988.196631","title":"Modeling acoustic-phonetic detail in an HMM-based large vocabulary speech recognizer","year":2003,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Hidden Markov model; Computer science; Speech recognition; Word (group theory); Vocabulary; Context (archaeology); Vowel; Set (abstract data type); Artificial intelligence; Duration (music); Natural language processing; Acoustics; Linguistics","score_opus":0.03335114007634879,"score_gpt":0.2593127218804179,"score_spread":0.22596158180406908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157458051","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04809406,0.00042632164,0.9454487,0.00011898956,0.00004819571,0.000040387444,0.00022879953,0.0036061138,0.001988445],"genre_scores_gemma":[0.61344457,0.00054547226,0.37572128,0.00009317372,0.00004504238,0.00015725623,0.00065040967,0.00022303643,0.009119782],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99982977,0.000049903047,0.000011625973,0.000051583567,0.000039558567,0.000017436065],"domain_scores_gemma":[0.99975365,0.00015518782,0.000013374536,0.000027753626,0.000041532767,0.000008571565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035563184,0.00029750713,0.00031482612,0.00019683319,0.00019333443,0.00058167154,0.00045369577,0.00044465158,0.002359674],"category_scores_gemma":[0.0009897443,0.00025368793,0.00031743583,0.0001465707,0.00018985983,0.0007672983,0.00023550716,0.0004241788,0.0013731584],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004965599,0.000118962256,0.0027838447,0.00019298932,0.00007954079,0.0003378361,0.00019505799,0.5696491,0.09374549,0.0071581723,0.0025285268,0.32271394],"study_design_scores_gemma":[0.00000912732,0.000052860072,0.000904963,0.000008342504,0.000019482814,0.00006745141,0.000013305626,0.987048,0.00868106,0.0014859065,0.0016991837,0.000010269924],"about_ca_topic_score_codex":0.0075089857,"about_ca_topic_score_gemma":0.01149238,"teacher_disagreement_score":0.0075089857,"about_ca_system_score_codex":0.000358154,"about_ca_system_score_gemma":0.0003807427,"threshold_uncertainty_score":0.014930546},"labels":[],"label_agreement":null},{"id":"W2159112514","doi":"10.1109/tasl.2007.906178","title":"Approximate Test Risk Bound Minimization Through Soft Margin Estimation","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University","keywords":"Discriminative model; Margin (machine learning); Computer science; Hidden Markov model; Artificial intelligence; Machine learning; Pattern recognition (psychology); Statistical learning theory; Support vector machine; Speech recognition","score_opus":0.012978543650113633,"score_gpt":0.25853970575772117,"score_spread":0.24556116210760753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159112514","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042258464,0.00009656261,0.99490464,0.00006998879,0.0000086932705,0.000013406357,0.00001476402,0.00025970506,0.00040646194],"genre_scores_gemma":[0.4861516,0.00027704742,0.50878334,0.00025884216,0.00009752995,0.00028901428,0.00039058062,0.00045919413,0.00329279],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99722856,0.0011148864,0.00014685564,0.00039132946,0.00095236173,0.00016606855],"domain_scores_gemma":[0.9947196,0.003645547,0.00038953195,0.0005449061,0.0005738606,0.00012658439],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034510316,0.0014131819,0.0016260745,0.00085293717,0.00039550202,0.0014208386,0.0017808074,0.0013820068,0.002147234],"category_scores_gemma":[0.014755638,0.0006988571,0.00074108667,0.00063611544,0.0014412606,0.0023974183,0.0027097731,0.0024888099,0.000980413],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000324114,0.00009142046,0.0011037771,0.00016946289,0.000091858215,0.00012388972,0.00011679704,0.74966145,0.00971606,0.031306583,0.002729765,0.2045648],"study_design_scores_gemma":[0.0000057400775,0.000030048306,0.000099040095,0.000006469179,0.0000045673414,0.000020317317,0.0000054168327,0.98968923,0.0019754763,0.007927221,0.0002299626,0.000006555981],"about_ca_topic_score_codex":0.0014626962,"about_ca_topic_score_gemma":0.0011472671,"teacher_disagreement_score":0.0034510316,"about_ca_system_score_codex":0.0009823916,"about_ca_system_score_gemma":0.0013041022,"threshold_uncertainty_score":0.018251061},"labels":[],"label_agreement":null},{"id":"W2160815625","doi":"10.1109/msp.2012.2205597","title":"Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups","year":2012,"lang":"en","type":"article","venue":"IEEE Signal Processing Magazine","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10313,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of Toronto","funders":"","keywords":"Hidden Markov model; Speech recognition; Computer science; Mixture model; Artificial neural network; Margin (machine learning); Deep neural networks; Pattern recognition (psychology); Frame (networking); Artificial intelligence; Acoustic model; Gaussian; Speech processing; Machine learning","score_opus":0.20839778899800224,"score_gpt":0.34057804277739956,"score_spread":0.13218025377939732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160815625","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019267417,0.14460856,0.71361667,0.09515172,0.0019052572,0.000096142954,0.00010438978,0.00074034906,0.024509545],"genre_scores_gemma":[0.31521723,0.23270468,0.41137543,0.011397412,0.0075665177,0.00031766063,0.00036575712,0.00046198,0.02059343],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99504364,0.0017836251,0.00041699852,0.00069670664,0.0018207823,0.00023822684],"domain_scores_gemma":[0.99310863,0.00279588,0.000264526,0.0009318378,0.002332389,0.00056676293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013158741,0.0014428385,0.0013262072,0.0023964115,0.00089750526,0.0058963797,0.00161119,0.0030957065,0.0013669463],"category_scores_gemma":[0.008225771,0.00072352175,0.00083123386,0.0018172546,0.0047651236,0.01145104,0.005651735,0.009063808,0.0009994664],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033676127,0.0001863531,0.0021468243,0.00057611003,0.00015415247,0.00009470756,0.0019432498,0.018461185,0.005896172,0.24744469,0.016157715,0.70660204],"study_design_scores_gemma":[0.00008538799,0.00044565726,0.0018504926,0.0012099465,0.00022014388,0.00039313533,0.0018605303,0.13071118,0.02232201,0.5292698,0.31127015,0.00036157898],"about_ca_topic_score_codex":0.0020252909,"about_ca_topic_score_gemma":0.002222325,"teacher_disagreement_score":0.013158741,"about_ca_system_score_codex":0.0022697828,"about_ca_system_score_gemma":0.0023956832,"threshold_uncertainty_score":0.06959087},"labels":[],"label_agreement":null},{"id":"W2160978380","doi":"10.1109/icassp.2007.366915","title":"Integration of Multiple Feature Sets for Reducing Ambiguity in ASR","year":2007,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"University of Edinburgh","keywords":"Mel-frequency cepstrum; Hidden Markov model; Speech recognition; Computer science; Ambiguity; Feature (linguistics); Pattern recognition (psychology); Phone; Cepstrum; Feature extraction; Artificial intelligence; Artificial neural network","score_opus":0.044685774133151814,"score_gpt":0.30616157936479627,"score_spread":0.26147580523164443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160978380","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07950871,0.0005028348,0.9181049,0.00009001108,0.000034569184,0.00006354706,0.000023564446,0.00067155436,0.001000407],"genre_scores_gemma":[0.5346833,0.00021235061,0.46371493,0.000058529,0.000065218206,0.00007350078,0.000087161316,0.000118294316,0.0009866654],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99852186,0.00039802722,0.00010610968,0.00020688743,0.00067408796,0.00009311915],"domain_scores_gemma":[0.9979265,0.0011476978,0.00018875829,0.00038739474,0.00030871964,0.000040881994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016615203,0.0008906246,0.0012317119,0.00065069867,0.00026025964,0.00082390377,0.0008819527,0.00066691864,0.0011929969],"category_scores_gemma":[0.0045932573,0.00046329616,0.0006361515,0.000544392,0.00043278246,0.001815426,0.0010021223,0.0008531379,0.00040643514],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005655732,0.00018177574,0.0009955565,0.00013675768,0.00010431536,0.00020604685,0.00013136465,0.04710203,0.17718115,0.0063695717,0.00034393228,0.76668197],"study_design_scores_gemma":[0.000079355734,0.0009000218,0.0037290908,0.000027796112,0.00016058284,0.0008118557,0.000060944036,0.8242326,0.1599121,0.0068250378,0.003156946,0.000103746745],"about_ca_topic_score_codex":0.0003579872,"about_ca_topic_score_gemma":0.0006016352,"teacher_disagreement_score":0.0016615203,"about_ca_system_score_codex":0.00024658808,"about_ca_system_score_gemma":0.00028227404,"threshold_uncertainty_score":0.008787096},"labels":[],"label_agreement":null},{"id":"W2161345650","doi":"10.1109/isimp.2004.1434042","title":"ARMA lattice model for phoneme feature extraction","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Mel-frequency cepstrum; Speech recognition; Computer science; Feature extraction; Autoregressive–moving-average model; Pattern recognition (psychology); Cepstrum; Hidden Markov model; Vowel; Autoregressive model; Noise (video); Artificial intelligence; Mathematics; Statistics","score_opus":0.041991741007474694,"score_gpt":0.29348150939653395,"score_spread":0.25148976838905923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161345650","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008225003,0.00027914564,0.9893645,0.00005595503,0.000047655463,0.000017594073,0.00012875114,0.00095794856,0.00092332764],"genre_scores_gemma":[0.44168013,0.00071573723,0.5442756,0.000108802946,0.000118365846,0.00028515604,0.0011340375,0.00030181103,0.011380373],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99947816,0.00013191764,0.000024225228,0.000117913834,0.00021066028,0.00003715525],"domain_scores_gemma":[0.9994917,0.00021487524,0.000040398972,0.000078579105,0.00015427591,0.000020196127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057715195,0.0005792064,0.0007440789,0.0005662445,0.00025378785,0.0007479136,0.0009723748,0.0005858668,0.0027389575],"category_scores_gemma":[0.0018675509,0.00030548492,0.0007443839,0.0006720498,0.00023311297,0.0011657209,0.00034836624,0.0010299492,0.0032809146],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005131934,0.00014387615,0.0012629837,0.00015503966,0.00017241362,0.00018235273,0.0000852221,0.44621724,0.060325623,0.017436648,0.0033343104,0.47017106],"study_design_scores_gemma":[0.000004533029,0.000029702356,0.00012781715,0.0000027044034,0.000007858858,0.00004203057,0.0000045677543,0.99431413,0.0027063296,0.0015042895,0.0012462573,0.000009753272],"about_ca_topic_score_codex":0.0030488393,"about_ca_topic_score_gemma":0.0029374966,"teacher_disagreement_score":0.0030488393,"about_ca_system_score_codex":0.00035097252,"about_ca_system_score_gemma":0.00056693546,"threshold_uncertainty_score":0.009162724},"labels":[],"label_agreement":null},{"id":"W2162638453","doi":"10.1109/icassp.2012.6289084","title":"Facilitating open vocabulary spoken term detection using a multiple pass hybrid search algorithm","year":2012,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Speech recognition; Vocabulary; Term (time); Word (group theory); Artificial intelligence; Artificial neural network; Pattern recognition (psychology); Natural language processing; Mathematics","score_opus":0.07957440462671649,"score_gpt":0.3096826233278061,"score_spread":0.2301082187010896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162638453","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05664744,0.00024099246,0.93905824,0.000043188575,0.000022826249,0.000079949714,0.00008321926,0.0024495053,0.0013747144],"genre_scores_gemma":[0.26713943,0.00012821234,0.7254071,0.00007959245,0.00004603603,0.0002520228,0.00059133174,0.00028636892,0.0060698693],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993767,0.000120542296,0.000058318023,0.00013848371,0.00024951232,0.00005645675],"domain_scores_gemma":[0.99843293,0.00092667714,0.000107006745,0.00015321738,0.0003208698,0.00005925704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007067282,0.00083397265,0.00091664854,0.0011421982,0.00038636217,0.0011018199,0.0012549805,0.00089729746,0.003978856],"category_scores_gemma":[0.002779188,0.00035295842,0.00045752234,0.0007189915,0.000385466,0.0013217768,0.000999476,0.0005884509,0.0025588193],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000885376,0.00025831934,0.0014125779,0.00017486754,0.00011963112,0.00020827478,0.0002411872,0.02292657,0.2381136,0.004259289,0.0016793248,0.72972095],"study_design_scores_gemma":[0.00010157893,0.00048056018,0.0021331492,0.000014378173,0.000076002165,0.0005417355,0.0001701755,0.8887623,0.10162388,0.0024170156,0.0036236914,0.000055578497],"about_ca_topic_score_codex":0.003329707,"about_ca_topic_score_gemma":0.0074283304,"teacher_disagreement_score":0.003978856,"about_ca_system_score_codex":0.00033731887,"about_ca_system_score_gemma":0.0009390581,"threshold_uncertainty_score":0.013310552},"labels":[],"label_agreement":null},{"id":"W2162965424","doi":"10.1109/tasl.2008.925882","title":"A Constrained Line Search Optimization Method for Discriminative Training of HMMs","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Discriminative model; Hidden Markov model; Computer science; Pattern recognition (psychology); Metric (unit); Optimization problem; Artificial intelligence; Benchmark (surveying); Gaussian; Divergence (linguistics); Speech recognition; Algorithm; Engineering","score_opus":0.05546290634126556,"score_gpt":0.3191860795479861,"score_spread":0.26372317320672056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162965424","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011986973,0.00006197454,0.99815035,0.000029551558,0.000009905388,0.000012251718,0.000012863002,0.00029553715,0.00022886877],"genre_scores_gemma":[0.10265726,0.00013731359,0.8937052,0.00020840566,0.00004368033,0.00025773668,0.00029766993,0.00033819288,0.00235458],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991905,0.00029546616,0.00004266315,0.00021867888,0.00020330693,0.000049381917],"domain_scores_gemma":[0.99900985,0.00058651256,0.00009679898,0.00008375089,0.00018516983,0.000037809943],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011045276,0.0010081241,0.001165016,0.0006872575,0.0004859871,0.0006112853,0.0016383968,0.0011983436,0.0039380584],"category_scores_gemma":[0.0031842615,0.00079332077,0.000638791,0.0009028603,0.00072872965,0.001202894,0.0009229911,0.0013854766,0.0013192269],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013299777,0.000090739166,0.000511807,0.0001233002,0.00007112546,0.00007345262,0.00009744922,0.703517,0.007555481,0.01220941,0.0034009945,0.27221614],"study_design_scores_gemma":[0.0000063634516,0.0000132840405,0.0000330726,0.0000026301184,0.0000024609049,0.00001305591,0.0000033092683,0.99757546,0.0006949081,0.0010830255,0.0005681514,0.0000042255683],"about_ca_topic_score_codex":0.0043121506,"about_ca_topic_score_gemma":0.004342382,"teacher_disagreement_score":0.0043121506,"about_ca_system_score_codex":0.000694194,"about_ca_system_score_gemma":0.001100569,"threshold_uncertainty_score":0.013174057},"labels":[],"label_agreement":null},{"id":"W2163376162","doi":"10.1109/icassp.1997.596213","title":"Speaker adaptation experiments using nonstationary-state hidden Markov models: a MAP approach","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Hidden Markov model; Polynomial; Adaptation (eye); Computer science; Gaussian; Speech recognition; Pattern recognition (psychology); State (computer science); Algorithm; Artificial intelligence; Mathematics","score_opus":0.1370463160265479,"score_gpt":0.2604941524964074,"score_spread":0.12344783646985949,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163376162","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7598279,0.00034650404,0.23355298,0.00010706269,0.00010190354,0.00036928194,0.00041221804,0.0027052246,0.0025769563],"genre_scores_gemma":[0.8517311,0.00027182163,0.14385077,0.00008341537,0.000044856708,0.00041207706,0.0008776099,0.00042312138,0.0023052401],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978917,0.0011804961,0.00012379276,0.00034681478,0.00035722888,0.00009987322],"domain_scores_gemma":[0.9937977,0.0046602394,0.00011157955,0.00058479066,0.0007458978,0.00009973751],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002966399,0.0007000163,0.0007628792,0.0004430064,0.00040793014,0.0004864689,0.00082759245,0.0006429912,0.002347229],"category_scores_gemma":[0.0075007486,0.00033243405,0.0005368067,0.0006701806,0.00032358454,0.001012219,0.0007473721,0.001019095,0.00079467514],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0039106393,0.0016410254,0.0071507515,0.0008869954,0.00079547527,0.0008759308,0.0026777291,0.25958255,0.21609026,0.0015511629,0.0025662333,0.5022712],"study_design_scores_gemma":[0.00025321028,0.0024443401,0.013035405,0.000022949158,0.00028459236,0.00046393982,0.00056674023,0.7455013,0.23306282,0.0019367457,0.002267068,0.00016081447],"about_ca_topic_score_codex":0.0034166703,"about_ca_topic_score_gemma":0.0026267336,"teacher_disagreement_score":0.0034166703,"about_ca_system_score_codex":0.0002175125,"about_ca_system_score_gemma":0.00025582293,"threshold_uncertainty_score":0.015688002},"labels":[],"label_agreement":null},{"id":"W2163786726","doi":"10.1007/s11265-015-1012-6","title":"Speaker Adaptation of Hybrid NN/HMM Model for Speech Recognition Based on Singular Value Decomposition","year":2015,"lang":"en","type":"article","venue":"Journal of Signal Processing Systems","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Speech recognition; Singular value decomposition; TIMIT; Hidden Markov model; Adaptation (eye); Vocabulary; Speaker recognition; Pattern recognition (psychology); Artificial intelligence; Artificial neural network; Task (project management)","score_opus":0.08558740047888537,"score_gpt":0.293905759405991,"score_spread":0.20831835892710565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163786726","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02934953,0.00047097806,0.9677425,0.00005300778,0.00012136043,0.00002035156,0.00008702793,0.0010139938,0.0011412152],"genre_scores_gemma":[0.6631777,0.0007867978,0.3270794,0.000096774405,0.00010078795,0.00011272879,0.00078744406,0.00027839097,0.007579882],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99974376,0.000060892024,0.00001616358,0.000079530495,0.000077258686,0.000022416225],"domain_scores_gemma":[0.99978393,0.00006602416,0.000009268396,0.00002948874,0.00010107396,0.000010203203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037969032,0.00039628986,0.00059574394,0.0002498154,0.00023499082,0.00032547401,0.00046379108,0.00045650842,0.0017545235],"category_scores_gemma":[0.0005862226,0.0002390027,0.0006575696,0.00028555634,0.00012044181,0.00041255323,0.0002842078,0.00062405795,0.0013276569],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00057834125,0.00016423687,0.0023993156,0.00018560156,0.00022557989,0.00020405758,0.00015757149,0.1749005,0.19781826,0.0022077113,0.0034699035,0.6176889],"study_design_scores_gemma":[0.000005631265,0.00004652831,0.0015153607,0.0000070600777,0.00003705798,0.0001014968,0.000010568454,0.9800832,0.016510796,0.0003931045,0.0012738857,0.000015262525],"about_ca_topic_score_codex":0.003930071,"about_ca_topic_score_gemma":0.0048492323,"teacher_disagreement_score":0.003930071,"about_ca_system_score_codex":0.00015731607,"about_ca_system_score_gemma":0.00032350185,"threshold_uncertainty_score":0.007814348},"labels":[],"label_agreement":null},{"id":"W2164517999","doi":"10.1109/icassp.1996.540320","title":"Clustering words for statistical language models based on contextual word similarity","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Perplexity; Computer science; Cluster analysis; Artificial intelligence; Word (group theory); Natural language processing; Similarity (geometry); Word error rate; Language model; Speech recognition; Mathematics","score_opus":0.06789550791532689,"score_gpt":0.280999772124081,"score_spread":0.2131042642087541,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164517999","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005377369,0.00015092878,0.9932857,0.000042275587,0.00002207759,0.000052433446,0.00008612984,0.0007218898,0.0002611967],"genre_scores_gemma":[0.15374675,0.0005401495,0.8404165,0.00013225993,0.00014170136,0.000557637,0.0016124164,0.00077902275,0.0020736482],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855095,0.00057395233,0.0001169499,0.0003345736,0.00035612387,0.00006746134],"domain_scores_gemma":[0.99797887,0.0012637115,0.00013199628,0.00024559814,0.0003363817,0.000043490276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013728216,0.0011982943,0.0011988002,0.0019225212,0.00069256115,0.0013472718,0.0016171071,0.00095709553,0.002825406],"category_scores_gemma":[0.006564256,0.0006381816,0.0016491197,0.0013578553,0.00070272,0.002271668,0.0009459872,0.0011847566,0.0026397903],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031799084,0.00012725232,0.0019344179,0.00046735766,0.00045653072,0.00018693558,0.0005307088,0.43437228,0.018159641,0.066897824,0.0040162387,0.47253278],"study_design_scores_gemma":[0.0000125885545,0.00004945682,0.00023670233,0.000017658993,0.000041625888,0.000047837962,0.000038758397,0.9629553,0.0020607992,0.032207638,0.0023044688,0.000027280134],"about_ca_topic_score_codex":0.0050238757,"about_ca_topic_score_gemma":0.0070493217,"teacher_disagreement_score":0.0050238757,"about_ca_system_score_codex":0.0009209368,"about_ca_system_score_gemma":0.0009591395,"threshold_uncertainty_score":0.009989262},"labels":[],"label_agreement":null},{"id":"W2164898939","doi":"10.1109/pacrim.1991.160702","title":"Speaker-independent isolated-digit recognition based on hidden Markov models and multiple vocabulary specific vector quantization","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Codebook; Hidden Markov model; Vector quantization; Speech recognition; Computer science; Word (group theory); Artificial intelligence; Linde–Buzo–Gray algorithm; Vocabulary; Quantization (signal processing); Pattern recognition (psychology); Mathematics; Algorithm; Linguistics","score_opus":0.056052932594081194,"score_gpt":0.2169814565605006,"score_spread":0.1609285239664194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164898939","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005641282,0.00029824072,0.9894978,0.00003307701,0.00006054887,0.000052778334,0.000076799195,0.0034811038,0.00085840625],"genre_scores_gemma":[0.16522172,0.0005109694,0.82657975,0.00008056966,0.00004982353,0.00016933693,0.0007401036,0.0002458704,0.006401845],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99943155,0.00011492485,0.000042887797,0.00011158376,0.00025621505,0.000042744476],"domain_scores_gemma":[0.9994796,0.00022239647,0.000030912153,0.0000990809,0.00014773589,0.00002031069],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007231282,0.00044009186,0.00070118206,0.00045552276,0.00019764036,0.00057603716,0.0010768571,0.00046581146,0.0028080707],"category_scores_gemma":[0.001531706,0.0003617975,0.00048694163,0.0004132619,0.00027285196,0.00084591657,0.00041467807,0.0006018549,0.0020738759],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002984968,0.00008494317,0.0008256527,0.00026630305,0.00013209044,0.00020925539,0.00011557658,0.053605232,0.1029606,0.012154581,0.0057858354,0.82356143],"study_design_scores_gemma":[0.00005524961,0.00025021326,0.0013562231,0.000033816665,0.000086121785,0.0006051775,0.000025956982,0.9075427,0.076892346,0.0042055165,0.0088703865,0.00007630207],"about_ca_topic_score_codex":0.004262928,"about_ca_topic_score_gemma":0.0070917564,"teacher_disagreement_score":0.004262928,"about_ca_system_score_codex":0.0003742533,"about_ca_system_score_gemma":0.0005637173,"threshold_uncertainty_score":0.00939393},"labels":[],"label_agreement":null},{"id":"W2165088481","doi":"10.1109/icassp.1981.1171129","title":"Text-independent speaker recognition using orthogonal linear prediction","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Linear prediction; Speech recognition; Computer science; Speaker recognition; Set (abstract data type); Speaker verification; Pattern recognition (psychology); Feature (linguistics); Feature selection; Test set; Feature extraction; Artificial intelligence","score_opus":0.052873958658616584,"score_gpt":0.26356433678712865,"score_spread":0.21069037812851207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165088481","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17325795,0.00060849555,0.82170856,0.00010911009,0.00007942979,0.000081236605,0.000117996286,0.001954394,0.0020827702],"genre_scores_gemma":[0.72696,0.000417858,0.2692995,0.00006319877,0.0000714513,0.000101032194,0.00034568927,0.00012054275,0.0026208158],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99857295,0.00060607033,0.000056511337,0.00025025688,0.00042455186,0.00008970803],"domain_scores_gemma":[0.99823666,0.0009883164,0.00013548763,0.000198782,0.00040084095,0.00003991897],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016869692,0.0005162905,0.00064747076,0.00038349192,0.00023526633,0.0005343115,0.0004707784,0.00049880444,0.0010017166],"category_scores_gemma":[0.0043797847,0.0002676846,0.00035688558,0.0005022857,0.00026110167,0.0011622643,0.00056135753,0.0007742761,0.00085621834],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013899159,0.00019274879,0.0030794751,0.00013545543,0.00017267726,0.00017904348,0.0001233037,0.07158242,0.18054771,0.0012762044,0.0010558334,0.74026525],"study_design_scores_gemma":[0.000033821885,0.00034062946,0.0028719706,0.0000092451555,0.000066481814,0.000223917,0.000027623342,0.885075,0.10969096,0.00070668635,0.0009104961,0.00004306251],"about_ca_topic_score_codex":0.0014909918,"about_ca_topic_score_gemma":0.0016378297,"teacher_disagreement_score":0.0016869692,"about_ca_system_score_codex":0.00016073191,"about_ca_system_score_gemma":0.0003467939,"threshold_uncertainty_score":0.008921683},"labels":[],"label_agreement":null},{"id":"W2165712617","doi":"10.1109/tasl.2007.914114","title":"Capturing Local Variability for Speaker Normalization in Speech Recognition","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Hidden Markov model; Normalization (sociology); Image warping; Speech recognition; Computer science; Dynamic time warping; Artificial intelligence; Pattern recognition (psychology)","score_opus":0.023669024328760568,"score_gpt":0.24787706944188662,"score_spread":0.22420804511312606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165712617","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010234474,0.00031775405,0.98833907,0.00007626315,0.000031596497,0.000018821609,0.00004569019,0.00037882436,0.00055747444],"genre_scores_gemma":[0.57858026,0.0013365556,0.41319758,0.00016591806,0.00020211366,0.0002805554,0.0005878123,0.0004028106,0.005246383],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992872,0.0002603582,0.000026780064,0.00016626257,0.0002151456,0.00004425682],"domain_scores_gemma":[0.99930894,0.0003740868,0.000059747756,0.00015519426,0.00008367353,0.000018334295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012272723,0.0006729134,0.00077518634,0.0003976323,0.00031884864,0.00071225455,0.00079867215,0.0005568869,0.0013194298],"category_scores_gemma":[0.0026966163,0.00034387386,0.0008803827,0.00062613806,0.0006466619,0.0011465085,0.00082239107,0.0012974883,0.00091835024],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028844798,0.00009099125,0.0019685484,0.00018322197,0.00020401891,0.00018680522,0.00041919213,0.45454478,0.062333785,0.02223785,0.0026337872,0.45490843],"study_design_scores_gemma":[0.0000056546173,0.00007733579,0.0012474635,0.000013645684,0.000045535482,0.00014245408,0.000036435442,0.97593576,0.01003388,0.00966815,0.0027642439,0.000029566201],"about_ca_topic_score_codex":0.0019337917,"about_ca_topic_score_gemma":0.0040044184,"teacher_disagreement_score":0.0019337917,"about_ca_system_score_codex":0.00040956395,"about_ca_system_score_gemma":0.0006324707,"threshold_uncertainty_score":0.0064905286},"labels":[],"label_agreement":null},{"id":"W2165931417","doi":"10.1109/pacrim.1991.160778","title":"Development of a VQ-HMM continuous speech speaker-independent recognition system for small vocabularies","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hidden Markov model; Speech recognition; Computer science; Vector quantization; Viterbi algorithm; Vocabulary; Speaker recognition; Artificial intelligence; Pattern recognition (psychology); Linguistics","score_opus":0.06577192178803151,"score_gpt":0.22595863035787211,"score_spread":0.1601867085698406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165931417","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01795784,0.00017736234,0.96693903,0.00013186259,0.000106777734,0.00036584368,0.000411938,0.0113700535,0.0025392405],"genre_scores_gemma":[0.12526412,0.00019064128,0.86021996,0.0001444033,0.00004580625,0.00052079646,0.0020704553,0.00066301343,0.010880827],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99957603,0.000055516473,0.000046712612,0.00013540752,0.0001504645,0.000035888355],"domain_scores_gemma":[0.9992606,0.00016365324,0.000022385573,0.00008465405,0.0004199325,0.000048722264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009966338,0.00033738514,0.0007021122,0.00037562172,0.00035164104,0.00066398585,0.0011584884,0.00063899107,0.006350059],"category_scores_gemma":[0.0014783978,0.00042070635,0.00043002202,0.00028828304,0.00025000173,0.00086652325,0.00056498725,0.00072724116,0.0043382463],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039206934,0.00017418018,0.0016023744,0.00032895803,0.0000954994,0.00037432802,0.00036214088,0.016308002,0.32615355,0.00604372,0.013131116,0.635034],"study_design_scores_gemma":[0.00033890497,0.0010220779,0.005666161,0.00008785845,0.00018718143,0.0011627472,0.00015554305,0.5966361,0.33227322,0.0027913211,0.05946486,0.0002140919],"about_ca_topic_score_codex":0.00643031,"about_ca_topic_score_gemma":0.0039194766,"teacher_disagreement_score":0.00643031,"about_ca_system_score_codex":0.00039381915,"about_ca_system_score_gemma":0.0010363621,"threshold_uncertainty_score":0.021243095},"labels":[],"label_agreement":null},{"id":"W2166034902","doi":"","title":"New and Unified Templates for Canadian Acoustics Articles","year":2014,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Template; Acoustics; Computer science; Physics; Programming language","score_opus":0.022315707721196332,"score_gpt":0.21697454605867647,"score_spread":0.19465883833748013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166034902","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010965374,0.0015783168,0.89797515,0.0007953895,0.003330018,0.0005092379,0.016911851,0.016575335,0.051359426],"genre_scores_gemma":[0.09438167,0.0018319271,0.78385234,0.00039530094,0.0006452806,0.0006060044,0.034037057,0.005263162,0.07898722],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99733526,0.00019595372,0.00018568846,0.00046250928,0.0014765692,0.0003440722],"domain_scores_gemma":[0.9948656,0.0003470728,0.000111450674,0.000656982,0.0037947525,0.00022412968],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0014127641,0.0013350436,0.0008619747,0.0046775625,0.0022250505,0.0035292227,0.0019910668,0.0016050525,0.027300538],"category_scores_gemma":[0.0068086344,0.00079324597,0.0010396017,0.004716352,0.0007905595,0.0017573026,0.0015686495,0.0018088296,0.022000661],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041333586,0.000076916396,0.002363161,0.00028036494,0.000058963604,0.0003527847,0.00041111917,0.01236856,0.043218877,0.034048,0.14598872,0.76041913],"study_design_scores_gemma":[0.00008343101,0.000091533126,0.0075043025,0.00017971428,0.0001690075,0.00080418895,0.0006500579,0.17509718,0.09481858,0.011430043,0.70889556,0.00027642457],"about_ca_topic_score_codex":0.2862903,"about_ca_topic_score_gemma":0.40692624,"teacher_disagreement_score":0.99858725,"about_ca_system_score_codex":0.0040062745,"about_ca_system_score_gemma":0.01339295,"threshold_uncertainty_score":0.5692478},"labels":[],"label_agreement":null},{"id":"W2166688768","doi":"10.1109/icassp.2011.5947435","title":"Well-calibrated heavy tailed Bayesian speaker verification for microphone speech","year":2011,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Computer Research Institute of Montréal","funders":"","keywords":"NIST; Normalization (sociology); Computer science; Speech recognition; Microphone; Softmax function; Speaker recognition; Speaker verification; Bayesian probability; Feature extraction; Linear discriminant analysis; Classifier (UML); Phone; Discriminative model; Pattern recognition (psychology); Artificial intelligence; Artificial neural network","score_opus":0.041925801157286766,"score_gpt":0.23291125610706576,"score_spread":0.19098545494977898,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166688768","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022271233,0.0002904938,0.97408164,0.000064537766,0.000054702956,0.00007402587,0.00016091178,0.0019791857,0.00102328],"genre_scores_gemma":[0.34384876,0.00023589795,0.65169287,0.0001515127,0.00006121695,0.0002084504,0.00092242827,0.0003220603,0.002556767],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9926615,0.0027174212,0.00032526575,0.001570604,0.0023748172,0.00035038212],"domain_scores_gemma":[0.9952644,0.0016394,0.0004852004,0.0010318663,0.0014328135,0.00014630398],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004821105,0.0012480078,0.0014966548,0.0010686904,0.0007714454,0.0010620271,0.0014744553,0.0018996241,0.0037269138],"category_scores_gemma":[0.015976181,0.0006470769,0.00075839064,0.0005907434,0.00070724153,0.0020132295,0.0019813823,0.0015354282,0.0036754606],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014088241,0.0004882567,0.007056291,0.00044665832,0.0005199027,0.00024577582,0.00023492567,0.11608899,0.18591708,0.0063376995,0.00487143,0.6763841],"study_design_scores_gemma":[0.00007708386,0.00034585717,0.010633242,0.00005688427,0.00008508207,0.0006401825,0.00007026313,0.88085455,0.09775089,0.0053985817,0.003948651,0.00013875519],"about_ca_topic_score_codex":0.0028137232,"about_ca_topic_score_gemma":0.0070447405,"teacher_disagreement_score":0.004821105,"about_ca_system_score_codex":0.0007176481,"about_ca_system_score_gemma":0.0011271664,"threshold_uncertainty_score":0.02549678},"labels":[],"label_agreement":null},{"id":"W2167191127","doi":"10.1109/icassp.1989.266415","title":"A comparison of several acoustic representations for speech recognition with degraded and undegraded speech","year":2003,"lang":"en","type":"article","venue":"International Conference on Acoustics, Speech, and Signal Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":109,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Speech recognition; Cepstrum; Mel-frequency cepstrum; Computer science; Weighting; Noise (video); Filter (signal processing); Filter bank; Pattern recognition (psychology); Mathematics; Artificial intelligence; Feature extraction; Acoustics","score_opus":0.10345775018047919,"score_gpt":0.3427565667719608,"score_spread":0.2392988165914816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167191127","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6708349,0.0008492456,0.32144466,0.00017215264,0.00011320234,0.00022195672,0.00075750897,0.0025174425,0.0030889506],"genre_scores_gemma":[0.88973814,0.00032274227,0.10683074,0.000047169382,0.000018844332,0.00013080011,0.001248876,0.00010514304,0.0015574087],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99907315,0.00028485214,0.000086307344,0.00019107842,0.0002924996,0.00007206361],"domain_scores_gemma":[0.99743927,0.0015283916,0.00013239993,0.00026613116,0.0005353014,0.00009841709],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022015832,0.0008172153,0.0004942533,0.0011098476,0.00019315275,0.001016109,0.0006730722,0.0006541306,0.0017678889],"category_scores_gemma":[0.007881362,0.00021323087,0.00068604527,0.0005290668,0.00032302018,0.001424047,0.00061304757,0.000515302,0.0010419805],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0064724316,0.0005604306,0.010498007,0.00047248532,0.00039609976,0.0001633455,0.0003994448,0.055507734,0.10627643,0.0016104414,0.0011113607,0.81653184],"study_design_scores_gemma":[0.00029437983,0.0048674205,0.044947002,0.00012613357,0.0005826003,0.0012422199,0.00052314973,0.80511606,0.13709506,0.0020181593,0.0029010456,0.00028678737],"about_ca_topic_score_codex":0.0019813161,"about_ca_topic_score_gemma":0.001968136,"teacher_disagreement_score":0.0022015832,"about_ca_system_score_codex":0.00043936647,"about_ca_system_score_gemma":0.00040802523,"threshold_uncertainty_score":0.011643231},"labels":[],"label_agreement":null},{"id":"W2167308595","doi":"10.1136/jnnp-2012-303538.27","title":"P10 Cultural effects on the perception of non-linguistic affective vocalisation by Japanese and Canadian subjects","year":2012,"lang":"en","type":"article","venue":"Journal of Neurology Neurosurgery & Psychiatry","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Psychology; Valence (chemistry); Disgust; Sadness; Arousal; Nonverbal communication; Anger; Affect (linguistics); Happiness; Surprise; Facial expression; Perception; Developmental psychology; Audiology; Social psychology; Communication; Medicine","score_opus":0.01221067154532821,"score_gpt":0.23974694187301535,"score_spread":0.22753627032768714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167308595","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9985587,0.00007022896,0.000063437205,0.000021308684,0.000008999325,0.000011432387,0.00008272532,0.0000020124053,0.0011810987],"genre_scores_gemma":[0.99833554,0.00009071112,0.00017476306,0.000052730684,0.00000925805,0.000016623442,0.00013956465,0.0000048034753,0.0011760148],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99951136,0.00008044705,0.000037481885,0.00009255099,0.00016824396,0.000109899265],"domain_scores_gemma":[0.9986185,0.0003034297,0.00020297692,0.0000649848,0.0004873182,0.00032275845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067480153,0.00041729925,0.00024807276,0.00036307468,0.0008814919,0.00069934886,0.00020408577,0.00026137292,0.0037831473],"category_scores_gemma":[0.0022394273,0.00013069688,0.0002743817,0.00035686395,0.00067451055,0.00018014615,0.0004758559,0.00025583906,0.00031594705],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0045655738,0.00026601492,0.85435253,0.00026405047,0.00024143973,0.000937433,0.03943522,0.00010566881,0.06855791,0.00019662279,0.0012873133,0.029790167],"study_design_scores_gemma":[0.000009655646,0.00016689245,0.9911533,0.000011482537,0.000030835483,0.00014864106,0.007275891,0.00006146713,0.00064377085,0.000012209512,0.0004710092,0.000015018359],"about_ca_topic_score_codex":0.25818074,"about_ca_topic_score_gemma":0.40456977,"teacher_disagreement_score":0.74181926,"about_ca_system_score_codex":0.0007496772,"about_ca_system_score_gemma":0.000932839,"threshold_uncertainty_score":0.5133559},"labels":[],"label_agreement":null},{"id":"W2168166926","doi":"10.64152/10125/44034","title":"Establishing a methodology for benchmarking speech synthesis for computer-assisted language learning (CALL)","year":2005,"lang":"en","type":"article","venue":"Language learning & technology","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Benchmarking; Computer science; Benchmark (surveying); Pronunciation; Context (archaeology); Speech synthesis; Task (project management); Set (abstract data type); Artificial intelligence; Natural language processing; Programming language; Linguistics; Engineering","score_opus":0.03088655784593764,"score_gpt":0.29958428153839706,"score_spread":0.2686977236924594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168166926","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08592806,0.0007863762,0.8891461,0.00033548626,0.00015062999,0.0079483045,0.0012433097,0.0035701394,0.0108915875],"genre_scores_gemma":[0.21885704,0.00027052514,0.77059835,0.000105514984,0.00003105687,0.0058148173,0.0022373693,0.00039924023,0.0016860892],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.94209385,0.030390264,0.0068236417,0.0031373668,0.01636702,0.0011878129],"domain_scores_gemma":[0.9198712,0.032070246,0.0071907053,0.009079143,0.030716322,0.0010724793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04650227,0.0017185982,0.0015501014,0.007523623,0.0012818292,0.0042294823,0.003182494,0.0020820503,0.0028549645],"category_scores_gemma":[0.09636955,0.00065096014,0.0012333533,0.0041958317,0.0016730266,0.0028515318,0.0034048383,0.0017120464,0.0015016906],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010238914,0.0027707517,0.03282032,0.0042523993,0.0005418852,0.0006159278,0.0041758097,0.12156672,0.07622021,0.031605594,0.0065289107,0.7178776],"study_design_scores_gemma":[0.0005327129,0.011501771,0.064860694,0.0020744517,0.00045954884,0.0012933337,0.0077860886,0.56960857,0.24181686,0.03342807,0.066011846,0.0006260828],"about_ca_topic_score_codex":0.004309594,"about_ca_topic_score_gemma":0.004503138,"teacher_disagreement_score":0.04650227,"about_ca_system_score_codex":0.003266777,"about_ca_system_score_gemma":0.004291424,"threshold_uncertainty_score":0.2459305},"labels":[],"label_agreement":null},{"id":"W2168287019","doi":"10.1109/icassp.2008.4518745","title":"Adaptive score normalization for progressive model adaptation in text independent speaker verification","year":2008,"lang":"en","type":"article","venue":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Computer Research Institute of Montréal","funders":"","keywords":"Normalization (sociology); NIST; Speaker verification; Computer science; Speech recognition; Artificial intelligence; Speaker recognition","score_opus":0.10252485371504456,"score_gpt":0.2861246260957818,"score_spread":0.18359977238073727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168287019","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0061414563,0.00017476227,0.9919081,0.000038659407,0.000042451844,0.000061656654,0.000024359404,0.0007109492,0.0008976401],"genre_scores_gemma":[0.21978654,0.00036003158,0.77501076,0.00011330884,0.00010236484,0.00023621265,0.00024934305,0.00035120125,0.0037902493],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99683374,0.0009709119,0.00015685982,0.00052862597,0.0013903275,0.00011950281],"domain_scores_gemma":[0.99788874,0.0009096352,0.00014941815,0.00039601102,0.0006070701,0.00004920009],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027226473,0.000897498,0.0006788565,0.0007703901,0.00042365733,0.0008183702,0.0015572759,0.0006851397,0.002676672],"category_scores_gemma":[0.010217491,0.00026030678,0.0006698284,0.0008531351,0.0007670672,0.001318273,0.0014749953,0.0012532162,0.0016040801],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043543932,0.00014232936,0.00081211946,0.00012523048,0.00009753192,0.000118187316,0.00019641599,0.067696445,0.10632014,0.016662875,0.0024273242,0.8049659],"study_design_scores_gemma":[0.000052197658,0.0003345128,0.0023511406,0.000032735596,0.00007378691,0.00039522472,0.000056358498,0.8764295,0.094455026,0.015208608,0.01051652,0.00009436923],"about_ca_topic_score_codex":0.0017654988,"about_ca_topic_score_gemma":0.002118626,"teacher_disagreement_score":0.0027226473,"about_ca_system_score_codex":0.0005518663,"about_ca_system_score_gemma":0.0007205626,"threshold_uncertainty_score":0.014398932},"labels":[],"label_agreement":null},{"id":"W2168775301","doi":"10.1109/icassp.2001.940839","title":"Hypothesis-driven adaptation (Hydra): a flexible eigenvoice architecture","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nuance Communications (Canada)","funders":"","keywords":"Computer science; Speech recognition; Utterance; Adaptation (eye); Construct (python library); Task (project management); Artificial intelligence; Architecture; Pattern recognition (psychology)","score_opus":0.06641560512875076,"score_gpt":0.21953062565536943,"score_spread":0.15311502052661868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168775301","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01128449,0.00023250633,0.98514766,0.00012514662,0.00005413908,0.000033071992,0.000032447515,0.0019071636,0.0011833884],"genre_scores_gemma":[0.53884035,0.000278547,0.45482358,0.00030540745,0.00009315067,0.00020561833,0.00021718141,0.00042481607,0.004811321],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99967027,0.000097888005,0.000015763348,0.0001118636,0.000065658205,0.00003861153],"domain_scores_gemma":[0.99960035,0.0001865733,0.000019793753,0.000109028566,0.000050493567,0.000033764263],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011623888,0.0004861722,0.0005804061,0.00028175188,0.000285537,0.0007301064,0.0019116765,0.00085014314,0.0024009072],"category_scores_gemma":[0.0012431418,0.000574373,0.0006853728,0.00022629,0.00073891814,0.0012010712,0.0014163642,0.0014030909,0.0011777017],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004005593,0.00019734872,0.0017663144,0.00014334221,0.0003367054,0.00024235623,0.0004296774,0.3456645,0.08624209,0.044385433,0.0032592632,0.5169325],"study_design_scores_gemma":[0.000012877279,0.00005522081,0.0003229976,0.0000072911453,0.000022542079,0.000062567764,0.000013807743,0.9760212,0.0075856643,0.01361729,0.00225702,0.000021508122],"about_ca_topic_score_codex":0.0016172087,"about_ca_topic_score_gemma":0.0023829082,"teacher_disagreement_score":0.0024009072,"about_ca_system_score_codex":0.00035470322,"about_ca_system_score_gemma":0.00055801275,"threshold_uncertainty_score":0.008031845},"labels":[],"label_agreement":null},{"id":"W2169890399","doi":"10.1007/978-3-642-25020-0_32","title":"Comparative Evaluation of Feature Normalization Techniques for Speaker Verification","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal; Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Normalization (sociology); NIST; Computer science; Speaker verification; Linear discriminant analysis; Speech recognition; Pattern recognition (psychology); Artificial intelligence; Probabilistic logic; Feature vector; Feature (linguistics); Speaker recognition","score_opus":0.07976696728653544,"score_gpt":0.3120268597436664,"score_spread":0.23225989245713097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169890399","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28325835,0.026015641,0.6717182,0.000305811,0.000717915,0.00041128066,0.0011519644,0.007895978,0.008524912],"genre_scores_gemma":[0.57609683,0.008826321,0.3996212,0.00015130131,0.00029732636,0.000257236,0.005392863,0.0010440777,0.008312884],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9958845,0.001269158,0.0003062223,0.00059658766,0.001691921,0.00025159723],"domain_scores_gemma":[0.9899002,0.006992546,0.0002481986,0.00070417626,0.0020505171,0.00010452726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0048416657,0.0014211636,0.0014380176,0.0019615802,0.0006122651,0.0012289609,0.0017243811,0.0011722355,0.0053603486],"category_scores_gemma":[0.011643476,0.00043920797,0.0010581914,0.0016304556,0.0005112167,0.001971205,0.0012906546,0.00071593485,0.0021012852],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00396914,0.00021568923,0.0015408596,0.0007428087,0.00044229807,0.00010490752,0.00013565677,0.008634699,0.09307662,0.00061684835,0.0016537019,0.88886684],"study_design_scores_gemma":[0.0005134107,0.004616369,0.033954535,0.0002260741,0.0024473467,0.0032452128,0.00051713403,0.39244848,0.5475624,0.0020642756,0.012151475,0.00025324748],"about_ca_topic_score_codex":0.0028553728,"about_ca_topic_score_gemma":0.0037420772,"teacher_disagreement_score":0.0053603486,"about_ca_system_score_codex":0.0005157256,"about_ca_system_score_gemma":0.0005512168,"threshold_uncertainty_score":0.0256055},"labels":[],"label_agreement":null},{"id":"W2170521850","doi":"10.1109/mwscas.2000.951427","title":"ARMA lattice modeling for isolated word speech recognition","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Autoregressive–moving-average model; Speech recognition; Lattice (music); Computer science; Autoregressive model; Artificial intelligence; Pattern recognition (psychology); Natural language processing; Mathematics; Statistics; Acoustics; Physics","score_opus":0.10108087647937199,"score_gpt":0.2618220852740568,"score_spread":0.16074120879468484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170521850","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009483013,0.0004015485,0.98752964,0.00009324345,0.00008350696,0.000020020025,0.00011825606,0.0012043519,0.0010663182],"genre_scores_gemma":[0.5013522,0.0010057171,0.48544675,0.00016448033,0.00017942589,0.00024513155,0.00077608693,0.00033843218,0.010491788],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994592,0.00017793765,0.000030407391,0.000111679794,0.00018406863,0.00003667559],"domain_scores_gemma":[0.99930644,0.0003225526,0.00006105614,0.00009041877,0.0001924746,0.000027006305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007548972,0.00056674826,0.0006860358,0.0005478585,0.00022682115,0.0006443936,0.0009704211,0.0005519071,0.0024756806],"category_scores_gemma":[0.0019748416,0.00030178222,0.0007629876,0.0005712141,0.00028007102,0.000789448,0.00033931003,0.0010524814,0.0022579976],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032118143,0.00012947532,0.0008915957,0.00013955151,0.00014915413,0.00016471406,0.000087053624,0.5985135,0.03599061,0.016480677,0.0030052338,0.34412727],"study_design_scores_gemma":[0.0000025060588,0.000012826721,0.000062486906,0.000002000567,0.0000049204486,0.000018897334,0.0000023277603,0.9969586,0.0012551921,0.0011327555,0.0005431419,0.0000044620233],"about_ca_topic_score_codex":0.004535501,"about_ca_topic_score_gemma":0.004629575,"teacher_disagreement_score":0.004535501,"about_ca_system_score_codex":0.000450532,"about_ca_system_score_gemma":0.0005748566,"threshold_uncertainty_score":0.009018183},"labels":[],"label_agreement":null},{"id":"W2172097686","doi":"10.1109/icassp.2012.6288863","title":"Understanding how Deep Belief Networks perform acoustic modelling","year":2012,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":270,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Deep belief network; TIMIT; Computer science; Hidden Markov model; Artificial intelligence; Artificial neural network; Similarity (geometry); Feature (linguistics); Pattern recognition (psychology); Speech recognition; Feature vector; Visualization; Representation (politics)","score_opus":0.15426382191673457,"score_gpt":0.23917869812238465,"score_spread":0.08491487620565008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2172097686","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020901185,0.0011318645,0.9638004,0.002627853,0.000097252916,0.000029457102,0.00019044102,0.0005428229,0.010678761],"genre_scores_gemma":[0.76421785,0.0027224594,0.22450654,0.00034509698,0.000108411914,0.00009391319,0.00025905992,0.00018057962,0.0075660516],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994228,0.00025157732,0.000026381636,0.000088480294,0.00013339525,0.000077387085],"domain_scores_gemma":[0.9976507,0.0016186896,0.00012545865,0.0001904199,0.00032140824,0.00009327093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016873128,0.0007813609,0.00042779246,0.000724728,0.0004480001,0.0033673071,0.0012640998,0.0014271153,0.0035348732],"category_scores_gemma":[0.010845619,0.00074982113,0.0005334429,0.0006587364,0.0010222192,0.0059330994,0.0010970153,0.002342584,0.0008149823],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006522417,0.00004182141,0.0022952706,0.00014852424,0.00009920784,0.000110972505,0.0004306845,0.5040702,0.0019292574,0.40559533,0.0028601685,0.08235339],"study_design_scores_gemma":[0.0000053674444,0.000009629904,0.00023200433,0.00003057209,0.000009293662,0.000017133156,0.000054623448,0.7638219,0.00066569156,0.23342818,0.0017136238,0.000011907867],"about_ca_topic_score_codex":0.013729738,"about_ca_topic_score_gemma":0.0099910805,"teacher_disagreement_score":0.013729738,"about_ca_system_score_codex":0.0012318615,"about_ca_system_score_gemma":0.00093415537,"threshold_uncertainty_score":0.027299643},"labels":[],"label_agreement":null},{"id":"W2178103884","doi":"10.48550/arxiv.1511.08400","title":"Regularizing RNNs by Stabilizing Activations","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Air Force Research Laboratory; Advanced Research Projects Agency; Defense Advanced Research Projects Agency; U.S. Department of Defense","keywords":"Recurrent neural network; TIMIT; Computer science; Term (time); Dropout (neural networks); Speech recognition; Task (project management); Language model; Artificial intelligence; Artificial neural network; Machine learning; Hidden Markov model","score_opus":0.1401149921742679,"score_gpt":0.19757555390488912,"score_spread":0.057460561730621224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2178103884","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036152747,0.00020613971,0.95838654,0.00018607867,0.00010535516,0.000036634774,0.00008487643,0.0024406207,0.0024009407],"genre_scores_gemma":[0.7222145,0.00022053251,0.27055007,0.0002731492,0.00008784802,0.00020724542,0.00040691116,0.00075349753,0.005286265],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99944,0.00011977401,0.000042065443,0.00019586174,0.00013639776,0.00006586581],"domain_scores_gemma":[0.9989196,0.00035346896,0.00012722096,0.00024575862,0.00030995687,0.000044028533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011082301,0.0014273592,0.0005523794,0.00039254085,0.00041652925,0.00074810605,0.0014020163,0.0008845882,0.0022187857],"category_scores_gemma":[0.004862304,0.00045657676,0.00048775595,0.0003351168,0.00069515296,0.0011005931,0.0011211134,0.0016187779,0.0016047568],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013119247,0.00007003929,0.0011705455,0.00008350673,0.00006509164,0.00009606288,0.00010491626,0.84119654,0.042897474,0.009808319,0.0029124194,0.10146386],"study_design_scores_gemma":[0.000005295406,0.000022051761,0.0000892703,0.000005038476,0.0000062230406,0.000014477119,0.000006485667,0.99024546,0.0065146517,0.0024760526,0.0006104173,0.0000045773145],"about_ca_topic_score_codex":0.003656034,"about_ca_topic_score_gemma":0.0060379244,"teacher_disagreement_score":0.003656034,"about_ca_system_score_codex":0.00068580534,"about_ca_system_score_gemma":0.0009815529,"threshold_uncertainty_score":0.0074225664},"labels":[],"label_agreement":null},{"id":"W2178178359","doi":"10.1121/1.4934055","title":"Using automatic alignment on child speech: Directions for improvement","year":2015,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Western University","funders":"","keywords":"Speech recognition; Computer science; Limiting; Transcription (linguistics); Natural language processing; Training set; Speech production; Artificial intelligence; Linguistics","score_opus":0.049908043215891554,"score_gpt":0.2916734415916672,"score_spread":0.24176539837577565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2178178359","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1517615,0.047689285,0.6365645,0.052922226,0.0033360366,0.0036859952,0.017633138,0.04403098,0.042376354],"genre_scores_gemma":[0.14591035,0.011649648,0.8011644,0.00425429,0.0010025246,0.0031733066,0.020815132,0.0028071834,0.009223218],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97774804,0.013152695,0.0014613797,0.00360194,0.003030219,0.0010056492],"domain_scores_gemma":[0.8431724,0.07360409,0.0042103766,0.025075963,0.049436208,0.0045010303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.043654934,0.004285299,0.0041144206,0.0042776885,0.0015656867,0.0060135718,0.0069859405,0.0037161543,0.033467945],"category_scores_gemma":[0.097039305,0.0015221904,0.002185022,0.0058612134,0.0019052087,0.016327517,0.0039254013,0.0035987522,0.019871783],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015521371,0.0014195585,0.054308288,0.0032813116,0.0005027816,0.00023179047,0.0034843807,0.004071875,0.020385576,0.004161351,0.04958329,0.8570176],"study_design_scores_gemma":[0.0011007428,0.004778658,0.30939198,0.007056776,0.0018060567,0.0017927701,0.015256883,0.14304885,0.06288937,0.03201854,0.41962418,0.0012351954],"about_ca_topic_score_codex":0.03961435,"about_ca_topic_score_gemma":0.032384682,"teacher_disagreement_score":0.043654934,"about_ca_system_score_codex":0.0021947757,"about_ca_system_score_gemma":0.0084045045,"threshold_uncertainty_score":0.2308721},"labels":[],"label_agreement":null},{"id":"W2179428711","doi":"10.1007/s11042-015-3039-x","title":"High quality voice conversion using prosodic and high-resolution spectral features","year":2015,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Research (Canada)","funders":"","keywords":"Timbre; Autoencoder; Feature (linguistics); Focus (optics); Artificial neural network; Quality (philosophy); Pattern recognition (psychology)","score_opus":0.07011119276320464,"score_gpt":0.29739668727738267,"score_spread":0.227285494514178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2179428711","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2024489,0.0012453607,0.7745383,0.0002471957,0.00024956156,0.000110608344,0.00032311166,0.0024414263,0.018395657],"genre_scores_gemma":[0.7229268,0.00093268376,0.26426437,0.0001598206,0.00018951856,0.00007009051,0.0006389161,0.00042031932,0.0103974445],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9998406,0.000029675344,0.000008636173,0.000030794123,0.00007318555,0.000017078553],"domain_scores_gemma":[0.99969304,0.00014800069,0.000014190226,0.000045665332,0.00008373714,0.000015337571],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027472276,0.0004037628,0.00026631381,0.00040657367,0.00017675442,0.0007381021,0.00029568464,0.000499155,0.0057240175],"category_scores_gemma":[0.00075702235,0.00021366662,0.00025945716,0.0003702138,0.0002604808,0.00079690345,0.0005004561,0.00054098887,0.001637008],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00068627135,0.00009723683,0.0008908826,0.00021920935,0.0000436453,0.00031752026,0.00008664578,0.0038401035,0.67619807,0.0020788168,0.0010664462,0.31447515],"study_design_scores_gemma":[0.00016339417,0.0005419866,0.008951922,0.00009498622,0.0001899727,0.0014545356,0.00023978666,0.12465481,0.84382665,0.0035466251,0.0162532,0.00008213554],"about_ca_topic_score_codex":0.00019911553,"about_ca_topic_score_gemma":0.00047297636,"teacher_disagreement_score":0.0057240175,"about_ca_system_score_codex":0.00007432829,"about_ca_system_score_gemma":0.000101333615,"threshold_uncertainty_score":0.019148707},"labels":[],"label_agreement":null},{"id":"W217970951","doi":"","title":"Roles of Pre-Training and Fine-Tuning in Context-Dependent DBN-HMMs for Real-World Speech Recognition","year":2010,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":193,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Hidden Markov model; Computer science; Artificial intelligence; Speech recognition; Context (archaeology); Deep belief network; Vocabulary; Deep learning; Pattern recognition (psychology)","score_opus":0.042077798734252304,"score_gpt":0.2835390570334626,"score_spread":0.2414612582992103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W217970951","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23262925,0.0010076368,0.76054484,0.000394664,0.00010789766,0.0001296132,0.00007674225,0.002095452,0.0030139177],"genre_scores_gemma":[0.80107033,0.00023536231,0.19709188,0.00017708921,0.000028243676,0.0001128555,0.00014997937,0.00015057958,0.0009836755],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998961,0.0004882344,0.000078486686,0.00024015481,0.00014500403,0.00008711986],"domain_scores_gemma":[0.99531883,0.0030909374,0.00019846956,0.0008934874,0.00034249222,0.00015564733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023682162,0.0009037516,0.0006792231,0.00024822893,0.0004271232,0.00089392293,0.0010149669,0.0009694697,0.0011499099],"category_scores_gemma":[0.010766006,0.0005981241,0.0002994373,0.00026871433,0.00075729756,0.0018347009,0.0008233417,0.0022859538,0.0004435473],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010193089,0.00094818696,0.00597988,0.0002653667,0.00012152137,0.0001828043,0.00035192864,0.3391735,0.16177206,0.004298137,0.001051577,0.48483577],"study_design_scores_gemma":[0.0000393183,0.00023968973,0.0036314118,0.000034711516,0.000037438505,0.000111494046,0.000056170724,0.900795,0.09020231,0.0035598683,0.0012493114,0.000043307664],"about_ca_topic_score_codex":0.0027238012,"about_ca_topic_score_gemma":0.0056898687,"teacher_disagreement_score":0.0027238012,"about_ca_system_score_codex":0.00052065845,"about_ca_system_score_gemma":0.0007364769,"threshold_uncertainty_score":0.012524426},"labels":[],"label_agreement":null},{"id":"W2188183693","doi":"10.21437/interspeech.2013-744","title":"Exploring convolutional neural network structures and optimization techniques for speech recognition","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":388,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Convolutional neural network; Speech recognition; Artificial neural network; Artificial intelligence; Recurrent neural network; Time delay neural network","score_opus":0.09942673034509407,"score_gpt":0.2529693359682053,"score_spread":0.15354260562311123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2188183693","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02775985,0.0019073462,0.965208,0.00044941952,0.00004555968,0.00003615155,0.000088135974,0.00082352373,0.0036820727],"genre_scores_gemma":[0.5340862,0.002624897,0.4563635,0.00021384888,0.00008332929,0.00012861627,0.00032954133,0.00022227998,0.0059478064],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997811,0.0000639587,0.000013458366,0.000053283875,0.000060503447,0.000027692624],"domain_scores_gemma":[0.99959654,0.00025414917,0.000038632035,0.00003822003,0.00006206777,0.000010410143],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009021444,0.0009582224,0.0003728415,0.0005512431,0.00019209429,0.0005013238,0.00064229086,0.0006804772,0.0018432671],"category_scores_gemma":[0.0024123369,0.0005313866,0.000468861,0.00062021654,0.00044774628,0.0013176114,0.00056403544,0.0009942306,0.00039783612],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006713961,0.000042695337,0.0005876063,0.000113181515,0.00007328575,0.0000454584,0.00003169056,0.8388044,0.009638952,0.016360145,0.0011540799,0.13308139],"study_design_scores_gemma":[0.000002937505,0.000010974557,0.000076044096,0.0000054977263,0.000005459241,0.0000048508746,0.000002612001,0.9949066,0.0015008841,0.0030508323,0.00043079097,0.0000024869657],"about_ca_topic_score_codex":0.0076574557,"about_ca_topic_score_gemma":0.013811131,"teacher_disagreement_score":0.0076574557,"about_ca_system_score_codex":0.00096888293,"about_ca_system_score_gemma":0.0008418691,"threshold_uncertainty_score":0.015225768},"labels":[],"label_agreement":null},{"id":"W2189251954","doi":"","title":"Speech Inversion with Acoustic Classification","year":2012,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Hidden Markov model; Speech recognition; Computer science; Vocal tract; Acoustic model; Inversion (geology); Component (thermodynamics); Artificial intelligence; Speech processing","score_opus":0.04104107336699916,"score_gpt":0.2434795323085668,"score_spread":0.20243845894156764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2189251954","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015983976,0.00043663743,0.9769189,0.00028865944,0.00018189731,0.00008406728,0.0001485009,0.0026901378,0.0032672335],"genre_scores_gemma":[0.32193407,0.00034472835,0.6663602,0.00036564659,0.00035069694,0.00019493657,0.0010770718,0.00029007,0.009082578],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999064,0.00021403696,0.000050631006,0.0002852187,0.00029768597,0.00008838073],"domain_scores_gemma":[0.9975188,0.0011915843,0.00016511804,0.0004461513,0.00059653405,0.00008169859],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015162901,0.0013642632,0.0009996921,0.0015703508,0.0006110077,0.0010914407,0.0016606095,0.001708321,0.0061406265],"category_scores_gemma":[0.006843418,0.00057486753,0.0010298652,0.00081280526,0.00081483787,0.0020375815,0.0017977707,0.0023551993,0.0035365114],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029751912,0.00014927465,0.0012941364,0.00008267735,0.000057770078,0.000078077384,0.000080708385,0.09249262,0.012680501,0.005030823,0.0028846331,0.8848712],"study_design_scores_gemma":[0.000010495135,0.00003135388,0.00034935828,0.000009796247,0.000014139931,0.00006453523,0.000017126262,0.9852225,0.0068665636,0.005669739,0.0017320616,0.000012269705],"about_ca_topic_score_codex":0.0033003103,"about_ca_topic_score_gemma":0.0035138417,"teacher_disagreement_score":0.0061406265,"about_ca_system_score_codex":0.00074082747,"about_ca_system_score_gemma":0.00090394233,"threshold_uncertainty_score":0.020542443},"labels":[],"label_agreement":null},{"id":"W2189903590","doi":"10.1016/j.csl.2015.11.002","title":"Speech Production in Speech Technologies: Introduction to the CSL Special Issue","year":2015,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Rehabilitation Institute","funders":"","keywords":"Computer science; Speech production; Speech technology; Production (economics); Context (archaeology); Speech processing; Speech recognition; History","score_opus":0.01931376996621591,"score_gpt":0.2584920550608656,"score_spread":0.23917828509464967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2189903590","genre_codex":"review","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003580717,0.5749885,0.13398972,0.054377142,0.10541261,0.00029943683,0.0011892621,0.003140173,0.123022415],"genre_scores_gemma":[0.033947907,0.39838818,0.05692056,0.013795653,0.2316523,0.00044122405,0.0026228162,0.0028008649,0.25943056],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984059,0.00028552432,0.00027358497,0.0003166947,0.00061448215,0.00010374749],"domain_scores_gemma":[0.99400663,0.0018912634,0.00021200516,0.0004778018,0.00295244,0.00045983042],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003893252,0.0012313905,0.0011623024,0.0058639958,0.0010304379,0.005729657,0.0017031465,0.0032483265,0.020887103],"category_scores_gemma":[0.004534401,0.00083529047,0.0007980186,0.0031044674,0.0024708644,0.0050787213,0.0029973781,0.0041748667,0.017898617],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007923703,0.0001412045,0.00045837773,0.0010200448,0.000021248581,0.00014121163,0.00020391587,0.0006781704,0.005261942,0.012479598,0.26757464,0.71194047],"study_design_scores_gemma":[0.000005613782,0.00008914422,0.0015819956,0.0005035844,0.000012622497,0.0005861665,0.00011698146,0.0013131818,0.0022364333,0.0054299114,0.9880824,0.000041991007],"about_ca_topic_score_codex":0.0035184915,"about_ca_topic_score_gemma":0.0056056674,"teacher_disagreement_score":0.020887103,"about_ca_system_score_codex":0.002318445,"about_ca_system_score_gemma":0.002382567,"threshold_uncertainty_score":0.069874346},"labels":[],"label_agreement":null},{"id":"W2235204424","doi":"10.48550/arxiv.1111.3182","title":"Context Tree Switching","year":2011,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Weighting; Tree (set theory); Context (archaeology); Markov chain; Computer science; Binary tree; Generalization; Mathematics; Class (philosophy); Markov process; Algorithm; Artificial intelligence; Machine learning; Statistics; Combinatorics; Geography","score_opus":0.14249565766110855,"score_gpt":0.16491138096625207,"score_spread":0.02241572330514352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2235204424","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011993748,0.0004400466,0.97868013,0.00015171106,0.00017374777,0.00009654476,0.00022531793,0.0016307249,0.0066080433],"genre_scores_gemma":[0.41079703,0.0007762721,0.57319546,0.0005503641,0.0003176646,0.0003334969,0.0011982406,0.0008295083,0.01200199],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99853873,0.00038674165,0.0000665806,0.00036775926,0.00051600276,0.00012420164],"domain_scores_gemma":[0.9977366,0.0010942478,0.000091206224,0.0005996209,0.00037518234,0.00010317264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013322078,0.0007134176,0.000753959,0.000928906,0.00078059506,0.0013014185,0.0016908258,0.0009596879,0.009747889],"category_scores_gemma":[0.0070119053,0.00040576328,0.0008065727,0.0013900389,0.00054496515,0.002929267,0.0021114685,0.001818581,0.0027104435],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002684356,0.00018052249,0.0022256556,0.00020630259,0.000089308116,0.00030467557,0.0003506731,0.057833288,0.02488819,0.13883995,0.010633051,0.76418],"study_design_scores_gemma":[0.000040660747,0.00011756537,0.00089831516,0.00006070058,0.00007734494,0.0004930535,0.00008008825,0.77423704,0.022390297,0.1554855,0.04605682,0.00006260712],"about_ca_topic_score_codex":0.0024822694,"about_ca_topic_score_gemma":0.0038089463,"teacher_disagreement_score":0.009747889,"about_ca_system_score_codex":0.0005816857,"about_ca_system_score_gemma":0.0011009423,"threshold_uncertainty_score":0.03260994},"labels":[],"label_agreement":null},{"id":"W2248508985","doi":"10.21437/interspeech.2016-1297","title":"Automatic Dialect Detection in Arabic Broadcast Speech","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Modern Standard Arabic; Support vector machine; Artificial intelligence; Arabic; Classifier (UML); Speech recognition; Natural language processing; Language identification; Identification (biology); Linguistics; Natural language","score_opus":0.025306347845595212,"score_gpt":0.2544226352888353,"score_spread":0.22911628744324009,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2248508985","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9275226,0.00041556958,0.066832654,0.00011030884,0.00007335585,0.00009899437,0.00059107284,0.0014909913,0.0028645261],"genre_scores_gemma":[0.94298637,0.0001893268,0.05397748,0.00003924849,0.000030365058,0.000046554673,0.0011084576,0.00011934886,0.0015028642],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898607,0.00032509817,0.00007060467,0.00026052832,0.00025998428,0.00009773699],"domain_scores_gemma":[0.9974515,0.0010318522,0.00018766154,0.0002810575,0.000932544,0.00011539],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092810014,0.0005405026,0.00046730464,0.0017371294,0.0004488133,0.0008921692,0.00041100173,0.00057037116,0.001361951],"category_scores_gemma":[0.003558591,0.00015618477,0.00029111793,0.00055195444,0.0002820287,0.0007572789,0.000537036,0.00045346573,0.0015664689],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016002939,0.0002513047,0.058225144,0.00051823247,0.0001017052,0.00046044224,0.0016203239,0.009231337,0.29239023,0.0011191147,0.0023434197,0.6321384],"study_design_scores_gemma":[0.00008699787,0.0007288669,0.20894092,0.000076094235,0.00015708573,0.0018915249,0.0014739208,0.41254434,0.36539528,0.001662766,0.0069013224,0.0001409213],"about_ca_topic_score_codex":0.0032153514,"about_ca_topic_score_gemma":0.0028097497,"teacher_disagreement_score":0.0032153514,"about_ca_system_score_codex":0.00030733668,"about_ca_system_score_gemma":0.0002897155,"threshold_uncertainty_score":0.006393254},"labels":[],"label_agreement":null},{"id":"W2250185923","doi":"10.18653/v1/w15-5117","title":"Remote Speech Technology for Speech Professionals - the CloudCAST initiative","year":2015,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Rehabilitation Institute; University of Toronto","funders":"Leverhulme Trust","keywords":"Speech technology; Speech processing; Computer science; Speech recognition; Engineering","score_opus":0.09780048706451855,"score_gpt":0.32936750575030815,"score_spread":0.2315670186857896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2250185923","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047079064,0.025019327,0.34801373,0.12868242,0.024380628,0.0022926568,0.03091526,0.07922428,0.3143927],"genre_scores_gemma":[0.17399192,0.013497349,0.19541402,0.013069782,0.0068358094,0.0015768415,0.053438023,0.015799614,0.52637666],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99852777,0.0001804689,0.00004268644,0.00025067668,0.0006833473,0.00031493878],"domain_scores_gemma":[0.992334,0.00140157,0.00017648842,0.0007699565,0.0016616001,0.0036564388],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005875315,0.00069933385,0.0005516588,0.0007608229,0.0012381597,0.0031935514,0.00172053,0.0023666597,0.033138387],"category_scores_gemma":[0.004306477,0.0003524349,0.0003371252,0.000743671,0.0007011637,0.0053753844,0.004891012,0.002952446,0.023238331],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010360529,0.00043735615,0.0010538183,0.00019670611,0.00001514938,0.00015330127,0.00033831538,0.00039947857,0.014986944,0.013939789,0.68288344,0.28455964],"study_design_scores_gemma":[0.00035780127,0.00018089314,0.004315582,0.00010624529,0.000022913564,0.00019990018,0.00050787244,0.0058259186,0.0114273215,0.0076848255,0.96933794,0.000032809963],"about_ca_topic_score_codex":0.010776574,"about_ca_topic_score_gemma":0.014677992,"teacher_disagreement_score":0.033138387,"about_ca_system_score_codex":0.00096981844,"about_ca_system_score_gemma":0.004527222,"threshold_uncertainty_score":0.11085898},"labels":[],"label_agreement":null},{"id":"W2250268452","doi":"","title":"Identification of Speakers in Novels","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":63,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Task (project management); Identification (biology); Computer science; Natural language processing; Narrative; Artificial intelligence; Speech recognition; Linguistics; Engineering","score_opus":0.01587556571042371,"score_gpt":0.2291732713894288,"score_spread":0.2132977056790051,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2250268452","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85442865,0.0010886195,0.12403275,0.0005033039,0.000462616,0.00028042257,0.0018338956,0.0028494466,0.01452022],"genre_scores_gemma":[0.9278398,0.00033382338,0.064644024,0.00008071888,0.00015414719,0.00009137868,0.0022707959,0.00021325816,0.0043721213],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973023,0.0008405942,0.00013276914,0.0011639062,0.00040912806,0.0001513193],"domain_scores_gemma":[0.9950216,0.002254356,0.00068334304,0.0008154662,0.0009617484,0.0002635299],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019185351,0.0006632806,0.00068073143,0.0009213213,0.0012259042,0.0017576431,0.0006944309,0.0011214488,0.0038303104],"category_scores_gemma":[0.007906873,0.00032687333,0.00050514785,0.0004731288,0.0006598208,0.0023921712,0.0014608213,0.0010092913,0.0035754694],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003017508,0.0004930588,0.054267786,0.0012558397,0.0003265297,0.0031648935,0.014209298,0.008062761,0.25358278,0.00660772,0.016329842,0.638682],"study_design_scores_gemma":[0.00026195234,0.001558886,0.16733126,0.0004008404,0.0005151848,0.014975535,0.023425141,0.38660797,0.31042072,0.017320683,0.07675721,0.0004246857],"about_ca_topic_score_codex":0.00060849305,"about_ca_topic_score_gemma":0.00089002616,"teacher_disagreement_score":0.0038303104,"about_ca_system_score_codex":0.00037499095,"about_ca_system_score_gemma":0.0002865545,"threshold_uncertainty_score":0.012813687},"labels":[],"label_agreement":null},{"id":"W2266004465","doi":"","title":"Evaluating Bayesian and L1 Approaches for Sparse Unsupervised Learning .","year":2012,"lang":"en","type":"article","venue":"Cambridge University Engineering Department Publications Database","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Bayesian probability; Artificial intelligence; Unsupervised learning; Machine learning; Pattern recognition (psychology)","score_opus":0.08170086113538608,"score_gpt":0.2562536995249276,"score_spread":0.17455283838954153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2266004465","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10712876,0.0071740733,0.86996293,0.0020422214,0.00031177927,0.00030999543,0.0016096977,0.0032310018,0.008229575],"genre_scores_gemma":[0.5501061,0.0017603006,0.43189883,0.0006892397,0.00051081483,0.0003659706,0.0067595374,0.0010284643,0.0068807728],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9890786,0.0068557602,0.0005581484,0.0010014835,0.002139174,0.0003667983],"domain_scores_gemma":[0.9154897,0.07288998,0.0014460449,0.0033139116,0.005910394,0.0009499818],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019997362,0.0015645288,0.0019009446,0.0029144806,0.0011952718,0.0026413917,0.0027374083,0.0034463743,0.003957292],"category_scores_gemma":[0.090706535,0.0010256056,0.0011633177,0.0019686786,0.0015150871,0.0043469737,0.0033751975,0.0028130354,0.0014687581],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030114166,0.00061199407,0.009130837,0.00071348,0.0008828735,0.00009317818,0.00027634605,0.4920037,0.0019157655,0.024755303,0.01801523,0.44858995],"study_design_scores_gemma":[0.0001264657,0.00018771357,0.0012143758,0.00005166132,0.00009987978,0.00004830792,0.00008349599,0.9768116,0.0014610207,0.01872543,0.0011652044,0.000024845924],"about_ca_topic_score_codex":0.016764726,"about_ca_topic_score_gemma":0.028876817,"teacher_disagreement_score":0.019997362,"about_ca_system_score_codex":0.0023011367,"about_ca_system_score_gemma":0.0025904507,"threshold_uncertainty_score":0.105757415},"labels":[],"label_agreement":null},{"id":"W2292259253","doi":"10.1109/asru.2015.7404844","title":"Deep bottleneck features for i-vector based text-independent speaker verification","year":2015,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Speaker verification; NIST; Computer science; Speech recognition; Discriminative model; Bottleneck; Speaker recognition; Cepstrum; Mel-frequency cepstrum; Artificial intelligence; Artificial neural network; Pattern recognition (psychology); Feature extraction","score_opus":0.04303567032976717,"score_gpt":0.26536641523679655,"score_spread":0.22233074490702937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2292259253","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10055599,0.0013863161,0.8894744,0.0001905257,0.0001282153,0.000111523994,0.0006866432,0.004463135,0.0030032226],"genre_scores_gemma":[0.7070033,0.00046339436,0.28505072,0.000106708794,0.0000644852,0.00014777543,0.0020732302,0.00019486013,0.0048955427],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995198,0.00008982847,0.000032408825,0.00010437651,0.0001904778,0.00006308318],"domain_scores_gemma":[0.99921787,0.00030840037,0.00008475076,0.00012008326,0.00023476411,0.000034214325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012671321,0.0007317749,0.00067511154,0.0006480628,0.00035638918,0.00052840787,0.00091435877,0.00052099506,0.0036780105],"category_scores_gemma":[0.0024022793,0.00026391886,0.00038623976,0.00039985505,0.00025604744,0.0011690736,0.00097439974,0.001061762,0.0014625924],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010402843,0.00021126134,0.0019179466,0.00017894276,0.00006466227,0.00014262955,0.0001039889,0.065528564,0.16792761,0.004064419,0.004211087,0.7546087],"study_design_scores_gemma":[0.000022462558,0.00027173935,0.0027865781,0.000027848988,0.00004177444,0.00015195618,0.000033972257,0.8877248,0.101698555,0.0030932717,0.0041086506,0.000038445167],"about_ca_topic_score_codex":0.0027356488,"about_ca_topic_score_gemma":0.004404826,"teacher_disagreement_score":0.0036780105,"about_ca_system_score_codex":0.0005591329,"about_ca_system_score_gemma":0.0008440868,"threshold_uncertainty_score":0.012304187},"labels":[],"label_agreement":null},{"id":"W2294245963","doi":"10.21437/interspeech.2014-82","title":"Manifold regularized deep neural networks","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Artificial neural network; Bottleneck; Discriminative model; Feature extraction; Artificial intelligence; Pattern recognition (psychology); Speech recognition; Locality; Regularization (linguistics); Deep learning; Context (archaeology); Feature vector; Deep neural networks","score_opus":0.011047712830058188,"score_gpt":0.20318778475589586,"score_spread":0.19214007192583768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2294245963","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018138805,0.00059388194,0.9787507,0.00011827046,0.00003213761,0.000023378714,0.00008710934,0.00073779526,0.0015179308],"genre_scores_gemma":[0.648026,0.0010616835,0.34360644,0.00014928657,0.00011814473,0.00015865488,0.00074734027,0.00021382682,0.0059186644],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995969,0.00012833178,0.000020866659,0.00010002871,0.0001236149,0.000030340028],"domain_scores_gemma":[0.9994574,0.00020440247,0.000070593196,0.0000922904,0.00016055274,0.000014659083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006363792,0.00075896113,0.0006670916,0.00039309484,0.0002591565,0.00047448959,0.00071552454,0.00058671116,0.0013755072],"category_scores_gemma":[0.0020705017,0.00026423056,0.0003977781,0.0004800915,0.00057029695,0.0010780612,0.0007488849,0.0010087173,0.0005603376],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001057354,0.000036314188,0.00044131273,0.00008907925,0.000052936193,0.000053654712,0.000048693775,0.8138638,0.01293825,0.016062725,0.0023375896,0.15396994],"study_design_scores_gemma":[0.000001675999,0.000014445514,0.00011105762,0.000002696476,0.000003082669,0.000009452499,0.0000027803526,0.9918128,0.0014381899,0.0059591588,0.00064096384,0.000003631697],"about_ca_topic_score_codex":0.0023927756,"about_ca_topic_score_gemma":0.0030803694,"teacher_disagreement_score":0.0023927756,"about_ca_system_score_codex":0.0006913382,"about_ca_system_score_gemma":0.0005669983,"threshold_uncertainty_score":0.005016029},"labels":[],"label_agreement":null},{"id":"W2333871989","doi":"10.1109/taslp.2016.2546458","title":"Text-Dependent Speaker Recognition With Random Digit Strings","year":2016,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Normalization (sociology); Speech recognition; Computer science; String (physics); Pattern recognition (psychology); Logistic regression; Numerical digit; Speaker recognition; Random forest; Digit recognition; Artificial intelligence; Statistics; Mathematics; Machine learning; Arithmetic; Artificial neural network","score_opus":0.016445153151105202,"score_gpt":0.23468969299936557,"score_spread":0.21824453984826037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2333871989","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07859372,0.0015239003,0.89824516,0.00041484903,0.0006622517,0.00015433332,0.0029266349,0.013337616,0.004141411],"genre_scores_gemma":[0.5285268,0.0005944993,0.4491371,0.0004906402,0.00047786647,0.00030373654,0.0077812667,0.0005751689,0.012112926],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99790704,0.0006338199,0.00009357567,0.0006744598,0.00052875147,0.0001623273],"domain_scores_gemma":[0.9984769,0.0005923804,0.000098381264,0.00034141893,0.00042006862,0.00007077809],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015693099,0.0011927611,0.0010758061,0.00081259885,0.00027826513,0.0006473042,0.0011641685,0.000913414,0.004288937],"category_scores_gemma":[0.0032363294,0.0002143479,0.0010780237,0.0008190695,0.00029047168,0.0012166719,0.0011581056,0.0011125798,0.0064093573],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001020933,0.000205984,0.0032157789,0.00028497723,0.0003015625,0.0004415489,0.00015761472,0.023651447,0.12294602,0.0022827103,0.012940472,0.8325509],"study_design_scores_gemma":[0.00007483643,0.0004990316,0.008760137,0.000041403913,0.00015870441,0.0014517962,0.0001289275,0.80763304,0.16179188,0.0057804473,0.013529641,0.00015017651],"about_ca_topic_score_codex":0.001393925,"about_ca_topic_score_gemma":0.0017327475,"teacher_disagreement_score":0.004288937,"about_ca_system_score_codex":0.00026219332,"about_ca_system_score_gemma":0.00039739718,"threshold_uncertainty_score":0.014347911},"labels":[],"label_agreement":null},{"id":"W2345781070","doi":"10.1121/1.4949912","title":"Towards real-time two-dimensional wave propagation for articulatory speech synthesis","year":2016,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Vocal tract; Computer science; Leverage (statistics); Speech production; Time domain; Acoustics; Aerodynamics; Speech recognition; Simulation; Artificial intelligence; Computer vision; Physics","score_opus":0.019691800717575154,"score_gpt":0.24917908959101695,"score_spread":0.2294872888734418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2345781070","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034450088,0.00011977027,0.9623676,0.00010419774,0.000047080848,0.000031590927,0.00005843893,0.0006122231,0.002209042],"genre_scores_gemma":[0.5033298,0.00036159955,0.49249774,0.00009521707,0.000037955768,0.00016393552,0.00017865644,0.00032914642,0.0030058746],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99986243,0.000035416615,0.000006548954,0.000017389902,0.00006491068,0.000013215632],"domain_scores_gemma":[0.999666,0.00020598297,0.000027178487,0.000032469907,0.000046070814,0.000022238057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033856847,0.0005924462,0.00034440093,0.0002776331,0.00020480195,0.0010143298,0.00067858485,0.0010531046,0.0017263095],"category_scores_gemma":[0.0011329117,0.0004030731,0.0005260056,0.00021368168,0.0005527915,0.00071962556,0.00079939613,0.0007140672,0.0005770288],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057405265,0.000039919745,0.00048211197,0.00007418195,0.000015850683,0.00012347003,0.00019565191,0.93865705,0.0349688,0.00820311,0.0004263669,0.016756045],"study_design_scores_gemma":[0.000004634235,0.000008221687,0.00003720101,0.000002497521,9.874377e-7,0.000013007525,0.000007875578,0.9970912,0.0015201118,0.00074043364,0.00057084765,0.0000030188032],"about_ca_topic_score_codex":0.002132636,"about_ca_topic_score_gemma":0.0015367548,"teacher_disagreement_score":0.002132636,"about_ca_system_score_codex":0.00035729987,"about_ca_system_score_gemma":0.00046094233,"threshold_uncertainty_score":0.0057750344},"labels":[],"label_agreement":null},{"id":"W2357807430","doi":"","title":"A Comparative Study of MOS and PC Methods for Quality Evaluation of Text-to-Speech System in Mandarin","year":2006,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mandarin Chinese; Computer science; Active listening; Impression; Prosody; Speech recognition; Test (biology); Word (group theory); Quality (philosophy); Mean opinion score; Natural language processing; Psychology; Linguistics; Communication","score_opus":0.08825679431518552,"score_gpt":0.4269068721197545,"score_spread":0.33865007780456896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2357807430","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8758274,0.003293222,0.10997361,0.00011304123,0.00019097452,0.00023063665,0.0009246606,0.0010249937,0.00842152],"genre_scores_gemma":[0.94783854,0.0008022266,0.0481537,0.000039261693,0.00014018058,0.00018507191,0.0008596681,0.0001354927,0.0018458709],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99611795,0.0015496986,0.00028471844,0.0003711581,0.0015589988,0.00011741613],"domain_scores_gemma":[0.9883845,0.0062367893,0.00057961466,0.0004411482,0.0040523196,0.00030561176],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036703933,0.00067182694,0.00048388386,0.002299303,0.0002533754,0.0007780055,0.00034451802,0.0005358467,0.0019527967],"category_scores_gemma":[0.01235097,0.00021480396,0.00032687676,0.0016676466,0.00030422208,0.00087261986,0.0004544383,0.0002734921,0.0004967987],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009770714,0.00034414628,0.13218012,0.0011325106,0.00078982173,0.0005904022,0.002259274,0.0056365947,0.15156083,0.0017079865,0.0030418546,0.6909856],"study_design_scores_gemma":[0.0005254388,0.008483945,0.6550449,0.00017160937,0.0008267211,0.0038916864,0.0026839564,0.19239238,0.12334994,0.0015026627,0.010659595,0.00046719253],"about_ca_topic_score_codex":0.001751185,"about_ca_topic_score_gemma":0.0025563256,"teacher_disagreement_score":0.0036703933,"about_ca_system_score_codex":0.00033389794,"about_ca_system_score_gemma":0.0002036449,"threshold_uncertainty_score":0.019411147},"labels":[],"label_agreement":null},{"id":"W2358981474","doi":"10.1121/1.4948755","title":"Non-stationary Bayesian estimation of parameters from a body cover model of the vocal folds","year":2016,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Ontario Ministry of Research and Innovation; Comisión Nacional de Investigación Científica y Tecnológica; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Fundação Carlos Chagas Filho de Amparo à Pesquisa do Estado do Rio de Janeiro; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; National Institute on Deafness and Other Communication Disorders; Universidad Técnica Federico Santa María","keywords":"Bayesian probability; Computer science; Bayesian inference; Particle filter; Estimation theory; Mathematics; Algorithm; Artificial intelligence; Pattern recognition (psychology); Kalman filter","score_opus":0.014846652309159502,"score_gpt":0.23942487876254945,"score_spread":0.22457822645338996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2358981474","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019866407,0.0001142114,0.97910416,0.00010456836,0.000010139652,0.000016380205,0.000037598034,0.00011403192,0.0006325264],"genre_scores_gemma":[0.82701635,0.00064251246,0.16803786,0.00009813682,0.00005062184,0.00012412047,0.00023042031,0.000115781964,0.0036841994],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997899,0.00006963767,0.000009956947,0.00004327147,0.000069261005,0.000017976618],"domain_scores_gemma":[0.9992545,0.000556653,0.000070758346,0.00005011922,0.000050435632,0.000017584778],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087078766,0.00043576615,0.00045783824,0.0003754751,0.00021060958,0.00060995104,0.0006132246,0.00075916795,0.0010664297],"category_scores_gemma":[0.00461171,0.0004438969,0.0005334286,0.0002039251,0.00064130884,0.0005552446,0.00050843874,0.0008840401,0.00034145243],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006522063,0.000025472558,0.0016128605,0.000060840743,0.000029684368,0.00012588508,0.0001325205,0.9286277,0.0064766146,0.013426283,0.00051216973,0.048904806],"study_design_scores_gemma":[0.000003452406,0.000010779951,0.0005687337,0.000008221031,0.0000053316494,0.00003845992,0.0000072975854,0.99384093,0.0006296446,0.0045874487,0.0002920729,0.0000077042005],"about_ca_topic_score_codex":0.004977719,"about_ca_topic_score_gemma":0.00510288,"teacher_disagreement_score":0.004977719,"about_ca_system_score_codex":0.00046060525,"about_ca_system_score_gemma":0.00079426554,"threshold_uncertainty_score":0.00989753},"labels":[],"label_agreement":null},{"id":"W2361883049","doi":"","title":"Design and Implementation of a Lightweight Telephone Voice Process Definition Language","year":2009,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Process (computing); Mobile radio telephone; Flexibility (engineering); Telephone network; Telephony; Interactive voice response; Parsing; Voice over IP; Speech recognition; Telephone line; Telecommunications; Operating system; Programming language","score_opus":0.014962877190146703,"score_gpt":0.2782737371753436,"score_spread":0.2633108599851969,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2361883049","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048531233,0.00014633418,0.988309,0.00013614504,0.00006239371,0.0003027936,0.000059830534,0.0043823873,0.0017478827],"genre_scores_gemma":[0.09730274,0.0003359178,0.8930655,0.00037139832,0.00005999892,0.0006873143,0.0007398051,0.00094810803,0.0064892597],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.997168,0.0005243889,0.00047392806,0.00044600823,0.0010730915,0.0003145789],"domain_scores_gemma":[0.9976794,0.00048738066,0.00021855335,0.00040951956,0.0010467805,0.00015834134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039858823,0.0005964507,0.0007831499,0.0009537671,0.0006902046,0.0027878906,0.003655561,0.0012001884,0.0039821677],"category_scores_gemma":[0.00416852,0.001008468,0.0011572102,0.000607038,0.000815793,0.0036272476,0.0018748232,0.002637425,0.0020388695],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010327211,0.0006381847,0.003095349,0.0020262687,0.00018511106,0.0014084112,0.0027749215,0.020283602,0.27848083,0.20959848,0.01372167,0.46675444],"study_design_scores_gemma":[0.000594201,0.0011136159,0.0012330848,0.00042639923,0.0005174332,0.0018197745,0.00042106843,0.37624604,0.2811664,0.019586444,0.31657812,0.000297358],"about_ca_topic_score_codex":0.0014302159,"about_ca_topic_score_gemma":0.00091686175,"teacher_disagreement_score":0.0039858823,"about_ca_system_score_codex":0.0010093432,"about_ca_system_score_gemma":0.002984893,"threshold_uncertainty_score":0.0210796},"labels":[],"label_agreement":null},{"id":"W2364974426","doi":"","title":"Phoneme modeling units design for Mandarin LVCSR systems","year":2011,"lang":"en","type":"article","venue":"Journal of Tsinghua University(Science and Technology)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Mandarin Chinese; Computer science; Set (abstract data type); Speech recognition; Salient; Vocabulary; Artificial intelligence; Vowel; Natural language processing; Linguistics; Programming language","score_opus":0.08201215340333769,"score_gpt":0.21423467727794082,"score_spread":0.13222252387460315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2364974426","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026057838,0.00039380847,0.97028434,0.000055246965,0.00006151958,0.00014238294,0.00011573532,0.0012797257,0.0016093954],"genre_scores_gemma":[0.585874,0.00026196116,0.408934,0.00009684184,0.00006202792,0.00055838114,0.0005746591,0.00026738583,0.0033707002],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99946195,0.00014484284,0.00008560744,0.0001269799,0.0001438739,0.000036639958],"domain_scores_gemma":[0.99964845,0.00011093255,0.000039139806,0.000054914184,0.00012810143,0.000018561881],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045802767,0.00081918977,0.0004978717,0.0004019634,0.00035869062,0.00062909955,0.0009145518,0.0007070111,0.0033848833],"category_scores_gemma":[0.0010296117,0.0003831,0.00056808617,0.00018676226,0.0002215902,0.0008212356,0.0004338008,0.0007090951,0.0012662044],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010016586,0.00012956362,0.0013411345,0.0006057923,0.0001423521,0.00045977338,0.0005357608,0.11076872,0.45923376,0.012158012,0.00222308,0.41140047],"study_design_scores_gemma":[0.00010497874,0.0009874277,0.0015803189,0.00005120204,0.00016039482,0.00057005207,0.000111596135,0.71995574,0.24547133,0.0038274296,0.027096523,0.000083068146],"about_ca_topic_score_codex":0.0011831518,"about_ca_topic_score_gemma":0.0013102257,"teacher_disagreement_score":0.0033848833,"about_ca_system_score_codex":0.0003614613,"about_ca_system_score_gemma":0.00039036118,"threshold_uncertainty_score":0.011323571},"labels":[],"label_agreement":null},{"id":"W2364980412","doi":"","title":"Development and Prospect for Speech Synthesis","year":2007,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Generalization; Frame (networking); Speech synthesis; Property (philosophy); Speech recognition; Field (mathematics); Prosody; Basis (linear algebra); Development (topology); Noise (video); Harmonic; Artificial intelligence; Telecommunications; Acoustics; Mathematics","score_opus":0.019380997396341245,"score_gpt":0.25643524364916814,"score_spread":0.2370542462528269,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2364980412","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015030619,0.13081469,0.77909184,0.0051001683,0.0016355432,0.00013396745,0.00014988967,0.0010885111,0.06695475],"genre_scores_gemma":[0.26863673,0.14840086,0.51809084,0.0019436687,0.0043576844,0.0003417407,0.00066202885,0.00031820763,0.057248298],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99937695,0.000167612,0.00004133484,0.00015360948,0.00022103611,0.000039537932],"domain_scores_gemma":[0.9994868,0.0001722139,0.000022132777,0.00005734305,0.00021573207,0.00004572127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012127594,0.0005446842,0.00045564346,0.0012573723,0.0003997205,0.0012410182,0.00073872384,0.00109626,0.0071968464],"category_scores_gemma":[0.0010604716,0.0003318109,0.00047602577,0.0005919845,0.00074710615,0.0025292293,0.0009442141,0.0010366372,0.0023092842],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016345443,0.00006172198,0.0008145515,0.00093101425,0.000032889675,0.00017734554,0.00043993184,0.0039039915,0.037706874,0.17945321,0.0060193497,0.7702957],"study_design_scores_gemma":[0.0000967031,0.00087752636,0.0020398856,0.0007446773,0.0001247424,0.0013320787,0.000850767,0.078466795,0.038088918,0.12788185,0.74936193,0.00013409274],"about_ca_topic_score_codex":0.00073537487,"about_ca_topic_score_gemma":0.0003599543,"teacher_disagreement_score":0.0071968464,"about_ca_system_score_codex":0.0006004242,"about_ca_system_score_gemma":0.0009324445,"threshold_uncertainty_score":0.024075866},"labels":[],"label_agreement":null},{"id":"W2397184916","doi":"","title":"Hybrid orthogonal projection and estimation (HOPE): a new framework to learn neural networks","year":2016,"lang":"en","type":"article","venue":"Journal of Machine Learning Research","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"MNIST database; Computer science; Artificial intelligence; TIMIT; Unsupervised learning; Projection (relational algebra); Artificial neural network; Machine learning; Feature (linguistics); Generative model; Pattern recognition (psychology); Generative grammar; Hidden Markov model; Algorithm","score_opus":0.048229047213752776,"score_gpt":0.353960200129276,"score_spread":0.3057311529155232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2397184916","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011929155,0.00013948158,0.99816376,0.00010396377,0.000011766979,0.000010033501,0.000033976416,0.00013981985,0.0002042446],"genre_scores_gemma":[0.25868666,0.0009708275,0.73349667,0.00053284946,0.00027448116,0.00046255157,0.00067902874,0.00025726587,0.0046396246],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974879,0.001461324,0.000086951164,0.0004326163,0.0004001085,0.00013108527],"domain_scores_gemma":[0.9973972,0.0015829768,0.00021379402,0.00038339512,0.00031249598,0.000110172914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00389743,0.0014206986,0.0014049379,0.001125424,0.00050818536,0.0013586036,0.0032466731,0.0018551905,0.0017100208],"category_scores_gemma":[0.007084669,0.0010706318,0.0014509956,0.0014208244,0.0020234846,0.0034749103,0.0031136554,0.0033905744,0.0006189697],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001194381,0.0000845525,0.0015792502,0.00016366047,0.0002293617,0.00011503197,0.00016890022,0.69865113,0.0020328278,0.14478765,0.0029844749,0.14908361],"study_design_scores_gemma":[0.0000049859186,0.000023471037,0.00007920357,0.000009076288,0.000007924168,0.000018244638,0.000005705551,0.9628166,0.0002577311,0.03606269,0.0007051979,0.00000919879],"about_ca_topic_score_codex":0.0036919478,"about_ca_topic_score_gemma":0.004726877,"teacher_disagreement_score":0.00389743,"about_ca_system_score_codex":0.00087584736,"about_ca_system_score_gemma":0.0011806795,"threshold_uncertainty_score":0.020611823},"labels":[],"label_agreement":null},{"id":"W2398971481","doi":"10.21437/interspeech.2015-95","title":"The reddots data collection for speaker recognition","year":2015,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":138,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"VoiceAge (Canada); Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Speech recognition; Speaker recognition; Data collection; Natural language processing; Artificial intelligence; Mathematics","score_opus":0.285855109260436,"score_gpt":0.32520872167374876,"score_spread":0.039353612413312755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2398971481","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028671613,0.00051408756,0.025786249,0.0004700949,0.0016566984,0.0021054412,0.9023715,0.012935356,0.025488894],"genre_scores_gemma":[0.021691814,0.00013385207,0.017101763,0.00015820119,0.00023758643,0.00266003,0.9405276,0.0010628599,0.016426409],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99573225,0.0010466737,0.0004490991,0.00085245294,0.0015828345,0.00033673554],"domain_scores_gemma":[0.9905269,0.00088346674,0.00044152045,0.0027909102,0.004619694,0.0007375062],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003203561,0.0017318437,0.0018661149,0.0026294221,0.0011340848,0.0012315055,0.0023585001,0.0014962308,0.039588265],"category_scores_gemma":[0.007696688,0.00054829236,0.0010924304,0.0016630215,0.0006815023,0.0010969437,0.002748525,0.0015650518,0.07792414],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017440389,0.000500329,0.00875964,0.0009703119,0.00018680548,0.00028931414,0.0003286894,0.0018710388,0.012036192,0.0013324807,0.8495368,0.12244431],"study_design_scores_gemma":[0.0012111422,0.0008107804,0.08757093,0.00040433498,0.00021601931,0.0011879742,0.00075613015,0.010638894,0.022659834,0.0023078378,0.8719327,0.00030339425],"about_ca_topic_score_codex":0.016049257,"about_ca_topic_score_gemma":0.028869443,"teacher_disagreement_score":0.039588265,"about_ca_system_score_codex":0.0006650438,"about_ca_system_score_gemma":0.0023053007,"threshold_uncertainty_score":0.13243598},"labels":[],"label_agreement":null},{"id":"W2400893182","doi":"10.1109/icassp.2016.7472725","title":"Feature mapping, score-, and feature-level fusion for improved normal and whispered speech speaker verification","year":2016,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Speech recognition; Computer science; Mel-frequency cepstrum; Word error rate; Feature (linguistics); Fusion; Vocal tract; Speaker verification; Sensor fusion; Complementarity (molecular biology); Feature extraction; Speaker recognition; Test data; Pattern recognition (psychology); Artificial intelligence","score_opus":0.03598910046254787,"score_gpt":0.2347791838794743,"score_spread":0.19879008341692644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2400893182","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.064686224,0.00041150083,0.9317921,0.0000973859,0.00006234599,0.00006099912,0.00009056335,0.0015433263,0.0012556359],"genre_scores_gemma":[0.5930341,0.00021470699,0.4038379,0.00007810838,0.000050155915,0.00005449438,0.00038296438,0.000119324555,0.0022282773],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882,0.00024411056,0.000066297456,0.00017938833,0.00057270675,0.00011745606],"domain_scores_gemma":[0.9989624,0.0003001788,0.000080091166,0.00024472768,0.0003678018,0.00004472576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016971714,0.00065601827,0.00070600514,0.0006378772,0.0002669921,0.0006417239,0.00070447545,0.0006382701,0.0022014389],"category_scores_gemma":[0.0030416097,0.00021690402,0.00053610135,0.0005166343,0.00032732828,0.001438245,0.001359551,0.00078572176,0.001063556],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006975804,0.00016448562,0.0015988834,0.00011305568,0.00008818154,0.00012037308,0.00013926617,0.019175332,0.20678183,0.003601961,0.0010014233,0.76651764],"study_design_scores_gemma":[0.00004879978,0.0006575792,0.0074134883,0.00003297464,0.00014572202,0.00075459696,0.00010111472,0.6663642,0.31419763,0.0046914043,0.005475982,0.00011648959],"about_ca_topic_score_codex":0.0008486114,"about_ca_topic_score_gemma":0.0011322356,"teacher_disagreement_score":0.0022014389,"about_ca_system_score_codex":0.00025167246,"about_ca_system_score_gemma":0.0004425122,"threshold_uncertainty_score":0.008975565},"labels":[],"label_agreement":null},{"id":"W2403731734","doi":"10.21437/interspeech.2013-336","title":"Rapid and effective speaker adaptation of convolutional neural network based models for speech recognition","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Speech recognition; TIMIT; Adaptation (eye); Convolutional neural network; Speaker recognition; Artificial neural network; Speaker diarisation; Hidden Markov model; Artificial intelligence; Pattern recognition (psychology)","score_opus":0.0454800610501761,"score_gpt":0.2299923264230991,"score_spread":0.184512265372923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2403731734","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03160341,0.0010479863,0.9617324,0.000119360535,0.00015530447,0.000068087786,0.00018033785,0.0031995312,0.0018935654],"genre_scores_gemma":[0.59099215,0.0012178964,0.3969,0.00020982901,0.00014944465,0.00021628416,0.0010591403,0.00042339702,0.008831849],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997085,0.0000705301,0.000013536743,0.00007460583,0.00009868521,0.00003406358],"domain_scores_gemma":[0.99971884,0.000101603146,0.000022324828,0.00007125743,0.00007161045,0.000014363659],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006509009,0.0010020684,0.0004164119,0.00033432353,0.00017187544,0.00027519252,0.0008484554,0.000509091,0.0014586868],"category_scores_gemma":[0.0010603995,0.0004174813,0.000566259,0.00027017092,0.00021356516,0.00061672344,0.00065446674,0.0012742748,0.00080002943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021778814,0.00013885132,0.0013611708,0.00013824669,0.0002796455,0.00015736556,0.000095186515,0.4206574,0.092924714,0.00326619,0.0058728233,0.4748906],"study_design_scores_gemma":[0.000003078882,0.000018159422,0.00032875015,0.0000036522167,0.000014487897,0.000029570701,0.0000034917064,0.9878114,0.010145014,0.00056829106,0.0010663596,0.000007797767],"about_ca_topic_score_codex":0.0058187405,"about_ca_topic_score_gemma":0.012167309,"teacher_disagreement_score":0.0058187405,"about_ca_system_score_codex":0.0004792867,"about_ca_system_score_gemma":0.00043212203,"threshold_uncertainty_score":0.011569798},"labels":[],"label_agreement":null},{"id":"W2404260248","doi":"10.21437/interspeech.2013-610","title":"Automatic human utility evaluation of ASR systems: does WER really predict performance?","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"","keywords":"Metric (unit); Computer science; Task (project management); Context (archaeology); Audit; Word error rate; Word (group theory); Speech recognition; Performance metric; Artificial intelligence; Natural language processing; Range (aeronautics); Machine learning; Mathematics; Engineering; Operations management","score_opus":0.04054442211315303,"score_gpt":0.27333764231025204,"score_spread":0.232793220197099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2404260248","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57750833,0.0033286354,0.39087653,0.0011661894,0.0003782273,0.00028452935,0.0011862855,0.0039004772,0.021370811],"genre_scores_gemma":[0.9642302,0.00032296384,0.03188057,0.00018925178,0.00009625817,0.00012533856,0.0007322059,0.00038907526,0.0020342332],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9740345,0.017358676,0.0014773797,0.0020191374,0.004509061,0.0006012638],"domain_scores_gemma":[0.9269429,0.052068867,0.0038550913,0.006993619,0.009183033,0.00095651153],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017415838,0.0016689133,0.0011562108,0.00212234,0.00052467536,0.0025295229,0.0011569296,0.0018846823,0.00244526],"category_scores_gemma":[0.079934835,0.00031483572,0.00042539425,0.0012234022,0.001707448,0.0036828385,0.0016754264,0.00094970746,0.0028885317],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0037097496,0.0007271668,0.13318568,0.0009992418,0.00089637213,0.00065625785,0.0023167941,0.05055661,0.08429689,0.011131646,0.009076894,0.7024467],"study_design_scores_gemma":[0.00031223067,0.0063815773,0.22875936,0.00034157847,0.0005050899,0.0028571906,0.002765389,0.48346996,0.20363773,0.052040175,0.018324228,0.00060546485],"about_ca_topic_score_codex":0.0013181927,"about_ca_topic_score_gemma":0.00151315,"teacher_disagreement_score":0.017415838,"about_ca_system_score_codex":0.00052296976,"about_ca_system_score_gemma":0.00054638006,"threshold_uncertainty_score":0.09210485},"labels":[],"label_agreement":null},{"id":"W2410946393","doi":"10.1109/acpr.2015.7486451","title":"IAPR keynote lecture IV: Deep learning","year":2015,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Deep learning; Computer science; Artificial intelligence; Deep neural networks; Transfer of learning; Variety (cybernetics); Language understanding; Artificial neural network; Recurrent neural network; Competence (human resources); Cognitive science; Machine learning; Data science; Psychology","score_opus":0.03173245847646136,"score_gpt":0.2436212647191048,"score_spread":0.21188880624264345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2410946393","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051947804,0.103570156,0.13172168,0.1691913,0.14982852,0.0002137103,0.0032409404,0.0041408013,0.43289822],"genre_scores_gemma":[0.079714365,0.05965013,0.046917565,0.015781304,0.09272972,0.0003189767,0.0048367037,0.0017787716,0.6982725],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984686,0.00027273773,0.00006041192,0.0004377678,0.00057418994,0.00018627322],"domain_scores_gemma":[0.9977036,0.0005762676,0.00006946015,0.00022992752,0.00072277046,0.0006979458],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031753576,0.0016756648,0.0012845001,0.0016031594,0.0014857621,0.005779405,0.0015507916,0.0030029737,0.048665345],"category_scores_gemma":[0.0059831287,0.0005345927,0.00090077956,0.0014610356,0.001457807,0.004135366,0.0030886566,0.007601242,0.039549816],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013628695,0.00008332373,0.0002904201,0.00020860782,0.0000434702,0.00008615945,0.00006663477,0.0022878314,0.0008487526,0.044727765,0.79701966,0.15420105],"study_design_scores_gemma":[0.000058523565,0.00011584825,0.0007759685,0.00044436505,0.000051202736,0.00017654442,0.00012331559,0.0090930825,0.0023041903,0.09395481,0.89285123,0.000050974424],"about_ca_topic_score_codex":0.0041974937,"about_ca_topic_score_gemma":0.0037427384,"teacher_disagreement_score":0.048665345,"about_ca_system_score_codex":0.0037045504,"about_ca_system_score_gemma":0.0023143177,"threshold_uncertainty_score":0.1628018},"labels":[],"label_agreement":null},{"id":"W2437182874","doi":"10.1007/978-3-319-33618-3_20","title":"Speaker Classification via Supervised Hierarchical Clustering Using ICA Mixture Model","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mixture model; Computer science; Cluster analysis; Pattern recognition (psychology); Artificial intelligence; TIMIT; Independent component analysis; Hierarchical clustering; Machine learning; Speech recognition; Hidden Markov model","score_opus":0.05107048488582587,"score_gpt":0.26526251848876903,"score_spread":0.21419203360294314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2437182874","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037947092,0.00031541756,0.99269485,0.000044513996,0.000056133053,0.000029762185,0.000101838756,0.0018046756,0.001158059],"genre_scores_gemma":[0.103795335,0.0006531603,0.88315445,0.000105621635,0.00016326223,0.00016375715,0.0016881968,0.0008238307,0.009452408],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990508,0.00020732619,0.000045878707,0.00030310082,0.0002863304,0.000106579064],"domain_scores_gemma":[0.99939454,0.00020474211,0.00003425734,0.00013561697,0.00020409373,0.000026708463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007882433,0.0013511453,0.0016112017,0.0013567597,0.0007657854,0.0009937638,0.0013686019,0.0010195834,0.0038865805],"category_scores_gemma":[0.0014914391,0.0006303408,0.0024450785,0.0013019831,0.0004428633,0.0010355464,0.0012901064,0.0016374743,0.008533423],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027110198,0.000099658406,0.0006162393,0.00012694558,0.00020218767,0.00008029457,0.0001353911,0.030512739,0.06576726,0.0033918791,0.0079083955,0.89088804],"study_design_scores_gemma":[0.000019014135,0.000074163596,0.0022368028,0.00002089063,0.000121427474,0.0003093685,0.00006616868,0.95300454,0.030450853,0.0075621908,0.006076744,0.00005783594],"about_ca_topic_score_codex":0.002980578,"about_ca_topic_score_gemma":0.005602617,"teacher_disagreement_score":0.0038865805,"about_ca_system_score_codex":0.00034787887,"about_ca_system_score_gemma":0.0006772146,"threshold_uncertainty_score":0.013001919},"labels":[],"label_agreement":null},{"id":"W2467063648","doi":"10.1016/j.scijus.2016.07.002","title":"Refining the relevant population in forensic voice comparison – A response to Hicks et alii (2015) The importance of distinguishing information from evidence/observations when formulating propositions","year":2016,"lang":"en","type":"letter","venue":"Science & Justice","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Stress (linguistics); Forensic science; Identity (music); Population; Psychology; Criminology; Computer science; Cognitive psychology; Speech recognition; Sociology; History; Acoustics","score_opus":0.08204880676153352,"score_gpt":0.33779118346657744,"score_spread":0.2557423767050439,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2467063648","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021747914,0.00033309948,0.00036973288,0.99536383,0.0031133145,0.000007020668,0.000013189059,0.000009480255,0.0005729258],"genre_scores_gemma":[0.0044536404,0.0002876685,0.0011799239,0.98559374,0.0074582845,0.00004101706,0.000013235893,0.000020169857,0.00095220207],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9731803,0.009583336,0.0039578644,0.0039708097,0.007119938,0.0021877277],"domain_scores_gemma":[0.8650092,0.09602765,0.004744929,0.004082286,0.022429118,0.007706867],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0391786,0.0009222957,0.0018829529,0.0013230678,0.014840709,0.008842443,0.0060592564,0.09848713,0.005927039],"category_scores_gemma":[0.18804206,0.0014863585,0.0016673369,0.0010289684,0.015850402,0.011366192,0.01071438,0.10834289,0.004388168],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008270901,0.00007706344,0.0013606723,0.00018686963,0.000033736298,0.0016436093,0.0034205436,0.00021583274,0.0007082298,0.022366688,0.9266171,0.043286953],"study_design_scores_gemma":[0.00009880136,0.00009556651,0.0021902132,0.0020587633,0.00008369065,0.004380176,0.008173953,0.00091796584,0.0011797384,0.11630701,0.8642828,0.00023128011],"about_ca_topic_score_codex":0.011907641,"about_ca_topic_score_gemma":0.03252989,"teacher_disagreement_score":0.09848713,"about_ca_system_score_codex":0.0078045963,"about_ca_system_score_gemma":0.016042277,"threshold_uncertainty_score":0.20719868},"labels":[],"label_agreement":null},{"id":"W2501000458","doi":"10.1109/ijcnn.1991.155435","title":"Global optimization of a neural network-hidden Markov model hybrid","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Hidden Markov model; TIMIT; Artificial neural network; Computer science; Speech recognition; Artificial intelligence; Sequence (biology); Markov model; Pattern recognition (psychology); SIGNAL (programming language); Markov chain; Machine learning","score_opus":0.026754927477651298,"score_gpt":0.22692734774199594,"score_spread":0.20017242026434465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2501000458","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015123641,0.00033995562,0.9798737,0.00014892379,0.000045005516,0.000032193147,0.000060578757,0.00049885333,0.0038771478],"genre_scores_gemma":[0.6534532,0.0003856265,0.33232173,0.00022036316,0.00007230542,0.00034816295,0.00036756473,0.00030583312,0.012525195],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99966097,0.0001335741,0.0000129949285,0.000088420726,0.00006401038,0.00004006768],"domain_scores_gemma":[0.9995265,0.00030249965,0.00003602528,0.000034058387,0.00007803049,0.000022959088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000973355,0.0010419671,0.0011584995,0.0004590792,0.00036084192,0.0007506898,0.0008621571,0.0012149006,0.002814194],"category_scores_gemma":[0.001491412,0.00061965117,0.00072001765,0.0004935892,0.0006233586,0.0008247124,0.00095075753,0.0008329386,0.00038683467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002320177,0.000011666793,0.00011512791,0.000021021107,0.000028159251,0.000022670893,0.000013282145,0.9848898,0.00040266375,0.0023747648,0.00033862234,0.011759],"study_design_scores_gemma":[0.0000029885894,0.00000859715,0.00003144764,0.000002027617,0.0000036125468,0.0000033679125,0.000001768728,0.99860567,0.00011794872,0.0010294811,0.00019092837,0.0000022076822],"about_ca_topic_score_codex":0.005819016,"about_ca_topic_score_gemma":0.0066275904,"teacher_disagreement_score":0.005819016,"about_ca_system_score_codex":0.0006845343,"about_ca_system_score_gemma":0.0010833751,"threshold_uncertainty_score":0.011570275},"labels":[],"label_agreement":null},{"id":"W2509141772","doi":"","title":"What Do Forced Alignment Likelihood Scores Tell Us About the Aligned Speech","year":2016,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Phone; Hidden Markov model; Speech recognition; TIMIT; Computer science; Formant; Duration (music); Variation (astronomy); Acoustics; Linguistics","score_opus":0.015315175636007542,"score_gpt":0.22509565489488684,"score_spread":0.2097804792588793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2509141772","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59796965,0.007024079,0.33888432,0.0072912415,0.0014213306,0.00015174803,0.0132222455,0.0044938265,0.02954151],"genre_scores_gemma":[0.94505054,0.0015702277,0.04134318,0.00071572023,0.00069138856,0.00010595039,0.0062532886,0.0014232262,0.0028465095],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99424875,0.0019099223,0.00044653608,0.0017962802,0.0012105666,0.0003879314],"domain_scores_gemma":[0.96241,0.02118618,0.0042739986,0.0049449224,0.006115991,0.0010688442],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008820088,0.0012938275,0.0018083999,0.0035819018,0.000714026,0.0072921803,0.0012629451,0.0029961602,0.008162936],"category_scores_gemma":[0.0646515,0.00069651334,0.001220318,0.0026091111,0.0020627808,0.0165877,0.0014845076,0.0021294754,0.009909552],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022261257,0.00025498122,0.3560397,0.00091898476,0.0013992758,0.0003797959,0.0030418737,0.015281646,0.021926237,0.009472983,0.014114112,0.5749443],"study_design_scores_gemma":[0.00016582024,0.0010657227,0.687107,0.0008279264,0.0009952869,0.0019694844,0.006778553,0.12537682,0.02310415,0.11702299,0.034263022,0.0013231386],"about_ca_topic_score_codex":0.0026908708,"about_ca_topic_score_gemma":0.0028425085,"teacher_disagreement_score":0.008820088,"about_ca_system_score_codex":0.0007923627,"about_ca_system_score_gemma":0.00057584123,"threshold_uncertainty_score":0.04664564},"labels":[],"label_agreement":null},{"id":"W2512343856","doi":"10.1016/j.forsciint.2016.08.017","title":"Use of relevant data, quantitative measurements, and statistical models to calculate a likelihood ratio for a Chinese forensic voice comparison case involving two sisters","year":2016,"lang":"en","type":"article","venue":"Forensic Science International","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Reliability (semiconductor); Conversation; Forensic science; Speech recognition; Statistics; Psychology; Natural language processing; Mathematics; Communication; History","score_opus":0.22378879477217886,"score_gpt":0.3800277103783245,"score_spread":0.15623891560614564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2512343856","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79298794,0.00013273563,0.20176008,0.00028367792,0.000026340584,0.00016935522,0.00022862248,0.00041825132,0.0039929603],"genre_scores_gemma":[0.9617764,0.00003637372,0.037652478,0.000019808533,0.0000069720018,0.000035257945,0.00012729318,0.00002269336,0.00032275525],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998026,0.0005775315,0.00022565712,0.00031017794,0.00072906876,0.00013156726],"domain_scores_gemma":[0.9925092,0.0054152114,0.00051650824,0.00060543005,0.0008323021,0.000121438774],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052812714,0.00076497876,0.00045820742,0.003305745,0.0010242391,0.0009752723,0.0016289132,0.0014531638,0.0015665039],"category_scores_gemma":[0.019136034,0.00043761072,0.0006464842,0.0009432057,0.0011930986,0.0015954722,0.0011019381,0.00065923214,0.00039235078],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002154162,0.0008100823,0.29560542,0.0007379275,0.00023299796,0.02363523,0.0047963397,0.20695187,0.114452176,0.050858587,0.0024069326,0.2973583],"study_design_scores_gemma":[0.00008639083,0.0006746783,0.040620018,0.00007557105,0.00025162692,0.007610002,0.0026009171,0.8588039,0.070168346,0.016862972,0.0020720218,0.00017350877],"about_ca_topic_score_codex":0.0035043426,"about_ca_topic_score_gemma":0.0032255522,"teacher_disagreement_score":0.0052812714,"about_ca_system_score_codex":0.0009101186,"about_ca_system_score_gemma":0.001101398,"threshold_uncertainty_score":0.027930379},"labels":[],"label_agreement":null},{"id":"W2515097069","doi":"","title":"Interdisciplinary Approaches for Advancing Articulatory Speech Theory and Synthesis","year":2016,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Nvidia","keywords":"Speech synthesis; Vocal tract; Speech production; Computer science; Natural (archaeology); Speech technology; Speech recognition; Production (economics); Speech processing; Human–computer interaction","score_opus":0.02531939367293034,"score_gpt":0.23725416557429993,"score_spread":0.21193477190136958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2515097069","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030683053,0.06274214,0.844129,0.016940279,0.0029616554,0.000118684635,0.00007653288,0.00045628,0.06950704],"genre_scores_gemma":[0.097586796,0.07990162,0.7805015,0.0037109698,0.0055239107,0.0006032515,0.00022104388,0.000323967,0.03162695],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99591345,0.0016319461,0.00036325716,0.0006909791,0.0012171495,0.00018317996],"domain_scores_gemma":[0.9940295,0.003070875,0.0001788023,0.0009658368,0.0014386604,0.00031629403],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008526515,0.0018245659,0.0013654962,0.0048468676,0.0014941926,0.00688147,0.0023805187,0.0037719,0.009368645],"category_scores_gemma":[0.0072234157,0.0008747381,0.0013745865,0.0016692675,0.008942108,0.0066058864,0.00718112,0.0058026253,0.003999955],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031866068,0.00007916973,0.00021801917,0.00048335982,0.000035559744,0.00006187221,0.0011259324,0.0047525354,0.002308303,0.87570095,0.0042465855,0.11095595],"study_design_scores_gemma":[0.000023983037,0.00010990077,0.0002700043,0.00043919118,0.000024887573,0.000158885,0.00071563164,0.017583461,0.0022639632,0.76884484,0.2094915,0.00007367118],"about_ca_topic_score_codex":0.0016525075,"about_ca_topic_score_gemma":0.0013717363,"teacher_disagreement_score":0.009368645,"about_ca_system_score_codex":0.0029880307,"about_ca_system_score_gemma":0.0025990496,"threshold_uncertainty_score":0.04509306},"labels":[],"label_agreement":null},{"id":"W2530400070","doi":"10.1007/978-81-322-3592-7_9","title":"Robust Speaker Verification Using GFCC Based i-Vectors","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in electrical engineering","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Garron Family Cancer Centre","keywords":"Speaker verification; NIST; Computer science; Speech recognition; Speaker recognition; Session (web analytics); Speaker diarisation; Channel (broadcasting); Pattern recognition (psychology); Cepstrum; Artificial intelligence; Telecommunications","score_opus":0.028073170745591545,"score_gpt":0.20940429207523284,"score_spread":0.1813311213296413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2530400070","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024523502,0.002070905,0.9615484,0.00022533858,0.00042493566,0.0001021586,0.0006359214,0.004338214,0.006130531],"genre_scores_gemma":[0.30055082,0.0019248404,0.6808451,0.0003611424,0.0003220181,0.00019728049,0.0030082846,0.0006775141,0.012112923],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989895,0.00022270078,0.000060825085,0.00022510983,0.00038707102,0.000114742856],"domain_scores_gemma":[0.99901724,0.00036218352,0.00007640702,0.00020987487,0.0003056033,0.000028589227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008615239,0.0014086411,0.0009546221,0.0009899484,0.00052688847,0.0010150064,0.0006923846,0.0017455834,0.007832317],"category_scores_gemma":[0.0023603004,0.000330301,0.00089929556,0.00065396045,0.00042193494,0.0012727991,0.0010570951,0.0009890859,0.010079971],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008033195,0.000050496423,0.0004438732,0.00029289612,0.00008544778,0.00021853589,0.00005808241,0.006331515,0.39483884,0.0024409546,0.0035344523,0.5909016],"study_design_scores_gemma":[0.000107677784,0.000664257,0.0063197487,0.00021529861,0.00030929758,0.002689824,0.0001279386,0.31029975,0.6557514,0.004363711,0.01900048,0.00015060841],"about_ca_topic_score_codex":0.0009984961,"about_ca_topic_score_gemma":0.0013917185,"teacher_disagreement_score":0.007832317,"about_ca_system_score_codex":0.0001921377,"about_ca_system_score_gemma":0.0005194764,"threshold_uncertainty_score":0.026201725},"labels":[],"label_agreement":null},{"id":"W2532585045","doi":"10.1109/nlpke.2003.1275932","title":"Performance improvement of automatic speech recognition systems via multiple language models produced by sentence-based clustering","year":2004,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Cluster analysis; Vocabulary; Artificial intelligence; Speech recognition; Language model; Sentence; Natural language processing; Grammar; Self-organizing map","score_opus":0.02378218736327504,"score_gpt":0.2199273004085662,"score_spread":0.19614511304529117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2532585045","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37181243,0.0005742086,0.60387284,0.00030345778,0.00015725904,0.00013530061,0.0003186296,0.020262666,0.0025632621],"genre_scores_gemma":[0.6898453,0.00015588092,0.30548945,0.000102578735,0.000045104112,0.0001410743,0.0011326642,0.0006250371,0.002462931],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998467,0.0005493197,0.0001241984,0.00042012977,0.00033498666,0.00010441155],"domain_scores_gemma":[0.997412,0.0014484887,0.000082927865,0.00029576977,0.00068575406,0.000075191434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002248014,0.0010325728,0.0011267446,0.0007689173,0.0005501332,0.0009669537,0.0009122334,0.0009837989,0.002046018],"category_scores_gemma":[0.00441747,0.0005268842,0.00079836283,0.00060599047,0.00031391619,0.0013139035,0.0008733232,0.0007080302,0.0021075977],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026177329,0.00029080347,0.0030103615,0.00027794534,0.00036684636,0.00026726018,0.0004792422,0.20319796,0.1655718,0.00133802,0.0034431738,0.6191387],"study_design_scores_gemma":[0.00003901968,0.0001723967,0.001257916,0.000006931399,0.000053691576,0.00010063312,0.00007624434,0.9437629,0.053331483,0.00059774995,0.0005586207,0.000042418764],"about_ca_topic_score_codex":0.00479579,"about_ca_topic_score_gemma":0.0040910332,"teacher_disagreement_score":0.00479579,"about_ca_system_score_codex":0.00060492987,"about_ca_system_score_gemma":0.0005842441,"threshold_uncertainty_score":0.011888802},"labels":[],"label_agreement":null},{"id":"W2539873419","doi":"10.1109/icscs.2009.5412479","title":"Comparison of GMM and fuzzy-GMM applied to phoneme classification","year":2009,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Keyword spotting; Speech recognition; Utterance; Classifier (UML); Vocabulary; Artificial intelligence; Mixture model; Spotting; Natural language; Hidden Markov model; Natural language processing; Word (group theory); Fuzzy logic; Linguistics","score_opus":0.06018352987154616,"score_gpt":0.32046603506690263,"score_spread":0.26028250519535645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2539873419","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31549382,0.005901814,0.66274154,0.0006166431,0.00083591574,0.00018279674,0.0004929481,0.0063457023,0.0073888726],"genre_scores_gemma":[0.82328355,0.0014299769,0.17130063,0.0001260873,0.000107757085,0.00007301299,0.0006106604,0.0003083717,0.0027599507],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99774134,0.00078392436,0.00011346393,0.00033457534,0.00079491385,0.00023178583],"domain_scores_gemma":[0.9942637,0.0032744068,0.000120670025,0.00031884288,0.0018632808,0.00015902049],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041691633,0.0008607239,0.000923746,0.0023877455,0.00042910763,0.0013095757,0.0007896834,0.0012898117,0.001602703],"category_scores_gemma":[0.012836364,0.00024456394,0.00057280826,0.0010968946,0.00038663094,0.0015366876,0.0006832321,0.0006355931,0.00086065294],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0035953794,0.00019453849,0.010557737,0.00039016845,0.00037553403,0.0001043373,0.00043487104,0.052191444,0.027217053,0.003738371,0.0033293676,0.89787126],"study_design_scores_gemma":[0.00007042113,0.0007634088,0.027293015,0.0000659578,0.00023495592,0.00028444178,0.0005169511,0.92784536,0.035455067,0.0027959815,0.004545837,0.00012860545],"about_ca_topic_score_codex":0.016617987,"about_ca_topic_score_gemma":0.013362696,"teacher_disagreement_score":0.016617987,"about_ca_system_score_codex":0.0009163212,"about_ca_system_score_gemma":0.0009872298,"threshold_uncertainty_score":0.03304249},"labels":[],"label_agreement":null},{"id":"W2539922005","doi":"10.1109/nnsp.1992.253696","title":"Maximum mutual information training of a neural predictive-based HMM speech recognition system","year":2003,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Hidden Markov model; Speech recognition; Computer science; Artificial intelligence; Mutual information; Artificial neural network; Pattern recognition (psychology); Scheme (mathematics); Training (meteorology); Machine learning; Mathematics","score_opus":0.03761875897832177,"score_gpt":0.2209160651004652,"score_spread":0.1832973061221434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2539922005","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08607814,0.00013173206,0.90693265,0.00013788942,0.00004665902,0.00007125923,0.00002984352,0.002030739,0.0045411387],"genre_scores_gemma":[0.8420315,0.00006672218,0.15420718,0.00006008425,0.000020187139,0.00011918201,0.00009526408,0.00007209311,0.0033278395],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995223,0.00014200696,0.000027818,0.000095950185,0.00016796973,0.000043995773],"domain_scores_gemma":[0.999271,0.00039406627,0.000060181235,0.00008293605,0.00016386968,0.000027936447],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011139447,0.00039947047,0.00038768505,0.0002540544,0.0003564779,0.0003809001,0.0008330287,0.0006107786,0.0018678432],"category_scores_gemma":[0.0028100517,0.00029539134,0.0002677165,0.00017412959,0.00041594758,0.0005163075,0.00059190294,0.0006677185,0.00051622064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004738496,0.00016668742,0.0013447332,0.00013660867,0.000052861214,0.00013390332,0.0002707559,0.4656386,0.06871887,0.004655182,0.0012317613,0.45717612],"study_design_scores_gemma":[0.0000054791853,0.000059892787,0.00041376243,0.0000051567995,0.000008718376,0.000029390305,0.0000055088617,0.98434377,0.014474724,0.00032927812,0.00031753734,0.000006855811],"about_ca_topic_score_codex":0.0031183937,"about_ca_topic_score_gemma":0.003185288,"teacher_disagreement_score":0.0031183937,"about_ca_system_score_codex":0.00044085455,"about_ca_system_score_gemma":0.0005710002,"threshold_uncertainty_score":0.0062485337},"labels":[],"label_agreement":null},{"id":"W2544551282","doi":"10.1109/icscs.2009.5412292","title":"Combined speech decoders output for phoneme recognition enhancement","year":2009,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Speech recognition; Mel-frequency cepstrum; Robustness (evolution); Feature extraction; Pattern recognition (psychology); Normalization (sociology); Cepstrum; Artificial intelligence; Naive Bayes classifier; Classifier (UML); Support vector machine; Speaker recognition; Speech enhancement; Noise reduction","score_opus":0.04394314540733342,"score_gpt":0.26703860471609464,"score_spread":0.22309545930876123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2544551282","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058784656,0.0010371904,0.9262275,0.00018181649,0.00037184078,0.00015454511,0.00047305596,0.0060810936,0.0066883173],"genre_scores_gemma":[0.32775486,0.0007005905,0.6482832,0.000303368,0.0002360986,0.000201385,0.0013753456,0.0006412802,0.020503845],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990414,0.00014114304,0.00007042888,0.00016740942,0.0005196982,0.00005995239],"domain_scores_gemma":[0.99877983,0.0003772946,0.00005531736,0.0001695582,0.0005692674,0.000048728743],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083165383,0.001194131,0.0009432763,0.000940502,0.00023249567,0.0010895572,0.00083553436,0.0011898238,0.010353362],"category_scores_gemma":[0.0024188429,0.00047909695,0.0007041204,0.00050154945,0.00024362671,0.0011607844,0.0009935716,0.00092821545,0.008840855],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010819427,0.00016286779,0.001056417,0.00040006542,0.00017899915,0.0003362799,0.000099455356,0.007672946,0.48864853,0.0015573772,0.0025796427,0.49622545],"study_design_scores_gemma":[0.000093029405,0.0005107847,0.0037189145,0.00007353408,0.00033479166,0.001186316,0.00006109407,0.23349386,0.73896354,0.0014823388,0.02000953,0.000072270086],"about_ca_topic_score_codex":0.00036693693,"about_ca_topic_score_gemma":0.0012185466,"teacher_disagreement_score":0.010353362,"about_ca_system_score_codex":0.00020783831,"about_ca_system_score_gemma":0.00037951532,"threshold_uncertainty_score":0.034635425},"labels":[],"label_agreement":null},{"id":"W2547760228","doi":"10.1109/icacci.2016.7732024","title":"Modified gammatone frequency cepstral coefficients to improve spoofing detection","year":2016,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Garron Family Cancer Centre; Tata Consultancy Services","keywords":"Spoofing attack; Mel-frequency cepstrum; Computer science; Cepstrum; Speech recognition; Discrete cosine transform; Pattern recognition (psychology); Detector; Speaker verification; Speaker recognition; Artificial intelligence; Feature extraction; Telecommunications; Computer security","score_opus":0.018526417548240755,"score_gpt":0.23695867241442642,"score_spread":0.21843225486618567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2547760228","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32216802,0.004233968,0.66236067,0.0004375822,0.00061597495,0.00024204575,0.001000333,0.0032047597,0.0057366057],"genre_scores_gemma":[0.6969933,0.0021115334,0.29579788,0.00017020639,0.00014367138,0.00008262393,0.0013110222,0.00020148075,0.003188293],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991436,0.0001236081,0.00006493835,0.00011939333,0.00045369982,0.00009482732],"domain_scores_gemma":[0.99788696,0.00062940456,0.00014591764,0.00021864302,0.0010627299,0.000056223333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010256456,0.0010992556,0.0006162123,0.0020216762,0.00025562764,0.0007503612,0.00043345254,0.0007310159,0.001599267],"category_scores_gemma":[0.004918243,0.00024680234,0.00038608623,0.0011514297,0.00024151818,0.0010237558,0.0004587834,0.00077808305,0.0012021919],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00052923185,0.00015914575,0.008003885,0.00028045935,0.0001235052,0.00044967682,0.00014878418,0.024555212,0.2464383,0.00142597,0.005014855,0.71287096],"study_design_scores_gemma":[0.00008219269,0.00060428056,0.06852536,0.00013264298,0.00034541506,0.0018417304,0.00023985853,0.6278173,0.27193743,0.0013914851,0.026878111,0.00020430649],"about_ca_topic_score_codex":0.0048040636,"about_ca_topic_score_gemma":0.0065362607,"teacher_disagreement_score":0.0048040636,"about_ca_system_score_codex":0.00031873622,"about_ca_system_score_gemma":0.00059615803,"threshold_uncertainty_score":0.00955224},"labels":[],"label_agreement":null},{"id":"W2556512059","doi":"10.1121/1.4970196","title":"The native language benefit for voice recognition is not contingent on lexical access","year":2016,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Indexicality; Psychology; Linguistics; Comprehension; Identification (biology); American English; Duration (music); Contrast (vision); Audiology; Speech recognition; Computer science; Acoustics; Artificial intelligence; Biology; Medicine","score_opus":0.03966639049154784,"score_gpt":0.30400934189432266,"score_spread":0.2643429514027748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2556512059","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9954047,0.00016962495,0.0017749025,0.000071461065,0.00002251781,0.000011170302,0.00005610252,0.000056377237,0.0024331254],"genre_scores_gemma":[0.9974752,0.00007855724,0.00116579,0.00009217792,0.00001617263,0.000019380894,0.00010098991,0.000035076428,0.0010166906],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9991104,0.0001928,0.00009523126,0.0003240929,0.00017369758,0.00010377517],"domain_scores_gemma":[0.9960424,0.0019788942,0.00056937605,0.0006869048,0.00030283953,0.0004196989],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00097174366,0.00036256845,0.0005523499,0.00035641124,0.0002429436,0.000789928,0.00028354255,0.00054632046,0.0054196874],"category_scores_gemma":[0.0035724144,0.00033927444,0.00026084564,0.000071656,0.0008514954,0.00085909705,0.0009950029,0.00064376136,0.0008035508],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00073586043,0.000123024,0.0042709704,0.00010044623,0.000039367587,0.00014665411,0.0002902121,0.00002871982,0.9809248,0.00009178142,0.00005966871,0.013188504],"study_design_scores_gemma":[0.00012575972,0.005839615,0.5702264,0.000032186643,0.00019426772,0.0030722115,0.0011475998,0.0005877784,0.41593018,0.0010338904,0.0017485513,0.00006167709],"about_ca_topic_score_codex":0.00034956087,"about_ca_topic_score_gemma":0.00067561393,"teacher_disagreement_score":0.0054196874,"about_ca_system_score_codex":0.00013460049,"about_ca_system_score_gemma":0.00020398207,"threshold_uncertainty_score":0.01813072},"labels":[],"label_agreement":null},{"id":"W2560180799","doi":"10.1093/acrefore/9780199384655.013.108","title":"Learnability and Learning Algorithms in Phonology","year":2016,"lang":"en","type":"reference-entry","venue":"Oxford Research Encyclopedia of Linguistics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Learnability; Grammar; Computer science; Morpheme; Artificial intelligence; Phonology; Natural language processing; Rule-based machine translation; Linguistics; Language acquisition; Phonotactics; Grammar induction; Class (philosophy); Task (project management)","score_opus":0.06140302826450727,"score_gpt":0.34953947115092215,"score_spread":0.2881364428864149,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560180799","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26621228,0.002807977,0.68378764,0.008594459,0.00017222151,0.00017515663,0.00016336687,0.0005422683,0.037544683],"genre_scores_gemma":[0.9137303,0.00081217085,0.07915519,0.0003986528,0.00020841062,0.00017119177,0.00015168545,0.0001365136,0.005235904],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9961994,0.0020957582,0.00023303996,0.000764795,0.00054083776,0.0001661573],"domain_scores_gemma":[0.9608463,0.03322977,0.0015307674,0.0020174684,0.0018756087,0.00050012313],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0055029425,0.0005606517,0.00080349576,0.0014676438,0.0006202509,0.0033624042,0.0013335027,0.00182674,0.0039762827],"category_scores_gemma":[0.044147734,0.00046769078,0.00091908505,0.0008457441,0.0073178066,0.0072649023,0.0026548656,0.0028923578,0.0004807782],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011255447,0.00009628204,0.007972571,0.00027309117,0.00013774257,0.00012153605,0.00070875644,0.13522895,0.0016697311,0.77702576,0.0008926068,0.0757605],"study_design_scores_gemma":[0.000023974602,0.000038332135,0.0007072407,0.000026471187,0.000008811742,0.00003700832,0.00004308606,0.14016753,0.00062346045,0.8573854,0.0009265211,0.000012232236],"about_ca_topic_score_codex":0.0014768231,"about_ca_topic_score_gemma":0.00075422274,"teacher_disagreement_score":0.0055029425,"about_ca_system_score_codex":0.0022167135,"about_ca_system_score_gemma":0.0008738884,"threshold_uncertainty_score":0.029102683},"labels":[],"label_agreement":null},{"id":"W2586956420","doi":"10.1109/slt.2016.7846264","title":"Modelling speaker and channel variability using deep neural networks for robust speaker verification","year":2016,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Computer Research Institute of Montréal","funders":"Nvidia","keywords":"Speaker verification; Computer science; Normalization (sociology); Word error rate; Speech recognition; Speaker recognition; Classifier (UML); Pattern recognition (psychology); Artificial neural network; Artificial intelligence; Discrete cosine transform; Deep neural networks","score_opus":0.07338699910887467,"score_gpt":0.2456055521845424,"score_spread":0.17221855307566772,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2586956420","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051847693,0.00031030228,0.9453151,0.00015639597,0.000059282578,0.000020210586,0.00011137395,0.0008262784,0.0013533864],"genre_scores_gemma":[0.8393699,0.00026993803,0.15622255,0.0001145402,0.000054615804,0.000049283568,0.00034580246,0.00015083462,0.003422581],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99953485,0.000113059985,0.000021581229,0.00013151107,0.00013641734,0.00006257952],"domain_scores_gemma":[0.9993222,0.00034354985,0.0000937595,0.00009468161,0.00012359541,0.000022309117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011462508,0.00070053886,0.0005018105,0.0003406738,0.00022720188,0.00061587733,0.0007813814,0.0005289216,0.001366419],"category_scores_gemma":[0.0025235503,0.00036215427,0.00055102876,0.00028247997,0.00036711083,0.0011134783,0.00081463327,0.00155464,0.000519366],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041001907,0.00010165809,0.003781073,0.00007576941,0.0001308091,0.00010099616,0.00009888728,0.60827833,0.050834868,0.0044674845,0.0013627457,0.3303573],"study_design_scores_gemma":[0.000002652255,0.000015517922,0.00041127048,0.000003393496,0.000007679811,0.000020985099,0.0000039859515,0.9925483,0.0056458847,0.0010621411,0.00027195105,0.000006259901],"about_ca_topic_score_codex":0.005307083,"about_ca_topic_score_gemma":0.008337209,"teacher_disagreement_score":0.005307083,"about_ca_system_score_codex":0.0005462218,"about_ca_system_score_gemma":0.0008082299,"threshold_uncertainty_score":0.010552347},"labels":[],"label_agreement":null},{"id":"W2606954870","doi":"10.1017/s0025100317000159","title":"Revisions to the VoQS system for the transcription of voice quality","year":2017,"lang":"en","type":"article","venue":"Journal of the International Phonetic Association","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Bangor University","keywords":"Phonation; Transcription (linguistics); Section (typography); Larynx; Quality (philosophy); Speech recognition; Computer science; Chart; Communication; Psychology; Audiology; Linguistics; Medicine; Mathematics; Statistics","score_opus":0.04588565896230793,"score_gpt":0.31908792235995737,"score_spread":0.2732022633976494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606954870","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01015648,0.003290974,0.7483005,0.0147734545,0.076456346,0.0029689807,0.039597124,0.048098173,0.056357943],"genre_scores_gemma":[0.06394054,0.0039022635,0.66271555,0.009498702,0.015378061,0.004754964,0.07148417,0.043948285,0.12437743],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97878575,0.005651766,0.005944836,0.0021038377,0.0066564875,0.0008573079],"domain_scores_gemma":[0.90591353,0.011609871,0.0026548295,0.01078556,0.06782315,0.0012130446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016350478,0.0011932396,0.0011867638,0.004471671,0.0014872801,0.0046899244,0.002450805,0.0020211537,0.049498957],"category_scores_gemma":[0.075716466,0.00086422893,0.0010466225,0.0025157926,0.0017373908,0.0026204113,0.0030094318,0.006433592,0.0620879],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00080628967,0.000073901814,0.0019421733,0.0010965936,0.00005444285,0.0005690621,0.002764504,0.00139545,0.0327248,0.019264534,0.5435384,0.39576977],"study_design_scores_gemma":[0.000063166124,0.00010698743,0.0024696342,0.00040238042,0.000020702144,0.00065920246,0.00037093155,0.0018406529,0.008556089,0.0029452357,0.9823799,0.00018520092],"about_ca_topic_score_codex":0.005456376,"about_ca_topic_score_gemma":0.003167531,"teacher_disagreement_score":0.049498957,"about_ca_system_score_codex":0.0024293708,"about_ca_system_score_gemma":0.0039525605,"threshold_uncertainty_score":0.16559052},"labels":[],"label_agreement":null},{"id":"W2610699719","doi":"10.71781/9853","title":"Weighted finite-state transducers in speech recognition : a compaction algorithm for non-determinizable transducers","year":2002,"lang":"en","type":"dissertation","venue":"Open MIND","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Transducer; Finite state; Speech recognition; Compaction; State (computer science); Computer science; Algorithm; Acoustics; Engineering; Machine learning; Physics","score_opus":0.055050317056273335,"score_gpt":0.3028397106030366,"score_spread":0.24778939354676327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2610699719","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025915576,0.00025884612,0.9954667,0.00005768696,0.000025365554,0.000031387193,0.000050873623,0.0010232902,0.00049425993],"genre_scores_gemma":[0.06565682,0.0004987695,0.92752916,0.000078451405,0.00006621851,0.00024044233,0.00051694916,0.00071944355,0.004693726],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987382,0.00036734407,0.0001354925,0.0003172857,0.00032715738,0.00011447826],"domain_scores_gemma":[0.99760807,0.0014832056,0.0001017378,0.00040165387,0.00035673348,0.00004857221],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001343259,0.0009820659,0.0010648739,0.0010624587,0.0005594837,0.0016673307,0.0021188245,0.0010301081,0.0056537343],"category_scores_gemma":[0.0048382506,0.0010566078,0.0009219847,0.0017993752,0.0010279283,0.0030440034,0.001303734,0.0016774717,0.0022911667],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000405512,0.00011132442,0.000475088,0.0003304865,0.00008854718,0.00019804244,0.00038972203,0.094927385,0.02630859,0.07163169,0.006361794,0.7987718],"study_design_scores_gemma":[0.000063218635,0.000110470806,0.0005469439,0.00006789164,0.00007612383,0.0001541407,0.00009894204,0.8358672,0.043961775,0.10136286,0.017634042,0.000056381494],"about_ca_topic_score_codex":0.0034505576,"about_ca_topic_score_gemma":0.0056090257,"teacher_disagreement_score":0.0056537343,"about_ca_system_score_codex":0.0008176819,"about_ca_system_score_gemma":0.0015853717,"threshold_uncertainty_score":0.018913627},"labels":[],"label_agreement":null},{"id":"W2610924493","doi":"10.1016/j.compbiolchem.2017.03.012","title":"PECC: Correcting contigs based on paired-end read distribution","year":2017,"lang":"en","type":"article","venue":"Computational Biology and Chemistry","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Outstanding Youth Science Fund Project of National Natural Science Foundation of China; National Natural Science Foundation of China","keywords":"Computer science","score_opus":0.020562206355106173,"score_gpt":0.275028273531399,"score_spread":0.25446606717629283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2610924493","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012085792,0.00040621107,0.90614974,0.00017726276,0.0007473892,0.00014020552,0.00324446,0.07519258,0.0018563253],"genre_scores_gemma":[0.055745374,0.00019058569,0.91868585,0.00027377368,0.00021966425,0.00025836704,0.008927322,0.008580954,0.007118055],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9966989,0.00047112672,0.00019422286,0.001188326,0.0012023571,0.00024495332],"domain_scores_gemma":[0.9898627,0.0028614951,0.0007068338,0.003931343,0.0023537253,0.00028387326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031096202,0.0033154166,0.0016824107,0.0031924027,0.002119367,0.0017015185,0.0036152368,0.0025058328,0.015080969],"category_scores_gemma":[0.015097977,0.0014400999,0.001800129,0.0033723966,0.001334066,0.0021652058,0.004097646,0.0030031134,0.01172135],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019617323,0.00023042179,0.008870045,0.0011314858,0.00049849466,0.0013154075,0.0006808703,0.03046796,0.08753534,0.017567508,0.075456716,0.77428406],"study_design_scores_gemma":[0.00032011673,0.00039286286,0.0060032713,0.00021614331,0.00039009418,0.0019153327,0.00038226915,0.48944998,0.37486455,0.039073985,0.08667573,0.00031567944],"about_ca_topic_score_codex":0.004332843,"about_ca_topic_score_gemma":0.008393179,"teacher_disagreement_score":0.015080969,"about_ca_system_score_codex":0.00077738485,"about_ca_system_score_gemma":0.0026644075,"threshold_uncertainty_score":0.05045086},"labels":[],"label_agreement":null},{"id":"W2611386872","doi":"10.2172/1289367","title":"Analysis of Pre-Trained Deep Neural Networks for Large-Vocabulary Automatic Speech Recognition","year":2016,"lang":"en","type":"report","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Circulatory and Respiratory Health; Lawrence Livermore National Laboratory; U.S. Department of Energy","keywords":"Convolutional neural network; Sensitivity (control systems); Computer science; Artificial neural network; Pattern recognition (psychology); Event (particle physics); Field (mathematics); Artificial intelligence; Detector; Selection (genetic algorithm); Speech recognition; Vocabulary; Particle (ecology); Nova (rocket); SIGNAL (programming language); Physics; Mathematics; Engineering; Astrophysics; Electronic engineering","score_opus":0.03970584771201347,"score_gpt":0.29763167030373283,"score_spread":0.25792582259171937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2611386872","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75614965,0.001690223,0.22268799,0.0007717672,0.0003866775,0.00014042726,0.0036678421,0.004607018,0.009898368],"genre_scores_gemma":[0.9602655,0.00035720435,0.02326688,0.000091417234,0.00006749007,0.00009848559,0.0056244605,0.00035157302,0.009876753],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99966323,0.000043472293,0.000018581073,0.00006574307,0.00013908003,0.00006991176],"domain_scores_gemma":[0.9981078,0.0010857002,0.00004468366,0.00012750417,0.00059999246,0.000034250515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057979516,0.00082302134,0.0003701665,0.0005633926,0.00034790803,0.00055995374,0.0005386141,0.0004655105,0.008126015],"category_scores_gemma":[0.002573142,0.0003188766,0.00051312,0.00035711104,0.00021897722,0.0007135801,0.0003401223,0.00095301494,0.0014765594],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020891894,0.0006447605,0.009759529,0.00049021357,0.00035947261,0.0006970752,0.0001251175,0.28348815,0.25091323,0.004309983,0.016213909,0.4309094],"study_design_scores_gemma":[0.000014651176,0.00014863283,0.009462023,0.00001077871,0.00004446873,0.000061254585,0.000034720444,0.9467585,0.04143233,0.00071396434,0.0013040536,0.000014635674],"about_ca_topic_score_codex":0.013538618,"about_ca_topic_score_gemma":0.026393266,"teacher_disagreement_score":0.013538618,"about_ca_system_score_codex":0.0010479145,"about_ca_system_score_gemma":0.0008332808,"threshold_uncertainty_score":0.027184248},"labels":[],"label_agreement":null},{"id":"W2620616604","doi":"","title":"Predicting the quality of processed speech by combining modulation-based features and model trees.","year":2016,"lang":"en","type":"article","venue":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Quality (philosophy); Speech recognition; Modulation (music); Artificial intelligence; Pattern recognition (psychology); Acoustics","score_opus":0.03210785264559545,"score_gpt":0.2759148809231232,"score_spread":0.24380702827752776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2620616604","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4106472,0.0013969778,0.5806172,0.00039370998,0.00018535324,0.000083335006,0.0012250834,0.0021974002,0.0032537752],"genre_scores_gemma":[0.92990273,0.00032334475,0.067062564,0.000044331682,0.000053372725,0.000031899563,0.0012424119,0.00014484047,0.0011945732],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997726,0.000064862026,0.0000122624815,0.000051747793,0.00006363637,0.00003491111],"domain_scores_gemma":[0.9988784,0.00075129396,0.00008728571,0.000062172534,0.00017683391,0.000043971788],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060733454,0.0006160561,0.00053604925,0.0011615641,0.000186988,0.0007144102,0.00032911066,0.0008449169,0.0017284276],"category_scores_gemma":[0.0036024235,0.000317675,0.0005792825,0.0006232751,0.00018403286,0.0010106075,0.0004433482,0.0007620931,0.0011996501],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016731127,0.00041406008,0.024975644,0.00018773487,0.00028697026,0.00028338307,0.00012390687,0.3070995,0.15151879,0.0017122015,0.004667038,0.5070576],"study_design_scores_gemma":[0.000014073229,0.00008397392,0.0068951924,0.00000829753,0.000039570845,0.000051405077,0.000012156157,0.984934,0.006922916,0.0007920421,0.00023575746,0.00001058213],"about_ca_topic_score_codex":0.003389814,"about_ca_topic_score_gemma":0.0051977173,"teacher_disagreement_score":0.003389814,"about_ca_system_score_codex":0.0002469417,"about_ca_system_score_gemma":0.00030318953,"threshold_uncertainty_score":0.006740153},"labels":[],"label_agreement":null},{"id":"W2620638943","doi":"10.5445/ir/1000166279","title":"Phoneme Boundary Detection using Deep Bidirectional LSTMs","year":2016,"lang":"en","type":"article","venue":"KITopen","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Speech recognition; Boundary (topology); Natural language processing; Pattern recognition (psychology); Mathematics","score_opus":0.030527414604483313,"score_gpt":0.2520615829131662,"score_spread":0.2215341683086829,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2620638943","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05000309,0.0009823302,0.9211684,0.00029557524,0.0006242939,0.00010373431,0.0014690334,0.016388519,0.008964948],"genre_scores_gemma":[0.53224134,0.0006065204,0.44125187,0.0004485968,0.00015817775,0.00018947311,0.0049787154,0.0011637852,0.018961605],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996859,0.000033890203,0.000017083288,0.00011915513,0.00007943319,0.000064610205],"domain_scores_gemma":[0.9995396,0.00015497596,0.000030798157,0.000075716904,0.00015648546,0.000042488038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037708337,0.0010914584,0.0007353366,0.00071352976,0.00036532315,0.0011357648,0.0008586387,0.0011583627,0.012017859],"category_scores_gemma":[0.0013267398,0.0004737182,0.0005956957,0.00047354342,0.00024527684,0.0014456166,0.0014608102,0.0018180357,0.008130656],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042350244,0.00011309797,0.0007047098,0.00017737238,0.000054980894,0.0001585371,0.00007894329,0.011878485,0.15056038,0.0024955105,0.008769073,0.82458544],"study_design_scores_gemma":[0.000038185095,0.00018396003,0.0024559838,0.00009999311,0.0000698436,0.00023169146,0.00012659181,0.8309097,0.1470734,0.007916359,0.010843809,0.000050507686],"about_ca_topic_score_codex":0.0036149635,"about_ca_topic_score_gemma":0.0072807875,"teacher_disagreement_score":0.012017859,"about_ca_system_score_codex":0.0003824235,"about_ca_system_score_gemma":0.00083107664,"threshold_uncertainty_score":0.04020369},"labels":[],"label_agreement":null},{"id":"W2624150886","doi":"10.1121/1.4989096","title":"Cross-register speaker identification: The case of infant and adult directed speech","year":2017,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Register (sociolinguistics); Computer science; Speech recognition; Classifier (UML); Speaker identification; Identification (biology); Speaker recognition; Artificial intelligence; Linguistics","score_opus":0.020827259953875438,"score_gpt":0.2903955218247226,"score_spread":0.26956826187084715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2624150886","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.952608,0.0013740641,0.0395194,0.000093700575,0.000087664404,0.00009729298,0.00057597854,0.00040581444,0.005238122],"genre_scores_gemma":[0.987941,0.00021992506,0.0099763125,0.000059325168,0.000035048713,0.000051717197,0.0007394605,0.00007448626,0.0009025813],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9958326,0.0012638255,0.00036037437,0.0014823172,0.00080189994,0.00025889237],"domain_scores_gemma":[0.99318403,0.003381201,0.00058692956,0.0015647036,0.0010345108,0.00024868498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035027426,0.0005395848,0.0007462796,0.0008881248,0.00033990789,0.00094810216,0.00052885356,0.0009428324,0.0013502024],"category_scores_gemma":[0.009777549,0.00025709884,0.00044122792,0.00044973538,0.0005345074,0.0008168607,0.0011984052,0.00041782032,0.0009566959],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0041985908,0.00045925713,0.16405234,0.0010023104,0.0010055715,0.005696138,0.004598438,0.011198095,0.41507313,0.0015379939,0.0023892217,0.38878888],"study_design_scores_gemma":[0.00008838135,0.00240078,0.68716896,0.00015601507,0.0008405822,0.014898632,0.002769935,0.10043078,0.18004383,0.0029584093,0.00803391,0.00020977312],"about_ca_topic_score_codex":0.001615359,"about_ca_topic_score_gemma":0.0021274297,"teacher_disagreement_score":0.0035027426,"about_ca_system_score_codex":0.00022304582,"about_ca_system_score_gemma":0.00023391492,"threshold_uncertainty_score":0.018524468},"labels":[],"label_agreement":null},{"id":"W2678453873","doi":"10.1109/ccece.2017.7946643","title":"Feature fusion techniques based training MLP for speaker identification system","year":2017,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Feature (linguistics); Speech recognition; Artificial intelligence; Speaker identification; Identification (biology); Speaker recognition; Pattern recognition (psychology); Feature extraction; Speaker diarisation; Training (meteorology); Training set","score_opus":0.060063312929288896,"score_gpt":0.2943440950155201,"score_spread":0.2342807820862312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2678453873","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06755447,0.0005263713,0.9269263,0.00009927248,0.000089577596,0.00006422332,0.000103739934,0.0028220625,0.0018139344],"genre_scores_gemma":[0.7497915,0.00034904853,0.24648865,0.0000564884,0.00005412826,0.00013262306,0.0002531462,0.000062050196,0.0028123974],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99966085,0.00005108085,0.00002278611,0.000092740054,0.0001352608,0.000037362643],"domain_scores_gemma":[0.9997621,0.00007083662,0.000017780894,0.000026238364,0.00011439961,0.000008587092],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005279437,0.00040717795,0.00039838263,0.0003595126,0.00026122743,0.0003025742,0.00044221236,0.0004754281,0.0020752135],"category_scores_gemma":[0.0008980682,0.00019439621,0.00033206187,0.0002779586,0.00015015677,0.0005948767,0.00033456204,0.0005613762,0.0007900018],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038548664,0.00012906853,0.0016239147,0.0002025402,0.000076168886,0.00017599703,0.00015309257,0.06705881,0.23276174,0.0012645565,0.0018015683,0.69436693],"study_design_scores_gemma":[0.000014557317,0.00029842783,0.0046126638,0.000024378265,0.00007735916,0.00024871025,0.00003580428,0.9019277,0.08757995,0.00077060104,0.0043780226,0.000031720356],"about_ca_topic_score_codex":0.0014694465,"about_ca_topic_score_gemma":0.0012130765,"teacher_disagreement_score":0.0020752135,"about_ca_system_score_codex":0.00024461196,"about_ca_system_score_gemma":0.00031789954,"threshold_uncertainty_score":0.006942332},"labels":[],"label_agreement":null},{"id":"W2688145745","doi":"10.1109/ccece.2017.7946645","title":"Performance evaluation of mixtures of PLDA and conventional PLDA for a small-set speaker verification system","year":2017,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Speech recognition; Speaker verification; Signal-to-noise ratio (imaging); Set (abstract data type); Speech enhancement; Noise (video); Probabilistic logic; Pattern recognition (psychology); Speaker recognition; Artificial intelligence; Noise reduction; Telecommunications","score_opus":0.10954139473737029,"score_gpt":0.3081377052994708,"score_spread":0.19859631056210053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2688145745","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5432789,0.0037195312,0.44521073,0.0002891818,0.00029621972,0.00021390026,0.0001882792,0.00414153,0.0026617453],"genre_scores_gemma":[0.82567143,0.0004275839,0.17186852,0.00007612674,0.000054361295,0.00010534524,0.00029605997,0.00012804038,0.0013725486],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99715793,0.0010121544,0.000245664,0.00050241547,0.0009091697,0.00017262185],"domain_scores_gemma":[0.9954268,0.00231742,0.00023029518,0.00034298765,0.0014414379,0.00024102665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040544937,0.0010650028,0.0010371918,0.0007487033,0.000561907,0.001125005,0.0008923719,0.0011271052,0.0021459698],"category_scores_gemma":[0.008047651,0.00046970128,0.0005635534,0.0003840513,0.00038291415,0.0019277912,0.0012469122,0.0009030381,0.0010639622],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012425197,0.00071607967,0.008488168,0.0007177598,0.000661671,0.0003239354,0.00035468736,0.030439647,0.26662296,0.0007986457,0.0012414221,0.6772098],"study_design_scores_gemma":[0.00019505929,0.00332441,0.017982766,0.000042446678,0.0003435377,0.0013122509,0.00017150442,0.7728704,0.20048477,0.00029415375,0.0028035135,0.00017514058],"about_ca_topic_score_codex":0.0011706231,"about_ca_topic_score_gemma":0.001784771,"teacher_disagreement_score":0.0040544937,"about_ca_system_score_codex":0.00046623347,"about_ca_system_score_gemma":0.00048131903,"threshold_uncertainty_score":0.021442413},"labels":[],"label_agreement":null},{"id":"W2724202180","doi":"","title":"Development of the Vietnamese speech assessment","year":2018,"lang":"vi","type":"article","venue":"Charles Sturt University Research Output (CRO)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Vietnamese; Computer science; Speech recognition; Linguistics; Natural language processing","score_opus":0.12962657413773948,"score_gpt":0.3461056309661509,"score_spread":0.2164790568284114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2724202180","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7982256,0.00093285396,0.09131235,0.0027296862,0.00076860335,0.018947031,0.004124931,0.0015007728,0.081458196],"genre_scores_gemma":[0.62364995,0.0015116087,0.31253612,0.0005153248,0.00011536884,0.010429299,0.0035582145,0.0003114095,0.04737262],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99696296,0.0010654784,0.00049957435,0.00032881813,0.0009792517,0.00016390083],"domain_scores_gemma":[0.99244773,0.0007684275,0.00018293376,0.00026862303,0.0056100944,0.000722252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005641673,0.00059772434,0.0004740782,0.0012353255,0.00081509136,0.0011676452,0.0008493509,0.00032326602,0.004336187],"category_scores_gemma":[0.007618239,0.00036413953,0.00038870663,0.0003625783,0.00042880687,0.0007363131,0.002163241,0.0011469213,0.002169539],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041612698,0.0012383831,0.107177734,0.00069727545,0.000032903867,0.0020644916,0.033365186,0.0019131876,0.034898773,0.00370393,0.012284045,0.80220807],"study_design_scores_gemma":[0.00018276654,0.005849257,0.4912322,0.0016588849,0.00011716708,0.0052811196,0.033672705,0.015277426,0.062422,0.0042993687,0.3796099,0.00039712826],"about_ca_topic_score_codex":0.0108992895,"about_ca_topic_score_gemma":0.016151782,"teacher_disagreement_score":0.0108992895,"about_ca_system_score_codex":0.0011627876,"about_ca_system_score_gemma":0.005804499,"threshold_uncertainty_score":0.029836357},"labels":[],"label_agreement":null},{"id":"W2735115738","doi":"","title":"Forced Alignment for Understudied Language Varieties: Testing Prosodylab-Aligner with Tongan Data.","year":2018,"lang":"en","type":"article","venue":"ScholarSpace (University of Hawaii at Manoa)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Process (computing); Speech recognition; Transcription (linguistics); Documentation; Natural language processing; Field (mathematics); Phonetic transcription; Segmentation; Artificial intelligence; Linguistics; Programming language","score_opus":0.0590055234052734,"score_gpt":0.2485947740864726,"score_spread":0.1895892506811992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2735115738","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94011533,0.00091554306,0.027556038,0.0004213951,0.0005853633,0.0004897129,0.011738089,0.009617763,0.008560679],"genre_scores_gemma":[0.8562401,0.00027590778,0.072002776,0.0005539285,0.00010521429,0.00076340546,0.06031391,0.0023935977,0.007351253],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9955831,0.0016516682,0.00038422935,0.0015877819,0.0005519237,0.00024141511],"domain_scores_gemma":[0.9907692,0.0042025563,0.00041805702,0.0021981518,0.0018958345,0.00051606615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009842093,0.0011799701,0.0007028717,0.0012047086,0.001667838,0.0013142396,0.0018702648,0.0012214041,0.005841442],"category_scores_gemma":[0.018058142,0.00045982632,0.00079153344,0.0015805855,0.00107586,0.0030938485,0.0029994836,0.0017117017,0.005480124],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006127928,0.0023156693,0.12742475,0.0025367176,0.0018644886,0.0028187928,0.016637495,0.022345481,0.08790547,0.0038251185,0.076906145,0.64929205],"study_design_scores_gemma":[0.0023763657,0.0056930673,0.47227627,0.00044608474,0.0011121011,0.003513468,0.022664892,0.25856143,0.08976099,0.0053941086,0.13754328,0.00065797474],"about_ca_topic_score_codex":0.016049888,"about_ca_topic_score_gemma":0.026340045,"teacher_disagreement_score":0.016049888,"about_ca_system_score_codex":0.0006555726,"about_ca_system_score_gemma":0.0015695146,"threshold_uncertainty_score":0.05205059},"labels":[],"label_agreement":null},{"id":"W2740120517","doi":"","title":"Learning Latent Space Models with Angular Constraints","year":2017,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Space (punctuation); Artificial intelligence","score_opus":0.06111164871674642,"score_gpt":0.29273717667035065,"score_spread":0.23162552795360425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2740120517","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0093944445,0.00062415184,0.9870745,0.00045349958,0.00007394283,0.000029186154,0.00035563883,0.0008981386,0.0010966237],"genre_scores_gemma":[0.5915012,0.001751934,0.38363704,0.00069938053,0.00044889923,0.00055874564,0.005245357,0.00081103644,0.015346487],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980673,0.0010042134,0.00008966073,0.00044692954,0.0002293621,0.0001624195],"domain_scores_gemma":[0.9918047,0.0064781466,0.00040767892,0.0007460024,0.000352973,0.00021048226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029847242,0.0015804463,0.0018907998,0.0012442849,0.0007410075,0.003127504,0.0025905655,0.002631838,0.0065804953],"category_scores_gemma":[0.011709497,0.0020342255,0.0020972476,0.002021021,0.0016362609,0.0043080966,0.003104643,0.004724984,0.002965838],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004889316,0.00022260296,0.0019732688,0.00018756387,0.00028132973,0.000135235,0.00018933427,0.74106634,0.0013638479,0.09478042,0.00786791,0.15144323],"study_design_scores_gemma":[0.000022252,0.000015063206,0.000068680485,0.0000120735585,0.000012597752,0.000009834981,0.000010608584,0.9736921,0.0001533958,0.025434349,0.0005612256,0.000007732916],"about_ca_topic_score_codex":0.007337723,"about_ca_topic_score_gemma":0.0088565,"teacher_disagreement_score":0.007337723,"about_ca_system_score_codex":0.00089331076,"about_ca_system_score_gemma":0.0013087147,"threshold_uncertainty_score":0.022013962},"labels":[],"label_agreement":null},{"id":"W27446868","doi":"","title":"Speech analysis and synthesis based on ARMA lattice model.","year":2003,"lang":"en","type":"article","venue":"Scholarship at UWindsor (University of Windsor)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Speech recognition; Computer science; Speech synthesis; Natural language processing; Artificial intelligence","score_opus":0.025008954915785735,"score_gpt":0.21870487279382475,"score_spread":0.19369591787803903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W27446868","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0069798874,0.0002484103,0.9891377,0.000046771336,0.000058572943,0.000040391922,0.000064406035,0.00083662325,0.0025872225],"genre_scores_gemma":[0.31106958,0.000911569,0.6731352,0.00010000781,0.000077222656,0.00021898153,0.0005510671,0.00022720238,0.013709104],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997029,0.00006343852,0.000017778686,0.00007480047,0.00012388683,0.000017161192],"domain_scores_gemma":[0.999801,0.000082894534,0.000018322813,0.000027732767,0.000062208004,0.000007860555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003916445,0.00043712725,0.00039582356,0.00035982238,0.00027201584,0.00059458957,0.00042014386,0.00046658894,0.0033974696],"category_scores_gemma":[0.000605778,0.0001919524,0.00066854403,0.00027002773,0.00021843045,0.0006280228,0.00030964575,0.000551575,0.0022313655],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034768248,0.00009624337,0.00081278954,0.0005107853,0.00012459057,0.00028315582,0.00029478472,0.1634115,0.30792865,0.02313718,0.002726586,0.5003261],"study_design_scores_gemma":[0.000017036427,0.00015488111,0.00039170258,0.000022956741,0.000035453166,0.00018163664,0.000033888868,0.943881,0.039170083,0.0034849318,0.012603695,0.00002274874],"about_ca_topic_score_codex":0.0016710963,"about_ca_topic_score_gemma":0.0014220367,"teacher_disagreement_score":0.0033974696,"about_ca_system_score_codex":0.00026758,"about_ca_system_score_gemma":0.0004591715,"threshold_uncertainty_score":0.011365652},"labels":[],"label_agreement":null},{"id":"W2747874407","doi":"10.21437/interspeech.2017-1386","title":"Montreal Forced Aligner: Trainable Text-Speech Alignment Using Kaldi","year":2017,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1124,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Speech recognition; Natural language processing; Linguistics; Artificial intelligence","score_opus":0.04401314992965729,"score_gpt":0.2826153983171813,"score_spread":0.238602248387524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2747874407","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006596823,0.0007776082,0.8189954,0.00018151793,0.0005664086,0.0002779907,0.00539089,0.1621147,0.0050985096],"genre_scores_gemma":[0.0815911,0.00040529238,0.8635892,0.00042310846,0.00013865996,0.00063173246,0.02319972,0.008349862,0.02167131],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99878436,0.00017718779,0.00007479649,0.0005425241,0.00027482669,0.000146321],"domain_scores_gemma":[0.9990196,0.00029221686,0.000047452988,0.00025081597,0.00030991077,0.000080104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015165948,0.00277767,0.0013900839,0.0016832784,0.0010937607,0.0016022857,0.0029826886,0.0017463106,0.040155746],"category_scores_gemma":[0.0035138135,0.0012030659,0.0009146577,0.001191386,0.00053807255,0.0018346738,0.002860261,0.0028154107,0.032714356],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009877695,0.00014020188,0.0009038033,0.00043615172,0.00024491549,0.00032748116,0.00014053816,0.015110377,0.06774936,0.0047936193,0.09338108,0.8157847],"study_design_scores_gemma":[0.00034502288,0.00041493736,0.0029996696,0.00007115441,0.00016965387,0.0004948851,0.0001874056,0.6596141,0.2119787,0.0076715015,0.11583858,0.00021435955],"about_ca_topic_score_codex":0.024959225,"about_ca_topic_score_gemma":0.070832215,"teacher_disagreement_score":0.040155746,"about_ca_system_score_codex":0.001230704,"about_ca_system_score_gemma":0.0029980026,"threshold_uncertainty_score":0.13433433},"labels":[],"label_agreement":null},{"id":"W2756663932","doi":"10.3233/978-1-61499-798-6-322","title":"Cloud-Based Speech Technology for Assistive Technology Applications (CloudCAST)","year":2017,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Rehabilitation Institute","funders":"","keywords":"Cloud computing; Assistive technology; Computer science; Speech technology; Multimedia; World Wide Web; Human–computer interaction; Speech synthesis; Speech recognition; Operating system","score_opus":0.0717944582266798,"score_gpt":0.3826523058363527,"score_spread":0.3108578476096729,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2756663932","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08739915,0.0040941453,0.67755485,0.0030598468,0.0019935635,0.0018801938,0.008766671,0.11602287,0.09922867],"genre_scores_gemma":[0.68400407,0.0035740042,0.21712467,0.0017072057,0.00075764337,0.001096204,0.015014795,0.0050539747,0.071667485],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99940276,0.0000753579,0.00003567669,0.00008108543,0.00026262534,0.00014259179],"domain_scores_gemma":[0.9986759,0.00023600686,0.00008209212,0.0002847807,0.00043482508,0.00028633326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007986074,0.0006833119,0.00053326343,0.0006710252,0.0008970966,0.0021038544,0.0011683188,0.00089069124,0.015314765],"category_scores_gemma":[0.0021528495,0.00022995925,0.0005678036,0.0008521602,0.00040457325,0.001726436,0.002623701,0.0010723047,0.007403953],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003365992,0.0006356924,0.0035084863,0.0012369255,0.00014545412,0.0020523092,0.0009055398,0.010048685,0.080222726,0.049815927,0.2373679,0.6106944],"study_design_scores_gemma":[0.00095009553,0.00065931014,0.01253632,0.00042822649,0.00017082736,0.0025877135,0.00069378485,0.24338967,0.103058055,0.03152554,0.6036858,0.00031472533],"about_ca_topic_score_codex":0.0061500035,"about_ca_topic_score_gemma":0.0045605036,"teacher_disagreement_score":0.015314765,"about_ca_system_score_codex":0.00092127384,"about_ca_system_score_gemma":0.001903376,"threshold_uncertainty_score":0.051232994},"labels":[],"label_agreement":null},{"id":"W2757362440","doi":"10.3390/cryptography1030016","title":"A Text-Independent Speaker Authentication System for Mobile Devices","year":2017,"lang":"en","type":"article","venue":"Cryptography","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Computer science; Authentication (law); Classifier (UML); Biometrics; Naive Bayes classifier; Mobile device; Reliability (semiconductor); Artificial intelligence; Speaker recognition; Speech recognition; Data mining; Machine learning; Computer security; Support vector machine; World Wide Web","score_opus":0.023812572285493803,"score_gpt":0.274783175883733,"score_spread":0.2509706035982392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2757362440","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052833837,0.000824962,0.930131,0.00018135218,0.00050841016,0.0004480991,0.00036985683,0.01124302,0.0034594198],"genre_scores_gemma":[0.5554342,0.0005179737,0.42757118,0.0002792577,0.0002840547,0.00045702772,0.0009942661,0.0002192588,0.014242676],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994272,0.00011634182,0.000050572526,0.00015549648,0.00020511214,0.00004527334],"domain_scores_gemma":[0.9996327,0.00006235004,0.000026992073,0.000072138566,0.00017315014,0.000032627224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060314836,0.00054351526,0.00060719333,0.0004948402,0.00050666975,0.00054319855,0.00080710434,0.00083785487,0.0039801616],"category_scores_gemma":[0.0010094945,0.0002199146,0.00040715022,0.00027655813,0.00021133777,0.0007541199,0.0006791995,0.0006431034,0.0035796033],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00080952793,0.000113489994,0.001079533,0.0003312809,0.00010823118,0.00037508554,0.00023583353,0.0026060664,0.5336639,0.0028547049,0.005479058,0.45234329],"study_design_scores_gemma":[0.0002313991,0.0018428417,0.010895982,0.000112003836,0.00040336288,0.0035140656,0.00013596157,0.3781782,0.52883625,0.002375424,0.0732303,0.00024419365],"about_ca_topic_score_codex":0.0005605339,"about_ca_topic_score_gemma":0.0005010649,"teacher_disagreement_score":0.0039801616,"about_ca_system_score_codex":0.00021916917,"about_ca_system_score_gemma":0.00031149125,"threshold_uncertainty_score":0.013314962},"labels":[],"label_agreement":null},{"id":"W2766171655","doi":"10.1016/j.csl.2017.10.006","title":"Application of the pairwise variability index of speech rhythm with particle swarm optimization to the classification of native and non-native accents","year":2017,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick; Université de Moncton; Université du Québec à Trois-Rivières","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Particle swarm optimization; Support vector machine; Pairwise comparison; Metric (unit); Artificial intelligence; Speech recognition; Pattern recognition (psychology); Rhythm; Generalization; Point (geometry); Machine learning; Mathematics","score_opus":0.015791004986658013,"score_gpt":0.2634387689169221,"score_spread":0.24764776393026408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766171655","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40081227,0.0007923974,0.59566283,0.00025930087,0.00016362825,0.00007783033,0.00014174882,0.0004096035,0.001680389],"genre_scores_gemma":[0.91662306,0.00015372445,0.082379654,0.000023512237,0.000044015796,0.000040970383,0.00022301941,0.000043332155,0.00046862592],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99969757,0.00010522258,0.00002821083,0.00008242664,0.00005756788,0.000029033868],"domain_scores_gemma":[0.9990158,0.00061037595,0.00006825929,0.000060065882,0.00020170434,0.000043693486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017238517,0.00062481617,0.00080958614,0.0011159866,0.00041405458,0.0008804871,0.0004178982,0.0004676128,0.00029575033],"category_scores_gemma":[0.002992883,0.00019355041,0.0007731203,0.00083821977,0.00035136408,0.00039212624,0.00045793928,0.0005719063,0.000084740626],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047380474,0.00023590194,0.015821438,0.00012129141,0.0003804475,0.00012147233,0.00029189026,0.6489842,0.014600356,0.00203548,0.001578162,0.3153557],"study_design_scores_gemma":[0.0000047586636,0.000031546588,0.0024392433,0.0000025017084,0.000013320215,0.0000107973,0.000021831082,0.9964587,0.00064282224,0.00029425792,0.00007498237,0.000005224724],"about_ca_topic_score_codex":0.0050573344,"about_ca_topic_score_gemma":0.0026748371,"teacher_disagreement_score":0.0050573344,"about_ca_system_score_codex":0.0003474864,"about_ca_system_score_gemma":0.00062438485,"threshold_uncertainty_score":0.01005578},"labels":[],"label_agreement":null},{"id":"W2766244607","doi":"10.23919/eusipco.2017.8081177","title":"Spoofing detection employing infinite impulse response — constant Q transform-based feature representations","year":2017,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Spoofing attack; Computer science; Speech recognition; Infinite impulse response; Mel-frequency cepstrum; Bottleneck; Pattern recognition (psychology); Cepstrum; Speaker recognition; Artificial intelligence; Word error rate; Finite impulse response; Feature extraction; Filter (signal processing); Algorithm; Digital filter; Computer vision","score_opus":0.03334548812332466,"score_gpt":0.298301219258045,"score_spread":0.2649557311347203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766244607","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19087929,0.0005490247,0.8032407,0.00023653625,0.000096432996,0.00006192021,0.0005039696,0.0019989072,0.002433234],"genre_scores_gemma":[0.8209599,0.00037732918,0.17515896,0.00010767915,0.000056139637,0.00006275372,0.0014584308,0.000112979666,0.0017058362],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99966407,0.000056362256,0.000023718478,0.00008048359,0.00012499208,0.000050321414],"domain_scores_gemma":[0.9991794,0.0003627666,0.000111353875,0.0001165934,0.00020340165,0.000026354493],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059529557,0.00053732167,0.00037820046,0.0012239389,0.00017758353,0.00057289755,0.00041559458,0.0005242037,0.0010818616],"category_scores_gemma":[0.002728054,0.00012822503,0.0004476193,0.00075280346,0.00029044205,0.001037427,0.00047356443,0.00069782994,0.0007009309],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00067922083,0.00031008772,0.0049813637,0.00011240342,0.00007441374,0.00027478853,0.00013355429,0.07664217,0.14067717,0.005121567,0.00430896,0.76668423],"study_design_scores_gemma":[0.000022870321,0.00019052104,0.0057075457,0.000022203236,0.000030387551,0.00027000188,0.0000429925,0.9433187,0.04586131,0.00224083,0.0022531648,0.000039414375],"about_ca_topic_score_codex":0.0026406858,"about_ca_topic_score_gemma":0.0019545616,"teacher_disagreement_score":0.0026406858,"about_ca_system_score_codex":0.00027175635,"about_ca_system_score_gemma":0.00047600426,"threshold_uncertainty_score":0.005250573},"labels":[],"label_agreement":null},{"id":"W2766944760","doi":"10.48550/arxiv.1711.00333","title":"An Experimental Analysis of the Power Consumption of Convolutional Neural Networks for Keyword Spotting","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Keyword spotting; Computer science; Proxy (statistics); Convolutional neural network; Predictive power; Inference; Spotting; Artificial intelligence; Footprint; Artificial neural network; Data mining; Machine learning; Geography","score_opus":0.10422870171118952,"score_gpt":0.23768537631068737,"score_spread":0.13345667459949784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766944760","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96808916,0.0005728142,0.022933709,0.00034896648,0.000115657196,0.000059728183,0.0007856555,0.0017874558,0.0053068884],"genre_scores_gemma":[0.99274254,0.00014598938,0.004990989,0.00004281679,0.000010199445,0.000034761168,0.00044041773,0.000100664045,0.0014915711],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995328,0.00008322594,0.00004356311,0.00010359611,0.00013688831,0.00009986551],"domain_scores_gemma":[0.997827,0.0012976761,0.00013301914,0.00029361286,0.00037722144,0.000071484275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057019206,0.0007788408,0.00037948042,0.00041094233,0.00030582293,0.000480479,0.0010306352,0.00042982982,0.004068101],"category_scores_gemma":[0.004467888,0.0002121692,0.00022684429,0.0006389015,0.00038379527,0.0013282569,0.0003491311,0.00067678577,0.0006529743],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0052847187,0.0010611129,0.013235791,0.0011408419,0.00032857282,0.00088542653,0.00033837862,0.49153748,0.14283113,0.005043943,0.01200663,0.326306],"study_design_scores_gemma":[0.0000875845,0.0008514265,0.0058628153,0.00003168258,0.00008268699,0.00020847541,0.00013345708,0.8903227,0.097542375,0.0020570743,0.0027921782,0.000027573855],"about_ca_topic_score_codex":0.0047910046,"about_ca_topic_score_gemma":0.006475412,"teacher_disagreement_score":0.0047910046,"about_ca_system_score_codex":0.0008892399,"about_ca_system_score_gemma":0.00048542666,"threshold_uncertainty_score":0.013609171},"labels":[],"label_agreement":null},{"id":"W2770699629","doi":"10.1121/1.5014453","title":"Dialect contact and word-specific phonetics: North Koreans in Seoul","year":2017,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Voice-onset time; Vowel; Word (group theory); Phonetics; Linguistics; History; Audiology; Geography; Psychology; Medicine","score_opus":0.02116397393980148,"score_gpt":0.24484580763330033,"score_spread":0.22368183369349884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2770699629","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9998622,0.000020321526,0.000011677519,0.000003431165,5.591546e-7,7.7631086e-7,0.000011392584,4.5520989e-7,0.00008903072],"genre_scores_gemma":[0.99963295,0.000039601313,0.000042287815,0.000010344738,8.9351346e-7,0.000003408263,0.00005875389,0.000002730055,0.00020899867],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9998361,0.000031991374,0.00002325139,0.00004966668,0.0000324287,0.000026544225],"domain_scores_gemma":[0.999619,0.00010066522,0.0001201136,0.000030457619,0.000053648906,0.00007607245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023988371,0.00022852758,0.00030532505,0.00036629333,0.00034078248,0.00069179793,0.00015485741,0.00029044398,0.0018219877],"category_scores_gemma":[0.0007052809,0.00023330197,0.00015464978,0.00033818264,0.00040413596,0.0004907119,0.0007657869,0.00021213198,0.00037284466],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011521316,0.00012434075,0.8054241,0.00013545057,0.00008078133,0.0022806835,0.07011326,0.000055261193,0.10898152,0.000104789135,0.00011129147,0.011436346],"study_design_scores_gemma":[0.000011644974,0.00019902925,0.96133286,0.000010669643,0.000025413212,0.0012930982,0.03488804,0.00006595647,0.0015349663,0.00004195156,0.00058337086,0.000012832776],"about_ca_topic_score_codex":0.0028767802,"about_ca_topic_score_gemma":0.007947981,"teacher_disagreement_score":0.0028767802,"about_ca_system_score_codex":0.0001737584,"about_ca_system_score_gemma":0.00017429121,"threshold_uncertainty_score":0.006095171},"labels":[],"label_agreement":null},{"id":"W2773275010","doi":"","title":"A Biological Approach to Speech Spectrography","year":2017,"lang":"en","type":"article","venue":"CMBES Proceedings","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Speech recognition","score_opus":0.0544217407407934,"score_gpt":0.2710896909148267,"score_spread":0.2166679501740333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2773275010","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011618202,0.004268293,0.95142645,0.0018165251,0.00069768965,0.00003405293,0.00018220588,0.0003165939,0.02964002],"genre_scores_gemma":[0.5467957,0.008062945,0.390129,0.001297844,0.001800338,0.00017725844,0.0003936245,0.00024789767,0.051095393],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99974626,0.000059619902,0.000012981,0.000087020126,0.0000746421,0.000019515799],"domain_scores_gemma":[0.9995623,0.00015012405,0.000038099904,0.00006103532,0.00012267266,0.00006568931],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048469473,0.0004585834,0.00033980465,0.0013154937,0.00078436837,0.0021182448,0.0010643328,0.0013448476,0.0044280775],"category_scores_gemma":[0.0012850031,0.00028483605,0.00049910287,0.0006336044,0.002063152,0.0010704274,0.0010635467,0.0012181202,0.0016092192],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000065362125,0.00009911738,0.0016983366,0.00039891826,0.000097472635,0.0005726381,0.0008170153,0.033548325,0.19436266,0.6198079,0.0029913706,0.14554095],"study_design_scores_gemma":[0.000028228545,0.0003677975,0.010458827,0.00025475956,0.00010991652,0.0018830989,0.00088822696,0.23192562,0.0440985,0.58257663,0.12723926,0.00016908997],"about_ca_topic_score_codex":0.0019792374,"about_ca_topic_score_gemma":0.0016470687,"teacher_disagreement_score":0.0044280775,"about_ca_system_score_codex":0.0008998874,"about_ca_system_score_gemma":0.0007569091,"threshold_uncertainty_score":0.014813423},"labels":[],"label_agreement":null},{"id":"W2791919658","doi":"","title":"Study by simulation of the acoustic characteristics of the vocal tract with losses","year":2005,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formant; Vocal tract; Acoustics; Transfer function; Lossy compression; Computer science; Physics; Engineering; Speech recognition","score_opus":0.015306049973742212,"score_gpt":0.2262474016236843,"score_spread":0.2109413516499421,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2791919658","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6226039,0.00033616228,0.36239177,0.00017704187,0.00006721559,0.00009767061,0.0002396237,0.0010713262,0.013015353],"genre_scores_gemma":[0.9764727,0.00019447404,0.018622953,0.00001955444,0.000013827602,0.00006792916,0.00013243056,0.00009508744,0.004381063],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998568,0.000037423604,0.000006024084,0.000015668546,0.00006386486,0.000020111615],"domain_scores_gemma":[0.9992494,0.00050981005,0.00006716401,0.00005296173,0.00008945124,0.000031164836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028918733,0.0004889258,0.00042092858,0.00030991714,0.00029044953,0.000519897,0.00052126375,0.0010021495,0.0016960704],"category_scores_gemma":[0.0015880065,0.00026434066,0.00049192226,0.00022440203,0.0004989366,0.00037386673,0.00034464957,0.00035608961,0.00030870634],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010911045,0.00004563725,0.0022010815,0.00007272046,0.000026089912,0.0002983214,0.00017313896,0.96690214,0.021372266,0.0023686716,0.0002258235,0.0062049464],"study_design_scores_gemma":[0.000008326967,0.00005978904,0.0005917013,0.0000066884695,0.000009948992,0.0000833506,0.000030648673,0.9948695,0.0033738085,0.0004093589,0.00055027555,0.000006565924],"about_ca_topic_score_codex":0.0030185648,"about_ca_topic_score_gemma":0.0013285549,"teacher_disagreement_score":0.0030185648,"about_ca_system_score_codex":0.00030059228,"about_ca_system_score_gemma":0.00039695058,"threshold_uncertainty_score":0.0060019493},"labels":[],"label_agreement":null},{"id":"W2793646841","doi":"10.1109/icassp.2018.8462037","title":"Extracting Domain Invariant Features by Unsupervised Learning for Robust Automatic Speech Recognition","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Autoencoder; Computer science; Robustness (evolution); Invariant (physics); Speech recognition; Word error rate; Artificial intelligence; Pattern recognition (psychology); Latent variable; Domain (mathematical analysis); Encoder; Natural language processing; Deep learning; Mathematics","score_opus":0.050654055380827755,"score_gpt":0.26840475806392855,"score_spread":0.2177507026831008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2793646841","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018598242,0.00017311033,0.98002774,0.000050381146,0.000016406573,0.000016620927,0.00006665353,0.0007289975,0.00032184194],"genre_scores_gemma":[0.48739457,0.00035661674,0.50851077,0.00011876578,0.00007210637,0.000114920345,0.0010792221,0.00034789392,0.002005148],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99933666,0.0002185405,0.000030324261,0.00019540063,0.00016422026,0.000054845143],"domain_scores_gemma":[0.9989513,0.00050246343,0.00009729892,0.0002723182,0.00014895831,0.000027575887],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010007165,0.0006310639,0.0006145305,0.00056729,0.00023942259,0.00045968613,0.0006326323,0.00051228696,0.0007609015],"category_scores_gemma":[0.0026675658,0.0003727574,0.0006395607,0.00058995787,0.00074001995,0.0009984799,0.000791696,0.0010818971,0.000637597],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021299219,0.00016069363,0.0017789038,0.0001334468,0.00013624477,0.0001064024,0.00012987702,0.32824767,0.10270541,0.011231648,0.0028986007,0.5522581],"study_design_scores_gemma":[0.000006046955,0.000039846473,0.00055634027,0.0000039927586,0.000009964221,0.000032073647,0.000015906784,0.97943044,0.013302986,0.005573971,0.001016778,0.000011595553],"about_ca_topic_score_codex":0.0019434525,"about_ca_topic_score_gemma":0.0030214463,"teacher_disagreement_score":0.0019434525,"about_ca_system_score_codex":0.00034740526,"about_ca_system_score_gemma":0.0006491359,"threshold_uncertainty_score":0.005292356},"labels":[],"label_agreement":null},{"id":"W2795552730","doi":"10.1177/0023830918765012","title":"Investigating Perceptual Biases, Data Reliability, and Data Discovery in a Methodology for Collecting Speech Errors From Audio Recordings","year":2018,"lang":"en","type":"article","venue":"Language and Speech","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Computer science; Speech recognition; Reliability (semiconductor); Perception; Sound quality; Sound recording and reproduction; Natural language processing; Psychology; Acoustics","score_opus":0.231578198380963,"score_gpt":0.3871973809097454,"score_spread":0.15561918252878243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2795552730","genre_codex":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10095471,0.00052864436,0.88865876,0.0017300616,0.00020357667,0.004841433,0.00037436,0.00033136786,0.0023770728],"genre_scores_gemma":[0.30217403,0.00022657361,0.68545663,0.000949218,0.00021669305,0.00996147,0.0003659338,0.00024198675,0.00040748648],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.34588954,0.509827,0.050006147,0.033803895,0.058128167,0.0023451734],"domain_scores_gemma":[0.11079703,0.6690948,0.061363038,0.11218372,0.04501507,0.0015463647],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.466764,0.001677935,0.0018464132,0.005316838,0.005698851,0.009688697,0.0052738693,0.003968263,0.0010769059],"category_scores_gemma":[0.75820124,0.0032293824,0.0019242668,0.0060235327,0.014494306,0.008271872,0.009393575,0.004119995,0.00062150595],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0044358755,0.0016280434,0.3651745,0.0072968854,0.0034398807,0.0025512741,0.17706713,0.021357596,0.045268383,0.07642582,0.0044563194,0.29089835],"study_design_scores_gemma":[0.0025269347,0.009013207,0.30123103,0.006166672,0.0026530356,0.008907728,0.043929033,0.13738753,0.11623744,0.28408256,0.08564736,0.0022174935],"about_ca_topic_score_codex":0.004292661,"about_ca_topic_score_gemma":0.0053294217,"teacher_disagreement_score":0.533236,"about_ca_system_score_codex":0.004291526,"about_ca_system_score_gemma":0.009669742,"threshold_uncertainty_score":0.6575749},"labels":[],"label_agreement":null},{"id":"W2799789537","doi":"10.1109/icassp.2018.8462185","title":"Speech Prediction Using an Adaptive Recurrent Neural Network with Application to Packet Loss Concealment","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Packet loss; Speech recognition; Artificial neural network; Recurrent neural network; Network packet; Time delay neural network; Artificial intelligence; Computer network","score_opus":0.058256994380363865,"score_gpt":0.29273672239706344,"score_spread":0.23447972801669958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2799789537","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024710124,0.0004460455,0.97282106,0.00013437186,0.000070229005,0.000021533086,0.000032414173,0.0006727062,0.0010914409],"genre_scores_gemma":[0.7577521,0.00062892406,0.23662485,0.000081355254,0.000085218446,0.000053044096,0.00012226355,0.000096517826,0.0045557087],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997737,0.00006045432,0.000013980522,0.000056132507,0.000071132534,0.00002469219],"domain_scores_gemma":[0.9995415,0.00022457124,0.00004769161,0.000046844165,0.00012357728,0.000015811058],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070759444,0.00053572026,0.0003909119,0.00021560832,0.00019305242,0.00035764187,0.0007664546,0.00057370495,0.001250438],"category_scores_gemma":[0.0016243167,0.00027842727,0.0003274385,0.00026538942,0.0003257484,0.00055532804,0.0005196413,0.000814161,0.00032354012],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027021574,0.00006239485,0.0010219633,0.000108861226,0.000056987737,0.00029539244,0.00008727129,0.712656,0.039591137,0.008661503,0.0014784179,0.2357098],"study_design_scores_gemma":[0.000001838389,0.000014694207,0.000046854806,0.0000018609713,0.0000037530037,0.000013307394,0.0000013125787,0.99709773,0.0024400835,0.00023276568,0.00014370902,0.0000020666685],"about_ca_topic_score_codex":0.003788915,"about_ca_topic_score_gemma":0.0033301723,"teacher_disagreement_score":0.003788915,"about_ca_system_score_codex":0.00031688128,"about_ca_system_score_gemma":0.0004608804,"threshold_uncertainty_score":0.007533729},"labels":[],"label_agreement":null},{"id":"W2801548882","doi":"10.1139/tcsme-2013-0049","title":"IMPROVING EIGENSPACE-BASED FUZZY LOGIC SYSTEM USING A LINEAR INTERPOLATION SCHEME FOR SPEECH PATTERN RECOGNITION","year":2013,"lang":"en","type":"article","venue":"Transactions of the Canadian Society for Mechanical Engineering","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Science Council","keywords":"Eigenvalues and eigenvectors; Scheme (mathematics); Interpolation (computer graphics); Fuzzy logic; Linear interpolation; Computer science; Pattern recognition (psychology); Artificial intelligence; Algorithm; Speech recognition; Mathematics; Image (mathematics)","score_opus":0.03236661978797357,"score_gpt":0.2210443307129645,"score_spread":0.18867771092499094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801548882","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016885897,0.00010765446,0.9813819,0.000053907243,0.000023263221,0.000026639334,0.000016280044,0.00057446625,0.00093005557],"genre_scores_gemma":[0.42309391,0.00014645063,0.5731416,0.00009602946,0.000028100074,0.0000822299,0.00010623412,0.00004394797,0.003261558],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99960965,0.00008700326,0.000037001882,0.00007634609,0.00016442107,0.00002555002],"domain_scores_gemma":[0.9996045,0.0001216114,0.000033119966,0.00004673774,0.00018021798,0.000013874485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080771407,0.00037579398,0.00041048427,0.00056266645,0.00041629662,0.00052844663,0.0008812094,0.00045491025,0.0024750424],"category_scores_gemma":[0.0011403136,0.00021146837,0.0004802842,0.00039008737,0.00029738602,0.0009210817,0.00039164827,0.00056646386,0.0006157491],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003889633,0.00014255616,0.001165836,0.0001621915,0.00006421804,0.00011260421,0.000303659,0.17343739,0.09241815,0.012456658,0.0016047116,0.7177431],"study_design_scores_gemma":[0.000009753659,0.000068060326,0.00024063064,0.0000056156728,0.000009107386,0.000042096908,0.000013625636,0.9893422,0.008096218,0.001144128,0.0010153025,0.000013296018],"about_ca_topic_score_codex":0.0031557188,"about_ca_topic_score_gemma":0.0045770113,"teacher_disagreement_score":0.0031557188,"about_ca_system_score_codex":0.0004193408,"about_ca_system_score_gemma":0.0006006798,"threshold_uncertainty_score":0.00827986},"labels":[],"label_agreement":null},{"id":"W2801849754","doi":"10.5539/ijel.v8n5p27","title":"Acoustic Characteristics of Pakistani English Vowel Sounds","year":2018,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Vowel; Formant; Duration (music); Speech recognition; Statistical analysis; Mid vowel; Acoustics; Space (punctuation); Mathematics; Computer science; Statistics; Physics","score_opus":0.01588246871818565,"score_gpt":0.2761914715595188,"score_spread":0.2603090028413331,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801849754","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9981034,0.0000738565,0.00065807503,0.000013228905,0.000003658804,0.0000093134595,0.00008947067,0.000008638575,0.0010402775],"genre_scores_gemma":[0.9984763,0.00008715486,0.000567638,0.000013390342,0.0000056103545,0.0000122325755,0.00009167497,0.0000049837654,0.00074111694],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9998074,0.000023396104,0.000016394491,0.000046996523,0.0000781064,0.000027659677],"domain_scores_gemma":[0.9994436,0.00024986835,0.0000821713,0.000027197253,0.00015697621,0.000040148843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018261508,0.00018145771,0.0001799475,0.00035920375,0.00031469978,0.0004619184,0.000107795575,0.00022766918,0.0020687436],"category_scores_gemma":[0.0009293712,0.0001199061,0.00008624818,0.00022905224,0.00037535198,0.00022108287,0.0002581137,0.00016083862,0.0004831156],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011816918,0.00014293098,0.16124675,0.00041352518,0.000047491674,0.0020942013,0.007543285,0.0004912145,0.71246016,0.0002555708,0.0003762302,0.11374698],"study_design_scores_gemma":[0.000016648823,0.0010588259,0.924772,0.000026821102,0.000041584422,0.0041214856,0.0052836505,0.0008970212,0.060106825,0.00015251011,0.00347797,0.000044573175],"about_ca_topic_score_codex":0.0007072881,"about_ca_topic_score_gemma":0.00082251406,"teacher_disagreement_score":0.0020687436,"about_ca_system_score_codex":0.0000754997,"about_ca_system_score_gemma":0.00010736779,"threshold_uncertainty_score":0.0069206953},"labels":[],"label_agreement":null},{"id":"W2806367735","doi":"10.1609/aaai.v32i1.12140","title":"Towards Neural Speaker Modeling in Multi-Party Conversation: The Task, Dataset, and Models","year":2018,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Conversation; Computer science; Task (project management); Component (thermodynamics); Speaker diarisation; Speech recognition; Speaker recognition; Artificial intelligence; Natural language processing; Linguistics","score_opus":0.24178893384203265,"score_gpt":0.3237499481515659,"score_spread":0.08196101430953323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806367735","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2684461,0.0044652703,0.6879225,0.0049588145,0.0009084013,0.00076406443,0.019766083,0.00716484,0.0056040375],"genre_scores_gemma":[0.58073384,0.0012216265,0.34437045,0.0007829852,0.0006690043,0.0016147585,0.06479315,0.00039666536,0.0054174233],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974597,0.0013782155,0.000105470535,0.00064468913,0.0002793179,0.00013267453],"domain_scores_gemma":[0.99645364,0.0014491098,0.0001761829,0.001086509,0.0006036535,0.00023090064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044659222,0.0015613493,0.0010714434,0.0011898432,0.0012977145,0.0015191567,0.0021125549,0.002252067,0.002296386],"category_scores_gemma":[0.01081551,0.00044964536,0.0014901778,0.0009220778,0.00059981423,0.0023873046,0.0027590771,0.0044441917,0.0034101363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021772585,0.0024873693,0.04027375,0.000788221,0.0008564574,0.00042979585,0.0011479184,0.105009,0.03499335,0.010015327,0.06837146,0.7334502],"study_design_scores_gemma":[0.00011964601,0.00025577846,0.012624899,0.00012620805,0.00026092672,0.00036429174,0.00060702156,0.9351328,0.012411371,0.019327791,0.018649265,0.00012007546],"about_ca_topic_score_codex":0.008725256,"about_ca_topic_score_gemma":0.011857729,"teacher_disagreement_score":0.008725256,"about_ca_system_score_codex":0.0009820674,"about_ca_system_score_gemma":0.0016955466,"threshold_uncertainty_score":0.02361834},"labels":[],"label_agreement":null},{"id":"W2887814324","doi":"10.1109/slt.2018.8639585","title":"Speaker Recognition from Raw Waveform with SincNet","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":94,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Compute Canada","keywords":"Computer science; Sinc function; Waveform; Convolutional neural network; Speech recognition; Speaker recognition; Filter (signal processing); Formant; Artificial intelligence; Pattern recognition (psychology); Convolution (computer science); Artificial neural network; Telecommunications; Computer vision","score_opus":0.0396549809171314,"score_gpt":0.23259951903919576,"score_spread":0.19294453812206436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2887814324","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03398073,0.0005700795,0.9356503,0.00023769753,0.0003539647,0.00015397719,0.001656769,0.021853952,0.0055425973],"genre_scores_gemma":[0.31349257,0.00062842434,0.66227937,0.0002566792,0.00010962418,0.00032741972,0.0087810485,0.001088746,0.013036165],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996449,0.000046467223,0.000021363461,0.00010446994,0.00014590855,0.000036944937],"domain_scores_gemma":[0.9995515,0.0001231666,0.000043014974,0.00010497238,0.0001612335,0.000016169659],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068335223,0.0010778655,0.00047633945,0.0012394188,0.00022428867,0.00073329604,0.0011418093,0.0007754416,0.0080450475],"category_scores_gemma":[0.0022499047,0.00046246225,0.000529263,0.0012463862,0.00027763576,0.0011682921,0.0009328515,0.0012039812,0.0034532296],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004265002,0.00011377402,0.0010307609,0.00027672967,0.0001566456,0.00023255516,0.00007316361,0.12935048,0.039434474,0.005307464,0.015398676,0.8081988],"study_design_scores_gemma":[0.000017402377,0.00003842029,0.00050925417,0.000017289165,0.000013506613,0.000084784166,0.000017256383,0.9707658,0.020428365,0.00316441,0.004927837,0.000015654801],"about_ca_topic_score_codex":0.0045790994,"about_ca_topic_score_gemma":0.007203715,"teacher_disagreement_score":0.0080450475,"about_ca_system_score_codex":0.00053391926,"about_ca_system_score_gemma":0.0007363892,"threshold_uncertainty_score":0.026913345},"labels":[],"label_agreement":null},{"id":"W2896779944","doi":"10.1121/1.5067620","title":"Do low intelligibility voices induce false memories?","year":2018,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Variation (astronomy); False memory; Intelligibility (philosophy); Priming (agriculture); Psychology; Computer science; Linguistics; Cognitive psychology; Recall","score_opus":0.024414868188692044,"score_gpt":0.2836451154918068,"score_spread":0.2592302473031148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2896779944","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9979316,0.00019796558,0.0011395637,0.00007003175,0.000023361965,0.000024169802,0.000027936943,0.000026514315,0.00055889186],"genre_scores_gemma":[0.999198,0.00006488407,0.00039152408,0.000059025857,0.000014842207,0.000015759373,0.00003218903,0.000008941794,0.0002147769],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99830544,0.00069141155,0.00022896109,0.0002345862,0.0004022257,0.00013730874],"domain_scores_gemma":[0.9888565,0.006706742,0.0019559993,0.0017523987,0.00035567622,0.00037273305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029627907,0.0003832222,0.00039854788,0.0003710954,0.0001793909,0.0007475167,0.0003122438,0.0006348075,0.0023349714],"category_scores_gemma":[0.014891631,0.0003381417,0.00030526277,0.00009261496,0.00090368395,0.00064069696,0.0006200127,0.0006015294,0.00031560354],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01746275,0.0024657194,0.22767851,0.0005246849,0.0003918119,0.0062623606,0.0061402433,0.00059376704,0.64235467,0.0018061615,0.00047451534,0.093844704],"study_design_scores_gemma":[0.00050676824,0.019290514,0.5500328,0.0001535952,0.0004803667,0.024184672,0.0040622656,0.0025717942,0.3911564,0.0050453623,0.0024177504,0.000097683565],"about_ca_topic_score_codex":0.00015972707,"about_ca_topic_score_gemma":0.0001647871,"teacher_disagreement_score":0.0029627907,"about_ca_system_score_codex":0.00012037774,"about_ca_system_score_gemma":0.000126463,"threshold_uncertainty_score":0.015668988},"labels":[],"label_agreement":null},{"id":"W2897820244","doi":"10.1121/1.5067810","title":"Computational medicine in voice research","year":2018,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Phonation; Visualization; Computational model; Process (computing); Workflow; Scale (ratio); Oscillation (cell signaling); Human–computer interaction; Simulation; Artificial intelligence; Medicine; Biology","score_opus":0.0566726847425565,"score_gpt":0.3497351986685679,"score_spread":0.2930625139260114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2897820244","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008646055,0.3013236,0.5148908,0.073698506,0.008871279,0.00021711327,0.0010150844,0.0018077113,0.08952989],"genre_scores_gemma":[0.23873954,0.28203833,0.4177388,0.010813826,0.010614756,0.0010567419,0.0018445081,0.0009976057,0.036155842],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984692,0.0007107303,0.00010061676,0.00026376316,0.0003664186,0.00008938097],"domain_scores_gemma":[0.9951213,0.00344939,0.00019459274,0.00046422303,0.00055865565,0.00021191585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028095534,0.0009346072,0.0014207028,0.0018332745,0.0006705837,0.0043264073,0.0018742424,0.0028027336,0.008927131],"category_scores_gemma":[0.008772012,0.0004706305,0.0010821125,0.0016753154,0.0032778336,0.0037489897,0.0026804286,0.0033428958,0.0022539857],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000686002,0.00006536177,0.0018949091,0.001874971,0.00022114531,0.00021796628,0.00037315447,0.04732631,0.0014024442,0.6030938,0.070714034,0.27274725],"study_design_scores_gemma":[0.000038353388,0.00006382805,0.0007163993,0.0007613728,0.00004242597,0.0002495742,0.00026452242,0.07087617,0.00080212724,0.648256,0.2778727,0.000056494555],"about_ca_topic_score_codex":0.0020858136,"about_ca_topic_score_gemma":0.0015525867,"teacher_disagreement_score":0.008927131,"about_ca_system_score_codex":0.0014268782,"about_ca_system_score_gemma":0.0020872809,"threshold_uncertainty_score":0.029864252},"labels":[],"label_agreement":null},{"id":"W2899147640","doi":"","title":"An Empirical Study of Methods for SPN Learning and Inference","year":2018,"lang":"en","type":"article","venue":"Probabilistic Graphical Models","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of Regina","funders":"","keywords":"Computer science; Inference; Artificial intelligence; Machine learning","score_opus":0.11016250390616814,"score_gpt":0.42599450067440925,"score_spread":0.31583199676824114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2899147640","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04670438,0.0059880028,0.93948513,0.0024748414,0.00016832676,0.00015423511,0.00043495066,0.0005317101,0.0040584183],"genre_scores_gemma":[0.56480265,0.005401975,0.41700095,0.001093047,0.0009021986,0.0006470347,0.0027091461,0.0011295319,0.006313423],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9650451,0.02793948,0.0010024391,0.0027472558,0.0027574848,0.00050825905],"domain_scores_gemma":[0.3567132,0.6140142,0.004688465,0.017363532,0.0058790185,0.0013415489],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07888181,0.0023800398,0.0023980092,0.0040098666,0.0017963408,0.0036030945,0.0062622866,0.004395455,0.008453873],"category_scores_gemma":[0.36294448,0.001570235,0.002789994,0.0037966573,0.0058111707,0.014004878,0.005187638,0.0077915215,0.00081063906],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011514104,0.00049128104,0.030683067,0.0013722683,0.0013511955,0.000291244,0.001076333,0.31509417,0.00097537093,0.38130078,0.010378562,0.2558343],"study_design_scores_gemma":[0.00010118465,0.00016104824,0.00296986,0.0002873354,0.00014736116,0.00035614774,0.00020264013,0.7640078,0.00060324254,0.22801831,0.0030921486,0.00005289724],"about_ca_topic_score_codex":0.008232944,"about_ca_topic_score_gemma":0.0082978625,"teacher_disagreement_score":0.07888181,"about_ca_system_score_codex":0.003292119,"about_ca_system_score_gemma":0.0025963848,"threshold_uncertainty_score":0.41717184},"labels":[],"label_agreement":null},{"id":"W2899186436","doi":"","title":"AutoDL Challenge Design and Beta Tests-Towards automatic deep learning","year":2018,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Acadia University","funders":"Centre National de la Recherche Scientifique; Chinese Academy of Sciences","keywords":"Computer science; Deep learning; Baseline (sea); Schedule; Set (abstract data type); Artificial intelligence; Machine learning; Raw data; Data science; Labeled data; Data set","score_opus":0.02991579317343053,"score_gpt":0.24479446475496577,"score_spread":0.21487867158153523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2899186436","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5185527,0.0021307515,0.33755568,0.0034296047,0.004053183,0.0018482001,0.013689721,0.054290574,0.06444963],"genre_scores_gemma":[0.7477803,0.00036673778,0.17263852,0.0016245706,0.0003771371,0.0014497031,0.031282686,0.0058063213,0.038673997],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957326,0.0015311955,0.00028207264,0.00090650277,0.0010054009,0.00054225826],"domain_scores_gemma":[0.98928064,0.0031125974,0.00020096258,0.0024043734,0.003883072,0.0011183497],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056090816,0.0016916026,0.00065799034,0.00095347356,0.0007017496,0.0021177076,0.003229926,0.0022742255,0.0129748145],"category_scores_gemma":[0.013691519,0.00077000883,0.0006007247,0.0005042689,0.0011787192,0.002702429,0.003079703,0.0030141384,0.008264904],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0084118135,0.004176431,0.010363164,0.0013092024,0.00047389182,0.0011415875,0.0012216144,0.06980252,0.0867054,0.013728163,0.2075911,0.5950751],"study_design_scores_gemma":[0.0029854202,0.007081456,0.011355377,0.0003164454,0.00018380786,0.0010221209,0.0012978022,0.5482231,0.24160238,0.019219117,0.16649118,0.00022186713],"about_ca_topic_score_codex":0.0038795038,"about_ca_topic_score_gemma":0.004378038,"teacher_disagreement_score":0.0129748145,"about_ca_system_score_codex":0.0008497314,"about_ca_system_score_gemma":0.0015314698,"threshold_uncertainty_score":0.043405116},"labels":[],"label_agreement":null},{"id":"W2900022717","doi":"10.1109/icassp.2019.8682064","title":"Generative Adversarial Speaker Embedding Networks for Domain Robust End-to-end Speaker Verification","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal; McGill University","funders":"","keywords":"Discriminator; Speaker verification; Computer science; NIST; Classifier (UML); Speech recognition; End-to-end principle; Adversarial system; Baseline (sea); Artificial intelligence; Generative grammar; Trigonometric functions; Embedding; Dimensionality reduction; Pattern recognition (psychology); Speaker recognition; Mathematics; Detector","score_opus":0.04339371839715384,"score_gpt":0.27868557334946464,"score_spread":0.2352918549523108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900022717","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009747798,0.00023719078,0.9865262,0.000106083535,0.000051974668,0.00003532924,0.00007439137,0.001932354,0.0012886926],"genre_scores_gemma":[0.6496552,0.00031468776,0.33954528,0.0004179501,0.00010238615,0.00016437472,0.0009065601,0.00041445362,0.008479037],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989034,0.00047822317,0.000035514284,0.00022555586,0.00025494292,0.00010236609],"domain_scores_gemma":[0.99905974,0.0004708021,0.0000771635,0.00021138818,0.0001347295,0.000046228637],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018769008,0.0011912691,0.0007244159,0.00034400978,0.00028924525,0.00055277575,0.0012318582,0.000991615,0.0033090115],"category_scores_gemma":[0.0029997076,0.0004428107,0.00069802447,0.00025214587,0.0007533406,0.0011444308,0.0019970576,0.0024490885,0.0022058329],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004248811,0.00013859214,0.0009131906,0.00008093427,0.00014287334,0.00021698703,0.00010455648,0.72151864,0.026740769,0.01422083,0.006047985,0.22944978],"study_design_scores_gemma":[0.0000057377642,0.000029958981,0.00008781676,0.000005088121,0.0000058151068,0.00004496943,0.000005590126,0.9895706,0.005347861,0.00424529,0.000644204,0.0000069923044],"about_ca_topic_score_codex":0.0014581631,"about_ca_topic_score_gemma":0.002108343,"teacher_disagreement_score":0.0033090115,"about_ca_system_score_codex":0.000544142,"about_ca_system_score_gemma":0.0006080533,"threshold_uncertainty_score":0.011069775},"labels":[],"label_agreement":null},{"id":"W2900161882","doi":"10.1109/icassp.2019.8682611","title":"Adapting End-to-end Neural Speaker Verification to New Languages and Recording Conditions with Adversarial Training","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal; McGill University","funders":"","keywords":"Adversarial system; Computer science; NIST; Speaker verification; Speech recognition; Task (project management); Artificial neural network; Speaker recognition; Embedding; End-to-end principle; Margin (machine learning); Artificial intelligence; Training (meteorology); Speaker diarisation; Residual; Combing; Machine learning; Algorithm; Engineering","score_opus":0.05388103435155326,"score_gpt":0.29656352395245406,"score_spread":0.2426824896009008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900161882","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039844237,0.0002256926,0.9555407,0.00019018748,0.000105511186,0.000059060785,0.00009509134,0.0020767176,0.0018627313],"genre_scores_gemma":[0.8236669,0.00016093855,0.16851296,0.00033645958,0.00006431923,0.00010164615,0.00042954128,0.00024217083,0.006485205],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988902,0.00038621805,0.000042340864,0.00033118544,0.00023320368,0.00011682797],"domain_scores_gemma":[0.9985241,0.00070920395,0.00010947716,0.0003918625,0.00021195617,0.000053328604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020293505,0.0010937123,0.00069884316,0.000270897,0.00029364007,0.0006242608,0.0015907895,0.0011614033,0.0021638512],"category_scores_gemma":[0.005198215,0.0004391864,0.00065236253,0.00018911148,0.0009453673,0.001596825,0.0022891543,0.0023897896,0.0016953044],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041125485,0.0001742891,0.0014669332,0.00007878146,0.00012406883,0.00018186723,0.000116078656,0.7674162,0.035642765,0.004925389,0.0024891482,0.18697321],"study_design_scores_gemma":[0.000003888397,0.00003686683,0.0001545319,0.000004574674,0.000006322992,0.00004587775,0.000006910194,0.9900593,0.0073364577,0.0019982348,0.00033878852,0.000008233659],"about_ca_topic_score_codex":0.0018575037,"about_ca_topic_score_gemma":0.0023042457,"teacher_disagreement_score":0.0021638512,"about_ca_system_score_codex":0.0005394362,"about_ca_system_score_gemma":0.0005722408,"threshold_uncertainty_score":0.010732353},"labels":[],"label_agreement":null},{"id":"W2900688537","doi":"10.1109/taslp.2018.2882731","title":"Privacy-Preserving iVector-Based Speaker Verification","year":2018,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Password; Alphanumeric; Speaker recognition; Biometrics; Domain (mathematical analysis); Authentication (law); Speech recognition; Voice over IP; Computer security; World Wide Web; The Internet","score_opus":0.02376216840936063,"score_gpt":0.27477188364507155,"score_spread":0.2510097152357109,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900688537","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008834712,0.00016111108,0.9876686,0.000097203236,0.00005257687,0.00006589387,0.00015289389,0.0020744198,0.0008926389],"genre_scores_gemma":[0.3232933,0.0002287956,0.6687135,0.00018733882,0.00009710015,0.00015737464,0.00095302967,0.00019192434,0.006177671],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9971846,0.0006429259,0.00020310031,0.00067942846,0.0009696548,0.00032025686],"domain_scores_gemma":[0.9982546,0.0004938464,0.00019177792,0.0006614657,0.00033701785,0.000061187966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014528387,0.0007290783,0.0014084599,0.001186663,0.0007168859,0.0011962799,0.0014324213,0.001065935,0.0040625255],"category_scores_gemma":[0.004644266,0.0003180602,0.0016082926,0.0009344269,0.0007877271,0.0019576466,0.0020968025,0.001377503,0.0031597891],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013328368,0.00020541016,0.0018601177,0.00014890275,0.00014062888,0.00033746733,0.00013404115,0.08055801,0.10217811,0.032796394,0.00629741,0.77401066],"study_design_scores_gemma":[0.000074129006,0.0002015364,0.00073830684,0.000017253216,0.000039688883,0.00065888057,0.00004703854,0.8840259,0.09397472,0.014427532,0.005737489,0.00005756954],"about_ca_topic_score_codex":0.0014154136,"about_ca_topic_score_gemma":0.001312147,"teacher_disagreement_score":0.0040625255,"about_ca_system_score_codex":0.00067838765,"about_ca_system_score_gemma":0.0015758331,"threshold_uncertainty_score":0.013590515},"labels":[],"label_agreement":null},{"id":"W2900939497","doi":"10.1109/icassp.2019.8683713","title":"The Pytorch-kaldi Speech Recognition Toolkit","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Python (programming language); Plug-in; Software; Artificial intelligence; Deep learning; Artificial neural network; Exploit; Documentation; Flexibility (engineering); Programming language","score_opus":0.04602015729144891,"score_gpt":0.2592342611845588,"score_spread":0.21321410389310985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900939497","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002289034,0.00038921705,0.3973464,0.00030961345,0.0006218769,0.00026250788,0.026247948,0.56435454,0.008178773],"genre_scores_gemma":[0.052516263,0.0009659536,0.59652996,0.0012092697,0.00034113263,0.0025050666,0.13531835,0.17815195,0.032462057],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998485,0.00024140681,0.0001964897,0.00039867335,0.00053057534,0.00014772138],"domain_scores_gemma":[0.99824107,0.0006002786,0.00010293735,0.00053420395,0.00039533354,0.0001261565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013661041,0.0022080662,0.0012749473,0.0015345892,0.00057930243,0.0019927192,0.00454199,0.0013601733,0.07865199],"category_scores_gemma":[0.007071512,0.0012939274,0.0018472061,0.001060301,0.0006574713,0.002660986,0.0034966099,0.0038971934,0.07583331],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000988115,0.00011421747,0.0009862575,0.0022260465,0.00030205364,0.0006147927,0.0004990301,0.012073794,0.025151681,0.014460611,0.6992417,0.24334173],"study_design_scores_gemma":[0.00051895465,0.00014741611,0.0024243598,0.00031888418,0.00013998986,0.0012972561,0.00015843351,0.21317534,0.07215551,0.043532465,0.6657124,0.00041910438],"about_ca_topic_score_codex":0.003002668,"about_ca_topic_score_gemma":0.0028043655,"teacher_disagreement_score":0.07865199,"about_ca_system_score_codex":0.00072033674,"about_ca_system_score_gemma":0.0019618585,"threshold_uncertainty_score":0.26311713},"labels":[],"label_agreement":null},{"id":"W2901025079","doi":"10.1109/icassp.2019.8682880","title":"Representation Mixing for TTS Synthesis","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Pronunciation; Character (mathematics); Mixing (physics); Representation (politics); Speech synthesis; Software deployment; Speech recognition; Parametric statistics; Inference; Artificial intelligence; Natural language processing; Encoder; Control (management); Linguistics; Mathematics","score_opus":0.07700848133495143,"score_gpt":0.31340455708140497,"score_spread":0.23639607574645355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901025079","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004203159,0.00020101405,0.99176836,0.0000958088,0.00006037447,0.000021124402,0.00009657138,0.0016506447,0.0019028725],"genre_scores_gemma":[0.41393286,0.00050313544,0.5720714,0.00024374701,0.00018957545,0.00017732906,0.0011221969,0.00092821853,0.010831605],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99943095,0.0001479094,0.00004834812,0.00015673637,0.00016840667,0.00004754116],"domain_scores_gemma":[0.9995061,0.00021357246,0.000034483743,0.00012956222,0.00008279236,0.000033556993],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006311926,0.00071711687,0.0004224702,0.0005267527,0.000356808,0.0011127319,0.00060020824,0.00090692553,0.008142397],"category_scores_gemma":[0.0024027766,0.00033819457,0.0006761769,0.00056054915,0.00051873224,0.0013376907,0.0013719387,0.0014674894,0.0033244637],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004634512,0.00009610729,0.00044515572,0.00024727784,0.00008381156,0.00020888099,0.00017447899,0.1371446,0.15997612,0.069792,0.0050273295,0.62634075],"study_design_scores_gemma":[0.000025990663,0.00009874802,0.00017655556,0.000034134573,0.000029213783,0.0001797993,0.00002678109,0.8569558,0.07521423,0.04992346,0.017304836,0.000030313744],"about_ca_topic_score_codex":0.0009895033,"about_ca_topic_score_gemma":0.001208403,"teacher_disagreement_score":0.008142397,"about_ca_system_score_codex":0.0005352647,"about_ca_system_score_gemma":0.0005076893,"threshold_uncertainty_score":0.027238965},"labels":[],"label_agreement":null},{"id":"W2901997113","doi":"","title":"Char2Wav: End-to-End Speech Synthesis","year":2017,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":335,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Université de Montréal","funders":"","keywords":"End-to-end principle; Computer science; Speech synthesis; Speech recognition; Artificial intelligence","score_opus":0.09295328918588806,"score_gpt":0.3624233461629727,"score_spread":0.26947005697708465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901997113","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0062849456,0.0002746154,0.7827226,0.00009152506,0.00052884733,0.0002219966,0.0032209035,0.19864504,0.008009537],"genre_scores_gemma":[0.17060706,0.00030335886,0.7261784,0.00056750915,0.0002184688,0.0010551543,0.023474334,0.026199438,0.05139634],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99912673,0.00010224807,0.00004285313,0.0002398504,0.00035748514,0.00013091105],"domain_scores_gemma":[0.999571,0.00011981541,0.000015340924,0.0001375682,0.000119197466,0.000037039543],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076969847,0.0023806307,0.0013448182,0.0009871474,0.0005950771,0.0018389716,0.002063848,0.0016784926,0.052971486],"category_scores_gemma":[0.0016561317,0.0007843404,0.0010277325,0.0005160046,0.00041587002,0.0012264234,0.0032413863,0.0016867982,0.03085852],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025565126,0.00036314412,0.00070320285,0.00052925665,0.00030348045,0.00076769025,0.00020959681,0.017372686,0.12909526,0.007819952,0.12413717,0.716142],"study_design_scores_gemma":[0.0005033736,0.00051825994,0.0012992636,0.00008177346,0.00009213998,0.00080943917,0.00015588048,0.52064806,0.3414293,0.015427114,0.11885332,0.00018199437],"about_ca_topic_score_codex":0.0017858342,"about_ca_topic_score_gemma":0.0036821663,"teacher_disagreement_score":0.052971486,"about_ca_system_score_codex":0.00046708132,"about_ca_system_score_gemma":0.0007758544,"threshold_uncertainty_score":0.17720729},"labels":[],"label_agreement":null},{"id":"W2902368158","doi":"10.21437/interspeech.2019-2380","title":"Learning Speaker Representations with Mutual Information","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Discriminator; Mutual information; Computer science; Artificial intelligence; Encoder; Speech recognition; Feature learning; Sentence; Joint probability distribution; Feature (linguistics); Pattern recognition (psychology); Natural language processing; Mathematics; Linguistics; Statistics","score_opus":0.018845371718182673,"score_gpt":0.24623960198073427,"score_spread":0.2273942302625516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902368158","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023083963,0.0003385625,0.97370017,0.00027457566,0.000028806215,0.000034571447,0.00013828406,0.0011161439,0.001284939],"genre_scores_gemma":[0.73884135,0.00049564516,0.25347716,0.0003905709,0.00020844635,0.00019387134,0.0011342638,0.00041281586,0.0048458916],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981029,0.00086329714,0.000070777154,0.00046410045,0.0003659642,0.00013294037],"domain_scores_gemma":[0.99749017,0.0016130654,0.00025259744,0.00035215268,0.0002195576,0.00007258334],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026545424,0.0013237844,0.0011007335,0.0009868672,0.0003893807,0.001034081,0.0011443038,0.0014531846,0.0018878666],"category_scores_gemma":[0.006866603,0.0007599809,0.0011317262,0.0006616054,0.0010238044,0.0022501133,0.0025936733,0.0023275034,0.0009766583],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037389764,0.0001229998,0.0017261074,0.00014772353,0.000303069,0.00012261262,0.0002325636,0.6318833,0.0124600455,0.02172134,0.004171842,0.32673445],"study_design_scores_gemma":[0.000007813671,0.000036326426,0.00028619776,0.000009209863,0.00001934201,0.000045078268,0.000010332673,0.98261327,0.0026029332,0.013871597,0.00048427502,0.000013681859],"about_ca_topic_score_codex":0.0010879159,"about_ca_topic_score_gemma":0.0013354556,"teacher_disagreement_score":0.0026545424,"about_ca_system_score_codex":0.00074568955,"about_ca_system_score_gemma":0.0007195251,"threshold_uncertainty_score":0.014038682},"labels":[],"label_agreement":null},{"id":"W2912129510","doi":"10.1109/icassp.2019.8683565","title":"Exploring Attention Mechanism for Acoustic-based Classification of Speech Utterances into System-directed and Non-system-directed","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Phrase; Mechanism (biology); Speech recognition; Word (group theory); Convolutional neural network; Artificial intelligence; Recurrent neural network; Natural language processing; Artificial neural network; Linguistics","score_opus":0.08203991703136106,"score_gpt":0.26620627261648083,"score_spread":0.1841663555851198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912129510","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33749878,0.0017979225,0.6538905,0.00064040604,0.0002051365,0.00010253016,0.00020670125,0.0023066814,0.003351305],"genre_scores_gemma":[0.96325696,0.0003150086,0.032138344,0.00015538861,0.000071378796,0.000051857267,0.00025604814,0.000060068687,0.0036950014],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994875,0.00013053985,0.000028017483,0.00019614265,0.00006365718,0.000094113864],"domain_scores_gemma":[0.99883777,0.00063499453,0.00009528375,0.00010946309,0.00027043896,0.0000520957],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014770426,0.0009961863,0.00052991015,0.0006007453,0.00030684864,0.0007561666,0.0011361667,0.0010076755,0.0012809302],"category_scores_gemma":[0.002587711,0.00029491747,0.0006994958,0.00033743258,0.0004686456,0.0011592038,0.0007753219,0.0014229992,0.0004935441],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012122003,0.00052723486,0.009992444,0.00026125793,0.00034062663,0.00026722555,0.0004483777,0.23922527,0.11194978,0.0045398376,0.0029093649,0.6283265],"study_design_scores_gemma":[0.0000071489453,0.00011976097,0.0021994647,0.000008843848,0.000048291917,0.000036927853,0.000026113847,0.98343277,0.012495582,0.0012527392,0.0003617896,0.000010651299],"about_ca_topic_score_codex":0.00958624,"about_ca_topic_score_gemma":0.007826187,"teacher_disagreement_score":0.00958624,"about_ca_system_score_codex":0.0009180807,"about_ca_system_score_gemma":0.0007874806,"threshold_uncertainty_score":0.01906091},"labels":[],"label_agreement":null},{"id":"W2912293245","doi":"10.1109/slt.2018.8639599","title":"MOS Naturalness and the Quest for Human-Like Speech","year":2018,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Naturalness; Computer science; Speech recognition; Physics","score_opus":0.02196593384210739,"score_gpt":0.27952470275844427,"score_spread":0.2575587689163369,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912293245","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73278606,0.0020727408,0.22823791,0.0020525046,0.00044797597,0.00013247102,0.00064840924,0.00078214693,0.032839872],"genre_scores_gemma":[0.9860027,0.00013108797,0.012542229,0.00015239483,0.00009335266,0.000023147759,0.00019322582,0.000053468837,0.00080841786],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99782604,0.00078087073,0.00016543153,0.00033244182,0.0008312195,0.00006392275],"domain_scores_gemma":[0.98792344,0.007595938,0.0011238323,0.0010408654,0.001827578,0.0004883747],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003927393,0.00033165878,0.00032098638,0.00072475534,0.0003554576,0.0017303466,0.00035596814,0.0005812847,0.0026770693],"category_scores_gemma":[0.02164695,0.00013958335,0.00020853027,0.00025892412,0.0020498303,0.001973592,0.0011818857,0.00092095305,0.00041669345],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0037302794,0.00029206314,0.08286732,0.001215866,0.00034594032,0.0007813287,0.005487741,0.026305508,0.2986826,0.058750432,0.004772422,0.5167685],"study_design_scores_gemma":[0.00015355139,0.0056840223,0.4060695,0.00038706732,0.0002481043,0.0039235894,0.0047170464,0.18516222,0.16419014,0.19792631,0.030929359,0.00060902745],"about_ca_topic_score_codex":0.0007254152,"about_ca_topic_score_gemma":0.00088221923,"teacher_disagreement_score":0.003927393,"about_ca_system_score_codex":0.00041083584,"about_ca_system_score_gemma":0.00028446125,"threshold_uncertainty_score":0.020770311},"labels":[],"label_agreement":null},{"id":"W2912379194","doi":"10.1007/s11042-019-7154-y","title":"Multitaper chirp group delay Hilbert envelope coefficients for robust speaker verification","year":2019,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Multitaper; Computer science; Envelope (radar); Chirp; Group delay and phase delay; Speaker verification; Speech recognition; Hilbert transform; Group (periodic table); Spectral envelope; Algorithm; Telecommunications; Bandwidth (computing); Physics; Radar; Speaker recognition","score_opus":0.030362367487512216,"score_gpt":0.24477554651597055,"score_spread":0.21441317902845833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912379194","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06184526,0.0010164033,0.9323747,0.00017229299,0.00011323307,0.000068940826,0.00027411172,0.0009252992,0.0032097423],"genre_scores_gemma":[0.41859794,0.0014357434,0.5686426,0.00013724013,0.0001515436,0.000120960474,0.00092818873,0.00023488593,0.009750818],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99967694,0.0000843886,0.00001610841,0.000036127047,0.0001565758,0.000029826693],"domain_scores_gemma":[0.9992118,0.00035204767,0.00007978354,0.0001589055,0.00016643405,0.00003107513],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000542008,0.00041162243,0.00030901816,0.00062999874,0.0002294391,0.0005157865,0.00042039668,0.0006750807,0.005226127],"category_scores_gemma":[0.001936127,0.00019018888,0.00025203123,0.0005454957,0.00024681247,0.0007974633,0.0005858668,0.0006277448,0.002333438],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000692032,0.000098645636,0.0005504636,0.00016461249,0.00004298906,0.0001338987,0.000079055484,0.017669544,0.42071462,0.009138286,0.00222167,0.54849416],"study_design_scores_gemma":[0.000064038075,0.00031800874,0.0035685566,0.000068178706,0.00008601369,0.00080448115,0.00009840794,0.59599733,0.3802164,0.0035117993,0.015210207,0.000056481505],"about_ca_topic_score_codex":0.00059806684,"about_ca_topic_score_gemma":0.0010446018,"teacher_disagreement_score":0.005226127,"about_ca_system_score_codex":0.00019598186,"about_ca_system_score_gemma":0.00043276473,"threshold_uncertainty_score":0.017483175},"labels":[],"label_agreement":null},{"id":"W2912971336","doi":"10.1145/3251778","title":"Session details: Speech & Auditory Interfaces","year":2015,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Session (web analytics); Computer science; Speech recognition; Multimedia; World Wide Web","score_opus":0.07738289082967917,"score_gpt":0.2933072861296628,"score_spread":0.2159243952999836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912971336","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01180962,0.012036102,0.02164534,0.007677004,0.052641995,0.0019105639,0.020928212,0.009686413,0.8616648],"genre_scores_gemma":[0.036524598,0.0061250827,0.0025350852,0.0014832959,0.005602908,0.00047406074,0.0049762977,0.0014223958,0.9408563],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99962914,0.000044498083,0.000028273162,0.0000918499,0.00010038218,0.00010588406],"domain_scores_gemma":[0.9982874,0.0005803183,0.000033147728,0.00016934377,0.00040546083,0.0005242641],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009329564,0.0021665175,0.0025953439,0.0007430235,0.0015328907,0.0030605027,0.0015192977,0.0061521404,0.81616265],"category_scores_gemma":[0.0016621597,0.00034996832,0.0015325717,0.00062113465,0.00057668815,0.0015705036,0.0014413265,0.0027067633,0.6167134],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031392893,0.00080551306,0.00058647775,0.0013721983,0.00010101628,0.0005849313,0.0001552484,0.00022954053,0.0343933,0.0013566153,0.813164,0.14411183],"study_design_scores_gemma":[0.0003793897,0.0017208416,0.0041528363,0.00042629192,0.00010077847,0.0010742375,0.0001792198,0.0010182858,0.010345417,0.0020896634,0.97845024,0.00006273143],"about_ca_topic_score_codex":0.00094342243,"about_ca_topic_score_gemma":0.0014898202,"teacher_disagreement_score":0.18383735,"about_ca_system_score_codex":0.00036484562,"about_ca_system_score_gemma":0.00058041216,"threshold_uncertainty_score":0.2622217},"labels":[],"label_agreement":null},{"id":"W2914422976","doi":"10.48550/arxiv.1902.02375","title":"Centroid-based deep metric learning for speaker recognition","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Embedding; Computer science; Centroid; Speech recognition; Similarity (geometry); Task (project management); Artificial intelligence; Metric (unit); Set (abstract data type); Speaker recognition; Pattern recognition (psychology); Speaker diarisation; Natural language processing; Image (mathematics)","score_opus":0.09792118983636798,"score_gpt":0.1929767119206509,"score_spread":0.09505552208428293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914422976","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011095546,0.001447232,0.9832169,0.00024589946,0.00009734964,0.000024756695,0.00019557067,0.002334546,0.0013421022],"genre_scores_gemma":[0.59262204,0.0013324423,0.3890028,0.0003195125,0.0002588897,0.00014983093,0.002043417,0.0006890015,0.013582127],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992656,0.00024072733,0.000034893008,0.00020780729,0.00018262904,0.00006829179],"domain_scores_gemma":[0.9994784,0.00015733688,0.000050561226,0.00011374757,0.00015826043,0.00004179498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011477284,0.00093840255,0.0010614091,0.0006848404,0.00034901744,0.00067356887,0.0016630556,0.0009238489,0.0039049252],"category_scores_gemma":[0.0028518047,0.00037738978,0.0006177336,0.00073128246,0.00059770065,0.0017525135,0.0017118411,0.0019857716,0.0022120378],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028279395,0.00012617499,0.0008112091,0.00014026083,0.00013803007,0.00006446994,0.00014875642,0.2649578,0.015772505,0.030427115,0.013402619,0.67372835],"study_design_scores_gemma":[0.0000061975256,0.00003655137,0.00021422224,0.000006452845,0.000009955483,0.000031891588,0.000012111274,0.9764134,0.0034989186,0.018032266,0.0017260575,0.000011905964],"about_ca_topic_score_codex":0.0063145584,"about_ca_topic_score_gemma":0.0073401616,"teacher_disagreement_score":0.0063145584,"about_ca_system_score_codex":0.0011426726,"about_ca_system_score_gemma":0.0008040553,"threshold_uncertainty_score":0.013063312},"labels":[],"label_agreement":null},{"id":"W2917672101","doi":"","title":"Voice biometrics distinction between English and Arabic using Sound Cleaner Filtering and SpeechPro SIS II analysis","year":2018,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Formant; Vowel; Speech recognition; Computer science; Speaker recognition; Spectrogram; Software; Articulation (sociology); Sound quality; Arabic; Biometrics; Linguistics; Artificial intelligence","score_opus":0.05138435495405243,"score_gpt":0.27860034919462473,"score_spread":0.22721599424057232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2917672101","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9084611,0.0006517556,0.07812407,0.00019421332,0.00015173951,0.0001756741,0.0005184737,0.00047149597,0.011251536],"genre_scores_gemma":[0.9395781,0.00031546605,0.056147505,0.000072148774,0.000040706796,0.000102602484,0.0004162457,0.000059276408,0.0032680475],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992198,0.00013616822,0.000101384634,0.00017880568,0.00029710494,0.00006679702],"domain_scores_gemma":[0.99860245,0.0004769761,0.0001977819,0.000107962085,0.0005351756,0.00007964619],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008490437,0.00043032586,0.00031217383,0.0025963725,0.0004207154,0.0012442322,0.00018213513,0.0005209153,0.0034704383],"category_scores_gemma":[0.0032125774,0.00015036511,0.00037206372,0.0008392084,0.00041887074,0.00082527485,0.0006089877,0.0003519115,0.0014242315],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001407491,0.00017631245,0.09843459,0.00030278627,0.00010202819,0.0007590828,0.002516265,0.00084603264,0.38238344,0.0020650388,0.0014519971,0.5095549],"study_design_scores_gemma":[0.00005866359,0.0012464735,0.7560862,0.0001574429,0.00027512747,0.0055524944,0.0065473244,0.028877223,0.1855495,0.002334398,0.013145172,0.00016999512],"about_ca_topic_score_codex":0.0010040738,"about_ca_topic_score_gemma":0.0014366078,"teacher_disagreement_score":0.0034704383,"about_ca_system_score_codex":0.00022920973,"about_ca_system_score_gemma":0.0002614382,"threshold_uncertainty_score":0.011609793},"labels":[],"label_agreement":null},{"id":"W2919923656","doi":"10.1007/s42452-019-0305-y","title":"Multitaper MFCC and normalized multitaper phase-based features for speaker verification","year":2019,"lang":"en","type":"article","venue":"SN Applied Sciences","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Multitaper; Computer science; Mel-frequency cepstrum; Speech recognition; Mixture model; Cepstrum; Artificial intelligence; Pattern recognition (psychology); Feature extraction","score_opus":0.024312204561038043,"score_gpt":0.28563690154598187,"score_spread":0.2613246969849438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2919923656","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1577998,0.0040919664,0.8230304,0.0002938663,0.00036325955,0.00021521411,0.0025632794,0.0041922578,0.0074499454],"genre_scores_gemma":[0.637593,0.0017005937,0.34269616,0.00013795891,0.00025544717,0.00023366847,0.00475335,0.00034417442,0.012285632],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999405,0.00014501813,0.000042642692,0.000115109804,0.00023089252,0.00006134986],"domain_scores_gemma":[0.9989747,0.00032760674,0.00007042672,0.00017515602,0.00041050275,0.000041738636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068715366,0.00043286104,0.0005227741,0.00097458734,0.00029542373,0.0005534437,0.0005057773,0.00079200725,0.0064286785],"category_scores_gemma":[0.002114202,0.00017563066,0.00038792536,0.00071337813,0.00017593135,0.000946075,0.00052637694,0.00055168173,0.0033856703],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012465816,0.00015328602,0.0010574234,0.00018470593,0.000057242265,0.00010574763,0.000052489795,0.0048236623,0.25272244,0.0014170131,0.004318509,0.7338609],"study_design_scores_gemma":[0.00011540255,0.00088333176,0.02737989,0.00008940865,0.00029756452,0.0010222748,0.00015105442,0.59820354,0.35062417,0.0020586222,0.019045427,0.00012938037],"about_ca_topic_score_codex":0.0017855512,"about_ca_topic_score_gemma":0.0035019438,"teacher_disagreement_score":0.0064286785,"about_ca_system_score_codex":0.00016606317,"about_ca_system_score_gemma":0.00052123447,"threshold_uncertainty_score":0.02150613},"labels":[],"label_agreement":null},{"id":"W2935267697","doi":"10.3758/s13414-019-01711-w","title":"Correction to: Gradient and categorical patterns of spoken-word recognition and processing of phonetic details","year":2019,"lang":"en","type":"erratum","venue":"Attention Perception & Psychophysics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Western University","funders":"","keywords":"Mistake; Computer science; Word (group theory); Natural language processing; Categorical variable; Speech recognition; Linguistics; Font; Artificial intelligence; Philosophy","score_opus":0.026920634063123446,"score_gpt":0.26057744604296557,"score_spread":0.23365681197984212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2935267697","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016866995,0.00048153597,0.00062180025,0.01525487,0.9800189,0.000022728875,0.0011768128,0.00046484187,0.0017899029],"genre_scores_gemma":[0.024355676,0.004679293,0.008672698,0.057019755,0.4248229,0.0004189044,0.0058808774,0.004858839,0.46929106],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.995812,0.0004184188,0.000934578,0.0006647003,0.0016030106,0.0005672266],"domain_scores_gemma":[0.9636892,0.0057576397,0.0015085598,0.0035403252,0.02361808,0.0018861684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026858363,0.003542955,0.0034592738,0.0062704994,0.004346476,0.0046566017,0.004789802,0.008085917,0.13991022],"category_scores_gemma":[0.051808998,0.0018545865,0.002308445,0.0030836393,0.0026802653,0.0025816567,0.0026844977,0.009729371,0.07696036],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008785811,0.000010761957,0.00007462774,0.00012997893,0.0000130343315,0.00033066646,0.000020158646,0.000030776428,0.000079806065,0.00041356156,0.9923752,0.0064336387],"study_design_scores_gemma":[0.00013176816,0.000045852576,0.0016568383,0.00027158196,0.000060378512,0.0013394197,0.000101755366,0.00043825712,0.00089003035,0.0019435072,0.99305564,0.000064975044],"about_ca_topic_score_codex":0.027690716,"about_ca_topic_score_gemma":0.027845575,"teacher_disagreement_score":0.13991022,"about_ca_system_score_codex":0.00433642,"about_ca_system_score_gemma":0.0045211785,"threshold_uncertainty_score":0.4680463},"labels":[],"label_agreement":null},{"id":"W2935542736","doi":"10.21437/interspeech.2019-2605","title":"Learning Problem-Agnostic Speech Representations from Multiple Self-Supervised Tasks","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Compute Canada","keywords":"Computer science; Encoder; Discriminator; Artificial intelligence; Speech recognition; Machine learning; Supervised learning; Construct (python library); SIGNAL (programming language); Adaptation (eye); Identity (music); Pattern recognition (psychology); Artificial neural network; Psychology","score_opus":0.030834728385458927,"score_gpt":0.26332052650836435,"score_spread":0.23248579812290543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2935542736","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04110538,0.00018688064,0.9561185,0.00017863732,0.00004100985,0.000083299135,0.00007992158,0.0009743631,0.001232031],"genre_scores_gemma":[0.6985314,0.0001901766,0.294868,0.00021423605,0.00017085308,0.0002711482,0.0007419251,0.00027499275,0.004737321],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986492,0.0004982452,0.000061462466,0.00047863502,0.00019958786,0.00011289486],"domain_scores_gemma":[0.99709666,0.0011818268,0.0003184176,0.0008591378,0.00037744068,0.00016659508],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002548915,0.0013431618,0.0011041905,0.0005917823,0.0004043057,0.00093918963,0.0019068097,0.0014912965,0.0016424888],"category_scores_gemma":[0.005702505,0.0005980774,0.0009562192,0.00048023587,0.0010538282,0.0019327695,0.002311302,0.0021930418,0.0009964919],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042330907,0.0005579426,0.002491941,0.0003196426,0.00025204243,0.00014155514,0.00035011687,0.41035706,0.030090395,0.0112814,0.0036256872,0.5401089],"study_design_scores_gemma":[0.000014986125,0.00007346705,0.00039211023,0.000009258678,0.000014401025,0.000039351053,0.000025653024,0.98428935,0.00586341,0.008743944,0.00052426156,0.000009768002],"about_ca_topic_score_codex":0.0006338095,"about_ca_topic_score_gemma":0.0011000324,"teacher_disagreement_score":0.002548915,"about_ca_system_score_codex":0.00050415855,"about_ca_system_score_gemma":0.00091718015,"threshold_uncertainty_score":0.013480127},"labels":[],"label_agreement":null},{"id":"W2938134751","doi":"10.1109/icassp.2019.8683674","title":"Parametric Cepstral Mean Normalization for Robust Speech Recognition","year":2019,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Normalization (sociology); Computer science; Speech recognition; Robustness (evolution); Parametric statistics; Cepstrum; Training set; Mel-frequency cepstrum; Test data; Pattern recognition (psychology); Artificial intelligence; Feature extraction; Mathematics; Statistics","score_opus":0.047716202140227454,"score_gpt":0.24333760598170381,"score_spread":0.19562140384147636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2938134751","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043746936,0.0010832857,0.9910386,0.00008750155,0.000118002165,0.00003205376,0.00012082597,0.0018315305,0.0013135156],"genre_scores_gemma":[0.18024096,0.0015832554,0.8116831,0.00019905882,0.00023423211,0.00020727763,0.0011828815,0.00071294134,0.0039562383],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984989,0.00029875635,0.00007631583,0.00031986012,0.0007206018,0.00008556999],"domain_scores_gemma":[0.9989065,0.0003948681,0.00007775515,0.00021356998,0.00038474117,0.000022554914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013922526,0.000967425,0.00088757236,0.0010908013,0.00044005516,0.0008073128,0.0010650245,0.0006570165,0.0027438095],"category_scores_gemma":[0.0048482064,0.00039013533,0.00061457703,0.0012967316,0.00052538724,0.001219935,0.0006865639,0.0015069168,0.0021106377],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018603982,0.000055731896,0.00041529606,0.00011871762,0.00006557322,0.000067948364,0.000040595845,0.053187463,0.053951122,0.007645919,0.0052560237,0.87900966],"study_design_scores_gemma":[0.000019820554,0.00010147151,0.0017199767,0.00003832032,0.000059006557,0.00025676613,0.000028647899,0.88943684,0.081726305,0.006742184,0.019796949,0.000073645315],"about_ca_topic_score_codex":0.0031476335,"about_ca_topic_score_gemma":0.0036448457,"teacher_disagreement_score":0.0031476335,"about_ca_system_score_codex":0.00068901107,"about_ca_system_score_gemma":0.0009140931,"threshold_uncertainty_score":0.0091789365},"labels":[],"label_agreement":null},{"id":"W2950689855","doi":"10.48550/arxiv.1303.5778","title":"Speech Recognition with Deep Recurrent Neural Networks","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Recurrent neural network; Computer science; Connectionism; TIMIT; Speech recognition; Artificial intelligence; Context (archaeology); Deep learning; Benchmark (surveying); Time delay neural network; Artificial neural network; Hidden Markov model","score_opus":0.0770478288527954,"score_gpt":0.17952142166561869,"score_spread":0.10247359281282328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950689855","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034026813,0.0021232192,0.9491483,0.00043801608,0.0002548428,0.000046624056,0.00064121076,0.007904011,0.005416936],"genre_scores_gemma":[0.61468744,0.0015059625,0.36449295,0.00031228724,0.00022929026,0.00010801954,0.003528577,0.0003594733,0.014776066],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99932146,0.00014108059,0.00004523105,0.00019378835,0.00023908679,0.00005937248],"domain_scores_gemma":[0.9994159,0.0002123979,0.000049105565,0.00014043799,0.00016021782,0.000021924725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007016102,0.0007251881,0.00053519127,0.000551443,0.00019373727,0.0010076324,0.00077999465,0.000770273,0.0037846575],"category_scores_gemma":[0.0021691509,0.0003735762,0.00053572765,0.0006179455,0.00030326933,0.0013027691,0.0008106133,0.0010182114,0.0034191262],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002624928,0.00010003651,0.0008159983,0.00019744408,0.00018194814,0.00016831081,0.00007839064,0.21792346,0.06614842,0.00924355,0.009987552,0.69489235],"study_design_scores_gemma":[0.000008309771,0.000045379224,0.000379938,0.000015472195,0.000016937389,0.00004700211,0.000012606812,0.975993,0.015241092,0.00469236,0.0035338546,0.000013952925],"about_ca_topic_score_codex":0.004250936,"about_ca_topic_score_gemma":0.0071904613,"teacher_disagreement_score":0.004250936,"about_ca_system_score_codex":0.00056641316,"about_ca_system_score_gemma":0.00041979674,"threshold_uncertainty_score":0.012660921},"labels":[],"label_agreement":null},{"id":"W2956804760","doi":"10.1109/icc.2019.8761244","title":"Spoofing Attacks on Speaker Verification Systems Based Generated Voice using Genetic Algorithm","year":2019,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Spoofing attack; Speaker verification; Computer science; Genetic algorithm; Authentication (law); Speaker recognition; Speech recognition; Population; Algorithm; Pattern recognition (psychology); Artificial intelligence; Machine learning; Computer network; Computer security","score_opus":0.03678619749085209,"score_gpt":0.2540703735878523,"score_spread":0.21728417609700018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2956804760","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5218667,0.000290249,0.4744493,0.0002299943,0.000066588356,0.00005327566,0.000029765617,0.0009844642,0.0020297237],"genre_scores_gemma":[0.9676404,0.00008133061,0.03156202,0.0000390795,0.0000055212217,0.000018928364,0.00001572716,0.000016602276,0.0006204138],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991835,0.00024938176,0.00004045475,0.00013499855,0.00029820603,0.00009340292],"domain_scores_gemma":[0.99917287,0.0003925148,0.00012491946,0.00013871,0.00014942249,0.000021558648],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006175081,0.00048872846,0.00040046655,0.00040371605,0.00030721453,0.00039505042,0.0004026769,0.0007017309,0.00043156015],"category_scores_gemma":[0.0021332349,0.00012407501,0.00040336617,0.00022294205,0.00051034376,0.0005778455,0.00041195194,0.00043267728,0.000110357374],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00066248863,0.0001696694,0.0038432651,0.00012031487,0.0001862338,0.00046146815,0.00030275568,0.5604032,0.22664182,0.012085119,0.00069212593,0.19443154],"study_design_scores_gemma":[0.000012143458,0.00013682398,0.00065115956,0.0000046661726,0.000021801578,0.000120330944,0.000016999176,0.9543341,0.04335707,0.0009831785,0.00034704144,0.000014628262],"about_ca_topic_score_codex":0.001385542,"about_ca_topic_score_gemma":0.0008006487,"teacher_disagreement_score":0.001385542,"about_ca_system_score_codex":0.00041592118,"about_ca_system_score_gemma":0.0003966752,"threshold_uncertainty_score":0.0032657385},"labels":[],"label_agreement":null},{"id":"W2962989420","doi":"10.21437/interspeech.2019-2240","title":"A Deep Neural Network for Short-Segment Speaker Recognition","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Speech recognition; Speaker recognition; Artificial neural network; Task (project management); Duration (music); Phone; Time delay neural network; Pattern recognition (psychology); Artificial intelligence; Engineering","score_opus":0.06662587784503783,"score_gpt":0.2763267100300315,"score_spread":0.2097008321849937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962989420","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042112637,0.00189622,0.9431358,0.0003956919,0.00046024393,0.0000829498,0.0012942702,0.0054839994,0.005138152],"genre_scores_gemma":[0.5134421,0.001129147,0.4536684,0.0004903881,0.0001783056,0.0002554157,0.0053275893,0.0004109407,0.025097786],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997358,0.000040671122,0.000013707909,0.00009391593,0.00007568945,0.000040276453],"domain_scores_gemma":[0.9998135,0.00004816915,0.000013858249,0.000030026138,0.0000755225,0.000018974632],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004347689,0.00072341354,0.00039578436,0.00031037783,0.00030697972,0.00044268835,0.00084488554,0.00079124153,0.003437527],"category_scores_gemma":[0.00078557193,0.00032684434,0.000448481,0.00028383438,0.00023798036,0.00079725886,0.0009030978,0.0015319086,0.0014683568],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054428336,0.00019458243,0.0011241867,0.00017694273,0.00017799715,0.0001530243,0.00010390109,0.11678068,0.1230148,0.004887391,0.014889692,0.73795265],"study_design_scores_gemma":[0.000013814569,0.00010559405,0.00081857125,0.000014688013,0.00003845715,0.00007020503,0.000015281537,0.9712691,0.020708777,0.002032434,0.0048907334,0.000022393255],"about_ca_topic_score_codex":0.006565363,"about_ca_topic_score_gemma":0.012266547,"teacher_disagreement_score":0.006565363,"about_ca_system_score_codex":0.00054925086,"about_ca_system_score_gemma":0.0008168747,"threshold_uncertainty_score":0.013054311},"labels":[],"label_agreement":null},{"id":"W2963403664","doi":"10.21437/interspeech.2016-1446","title":"Towards End-to-End Speech Recognition with Deep Convolutional Neural Networks","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":341,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research; Université de Montréal","funders":"","keywords":"End-to-end principle; Computer science; Speech recognition; Convolutional neural network; Deep learning; Artificial intelligence","score_opus":0.03436162498600204,"score_gpt":0.24910300660268944,"score_spread":0.2147413816166874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963403664","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009250979,0.00031199536,0.98301125,0.00015518417,0.00006832998,0.00003954097,0.00025587325,0.005293387,0.0016133729],"genre_scores_gemma":[0.22626534,0.00039711606,0.76135486,0.00034216914,0.00007610745,0.00012593686,0.0021153754,0.00034635063,0.008976784],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99927217,0.00014334236,0.000041616782,0.00024667464,0.00020718075,0.00008907293],"domain_scores_gemma":[0.999126,0.00024321502,0.000060015816,0.00022613755,0.00029632298,0.00004828269],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092335616,0.0013825229,0.00075257925,0.00048146336,0.0003201676,0.0010719589,0.0017360846,0.0016146294,0.0030917253],"category_scores_gemma":[0.002103507,0.0004994198,0.000519193,0.0004705319,0.00047342427,0.0017748795,0.0012921916,0.0019640985,0.0035040514],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044938215,0.0002997171,0.0012382093,0.00024535652,0.00008810541,0.00027393803,0.0001594382,0.11791027,0.10408977,0.014599952,0.014216395,0.7464294],"study_design_scores_gemma":[0.000010339927,0.00006413283,0.00033292337,0.000018104889,0.000014914009,0.0000592811,0.000025084255,0.94896245,0.03842642,0.0077997227,0.004271243,0.000015363586],"about_ca_topic_score_codex":0.004642928,"about_ca_topic_score_gemma":0.009980625,"teacher_disagreement_score":0.004642928,"about_ca_system_score_codex":0.0007616364,"about_ca_system_score_gemma":0.0008674857,"threshold_uncertainty_score":0.010342836},"labels":[],"label_agreement":null},{"id":"W2963596039","doi":"10.21437/interspeech.2017-556","title":"Dynamic Layer Normalization for Adaptive Neural Acoustic Modeling in Speech Recognition","year":2017,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":71,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Normalization (sociology); Computer science; Speech recognition; Artificial neural network; Deep neural networks; Acoustic model; Artificial intelligence; Pattern recognition (psychology); Speech processing","score_opus":0.12487949391130328,"score_gpt":0.31111239263630314,"score_spread":0.18623289872499987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963596039","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032175132,0.00031205392,0.9935643,0.00009273037,0.00007244378,0.00002032456,0.000107765954,0.0014177029,0.0011951316],"genre_scores_gemma":[0.31574523,0.0010896446,0.6716536,0.00036266766,0.00016398198,0.00030269494,0.0010112479,0.001149813,0.008521037],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99924326,0.00017159167,0.000058302783,0.00026218232,0.0002036866,0.000061027764],"domain_scores_gemma":[0.99948716,0.00016693908,0.000050460076,0.00014368817,0.00013449836,0.000017094086],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011382733,0.0012265678,0.0006845937,0.0006446986,0.00044619266,0.0010041652,0.0016865894,0.0007386819,0.003808103],"category_scores_gemma":[0.0032628605,0.00052396493,0.00100675,0.0011275783,0.00077791477,0.0021546725,0.0011804557,0.00237363,0.001548539],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017995221,0.00008373346,0.0008923872,0.00015124361,0.00015161664,0.00010766015,0.00015237911,0.38781923,0.030310122,0.030361548,0.007937748,0.5418524],"study_design_scores_gemma":[0.0000055312307,0.000014874243,0.00017328373,0.000010428831,0.000016769683,0.000033236163,0.000010652731,0.97401786,0.010786901,0.010585312,0.004331235,0.000014000015],"about_ca_topic_score_codex":0.006270321,"about_ca_topic_score_gemma":0.009085544,"teacher_disagreement_score":0.006270321,"about_ca_system_score_codex":0.001082245,"about_ca_system_score_gemma":0.0010635984,"threshold_uncertainty_score":0.01273942},"labels":[],"label_agreement":null},{"id":"W2963897404","doi":"10.63317/3bau89hm3k8v","title":"Towards Neural Speaker Modeling in Multi-Party Conversation: The Task, Dataset, and Models","year":2018,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Conversation; Computer science; Task (project management); Component (thermodynamics); Speaker recognition; Speaker diarisation; Speech recognition; Artificial intelligence; Data modeling; Natural language processing; Linguistics; Database","score_opus":0.13927681886795895,"score_gpt":0.2942934836241976,"score_spread":0.15501666475623865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963897404","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2714075,0.004031354,0.6907456,0.0042282697,0.00081556325,0.00069088145,0.016012697,0.0069284416,0.005139717],"genre_scores_gemma":[0.5938168,0.0012135453,0.34132475,0.00069952494,0.0006338193,0.0014312409,0.055092525,0.00038477726,0.005402989],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99778914,0.0011814268,0.00009262284,0.00056730193,0.000244803,0.00012470815],"domain_scores_gemma":[0.9968997,0.0012485286,0.00015263658,0.0009662595,0.0005208415,0.0002120273],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004119866,0.0015481005,0.0010708771,0.0011058615,0.001268696,0.0014054893,0.0019292231,0.0021483686,0.0023150602],"category_scores_gemma":[0.009892127,0.00041765545,0.0014158302,0.0008417611,0.00057867856,0.0022470986,0.0026517326,0.0040726243,0.0032396736],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002163038,0.0023520521,0.034745052,0.000731231,0.0007730977,0.00041279977,0.000999767,0.1048349,0.03854947,0.008841848,0.056581903,0.7490149],"study_design_scores_gemma":[0.00011171198,0.00026987353,0.01166724,0.00011979175,0.00024286199,0.0003666447,0.00057368225,0.9397813,0.012975425,0.017401837,0.016381066,0.0001085447],"about_ca_topic_score_codex":0.008320293,"about_ca_topic_score_gemma":0.011968556,"teacher_disagreement_score":0.008320293,"about_ca_system_score_codex":0.0008744276,"about_ca_system_score_gemma":0.0016422755,"threshold_uncertainty_score":0.02178824},"labels":[],"label_agreement":null},{"id":"W2963905071","doi":"","title":"Twin Networks: Matching the Future for Sequence Generation","year":2018,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Polytechnique Montréal","funders":"","keywords":"Computer science; Inference; Task (project management); Sequence (biology); Forcing (mathematics); Generative grammar; Matching (statistics); Generative model; Artificial intelligence; Recurrent neural network; Simple (philosophy); Term (time); Algorithm; Machine learning; Artificial neural network; Mathematics","score_opus":0.023151838101433373,"score_gpt":0.2514149227999537,"score_spread":0.22826308469852033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963905071","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012767757,0.00024677347,0.98106474,0.00040874182,0.00011632877,0.00006086853,0.00016043421,0.0017052216,0.0034691386],"genre_scores_gemma":[0.5137939,0.0004177339,0.47538665,0.00047193622,0.00016841703,0.00028515732,0.00084447686,0.00071540277,0.007916359],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992274,0.00025018337,0.000039501872,0.00024706262,0.00015514015,0.000080755286],"domain_scores_gemma":[0.99826056,0.0008749129,0.00012321581,0.0004246059,0.00022880304,0.00008790146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022167368,0.0010940431,0.0005850906,0.0007576831,0.000627746,0.0011078438,0.0021140531,0.0013660879,0.0062844856],"category_scores_gemma":[0.0077678463,0.0007591586,0.00067005446,0.00063306326,0.0008382234,0.004042669,0.0022539664,0.0020586858,0.0015434809],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00074050046,0.00021595453,0.0031893693,0.00020758166,0.00011925642,0.00038182514,0.00058377057,0.3978227,0.022153102,0.12276792,0.011572459,0.44024557],"study_design_scores_gemma":[0.00002385675,0.000049169368,0.00014153954,0.000017978746,0.00002089716,0.0000696988,0.000024062396,0.94133836,0.005045333,0.048951797,0.0043034935,0.000013790541],"about_ca_topic_score_codex":0.003606489,"about_ca_topic_score_gemma":0.0080527915,"teacher_disagreement_score":0.0062844856,"about_ca_system_score_codex":0.0008369815,"about_ca_system_score_gemma":0.0011893519,"threshold_uncertainty_score":0.02102369},"labels":[],"label_agreement":null},{"id":"W2963912924","doi":"","title":"Sample-efficient adaptive text-to-speech","year":2018,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Naturalness; Speech recognition; Artificial neural network; Embedding; Benchmark (surveying); Similarity (geometry); Stochastic gradient descent; Speaker recognition; Mean opinion score; Gradient descent; Artificial intelligence; Sample (material); Speaker diarisation; Metric (unit)","score_opus":0.08424185677777325,"score_gpt":0.19215710942935177,"score_spread":0.10791525265157852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963912924","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022197846,0.00046451492,0.96736133,0.00014188632,0.00015902978,0.00008202593,0.00029709452,0.00747208,0.0018242698],"genre_scores_gemma":[0.5408862,0.00027610324,0.44659525,0.0003436939,0.00019663878,0.0003166809,0.0017728648,0.0010144634,0.008598028],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99930847,0.00014053853,0.000043724503,0.00026904803,0.00017977996,0.000058511916],"domain_scores_gemma":[0.9986432,0.00056132674,0.00008035917,0.00040856595,0.00023401724,0.00007247877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093701103,0.0013786212,0.0010450364,0.0005616763,0.00033080872,0.00064663915,0.0024206133,0.0011845501,0.0046735415],"category_scores_gemma":[0.0036828178,0.0005184574,0.00082022394,0.0005381174,0.0006024945,0.0019413162,0.001843533,0.0016110728,0.0036236423],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008822295,0.0003730831,0.0009633872,0.00020290483,0.00017482802,0.000264578,0.0001813932,0.2659616,0.091198675,0.004289791,0.0061451644,0.6293624],"study_design_scores_gemma":[0.000027623253,0.00010442538,0.00022113622,0.0000069401117,0.00002187504,0.0000979193,0.000022210772,0.9719623,0.022444438,0.0033095926,0.0017670899,0.000014514567],"about_ca_topic_score_codex":0.0022573383,"about_ca_topic_score_gemma":0.0041049146,"teacher_disagreement_score":0.0046735415,"about_ca_system_score_codex":0.00054896384,"about_ca_system_score_gemma":0.00068557076,"threshold_uncertainty_score":0.015634537},"labels":[],"label_agreement":null},{"id":"W2964187693","doi":"10.1109/icassp.2018.8462688","title":"Deep Residual Learning for Small-Footprint Keyword Spotting","year":2018,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":227,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Keyword spotting; Computer science; Residual; Convolutional neural network; Deep learning; Footprint; Memory footprint; Benchmark (surveying); Artificial intelligence; Spotting; Machine learning; Speech recognition; Algorithm; Cartography","score_opus":0.041542598232747745,"score_gpt":0.26400828492633893,"score_spread":0.22246568669359118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964187693","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14656763,0.002288071,0.8134872,0.0005081226,0.0002911112,0.00014314387,0.0017146177,0.02908599,0.005914182],"genre_scores_gemma":[0.64200807,0.00061812473,0.34203455,0.00033060927,0.00011863326,0.00012099616,0.0036180066,0.0011091427,0.010041933],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999527,0.000086699474,0.000029237068,0.00015194349,0.0001301785,0.00007502254],"domain_scores_gemma":[0.9990049,0.00046244066,0.0000688508,0.00019832993,0.00019191987,0.000073573945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092710886,0.0012115967,0.0009383426,0.0006293041,0.00024854956,0.0008805081,0.001594987,0.0009658507,0.0051161167],"category_scores_gemma":[0.004365517,0.00027822613,0.00052122475,0.0006650115,0.0004252594,0.0019454401,0.0012300911,0.0012926039,0.0029870735],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014125131,0.00037134337,0.0014290651,0.00047209213,0.00015035384,0.0003329726,0.00016009327,0.17111894,0.086663015,0.0038917544,0.013256994,0.7207408],"study_design_scores_gemma":[0.00004602599,0.00021601273,0.00036639956,0.000015193791,0.000026499885,0.00009647236,0.000047907724,0.9521105,0.04153012,0.0025977842,0.0029269184,0.00002015509],"about_ca_topic_score_codex":0.0061486983,"about_ca_topic_score_gemma":0.010276912,"teacher_disagreement_score":0.0061486983,"about_ca_system_score_codex":0.0005349763,"about_ca_system_score_gemma":0.00090058736,"threshold_uncertainty_score":0.017115057},"labels":[],"label_agreement":null},{"id":"W2964250984","doi":"10.1109/icassp.2018.8461624","title":"An Experimental Analysis of the Power Consumption of Convolutional Neural Networks for Keyword Spotting","year":2018,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Keyword spotting; Computer science; Proxy (statistics); Convolutional neural network; Inference; Predictive power; Artificial intelligence; Footprint; Memory footprint; Spotting; Energy consumption; Predictive modelling; Artificial neural network; Machine learning; Data mining","score_opus":0.034677122342771385,"score_gpt":0.2989291442651436,"score_spread":0.26425202192237224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964250984","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97569644,0.00039687348,0.0174447,0.00024498094,0.0000837397,0.000051468465,0.00065747544,0.0013257508,0.004098461],"genre_scores_gemma":[0.9936935,0.00012065604,0.0042038965,0.000034522312,0.000008279668,0.000033389533,0.00038140028,0.00008599846,0.0014384256],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999589,0.00006981876,0.000039584207,0.000086825414,0.00012368844,0.000091118854],"domain_scores_gemma":[0.99794954,0.0012280847,0.00012823324,0.00024967644,0.0003803914,0.00006407405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048395584,0.0007497965,0.0003446483,0.00039660826,0.00027440078,0.00040825907,0.0009878207,0.00037663287,0.004005234],"category_scores_gemma":[0.0038106872,0.00020104059,0.00021195647,0.00060848723,0.0003422737,0.0011631376,0.00027941092,0.00056767947,0.00057659275],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005722887,0.0011886203,0.013853898,0.0011384315,0.0003196879,0.0009630176,0.00032717217,0.44992065,0.18638141,0.0038834396,0.009903224,0.32639757],"study_design_scores_gemma":[0.000090177076,0.0011389792,0.0078001064,0.000032058557,0.000086561166,0.00023181255,0.00013363251,0.85936224,0.1271059,0.0013881099,0.002601097,0.000029320918],"about_ca_topic_score_codex":0.004573845,"about_ca_topic_score_gemma":0.0063469005,"teacher_disagreement_score":0.004573845,"about_ca_system_score_codex":0.0007910116,"about_ca_system_score_gemma":0.00040708212,"threshold_uncertainty_score":0.013398826},"labels":[],"label_agreement":null},{"id":"W2970680405","doi":"10.18653/v1/d19-1201","title":"Modeling Personalization in Continuous Space for Response Generation via Augmented Wasserstein Autoencoders","year":2019,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China; National Science Foundation","keywords":"Personalization; Computer science; Chen; Joint (building); Space (punctuation); Artificial intelligence; Natural language processing; World Wide Web; Engineering; Operating system","score_opus":0.029475567868854604,"score_gpt":0.2524900829017831,"score_spread":0.2230145150329285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970680405","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019998647,0.000527666,0.9774154,0.0002235937,0.000086116364,0.000030196612,0.00008488999,0.0007272155,0.0009061955],"genre_scores_gemma":[0.7966493,0.0005309872,0.19210023,0.00033563713,0.0001518728,0.00020066719,0.0004970513,0.000362939,0.009171365],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994698,0.0001710032,0.00002313511,0.0001825843,0.00007428511,0.00007931664],"domain_scores_gemma":[0.99888796,0.00070324447,0.00008411646,0.00011007253,0.00015474766,0.000059874277],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012788555,0.0009905546,0.0010813257,0.0004510876,0.00034172807,0.00086324953,0.0013757509,0.0012457619,0.0029847298],"category_scores_gemma":[0.0032720352,0.0007050027,0.0010444212,0.0005742361,0.0007399409,0.0015337878,0.0014668021,0.002209446,0.001045117],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026296938,0.00012378536,0.0013823485,0.00009566121,0.00011175931,0.00010884898,0.00018621712,0.7888564,0.00571966,0.009677378,0.0035551146,0.18991987],"study_design_scores_gemma":[0.000003343568,0.000009590831,0.00006456347,0.0000024997023,0.0000047614453,0.0000070136043,0.000003427098,0.9980477,0.00027398227,0.001439278,0.00014095963,0.0000028780728],"about_ca_topic_score_codex":0.007736135,"about_ca_topic_score_gemma":0.009892107,"teacher_disagreement_score":0.007736135,"about_ca_system_score_codex":0.000695587,"about_ca_system_score_gemma":0.00071193016,"threshold_uncertainty_score":0.01538223},"labels":[],"label_agreement":null},{"id":"W2984770459","doi":"10.1121/1.5137272","title":"Improved vowel labeling for prenasal merger using customized forced alignment","year":2019,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Pronunciation; Vowel; Formant; Computer science; Speech recognition; Centroid; Linguistics; Artificial intelligence","score_opus":0.01871390558617517,"score_gpt":0.26021190191442783,"score_spread":0.24149799632825267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2984770459","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15809366,0.00030150078,0.80971825,0.00021406719,0.00026666716,0.00030119758,0.0022103966,0.022512231,0.00638206],"genre_scores_gemma":[0.27599964,0.00009254414,0.7119467,0.00016402146,0.000045111192,0.00020091097,0.0047880094,0.0022528556,0.004510197],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982944,0.00029485623,0.00017667121,0.0006614119,0.0004245715,0.00014804571],"domain_scores_gemma":[0.99524313,0.0010208772,0.0003859951,0.0014236069,0.0017860825,0.00014042044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001210329,0.00083972834,0.0007128504,0.0012372861,0.0009836915,0.0012665772,0.0013388328,0.00073306134,0.009711218],"category_scores_gemma":[0.006385585,0.00053734065,0.0005517556,0.0012563542,0.00051314855,0.0015382695,0.0017687078,0.0011278796,0.0064962814],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00088188524,0.00018170888,0.009523802,0.00032185487,0.00008603743,0.00026893982,0.001049109,0.0132909445,0.3544513,0.0024441823,0.009203242,0.608297],"study_design_scores_gemma":[0.00014326036,0.0005483723,0.030629266,0.000064665306,0.000116274074,0.0014482354,0.0009796111,0.38308495,0.53572124,0.0034075119,0.04357787,0.00027874496],"about_ca_topic_score_codex":0.014128928,"about_ca_topic_score_gemma":0.042398743,"teacher_disagreement_score":0.014128928,"about_ca_system_score_codex":0.0007357653,"about_ca_system_score_gemma":0.001730218,"threshold_uncertainty_score":0.032487214},"labels":[],"label_agreement":null},{"id":"W2989571531","doi":"10.1109/sped.2019.8906599","title":"FoR: A Dataset for Synthetic Speech Detection","year":2019,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":169,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Speech recognition; Artificial intelligence; Natural language processing","score_opus":0.024817805764369195,"score_gpt":0.2639481081266526,"score_spread":0.2391303023622834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2989571531","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023749303,0.0017369268,0.0065545808,0.0005123426,0.0008133026,0.0006060297,0.9511297,0.00899014,0.0059077283],"genre_scores_gemma":[0.012076431,0.00020737214,0.0073308228,0.00014141576,0.00007581643,0.0005404853,0.97661203,0.00020773098,0.0028079292],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981187,0.00040250423,0.00026605173,0.00046599715,0.0005553759,0.00019127311],"domain_scores_gemma":[0.99770457,0.0006202626,0.00017595026,0.00051958073,0.0007364329,0.0002432719],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011672515,0.004192942,0.0016075867,0.002997367,0.0011284024,0.0013328519,0.0028770838,0.002996895,0.016338488],"category_scores_gemma":[0.0038066162,0.00044797448,0.0015157141,0.002184469,0.0005430497,0.0010095811,0.0017892409,0.0020197385,0.026403999],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013276383,0.00094081275,0.005155356,0.0020964278,0.00030838427,0.0008773571,0.00024152716,0.0057271766,0.009279026,0.0009837461,0.87757444,0.095488064],"study_design_scores_gemma":[0.0009866751,0.00094016665,0.029230945,0.0005241001,0.00028249016,0.0033068883,0.00094613194,0.044028357,0.020233292,0.0026588782,0.8964717,0.0003905652],"about_ca_topic_score_codex":0.013151686,"about_ca_topic_score_gemma":0.028501162,"teacher_disagreement_score":0.016338488,"about_ca_system_score_codex":0.0011898092,"about_ca_system_score_gemma":0.0014847337,"threshold_uncertainty_score":0.054657698},"labels":[],"label_agreement":null},{"id":"W2990074387","doi":"10.1109/mlsp.2019.8918703","title":"End-To-End Detection Of Attacks To Automatic Speaker Recognizers With Time-Attentive Light Convolutional Neural Networks","year":2019,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Speech recognition; Convolutional neural network; Benchmark (surveying); Microphone; Word error rate; Speaker recognition; Biometrics; Dimension (graph theory); Set (abstract data type); Spectrogram; Artificial intelligence; Pattern recognition (psychology); Mathematics","score_opus":0.009264250930136903,"score_gpt":0.21120651866321333,"score_spread":0.2019422677330764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990074387","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27235472,0.0017819022,0.6881554,0.00054950477,0.0005116956,0.00037193304,0.0017682527,0.024114879,0.010391762],"genre_scores_gemma":[0.8374187,0.00039074267,0.14238933,0.00035164427,0.00010090566,0.00015309767,0.0036162992,0.00028205145,0.015297115],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99881786,0.00017730343,0.000054617027,0.00030209727,0.00040709515,0.0002409892],"domain_scores_gemma":[0.99884003,0.00031564356,0.00013440654,0.0002676613,0.00037385226,0.00006838782],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011194608,0.0015755818,0.0007812298,0.0006863716,0.00038828296,0.00088847685,0.0011321628,0.0012542588,0.0029059087],"category_scores_gemma":[0.002507719,0.00030740997,0.00047176064,0.000266469,0.00040580778,0.0012485541,0.0015828167,0.0013410329,0.003288178],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017852332,0.00086203474,0.0057799183,0.00022112181,0.0002917414,0.00050533726,0.00013154442,0.09652039,0.10860021,0.0018294478,0.013214041,0.7702591],"study_design_scores_gemma":[0.00002444633,0.0002869543,0.004120679,0.000024865996,0.00005832833,0.00021003617,0.000040460927,0.9039828,0.08696674,0.0013902059,0.002857477,0.00003703108],"about_ca_topic_score_codex":0.005212119,"about_ca_topic_score_gemma":0.010801541,"teacher_disagreement_score":0.005212119,"about_ca_system_score_codex":0.0007721562,"about_ca_system_score_gemma":0.0009629714,"threshold_uncertainty_score":0.010363579},"labels":[],"label_agreement":null},{"id":"W2990506421","doi":"","title":"Speech Perception and The Role of Semantic Richness in Processing","year":2019,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Concreteness; Lexical decision task; Speech perception; Psychology; Valence (chemistry); Semantic property; Perception; Semantic memory; Cognitive psychology; Semantic similarity; Computer science; Speech recognition; Natural language processing; Cognition","score_opus":0.005660513892169393,"score_gpt":0.19439392822627233,"score_spread":0.18873341433410293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990506421","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98013455,0.000646885,0.009913191,0.00010323612,0.000024836567,0.000022981509,0.00014827092,0.000051673396,0.008954375],"genre_scores_gemma":[0.99661726,0.0001978778,0.0026605176,0.000032143915,0.000016749998,0.000011435553,0.00008702054,0.000021449312,0.00035555495],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9994671,0.00013578897,0.000042346288,0.0001514642,0.0001501116,0.000053233976],"domain_scores_gemma":[0.9979558,0.0011487736,0.0003731729,0.00016860051,0.00019928651,0.0001543279],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007000117,0.00038132773,0.00029921756,0.0009050278,0.00025198245,0.0018483909,0.00019388826,0.00034831392,0.0026867841],"category_scores_gemma":[0.005326955,0.00029576276,0.0003463789,0.00030090424,0.00089812116,0.001854367,0.0016084702,0.0003736816,0.00030142278],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027739329,0.00019945705,0.100883804,0.0009879379,0.00040022744,0.0008571726,0.01167688,0.0032761188,0.71481043,0.0058628195,0.0005646529,0.15770659],"study_design_scores_gemma":[0.00008137252,0.0009731443,0.9335753,0.00012586945,0.00023928279,0.0011878645,0.00470673,0.0073510334,0.031383827,0.017705036,0.0025337965,0.00013692194],"about_ca_topic_score_codex":0.0009510684,"about_ca_topic_score_gemma":0.0010505154,"teacher_disagreement_score":0.0026867841,"about_ca_system_score_codex":0.00024662452,"about_ca_system_score_gemma":0.00018735726,"threshold_uncertainty_score":0.008988261},"labels":[],"label_agreement":null},{"id":"W2991975083","doi":"","title":"Strategies to Enhance Whispered Speech Speaker Verification: A Comparative Analysis","year":2015,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Speech recognition; Noise (video); Task (project management); Feature (linguistics); Speech enhancement; Speech technology; Speech processing; Background noise; Artificial intelligence; Linguistics; Engineering; Telecommunications","score_opus":0.05715611910217276,"score_gpt":0.31204669478241864,"score_spread":0.25489057568024587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2991975083","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7368091,0.015829613,0.23305847,0.00027792904,0.0001980183,0.0004460012,0.000224894,0.0011153747,0.012040633],"genre_scores_gemma":[0.89739186,0.003315918,0.09605113,0.000074846204,0.0000667823,0.00008372463,0.0004485641,0.00007886638,0.002488413],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.997733,0.000992597,0.00015466812,0.0002775048,0.0006994103,0.00014283686],"domain_scores_gemma":[0.9962037,0.0023168942,0.00011777122,0.00031432894,0.0009748194,0.00007242636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037428397,0.0007315184,0.00063210225,0.0011552282,0.00037648584,0.000739747,0.0006109087,0.00065266655,0.0023126449],"category_scores_gemma":[0.0068487087,0.00017448692,0.0006044098,0.00043813724,0.0003026261,0.0011910247,0.0008881531,0.00036712235,0.0009177611],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014321142,0.00030512287,0.006326011,0.00087613205,0.0002973075,0.00026495694,0.0006437284,0.007182861,0.1002379,0.001568134,0.0006603498,0.8802054],"study_design_scores_gemma":[0.0002728256,0.012597,0.0893243,0.00040269134,0.0029678426,0.0059734234,0.003170607,0.2845266,0.56841063,0.003136344,0.02890159,0.0003162301],"about_ca_topic_score_codex":0.0015067741,"about_ca_topic_score_gemma":0.0022802935,"teacher_disagreement_score":0.0037428397,"about_ca_system_score_codex":0.00033006238,"about_ca_system_score_gemma":0.0005436619,"threshold_uncertainty_score":0.019794285},"labels":[],"label_agreement":null},{"id":"W3006824058","doi":"10.1109/asru46091.2019.9003792","title":"Development of Voice Spoofing Detection Systems for 2019 Edition of Automatic Speaker Verification and Countermeasures Challenge","year":2019,"lang":"en","type":"article","venue":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Spoofing attack; Computer science; Convolutional neural network; Speaker verification; Speech recognition; Mel-frequency cepstrum; Speaker recognition; Artificial intelligence; Frame (networking); Bottleneck; Pattern recognition (psychology); Classifier (UML); Replay attack; Biometrics; Feature extraction; Artificial neural network; Authentication (law); Computer security","score_opus":0.08200242944652283,"score_gpt":0.2663433709157091,"score_spread":0.18434094146918625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006824058","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06442361,0.0016434994,0.9054545,0.0010255344,0.0007530037,0.00050649175,0.00050123845,0.017175186,0.008516817],"genre_scores_gemma":[0.5109946,0.00071318645,0.4649783,0.0005679818,0.00020498109,0.00032697566,0.0029919466,0.00041932726,0.018802732],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999121,0.00011767312,0.00006178023,0.00020880102,0.00036802303,0.00012264936],"domain_scores_gemma":[0.9985031,0.0001789228,0.00008982624,0.00021568402,0.00090954575,0.00010290754],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017629401,0.00068746053,0.0007922367,0.000633535,0.00039554163,0.0008736469,0.0012335217,0.0013791997,0.0042291507],"category_scores_gemma":[0.0022039823,0.00036837324,0.00041234875,0.00023844324,0.0003349073,0.0013915959,0.0012535523,0.0017610808,0.004626061],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00073738815,0.00027097546,0.0025257785,0.00021476435,0.0001096246,0.00024858327,0.00015441203,0.013789613,0.19434929,0.007453563,0.01975349,0.76039255],"study_design_scores_gemma":[0.000090561385,0.0011118255,0.0041653337,0.00006377773,0.00010449549,0.0005573293,0.000081716214,0.6837923,0.25576323,0.0032088577,0.05097361,0.00008704313],"about_ca_topic_score_codex":0.0014136039,"about_ca_topic_score_gemma":0.0013483359,"teacher_disagreement_score":0.0042291507,"about_ca_system_score_codex":0.00066419283,"about_ca_system_score_gemma":0.00095658144,"threshold_uncertainty_score":0.014147937},"labels":[],"label_agreement":null},{"id":"W3010128010","doi":"10.1007/s11042-020-08748-2","title":"Mixture linear prediction Gammatone Cepstral features for robust speaker verification under transmission channel noise","year":2020,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Additive white Gaussian noise; Speech recognition; Linear prediction; Mel-frequency cepstrum; Channel (broadcasting); Cepstrum; Rayleigh fading; Ranging; Noise (video); Word error rate; Pattern recognition (psychology); Artificial intelligence; Fading; Feature extraction; Telecommunications","score_opus":0.05204491654214465,"score_gpt":0.2542930151035971,"score_spread":0.20224809856145243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3010128010","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12922761,0.0009999658,0.86600065,0.00012063298,0.000094242045,0.000042335214,0.00027485477,0.0017321546,0.0015075478],"genre_scores_gemma":[0.7759004,0.0005807502,0.21767612,0.00007699429,0.000057232035,0.000058741152,0.0009447389,0.00021724748,0.0044876253],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996309,0.00009638398,0.000020354646,0.00005894678,0.00015276819,0.00004063127],"domain_scores_gemma":[0.99936885,0.00030990917,0.000049373826,0.00008541118,0.00016651863,0.00002001295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056213525,0.00044644618,0.0005788471,0.0004929256,0.00022384388,0.00039141218,0.00045854735,0.0005425024,0.0017884116],"category_scores_gemma":[0.0015472723,0.00026015617,0.00032574966,0.00034360564,0.00015424009,0.00066333974,0.00059552764,0.0005506394,0.0014810405],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014619934,0.00015264207,0.0014412104,0.000103846935,0.00008386123,0.00017962865,0.00007231703,0.042119667,0.25918636,0.0018723019,0.0024634523,0.6908627],"study_design_scores_gemma":[0.000023843462,0.00014679777,0.0043125264,0.0000151305385,0.000073053096,0.00019912471,0.000029055134,0.9158677,0.07711016,0.00065329653,0.0015394695,0.000029831202],"about_ca_topic_score_codex":0.0015048118,"about_ca_topic_score_gemma":0.0020135513,"teacher_disagreement_score":0.0017884116,"about_ca_system_score_codex":0.00014134718,"about_ca_system_score_gemma":0.00034172367,"threshold_uncertainty_score":0.005982816},"labels":[],"label_agreement":null},{"id":"W3012387963","doi":"10.1017/cbo9781139029377.006","title":"Computational Models of Spoken Word Recognition","year":2018,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":72,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Word (group theory); Computer science; Natural language processing; Artificial intelligence; Speech recognition; Linguistics; Philosophy","score_opus":0.05256983140844455,"score_gpt":0.20766540037962772,"score_spread":0.15509556897118315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012387963","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013813221,0.02298795,0.87318325,0.0039081564,0.00092179386,0.00006210915,0.0020399038,0.0020096123,0.081074014],"genre_scores_gemma":[0.58613116,0.023999285,0.25853676,0.0011738719,0.001709569,0.0006843576,0.007584723,0.0010576879,0.11912256],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995553,0.00015307266,0.000028620096,0.0001241146,0.000097808166,0.0000411213],"domain_scores_gemma":[0.99833137,0.0011352097,0.00006200984,0.0002589316,0.00016352585,0.000048930342],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008051037,0.00081069436,0.00097160536,0.0008827144,0.0004415902,0.0029851699,0.0020029023,0.000993141,0.014092909],"category_scores_gemma":[0.0043214164,0.0007314438,0.0008692627,0.0013113117,0.0012217694,0.0037734897,0.0011492786,0.0018494767,0.005869121],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000114719565,0.000057408895,0.0008085038,0.000423491,0.0001908485,0.00016621767,0.00035392822,0.08720664,0.0020255174,0.64092046,0.042501897,0.22523038],"study_design_scores_gemma":[0.000014219138,0.000020540609,0.00046308694,0.000070222515,0.000027859482,0.00015663407,0.000060499002,0.22445954,0.00060429436,0.75463045,0.019468782,0.000023949884],"about_ca_topic_score_codex":0.0027796663,"about_ca_topic_score_gemma":0.0040321043,"teacher_disagreement_score":0.014092909,"about_ca_system_score_codex":0.0009481,"about_ca_system_score_gemma":0.0008501679,"threshold_uncertainty_score":0.047145545},"labels":[],"label_agreement":null},{"id":"W3014279133","doi":"10.3233/jifs-179715","title":"Foreign accent classification using deep neural nets","year":2020,"lang":"en","type":"article","venue":"Journal of Intelligent & Fuzzy Systems","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Stress (linguistics); Convolutional neural network; Computer science; Architecture; Speech recognition; Spectrogram; Cascade; Deep learning; Artificial intelligence; Identification (biology); Artificial neural network; Convolution (computer science); Natural language processing; History; Engineering","score_opus":0.13553378409866199,"score_gpt":0.2953088282515196,"score_spread":0.15977504415285762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3014279133","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6490611,0.00471099,0.3170061,0.000677229,0.0007707058,0.00014120757,0.003499959,0.0064535365,0.017679192],"genre_scores_gemma":[0.94735235,0.00061701075,0.037133984,0.0001778533,0.00009966909,0.000038837676,0.004197002,0.000055216366,0.01032813],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997898,0.000031638705,0.000015043017,0.000060030266,0.000037196478,0.00006631375],"domain_scores_gemma":[0.9998306,0.000035782687,0.00001910832,0.000018381761,0.00007507261,0.000021044947],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003917162,0.00080507493,0.00040149977,0.0007248776,0.0002733026,0.0006134067,0.00048392976,0.00041124233,0.0022570773],"category_scores_gemma":[0.00046012297,0.00019423112,0.0006028466,0.00041630314,0.000118268064,0.0004906885,0.0004965414,0.0006067719,0.0013952671],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009225334,0.00046446634,0.016976703,0.00014167342,0.00024724074,0.0004164228,0.00012988811,0.11566151,0.049186863,0.0016486795,0.016882563,0.7973214],"study_design_scores_gemma":[0.000019011268,0.00015025867,0.007462282,0.000029418055,0.00006499469,0.00008355796,0.000116154544,0.97100306,0.01615276,0.0013975775,0.0034957237,0.000025170037],"about_ca_topic_score_codex":0.008613495,"about_ca_topic_score_gemma":0.01176681,"teacher_disagreement_score":0.008613495,"about_ca_system_score_codex":0.00050136924,"about_ca_system_score_gemma":0.00036302448,"threshold_uncertainty_score":0.017126739},"labels":[],"label_agreement":null},{"id":"W3015280134","doi":"10.1109/icassp40776.2020.9053831","title":"Improving Speech Recognition Using Consistent Predictions on Synthesized Speech","year":2020,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Speech recognition; Computer science; Audio mining; Voice activity detection; Acoustic model; Speech processing; Point (geometry); Speech synthesis; Speech coding; Natural language processing; Mathematics","score_opus":0.0889213252948868,"score_gpt":0.2574665341658127,"score_spread":0.16854520887092592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015280134","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36905336,0.0008354258,0.61158824,0.0005778724,0.00030352577,0.00012602679,0.0010173013,0.011839569,0.004658736],"genre_scores_gemma":[0.8421433,0.0003701617,0.15134415,0.00018212492,0.00008441243,0.00009658036,0.002041084,0.0005860228,0.0031520687],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983089,0.00059583463,0.00007735343,0.00055684405,0.0003504803,0.00011058345],"domain_scores_gemma":[0.995644,0.0030006932,0.00018656965,0.0004615191,0.00063671905,0.00007047766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016945315,0.0012254717,0.0007538871,0.00036361537,0.00024548202,0.0008673072,0.0006727653,0.0006660346,0.0031651484],"category_scores_gemma":[0.007402811,0.0005178884,0.0004706059,0.00024612393,0.00044720736,0.0012011755,0.00085009943,0.0011154998,0.0030096164],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00093716255,0.0002469815,0.004822471,0.00032595824,0.00013941227,0.0003815449,0.00045955516,0.11245203,0.53350407,0.0008199635,0.0028017904,0.343109],"study_design_scores_gemma":[0.00007383777,0.000681399,0.008029076,0.00004893811,0.00011563281,0.00021150752,0.00028498154,0.7045006,0.28072307,0.0009678724,0.0042735315,0.00008956578],"about_ca_topic_score_codex":0.002767372,"about_ca_topic_score_gemma":0.006278209,"teacher_disagreement_score":0.0031651484,"about_ca_system_score_codex":0.0003415589,"about_ca_system_score_gemma":0.0008062553,"threshold_uncertainty_score":0.010588527},"labels":[],"label_agreement":null},{"id":"W3015774894","doi":"10.1109/icassp40776.2020.9054558","title":"An Ensemble Based Approach for Generalized Detection of Spoofing Attacks to Automatic Speaker Recognizers","year":2020,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Spoofing attack; Computer science; Speech recognition; Speaker verification; Spotting; Replay attack; A priori and a posteriori; Speaker recognition; Artificial intelligence; Speech synthesis; Machine learning; Authentication (law); Computer security","score_opus":0.05890024659451769,"score_gpt":0.27698860753137416,"score_spread":0.21808836093685646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015774894","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037237685,0.0005213237,0.9581012,0.000104017745,0.00008345412,0.000055034434,0.00009472116,0.0026549136,0.0011477],"genre_scores_gemma":[0.6567249,0.0006637405,0.33490232,0.00022909565,0.00024371597,0.00013087188,0.0010056612,0.00023782396,0.0058619324],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984712,0.00039655363,0.000090786016,0.00037053658,0.00047711266,0.00019387402],"domain_scores_gemma":[0.99793917,0.0006433569,0.00015191377,0.00043091664,0.0007286168,0.00010597526],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016586083,0.0017314621,0.0017514018,0.0014393101,0.0004566157,0.0007265042,0.0013411626,0.0012285748,0.0010123546],"category_scores_gemma":[0.0033515352,0.00045360258,0.0009564301,0.0007722924,0.0003256804,0.0013967155,0.0013945524,0.0019698292,0.0010631274],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035035567,0.0002551297,0.0034628974,0.0000608936,0.00035893408,0.00019728116,0.00015604022,0.18086152,0.032089774,0.0016209153,0.0028584169,0.77772784],"study_design_scores_gemma":[0.0000036223726,0.00010381508,0.0009805151,0.000007016683,0.000045219007,0.00008228756,0.000017474911,0.9898797,0.007147788,0.0010159583,0.0007004295,0.00001612258],"about_ca_topic_score_codex":0.0032019096,"about_ca_topic_score_gemma":0.00555326,"teacher_disagreement_score":0.0032019096,"about_ca_system_score_codex":0.0003379728,"about_ca_system_score_gemma":0.00064986234,"threshold_uncertainty_score":0.008771658},"labels":[],"label_agreement":null},{"id":"W3025427857","doi":"10.48550/arxiv.2005.08520","title":"Robust Training of Vector Quantized Bottleneck Models","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Infrastruktura PL-Grid; Johns Hopkins University; Canadian Institute for Advanced Research","keywords":"Bottleneck; Computer science; Training (meteorology); Artificial intelligence; Machine learning","score_opus":0.3594836041480978,"score_gpt":0.20217616659545884,"score_spread":0.15730743755263898,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3025427857","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010852634,0.00021130643,0.9867928,0.00011144946,0.00003829424,0.000028267497,0.000089881745,0.001072322,0.0008030758],"genre_scores_gemma":[0.63531476,0.00028293824,0.35673723,0.0003079986,0.000069549715,0.0003128211,0.00100142,0.0006057118,0.0053675296],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988563,0.00045209847,0.000055749853,0.00030864237,0.00021566899,0.00011157198],"domain_scores_gemma":[0.9972932,0.0017225163,0.00014754475,0.0003839592,0.0003514092,0.000101345606],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024152098,0.0009708862,0.0012838342,0.00050589617,0.00038740315,0.0011077541,0.0027083033,0.0013598962,0.0035465169],"category_scores_gemma":[0.0103424145,0.00095826987,0.0006642669,0.0005501597,0.001071,0.0024121774,0.0024596972,0.0025511782,0.0013252401],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016373656,0.00008319056,0.00064770126,0.00011364742,0.000058288166,0.000053135183,0.00010543477,0.8807222,0.0052708793,0.022795467,0.0021473859,0.087838896],"study_design_scores_gemma":[0.00000410299,0.000010905002,0.00002546561,0.000003679994,0.000001470399,0.0000053428266,0.0000034261104,0.9953993,0.0007326126,0.0035996344,0.00021157597,0.0000026232046],"about_ca_topic_score_codex":0.0034906387,"about_ca_topic_score_gemma":0.0040493696,"teacher_disagreement_score":0.0035465169,"about_ca_system_score_codex":0.0010209369,"about_ca_system_score_gemma":0.0014361324,"threshold_uncertainty_score":0.012772977},"labels":[],"label_agreement":null},{"id":"W3028638700","doi":"","title":"Developing Resources for Automated Speech Processing of Quebec French","year":2020,"lang":"en","type":"preprint","venue":"SERVAL (Université de Lausanne)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Syllabification; Phonotactics; Computer science; Lexicon; Speech segmentation; Pronunciation; Phonetic transcription; Segmentation; Speech recognition; Natural language processing; Artificial intelligence; Speech processing; Phonology; Process (computing); Software; Linguistics; Syllable","score_opus":0.038236760357029165,"score_gpt":0.25135523636217255,"score_spread":0.2131184760051434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3028638700","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19598408,0.0030269213,0.54268706,0.0019529242,0.00037189695,0.0031503185,0.09155842,0.08982973,0.07143868],"genre_scores_gemma":[0.37974718,0.0015507301,0.3903904,0.00039102804,0.00021874731,0.0020903223,0.16554864,0.0069669047,0.053096056],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987758,0.00035135116,0.00006259889,0.0003082251,0.0002631373,0.00023890453],"domain_scores_gemma":[0.9958788,0.0013159126,0.00014304195,0.00045705377,0.0020057799,0.00019942688],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015549873,0.0022763296,0.000941172,0.0048544584,0.0021244425,0.0022376466,0.0017843863,0.0010499216,0.04058482],"category_scores_gemma":[0.0056589907,0.00059650984,0.00086908706,0.0027961484,0.00076670805,0.002033849,0.001627605,0.0009092136,0.015831254],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017461331,0.00021308396,0.0057555204,0.0011802248,0.00019642555,0.0013681436,0.0019400581,0.031629823,0.10499352,0.0072876136,0.12147698,0.72221255],"study_design_scores_gemma":[0.00036355277,0.00043029911,0.026319018,0.0005575334,0.00057099666,0.00064040505,0.0035353221,0.3452103,0.19404452,0.0052702427,0.4227694,0.0002884534],"about_ca_topic_score_codex":0.6681621,"about_ca_topic_score_gemma":0.6216085,"teacher_disagreement_score":0.3318379,"about_ca_system_score_codex":0.005966236,"about_ca_system_score_gemma":0.009325682,"threshold_uncertainty_score":0.6675843},"labels":[],"label_agreement":null},{"id":"W3029693316","doi":"","title":"Speech Transcription Challenges for Resource Constrained Indigenous Language Cree","year":2020,"lang":"en","type":"article","venue":"Workshop Spoken Language Technologies for Under-resourced Languages","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Word error rate; Transcription (linguistics); Speech recognition; Natural language processing; Word (group theory); Language model; Documentation; Artificial intelligence; Spoken language; Error analysis; Linguistics","score_opus":0.04157063800353791,"score_gpt":0.2814875973299665,"score_spread":0.23991695932642856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3029693316","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.72755617,0.0032282548,0.21896735,0.009161358,0.00074416306,0.000395151,0.006477325,0.011637233,0.0218329],"genre_scores_gemma":[0.8831086,0.0015497337,0.0884839,0.0015403997,0.00025585754,0.00031497978,0.008326894,0.001217337,0.015202462],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99755543,0.0006656584,0.00020769949,0.0005820958,0.00075288827,0.00023617232],"domain_scores_gemma":[0.99167496,0.0041840198,0.00017066629,0.00086646125,0.0028392754,0.000264549],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023715296,0.00050094834,0.0008586257,0.00056122243,0.0014891125,0.0021928542,0.0012957285,0.0017316566,0.004600545],"category_scores_gemma":[0.012679274,0.00033099324,0.00040639215,0.00080870796,0.000971753,0.001482107,0.0014279208,0.0014814825,0.0034634827],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013641465,0.00029710247,0.0106938025,0.0019272732,0.00022474323,0.0045146695,0.021381084,0.047583263,0.24633618,0.0045360043,0.035369232,0.6257726],"study_design_scores_gemma":[0.00045182722,0.0008256621,0.049768053,0.0008033625,0.0004323281,0.009776888,0.06214437,0.3343771,0.27606755,0.012208327,0.25230646,0.0008381027],"about_ca_topic_score_codex":0.105959356,"about_ca_topic_score_gemma":0.15416518,"teacher_disagreement_score":0.105959356,"about_ca_system_score_codex":0.0014403812,"about_ca_system_score_gemma":0.0031992549,"threshold_uncertainty_score":0.2106852},"labels":[],"label_agreement":null},{"id":"W3030267806","doi":"","title":"On The Performance of Time-Pooling Strategies for End-to-End Spoken Language Identification.","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Pooling; Computer science; Benchmark (surveying); Artificial intelligence; Dimension (graph theory); Representation (politics); Set (abstract data type); Spoken language; Identification (biology); Machine learning; Selection (genetic algorithm); Language model; Natural language processing; Test set; Mathematics","score_opus":0.0337936629644121,"score_gpt":0.28381202723240906,"score_spread":0.25001836426799695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3030267806","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44809765,0.009066168,0.51527435,0.00072534557,0.00071212114,0.00037080713,0.001971234,0.0108594345,0.0129229305],"genre_scores_gemma":[0.81299096,0.000981932,0.16959393,0.00043836256,0.00014890333,0.0002018616,0.0041782865,0.0004376133,0.011028305],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977842,0.0008316992,0.00018400654,0.00038368747,0.00052809075,0.00028831555],"domain_scores_gemma":[0.9956117,0.0031316748,0.000108556655,0.00028912324,0.0006953469,0.00016356229],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004529137,0.0017912817,0.0012485118,0.0009858542,0.0007086286,0.0015701199,0.0016306954,0.0017966118,0.005151122],"category_scores_gemma":[0.010193691,0.00042177847,0.0005805491,0.00053354405,0.0005035213,0.0029064144,0.0016960875,0.0011592562,0.0024025626],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008110458,0.0009206165,0.0036248646,0.0006567977,0.0008312168,0.00043860113,0.00025346066,0.09053636,0.07906456,0.0032465558,0.012195159,0.8001214],"study_design_scores_gemma":[0.00014931834,0.0011496574,0.0044236295,0.00004311497,0.0002502191,0.0003913434,0.0002690087,0.91046286,0.07875666,0.0020143776,0.0020238399,0.00006593536],"about_ca_topic_score_codex":0.013417034,"about_ca_topic_score_gemma":0.016990686,"teacher_disagreement_score":0.013417034,"about_ca_system_score_codex":0.00068163837,"about_ca_system_score_gemma":0.001427782,"threshold_uncertainty_score":0.026677907},"labels":[],"label_agreement":null},{"id":"W3035183237","doi":"10.1109/access.2020.3001426","title":"Multi-Objective Optimization of Wavelet-Packet-Based Features in Pathological Diagnosis of Alzheimer Using Spontaneous Speech Signals","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Wavelet packet decomposition; Computer science; Wavelet; Pattern recognition (psychology); Entropy (arrow of time); Feature selection; Artificial intelligence; Speech recognition; Network packet; Frequency band; Wavelet transform; Feature extraction; Bandwidth (computing)","score_opus":0.10267228334105753,"score_gpt":0.3261930617415912,"score_spread":0.22352077840053364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035183237","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44269934,0.0002211823,0.55560815,0.00013646967,0.000023695633,0.000088231514,0.000056847206,0.00021160554,0.0009544957],"genre_scores_gemma":[0.91629386,0.00008975226,0.08279745,0.00003083775,0.000008996981,0.00010070314,0.00009717944,0.000018291475,0.00056298956],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9998136,0.000072246636,0.0000140753045,0.000030422583,0.000037232425,0.00003243363],"domain_scores_gemma":[0.99952805,0.00030776675,0.000048297698,0.000011680265,0.00008668609,0.000017508773],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001040378,0.00054809486,0.00042932123,0.0004974541,0.00017377894,0.00049283984,0.00039147245,0.0004830601,0.00038332999],"category_scores_gemma":[0.001521336,0.00023453622,0.0004454419,0.0003172038,0.00027158333,0.00027219404,0.00027282775,0.00036706988,0.00006024875],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014455323,0.00018245936,0.0020257763,0.000074069285,0.000061075734,0.00006396923,0.000060306753,0.9336185,0.01124337,0.0007397819,0.00020440268,0.051581778],"study_design_scores_gemma":[0.000006103022,0.000050072867,0.0004750906,0.0000025516358,0.000008426709,0.000006821424,0.000011182159,0.99808383,0.0011883508,0.00012881643,0.000036783968,0.0000019485456],"about_ca_topic_score_codex":0.0022656885,"about_ca_topic_score_gemma":0.0014877064,"teacher_disagreement_score":0.0022656885,"about_ca_system_score_codex":0.00034736184,"about_ca_system_score_gemma":0.0006746906,"threshold_uncertainty_score":0.0055021644},"labels":[],"label_agreement":null},{"id":"W3039097787","doi":"10.5573/ieiespc.2020.9.3.185","title":"Adaptive Feature Generation for Speech Emotion Recognition","year":2020,"lang":"en","type":"article","venue":"IEIE Transactions on Smart Processing and Computing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Speech recognition; Mel-frequency cepstrum; Artificial intelligence; Classifier (UML); Feature (linguistics); Principal component analysis; Pattern recognition (psychology); Emotion recognition; Correlation; Emotion classification; Cepstrum; Sentiment analysis; Feature extraction; Mathematics","score_opus":0.07397113750810175,"score_gpt":0.2624858273158806,"score_spread":0.18851468980777886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3039097787","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008951604,0.00016428264,0.9886008,0.000054223925,0.000041857187,0.000053308017,0.00010311691,0.0015909167,0.000439917],"genre_scores_gemma":[0.262639,0.00021115899,0.7337923,0.00012130699,0.00007747884,0.00025917153,0.00086461066,0.0002198455,0.0018151454],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996885,0.00007164988,0.000024519686,0.00009188321,0.00009041367,0.000032923992],"domain_scores_gemma":[0.99948716,0.000245374,0.00003178446,0.00006606104,0.00015601443,0.0000135506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004923177,0.00066039775,0.00048430153,0.0006819369,0.00022451975,0.00033032306,0.0006687081,0.00045627175,0.0026327819],"category_scores_gemma":[0.0019026272,0.00016632877,0.00052897225,0.0006239352,0.00019894056,0.0004790983,0.00043558012,0.00054749724,0.0010262482],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023619512,0.00009218835,0.0004951906,0.000081723745,0.000032826785,0.000108408756,0.000067525856,0.028868875,0.08310732,0.0024850653,0.004401449,0.88002336],"study_design_scores_gemma":[0.000031564912,0.0001120529,0.0013194669,0.000010960902,0.00002679876,0.00016472986,0.000028479453,0.94084585,0.04829666,0.004067883,0.005071662,0.000023868432],"about_ca_topic_score_codex":0.0012351301,"about_ca_topic_score_gemma":0.0011813022,"teacher_disagreement_score":0.0026327819,"about_ca_system_score_codex":0.00030173964,"about_ca_system_score_gemma":0.0002387681,"threshold_uncertainty_score":0.00880748},"labels":[],"label_agreement":null},{"id":"W3082696729","doi":"10.21437/interspeech.2020-3132","title":"Neural Architecture Search for Keyword Spotting","year":2020,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Keyword spotting; Computer science; Convolutional neural network; Spotting; Artificial intelligence; Memory footprint; Architecture; Artificial neural network; Utterance; Speech recognition","score_opus":0.061623679488180434,"score_gpt":0.2687005166181165,"score_spread":0.20707683712993608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3082696729","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3083315,0.0031670467,0.66668224,0.0008586413,0.00015603681,0.00011660733,0.00091607834,0.011405701,0.008366175],"genre_scores_gemma":[0.8296053,0.00038318706,0.1614077,0.00026274435,0.000047931648,0.00006500576,0.001229771,0.00027799013,0.00672034],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99972683,0.000050605442,0.000023416807,0.00007379632,0.000073752555,0.00005167052],"domain_scores_gemma":[0.99960476,0.00016331741,0.000035738663,0.000053167736,0.000116897376,0.000026122889],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003992654,0.0009320199,0.0008160244,0.0007739109,0.00029721172,0.00052610884,0.0008243883,0.000871005,0.004612601],"category_scores_gemma":[0.0019363537,0.0002808095,0.00041880927,0.0006164429,0.00031552443,0.0010596284,0.0006778137,0.0006666137,0.0012258388],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00057734543,0.00013243526,0.0033518998,0.00030197468,0.00008485658,0.00032529785,0.0001554471,0.13523652,0.041127972,0.0062168944,0.015072184,0.7974171],"study_design_scores_gemma":[0.000041384286,0.00012501572,0.00049326697,0.000011952594,0.00002700032,0.000110713976,0.00008278614,0.97620934,0.014364243,0.006269749,0.0022531427,0.000011282177],"about_ca_topic_score_codex":0.0039270795,"about_ca_topic_score_gemma":0.008790511,"teacher_disagreement_score":0.004612601,"about_ca_system_score_codex":0.0006021911,"about_ca_system_score_gemma":0.0008598763,"threshold_uncertainty_score":0.015430689},"labels":[],"label_agreement":null},{"id":"W3082779874","doi":"","title":"Knowing What to Listen to: Early Attention for Deep Speech Representation Learning.","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Robustness (evolution); Speech recognition; Deep learning; Speaker recognition; Artificial intelligence; Deep neural networks; Speech processing; Task (project management); Emotion recognition; Feature learning","score_opus":0.12312090177717262,"score_gpt":0.23271275799311855,"score_spread":0.10959185621594593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3082779874","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05987217,0.0044699674,0.91954005,0.0018311309,0.00050162314,0.000113707516,0.0008461941,0.00527543,0.007549725],"genre_scores_gemma":[0.8196481,0.0015086369,0.16364498,0.0008970735,0.0002443323,0.00015534335,0.002160926,0.00029532224,0.011445271],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996407,0.00008759491,0.000013559689,0.00013278317,0.00006456072,0.000060737748],"domain_scores_gemma":[0.9993129,0.00033326467,0.000046214733,0.000120743076,0.000120055854,0.00006676802],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009956871,0.001142042,0.00044609696,0.0006004608,0.00033277142,0.00070227415,0.0016330347,0.0011945389,0.0036382244],"category_scores_gemma":[0.0028920195,0.0003442519,0.0005998356,0.00050359976,0.00047874657,0.001892033,0.0016106816,0.002231785,0.0014639623],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005965462,0.0002945796,0.0032726135,0.0002251188,0.00013889963,0.00017453496,0.00021627467,0.09910794,0.03365165,0.012682283,0.020805167,0.8288345],"study_design_scores_gemma":[0.00001946077,0.0000818363,0.0011321473,0.00002802463,0.000055095294,0.00007558068,0.000028758464,0.9594343,0.013713212,0.019954966,0.0054626726,0.000014014447],"about_ca_topic_score_codex":0.006634667,"about_ca_topic_score_gemma":0.012663732,"teacher_disagreement_score":0.006634667,"about_ca_system_score_codex":0.0011111324,"about_ca_system_score_gemma":0.0008828578,"threshold_uncertainty_score":0.013192058},"labels":[],"label_agreement":null},{"id":"W3086122814","doi":"","title":"Voice Biometrics Distinction Between English, French, Arabic and Spanish Using Sound Cleaner Filtering and SpeechPro SIS II Analysis for Same Individual Identification in Multilingual Societies","year":2020,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"CLIPS; Identity (music); Computer science; Biometrics; Tone (literature); Arabic; Identification (biology); Isolation (microbiology); Speech recognition; Linguistics; Natural language processing; Artificial intelligence; Acoustics","score_opus":0.10400442122408006,"score_gpt":0.2957507449012484,"score_spread":0.19174632367716837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3086122814","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9919857,0.000066899156,0.006230907,0.00004084735,0.000016328091,0.000019805,0.00006667488,0.0000479858,0.0015248496],"genre_scores_gemma":[0.9938818,0.000039648512,0.004984017,0.00002016595,0.000004826801,0.000014331911,0.0000606394,0.000008101771,0.000986516],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999527,0.00015075975,0.000029958162,0.000098375276,0.00013357082,0.00006048086],"domain_scores_gemma":[0.99931574,0.00022932158,0.00006520642,0.00006692969,0.00025779754,0.00006506454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007164249,0.0001886812,0.00021882715,0.0007948747,0.00034010058,0.00046910305,0.00012479287,0.00029706213,0.0017915366],"category_scores_gemma":[0.001984299,0.0000580483,0.00016169067,0.0002534133,0.00022856289,0.00029532603,0.00036084605,0.00017368105,0.00053411396],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029179489,0.0004148523,0.13857716,0.00019701244,0.00010099426,0.0010683332,0.003943687,0.0037597907,0.47948515,0.0011176002,0.0012810563,0.36713648],"study_design_scores_gemma":[0.000069998394,0.0022441982,0.6732888,0.00006525389,0.00022712292,0.0033823375,0.010371408,0.052869923,0.24886218,0.00093063136,0.0075624194,0.00012563966],"about_ca_topic_score_codex":0.0024170785,"about_ca_topic_score_gemma":0.0034973694,"teacher_disagreement_score":0.0024170785,"about_ca_system_score_codex":0.0001894161,"about_ca_system_score_gemma":0.0002581004,"threshold_uncertainty_score":0.0059933066},"labels":[],"label_agreement":null},{"id":"W3088605365","doi":"10.1109/icassp39728.2021.9414722","title":"Siamese Capsule Network for End-to-End Speaker Recognition in the Wild","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Similarity (geometry); Feature (linguistics); End-to-end principle; Routing (electronic design automation); Adaptive routing; Pattern recognition (psychology); Speaker verification; Artificial intelligence; Speech recognition; Network model; Speaker recognition; Image (mathematics); Computer network; Routing protocol; Link-state routing protocol","score_opus":0.05773507453495559,"score_gpt":0.2757500919791833,"score_spread":0.21801501744422774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088605365","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013480084,0.000151145,0.974942,0.00023237725,0.00011344046,0.00007371103,0.00035124324,0.007913449,0.0027425892],"genre_scores_gemma":[0.45006707,0.00031948835,0.52110255,0.00066945696,0.00012434655,0.000328698,0.0042497166,0.0008517138,0.022286905],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994622,0.000102915656,0.000023332466,0.00019159542,0.00014711426,0.000072849485],"domain_scores_gemma":[0.99934477,0.00016162594,0.00003451917,0.00023852824,0.00017513905,0.000045455065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011859884,0.0012502893,0.0006749903,0.00043857767,0.00042340014,0.001128481,0.0021759889,0.0013300742,0.008732444],"category_scores_gemma":[0.002565113,0.0005404647,0.00061156496,0.00040111493,0.0007583231,0.0027860063,0.002180135,0.0023091268,0.0051679984],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00103985,0.00043064132,0.0018998025,0.00014826645,0.00024202137,0.000364829,0.00015044927,0.33146515,0.050856687,0.022304842,0.031630725,0.5594667],"study_design_scores_gemma":[0.000011466288,0.000053381937,0.00016764125,0.000004339024,0.000011187829,0.0000455427,0.000012512304,0.9832667,0.008886047,0.0051941606,0.0023336627,0.000013368107],"about_ca_topic_score_codex":0.0069879186,"about_ca_topic_score_gemma":0.013512272,"teacher_disagreement_score":0.008732444,"about_ca_system_score_codex":0.0007116866,"about_ca_system_score_gemma":0.0015071371,"threshold_uncertainty_score":0.029212892},"labels":[],"label_agreement":null},{"id":"W3089020900","doi":"10.18280/ria.340201x","title":"Retraction: MFCC-Based Feature Extraction Model for Long Time Period Emotion Speech Using CNN","year":2020,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":true,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mel-frequency cepstrum; Period (music); Computer science; Speech recognition; Feature extraction; Feature (linguistics); Emotion recognition; Artificial intelligence; Pattern recognition (psychology); Acoustics; Linguistics","score_opus":0.09829718061852849,"score_gpt":0.3027681411727362,"score_spread":0.20447096055420771,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3089020900","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000569654,0.0019473787,0.0017113994,0.077256694,0.9151849,0.00003953172,0.0012203591,0.000467863,0.0016021985],"genre_scores_gemma":[0.022552432,0.008285168,0.005990376,0.12085273,0.6652278,0.00041248847,0.0030744872,0.00092742045,0.1726771],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984321,0.00020234846,0.00044628116,0.00022919594,0.00053614774,0.00015380212],"domain_scores_gemma":[0.9830972,0.0044979723,0.00064166315,0.0009385372,0.01018583,0.0006388852],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0024728053,0.0016164983,0.0014620099,0.002056294,0.0016072101,0.0016253553,0.0023749198,0.00790323,0.01633251],"category_scores_gemma":[0.045435295,0.00073774875,0.0016402066,0.0008319007,0.0017848553,0.0015623658,0.0012887911,0.010466754,0.0179677],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000103542756,0.00001361491,0.00011576361,0.00024877043,0.00003320443,0.0005532227,0.000047588463,0.00010502007,0.00038065398,0.0005564595,0.9839716,0.013870546],"study_design_scores_gemma":[0.00010339979,0.0000838978,0.0028579005,0.00033601717,0.0001178862,0.001478188,0.00007990208,0.0011513643,0.0016325366,0.0015547517,0.99053216,0.000071851166],"about_ca_topic_score_codex":0.015423407,"about_ca_topic_score_gemma":0.011044908,"teacher_disagreement_score":0.9920968,"about_ca_system_score_codex":0.0021205049,"about_ca_system_score_gemma":0.0028187302,"threshold_uncertainty_score":0.05463767},"labels":[],"label_agreement":null},{"id":"W3095018479","doi":"10.48550/arxiv.2010.14230","title":"A Comparison of Discrete Latent Variable Models for Speech Representation Learning","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Latent variable; Speech recognition; Representation (politics); Variable (mathematics); Word (group theory); Word error rate; Latent variable model; Artificial intelligence; Encoding (memory); Pattern recognition (psychology); Mathematics","score_opus":0.22747979670419097,"score_gpt":0.2623826478792052,"score_spread":0.03490285117501421,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095018479","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058835242,0.00887713,0.9230778,0.0018670089,0.00036059288,0.00010593153,0.001172614,0.0026163796,0.0030874],"genre_scores_gemma":[0.66038847,0.0069789905,0.32067278,0.0005170534,0.00027042115,0.0003667668,0.0057858275,0.0005222366,0.0044974573],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99705935,0.0015615636,0.0001825589,0.0004674872,0.0005980136,0.00013106795],"domain_scores_gemma":[0.99207777,0.005889337,0.00019533666,0.000902438,0.00075141015,0.00018362873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0060303,0.0010230215,0.000937165,0.0014500294,0.00030504138,0.0020862978,0.0018092893,0.0014751253,0.0022510053],"category_scores_gemma":[0.015221258,0.00049436896,0.0012201646,0.0015037826,0.00055679824,0.0036279508,0.0016236958,0.0027056283,0.001196383],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015798896,0.00037315115,0.0051558083,0.00057667086,0.00062075903,0.000060245544,0.00026886145,0.3691659,0.0032253133,0.033412974,0.006540316,0.57902014],"study_design_scores_gemma":[0.000034198325,0.00012097182,0.00075719814,0.000040524887,0.000027622584,0.000024818715,0.000037038615,0.9870798,0.00074589375,0.009945606,0.001164403,0.000021802989],"about_ca_topic_score_codex":0.0067524817,"about_ca_topic_score_gemma":0.0063771703,"teacher_disagreement_score":0.0067524817,"about_ca_system_score_codex":0.0015651025,"about_ca_system_score_gemma":0.0011207077,"threshold_uncertainty_score":0.031891704},"labels":[],"label_agreement":null},{"id":"W3097523643","doi":"10.3390/app10217522","title":"Robust Deep Speaker Recognition: Learning Latent Representation with Joint Angular Margin Loss","year":2020,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Softmax function; Speaker recognition; Speech recognition; Artificial intelligence; Biometrics; TIMIT; Pattern recognition (psychology); Codebook; Machine learning; Convolutional neural network; Hidden Markov model","score_opus":0.10564192273135432,"score_gpt":0.23738835881611736,"score_spread":0.13174643608476305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3097523643","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029100524,0.0007233562,0.9644457,0.00026798304,0.0001103751,0.000056286517,0.00023647389,0.0025996906,0.0024595167],"genre_scores_gemma":[0.71578324,0.00085396116,0.25973728,0.0004985212,0.00017141228,0.0001952563,0.002381889,0.00045688846,0.01992158],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993488,0.00018342276,0.000028519757,0.00017220936,0.00018274214,0.000084364285],"domain_scores_gemma":[0.9994394,0.00019317883,0.000069026086,0.00011397442,0.00014900083,0.000035330333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017098165,0.0010906289,0.0007875474,0.00055110623,0.0002875394,0.00070923805,0.0016465114,0.0008116737,0.002934003],"category_scores_gemma":[0.0023977081,0.0004030166,0.0009334503,0.00056596356,0.0005436681,0.0015748551,0.0014966212,0.0021955278,0.0014995],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005603814,0.00025522374,0.0015558884,0.00011417316,0.00019174202,0.00009054548,0.00008706519,0.37977317,0.01686379,0.010051393,0.01073275,0.5797239],"study_design_scores_gemma":[0.000006344939,0.000031110074,0.00017874822,0.000006034473,0.000011060262,0.000018466664,0.000005405347,0.9940142,0.0030885115,0.0019795902,0.0006535679,0.000006956003],"about_ca_topic_score_codex":0.0050100773,"about_ca_topic_score_gemma":0.006360719,"teacher_disagreement_score":0.0050100773,"about_ca_system_score_codex":0.00083796546,"about_ca_system_score_gemma":0.0011164679,"threshold_uncertainty_score":0.009961784},"labels":[],"label_agreement":null},{"id":"W3108699229","doi":"10.1121/1.5147765","title":"Developing a cross-platform federated code repository for speech research","year":2020,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Documentation; Scripting language; Python (programming language); Code (set theory); World Wide Web; Point (geometry); Open research; Open science; Source code; Data science; Process (computing); Open source; Set (abstract data type); Programming language; Software","score_opus":0.1147673965792893,"score_gpt":0.3587112357129718,"score_spread":0.2439438391336825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3108699229","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008224231,0.00053742743,0.82009244,0.0051646153,0.002000478,0.0028595263,0.0045756893,0.1464173,0.01012829],"genre_scores_gemma":[0.029707493,0.0005856264,0.87272364,0.0013491872,0.00068460556,0.0028210962,0.023647409,0.04930021,0.01918065],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.93707395,0.021197919,0.0097771725,0.0075005516,0.022249034,0.0022014254],"domain_scores_gemma":[0.5584721,0.06509582,0.020312062,0.1752082,0.1606291,0.020282784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11540747,0.0019213055,0.00255715,0.017878318,0.0042826836,0.014575584,0.010551415,0.0033781694,0.019524235],"category_scores_gemma":[0.25527993,0.002560508,0.0034605793,0.009478162,0.0033896384,0.021327008,0.020113539,0.008034286,0.030595977],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009124146,0.0011546889,0.008339965,0.0016931909,0.0003292753,0.0014615466,0.005512444,0.006187749,0.015726065,0.044919647,0.24704784,0.6667152],"study_design_scores_gemma":[0.0005140744,0.00097541104,0.0053207767,0.0028650844,0.00025630396,0.0018317768,0.0020351154,0.068088725,0.051696498,0.053757645,0.811841,0.0008175464],"about_ca_topic_score_codex":0.0029022705,"about_ca_topic_score_gemma":0.0034953458,"teacher_disagreement_score":0.11540747,"about_ca_system_score_codex":0.0039212587,"about_ca_system_score_gemma":0.02662215,"threshold_uncertainty_score":0.61034036},"labels":[],"label_agreement":null},{"id":"W3110458199","doi":"10.48550/arxiv.2011.11588","title":"The Zero Resource Speech Benchmark 2021: Metrics and baselines for\\n unsupervised spoken language modeling","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Benchmark (surveying); Computer science; Zero (linguistics); Spoken language; Speech recognition; Language model; Resource (disambiguation); Natural language processing; Artificial intelligence; Linguistics; Computer network","score_opus":0.09401508568117196,"score_gpt":0.20319821575805327,"score_spread":0.10918313007688131,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3110458199","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25634748,0.015230847,0.44575122,0.0029255524,0.003632071,0.004064725,0.11859257,0.09531092,0.058144644],"genre_scores_gemma":[0.3260782,0.0017415055,0.2848444,0.0011286585,0.00040426967,0.0054057813,0.3527777,0.0075949305,0.02002462],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.987906,0.004983707,0.0011891329,0.0020717261,0.0030316412,0.00081780966],"domain_scores_gemma":[0.98944515,0.0038939426,0.00053951994,0.0029358184,0.0026246225,0.00056090095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008466177,0.0050353366,0.0018012259,0.00429544,0.0017336236,0.0033694473,0.0040345774,0.004251027,0.008236106],"category_scores_gemma":[0.02916052,0.00070936343,0.001345929,0.0025535817,0.0016101189,0.0038822372,0.0052213166,0.003079782,0.007929441],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0039753914,0.0026488737,0.0093753645,0.0038300045,0.001086266,0.0007030098,0.0006885391,0.110916585,0.027939435,0.012946128,0.28187317,0.5440172],"study_design_scores_gemma":[0.0010123963,0.0038340085,0.021447115,0.00091422757,0.00047725902,0.0015530334,0.0013167507,0.6758769,0.11425414,0.034582328,0.14413673,0.00059506064],"about_ca_topic_score_codex":0.02022963,"about_ca_topic_score_gemma":0.023025157,"teacher_disagreement_score":0.02022963,"about_ca_system_score_codex":0.0024443052,"about_ca_system_score_gemma":0.0027978215,"threshold_uncertainty_score":0.044773936},"labels":[],"label_agreement":null},{"id":"W3111767470","doi":"10.1016/j.dib.2020.106652","title":"Audio recordings dataset of genuine and replayed speech at both ends of a telecommunication channel","year":2020,"lang":"en","type":"article","venue":"Data in Brief","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Channel (broadcasting); Telecommunications; Computer science; Speech recognition","score_opus":0.07590754986961774,"score_gpt":0.2846322564540964,"score_spread":0.20872470658447867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111767470","genre_codex":"empirical","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49821,0.0023570673,0.030834762,0.0005139819,0.0013160396,0.0022819852,0.434682,0.009698091,0.02010609],"genre_scores_gemma":[0.3770245,0.0010952393,0.027195621,0.00028684994,0.00035505218,0.0018569416,0.57700706,0.00036674223,0.014811962],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986368,0.00013189786,0.00015966008,0.00032368975,0.0005723659,0.00017560716],"domain_scores_gemma":[0.99824166,0.00029209457,0.0001287329,0.00036952464,0.0007954009,0.00017262531],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055602763,0.0011734784,0.001173089,0.0013273339,0.0006100758,0.00073912484,0.0011127383,0.0012511344,0.00760185],"category_scores_gemma":[0.0014422127,0.00022742403,0.0005776082,0.001259173,0.00040073635,0.0004996272,0.000774438,0.0006506422,0.008372714],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0071921344,0.0030470784,0.022577472,0.0065326756,0.0006270794,0.0061945347,0.0012089094,0.008684522,0.24261579,0.0013496105,0.22113737,0.47883275],"study_design_scores_gemma":[0.0010265458,0.0050995606,0.4383993,0.00064699113,0.0007942773,0.013727625,0.003777184,0.049686063,0.15046787,0.0014858029,0.33431396,0.0005747361],"about_ca_topic_score_codex":0.0040411013,"about_ca_topic_score_gemma":0.008664932,"teacher_disagreement_score":0.00760185,"about_ca_system_score_codex":0.00040911738,"about_ca_system_score_gemma":0.00073822873,"threshold_uncertainty_score":0.025430739},"labels":[],"label_agreement":null},{"id":"W3111804057","doi":"","title":"Towards End-to-End Speech Recognitionwith Recurrent Neural Networks","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Trigram; Word error rate; Connectionism; Speech recognition; Lexicon; Language model; Artificial intelligence; Recurrent neural network; Artificial neural network; Word (group theory); Natural language processing; Linguistics","score_opus":0.02795731698678126,"score_gpt":0.25350137254277816,"score_spread":0.2255440555559969,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111804057","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008797692,0.00026858124,0.98463887,0.00012997889,0.00007363169,0.000030165691,0.00015392934,0.004842341,0.001064796],"genre_scores_gemma":[0.19209115,0.00039752817,0.7958158,0.00026868106,0.00012503102,0.00013139089,0.0014631073,0.00061334745,0.009093884],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998703,0.000303623,0.00008400174,0.00037050864,0.00042345747,0.00011535664],"domain_scores_gemma":[0.99861586,0.00052230014,0.000090905225,0.00021939783,0.0005053766,0.000046110454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001561272,0.0013948939,0.0009246058,0.00041879152,0.00036326444,0.0013987023,0.0018371153,0.0014754041,0.0033610335],"category_scores_gemma":[0.0033227769,0.00067551766,0.00065049686,0.00035768925,0.00046034253,0.0020966898,0.0013473916,0.0020791306,0.004729808],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005698385,0.0002540819,0.00087616686,0.0003156298,0.00013851977,0.0003490543,0.00026281143,0.090266354,0.17966157,0.007647356,0.00862503,0.7110336],"study_design_scores_gemma":[0.000027113976,0.00015059837,0.00041760594,0.000036089943,0.000043827506,0.00014164581,0.00004841178,0.9110253,0.07506368,0.0071943384,0.0058152005,0.000036125344],"about_ca_topic_score_codex":0.0024357464,"about_ca_topic_score_gemma":0.0055209543,"teacher_disagreement_score":0.0033610335,"about_ca_system_score_codex":0.0004944932,"about_ca_system_score_gemma":0.0006122703,"threshold_uncertainty_score":0.01124382},"labels":[],"label_agreement":null},{"id":"W3119746889","doi":"10.48550/arxiv.2101.03027","title":"User-friendly automatic transcription of low-resource languages: Plugging ESPnet into Elpis","year":2020,"lang":"en","type":"preprint","venue":"SOAS Research Online (SOAS University of London)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; User Friendly; Front and back ends; Transcription (linguistics); Graphical user interface; Interface (matter); CUDA; User interface; Set (abstract data type); Speech recognition; Natural language processing; World Wide Web; Human–computer interaction; Programming language; Operating system","score_opus":0.04480315530894974,"score_gpt":0.31716670997572166,"score_spread":0.2723635546667719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3119746889","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025029864,0.00016356635,0.7260332,0.00024437153,0.0003975301,0.00019519914,0.0050807158,0.23458275,0.008272811],"genre_scores_gemma":[0.22902313,0.00023906656,0.6734083,0.00050014415,0.00022131705,0.00060186675,0.034169387,0.033407006,0.028429711],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99880075,0.00027114816,0.00009416747,0.00037227842,0.00035469886,0.00010691771],"domain_scores_gemma":[0.9982096,0.00078933424,0.000043565346,0.0004237499,0.00042062032,0.000113083894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017307642,0.0013023148,0.00075002474,0.0008133038,0.0003848084,0.0015756928,0.0018532559,0.0006440001,0.033259787],"category_scores_gemma":[0.005114913,0.0008759663,0.0006407974,0.00046117022,0.0005206701,0.0021953448,0.0025335262,0.0016300303,0.024977243],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027463767,0.00031664653,0.002532502,0.0006132639,0.00018322043,0.0012358447,0.0012867216,0.038009685,0.12212331,0.0060652634,0.09414203,0.73074514],"study_design_scores_gemma":[0.00033413814,0.00026499122,0.0031060074,0.00013417861,0.00006296602,0.0007024806,0.0006127265,0.5942931,0.21044552,0.013435263,0.17641182,0.00019685713],"about_ca_topic_score_codex":0.0040120953,"about_ca_topic_score_gemma":0.0060062907,"teacher_disagreement_score":0.033259787,"about_ca_system_score_codex":0.0005425652,"about_ca_system_score_gemma":0.0008118048,"threshold_uncertainty_score":0.11126506},"labels":[],"label_agreement":null},{"id":"W3126967250","doi":"10.1109/sped53181.2021.9587406","title":"Synthetic Speech Detection Using Neural Networks","year":2021,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Artificial neural network; Speech recognition; Voice activity detection; Artificial intelligence; Speech processing","score_opus":0.031453642283931126,"score_gpt":0.2469382779964581,"score_spread":0.21548463571252696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3126967250","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49550954,0.0031039433,0.48557958,0.00060124905,0.0006586001,0.00016384866,0.0026595236,0.005221354,0.006502342],"genre_scores_gemma":[0.8835839,0.00053622405,0.10659346,0.00017374496,0.00013892242,0.0001229474,0.0045918613,0.00016970608,0.0040891427],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99886084,0.0003205047,0.00007196458,0.00033942267,0.00032589363,0.000081444115],"domain_scores_gemma":[0.9981085,0.00095832103,0.00017666441,0.00015676353,0.000525217,0.00007453311],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009405383,0.0009143989,0.00052553497,0.0012146351,0.00022154688,0.0007068588,0.0005600559,0.0007622739,0.001339672],"category_scores_gemma":[0.0033567445,0.00022760063,0.00043069647,0.00042352185,0.00038811087,0.00071326934,0.0006432802,0.0005908101,0.0008949993],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012052002,0.00033569426,0.01070634,0.00048608423,0.00023448226,0.0005265793,0.00022037803,0.19132796,0.116915435,0.00279636,0.009160386,0.6660851],"study_design_scores_gemma":[0.000015649763,0.00011622771,0.004115821,0.000023554323,0.000024838922,0.0002487971,0.000072867646,0.95875406,0.03220578,0.0013227038,0.003073323,0.000026335954],"about_ca_topic_score_codex":0.0018797474,"about_ca_topic_score_gemma":0.0021585072,"teacher_disagreement_score":0.0018797474,"about_ca_system_score_codex":0.0005786449,"about_ca_system_score_gemma":0.00043290644,"threshold_uncertainty_score":0.004974067},"labels":[],"label_agreement":null},{"id":"W3127781879","doi":"10.48550/arxiv.2102.01640","title":"SPEAK WITH YOUR HANDS Using Continuous Hand Gestures to control Articulatory Speech Synthesizer","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Vocal tract; Gesture; Computer science; Speech recognition; Spline (mechanical); Kinematics; Speech production; Speech synthesis; Wrist; Acoustics; Artificial intelligence; Engineering; Anatomy","score_opus":0.06921805763573322,"score_gpt":0.19292652973471655,"score_spread":0.12370847209898334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127781879","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10068227,0.00042096066,0.8748576,0.00018849366,0.0001554153,0.0001464704,0.00013956576,0.010416805,0.0129924705],"genre_scores_gemma":[0.6755539,0.0003279125,0.3003844,0.00022153386,0.0000860402,0.0001780781,0.00020404375,0.00095532695,0.022088733],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9998055,0.00002251312,0.0000129152095,0.00006427358,0.0000780822,0.000016835647],"domain_scores_gemma":[0.99976975,0.000106363215,0.000021744156,0.00003516872,0.00003669671,0.000030376255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025870078,0.0005683622,0.00032206753,0.00022937304,0.00019261151,0.00060372346,0.0005365658,0.00041491963,0.009539645],"category_scores_gemma":[0.0008702965,0.00021232804,0.00022162656,0.000093975024,0.00030756416,0.0005523676,0.00062533177,0.0003384389,0.0022999789],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040300534,0.0000853384,0.0010373577,0.00019293175,0.000040747655,0.000337185,0.00052203867,0.008373368,0.6181296,0.0021418857,0.0025566763,0.3661798],"study_design_scores_gemma":[0.00021147437,0.0012652501,0.008377141,0.00014530969,0.00014756549,0.0014879463,0.00039662412,0.42633808,0.47379947,0.004842236,0.08282028,0.00016860673],"about_ca_topic_score_codex":0.0006514886,"about_ca_topic_score_gemma":0.001143272,"teacher_disagreement_score":0.009539645,"about_ca_system_score_codex":0.00012218671,"about_ca_system_score_gemma":0.00014881947,"threshold_uncertainty_score":0.03191328},"labels":[],"label_agreement":null},{"id":"W3129129429","doi":"10.1007/s12559-020-09803-8","title":"Sigma-Lognormal Modeling of Speech","year":2021,"lang":"en","type":"article","venue":"Cognitive Computation","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Ministerio de Asuntos Económicos y Transformación Digital, Gobierno de España; Universidad de Las Palmas de Gran Canaria; Interreg; Natural Sciences and Engineering Research Council of Canada; European Commission; Fundación General CSIC; Ministerio de Educación y Formación Profesional; Ministerio de Ciencia, Innovación y Universidades","keywords":"Log-normal distribution; Sigma; Computer science; Speech recognition; Artificial intelligence; Mathematics; Statistics; Physics","score_opus":0.04439650461314287,"score_gpt":0.28271323511148716,"score_spread":0.2383167304983443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3129129429","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026187917,0.00043251418,0.9708161,0.00010961158,0.000043694297,0.000025558607,0.00017556487,0.00030184767,0.0019072494],"genre_scores_gemma":[0.92154264,0.0021638814,0.06236411,0.00010708671,0.00008544352,0.00013627231,0.00055151485,0.00014284514,0.012906188],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995658,0.00011091661,0.000030041323,0.00009802658,0.00014438949,0.000050831182],"domain_scores_gemma":[0.9991406,0.0004592685,0.000108858236,0.000072311705,0.00019072539,0.000028260692],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007165665,0.0005458559,0.00042977656,0.0007565327,0.00020299238,0.00074717554,0.000855493,0.00062574376,0.0014768203],"category_scores_gemma":[0.0021620193,0.00029612362,0.00068405725,0.0006659634,0.00061734155,0.0007666039,0.00047645182,0.0007291638,0.0006931482],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057470857,0.00002204957,0.0016773741,0.00007012372,0.00003508854,0.00017089973,0.00014604339,0.9379639,0.0050226124,0.022234168,0.00046466413,0.032135665],"study_design_scores_gemma":[0.0000011318554,0.0000070674614,0.00028014492,0.0000030448764,0.000003435148,0.000030569965,0.000007803898,0.9967542,0.00019556913,0.0024643645,0.00024797817,0.0000045056954],"about_ca_topic_score_codex":0.009938558,"about_ca_topic_score_gemma":0.005164305,"teacher_disagreement_score":0.009938558,"about_ca_system_score_codex":0.00057397975,"about_ca_system_score_gemma":0.00056566886,"threshold_uncertainty_score":0.019761443},"labels":[],"label_agreement":null},{"id":"W3131901777","doi":"10.71781/10868","title":"Advances in deep learning methods for speech recognition and understanding","year":2020,"lang":"en","type":"dissertation","venue":"Papyrus : Institutional Repository (Université de Montréal)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Samsung; Compute Canada","keywords":"Speech recognition; Deep learning; Computer science; Artificial intelligence","score_opus":0.02693497538385669,"score_gpt":0.24286779352638627,"score_spread":0.21593281814252957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3131901777","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0056059216,0.009186339,0.9768728,0.00096171483,0.0003473197,0.000052356034,0.00038412007,0.0016300025,0.004959388],"genre_scores_gemma":[0.28138137,0.02713846,0.6454496,0.001124443,0.0009975198,0.0003942223,0.003857481,0.0011184592,0.038538534],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985948,0.00038525753,0.00011700435,0.0003386771,0.00043691925,0.00012732366],"domain_scores_gemma":[0.9978143,0.0012645306,0.00010939808,0.0003150188,0.00043219983,0.000064580825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021669145,0.0018137685,0.001307997,0.0016003853,0.0005454219,0.0022277124,0.0020133331,0.0018785774,0.0072134035],"category_scores_gemma":[0.0049349614,0.00082754553,0.0014616993,0.0016406915,0.0007815057,0.0039356337,0.002084469,0.0040861736,0.0038669454],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013221557,0.00010667007,0.00090785936,0.0005540109,0.0001661665,0.00009948236,0.00018847277,0.08758288,0.009712935,0.02507157,0.009920879,0.86555684],"study_design_scores_gemma":[0.000018279528,0.00005530072,0.0007678883,0.0001425359,0.000048206184,0.00009405911,0.00007088696,0.9250467,0.008608176,0.037594978,0.027516756,0.000036296613],"about_ca_topic_score_codex":0.010036002,"about_ca_topic_score_gemma":0.011628357,"teacher_disagreement_score":0.010036002,"about_ca_system_score_codex":0.0013998075,"about_ca_system_score_gemma":0.00161289,"threshold_uncertainty_score":0.024131298},"labels":[],"label_agreement":null},{"id":"W3135041399","doi":"10.1044/2020_jslhr-20-00268","title":"Performance of Forced-Alignment Algorithms on Children's Speech","year":2021,"lang":"en","type":"article","venue":"Journal of Speech Language and Hearing Research","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute on Deafness and Other Communication Disorders","keywords":"Sample (material); Segmentation; Two-alternative forced choice; Speech processing; Phonetics; Electroglottograph; Speech segmentation; Workflow; Interval (graph theory)","score_opus":0.0544063089136956,"score_gpt":0.3407107227794535,"score_spread":0.28630441386575795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135041399","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6570446,0.003283921,0.3035488,0.00030061498,0.00053819275,0.0004941074,0.0041081673,0.022409687,0.008271933],"genre_scores_gemma":[0.53133136,0.0004749852,0.4538534,0.00018646903,0.00005727243,0.00041686394,0.007153725,0.0032272174,0.0032987585],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9920027,0.0021416387,0.0008754542,0.0031171031,0.001555702,0.00030748497],"domain_scores_gemma":[0.97622913,0.013803017,0.0013999112,0.0024303263,0.0057044164,0.00043323656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00743859,0.0016367532,0.0011730526,0.0016743236,0.0010068335,0.002244309,0.0017964877,0.001242102,0.0053870147],"category_scores_gemma":[0.027757574,0.0006002282,0.0010294357,0.0015646226,0.00073146017,0.00213802,0.0015642778,0.0012699075,0.0042414037],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027191949,0.0002091082,0.037764844,0.0010289642,0.0008007932,0.00036611606,0.0024925407,0.030128447,0.0814339,0.0017940457,0.007534132,0.8337279],"study_design_scores_gemma":[0.00038857714,0.0022763722,0.16815016,0.00042582085,0.0006537087,0.0024022264,0.0027727962,0.49707034,0.2919255,0.004128973,0.029240146,0.0005653753],"about_ca_topic_score_codex":0.011188882,"about_ca_topic_score_gemma":0.014416077,"teacher_disagreement_score":0.011188882,"about_ca_system_score_codex":0.0010802657,"about_ca_system_score_gemma":0.0015896239,"threshold_uncertainty_score":0.039339483},"labels":[],"label_agreement":null},{"id":"W3135815897","doi":"10.1109/iscslp49672.2021.9362084","title":"Age-Invariant Speaker Embedding for Diarization of Cognitive Assessments","year":2021,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Speaker diarisation; Utterance; Computer science; Speech recognition; Embedding; Invariant (physics); Cognition; Adversarial system; Training set; Speaker recognition; Artificial intelligence; Psychology; Mathematics","score_opus":0.04708542641867467,"score_gpt":0.3360434326566122,"score_spread":0.2889580062379375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135815897","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049984206,0.0012820752,0.9416688,0.0001946785,0.00037096624,0.00012309641,0.0007552826,0.002505851,0.003114972],"genre_scores_gemma":[0.6065528,0.0013942146,0.3695762,0.00030020336,0.00038988274,0.00024217698,0.004590322,0.0006936618,0.016260521],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906045,0.00028502816,0.000055946613,0.00030528152,0.00022268623,0.00007059936],"domain_scores_gemma":[0.9988194,0.00035080314,0.00012322413,0.00029572198,0.00035015238,0.00006067037],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011901186,0.0011008616,0.00047527766,0.0006602989,0.00021129988,0.00045281544,0.0006461888,0.0004571438,0.0024562983],"category_scores_gemma":[0.003419516,0.00020607283,0.0005895259,0.0004485657,0.00033081186,0.00085685373,0.00091847667,0.0012385601,0.0031544769],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00062339316,0.00020616842,0.0027449946,0.00014130681,0.00012421074,0.00014166358,0.00030203612,0.039506473,0.061022986,0.0036038428,0.0092447465,0.88233817],"study_design_scores_gemma":[0.00004117195,0.00040383876,0.011217466,0.000049798684,0.00012378796,0.0007637222,0.00024593936,0.8690987,0.08501829,0.009289426,0.023651602,0.00009620658],"about_ca_topic_score_codex":0.0013246994,"about_ca_topic_score_gemma":0.0017962304,"teacher_disagreement_score":0.0024562983,"about_ca_system_score_codex":0.00034223177,"about_ca_system_score_gemma":0.00039470955,"threshold_uncertainty_score":0.008217156},"labels":[],"label_agreement":null},{"id":"W3135892461","doi":"10.47839/ijc.6.3.445","title":"A ROBUST SPEECH RECOGNITION SYSTEM USING A GENERAL REGRESSION NEURAL NETWORK","year":2014,"lang":"en","type":"article","venue":"International Journal of Computing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Speech recognition; Artificial neural network; Robustness (evolution); Hidden Markov model; Artificial intelligence; Multilayer perceptron; Pattern recognition (psychology); Noise (video); Time delay neural network; Word recognition","score_opus":0.06130865123230914,"score_gpt":0.2828049857427917,"score_spread":0.2214963345104826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135892461","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043965146,0.0006408532,0.9412354,0.00013851223,0.00018159713,0.00018398251,0.00020934279,0.010629632,0.0028154494],"genre_scores_gemma":[0.45704088,0.00048498315,0.53068817,0.00029180665,0.00012883802,0.00024473702,0.0006875448,0.00018779335,0.01024524],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993186,0.00008402979,0.000040768686,0.00028763482,0.00021926491,0.000049641072],"domain_scores_gemma":[0.99968886,0.000055467277,0.000038407357,0.0000645934,0.00013417623,0.00001854066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008386273,0.0007006163,0.0009735043,0.00043193833,0.00032293765,0.000532598,0.0012645754,0.0011278737,0.0023200964],"category_scores_gemma":[0.00081162574,0.0003383858,0.0005868504,0.00040925076,0.00030159985,0.00084895926,0.0006117215,0.00084265677,0.002566708],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006824947,0.00024554034,0.001462821,0.00030177663,0.00024347218,0.00037709743,0.00012164551,0.05153149,0.3877996,0.0023744744,0.003321209,0.55153835],"study_design_scores_gemma":[0.00008228262,0.00082074816,0.0034178083,0.000030625582,0.00021165657,0.0007857204,0.000029869818,0.859979,0.121548645,0.0012520001,0.011740714,0.00010094878],"about_ca_topic_score_codex":0.0024930679,"about_ca_topic_score_gemma":0.0026005793,"teacher_disagreement_score":0.0024930679,"about_ca_system_score_codex":0.00034901028,"about_ca_system_score_gemma":0.00044604868,"threshold_uncertainty_score":0.007761538},"labels":[],"label_agreement":null},{"id":"W3139133216","doi":"10.1002/trc2.12147","title":"Multilingual automation of transcript preprocessing in Alzheimer's disease detection","year":2021,"lang":"en","type":"article","venue":"Alzheimer s & Dementia Translational Research & Clinical Interventions","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Preprocessor; Computer science; Pipeline (software); Natural language processing; Normalization (sociology); Scalability; Task (project management); Context (archaeology); Data pre-processing; Information extraction; Artificial intelligence; Machine learning; Programming language; Biology; Database","score_opus":0.34858535451689876,"score_gpt":0.4959002253631045,"score_spread":0.14731487084620576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3139133216","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045257956,0.0017472024,0.8904732,0.00083608256,0.00048781358,0.0006831874,0.010070184,0.04270335,0.0077410555],"genre_scores_gemma":[0.16746032,0.0010544334,0.7957753,0.00031166227,0.00034173726,0.0010410472,0.022834277,0.0044147586,0.006766395],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99579155,0.001843259,0.00034097774,0.0010784568,0.0006728548,0.00027290345],"domain_scores_gemma":[0.99100304,0.004066065,0.00051184965,0.0016478491,0.0024483656,0.00032279998],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00451807,0.0016454565,0.0009877557,0.0025501433,0.0012011915,0.0023041526,0.0011167768,0.00072264974,0.02015957],"category_scores_gemma":[0.014142949,0.0006373063,0.0012086608,0.0017477907,0.00070818985,0.0018795414,0.0036076186,0.0013507188,0.023266222],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011162604,0.00014441245,0.0067090057,0.001638376,0.00015946313,0.0006387175,0.0020594609,0.0023552284,0.1396637,0.002302836,0.031832866,0.8113796],"study_design_scores_gemma":[0.00035958822,0.001111601,0.059928842,0.0010860886,0.0006831442,0.004369784,0.0042281826,0.11398614,0.42178977,0.031109618,0.3607359,0.00061138446],"about_ca_topic_score_codex":0.0041185045,"about_ca_topic_score_gemma":0.00622205,"teacher_disagreement_score":0.02015957,"about_ca_system_score_codex":0.00062231295,"about_ca_system_score_gemma":0.0028544392,"threshold_uncertainty_score":0.06744051},"labels":[],"label_agreement":null},{"id":"W3143367551","doi":"10.21437/interspeech.2021-941","title":"ECAPA-TDNN Embeddings for Speaker Diarization","year":2021,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":92,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Speaker diarisation; Computer science; Speaker recognition; Robustness (evolution); Speech recognition; Artificial neural network; Discriminative model; Artificial intelligence; Time delay neural network; Pattern recognition (psychology)","score_opus":0.01856822171074096,"score_gpt":0.2489785712134402,"score_spread":0.23041034950269923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3143367551","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020416217,0.0008121345,0.96768457,0.00020603513,0.00040986686,0.000063623724,0.0006808893,0.0060347794,0.0036918337],"genre_scores_gemma":[0.4274446,0.0007655724,0.54483145,0.00044722823,0.00022659691,0.00027427488,0.00525278,0.0010578863,0.019699642],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925524,0.0001329216,0.000045594777,0.00028040147,0.00022495035,0.000060898503],"domain_scores_gemma":[0.9992736,0.00016349641,0.000048584723,0.00022968047,0.0002437758,0.00004092145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000815652,0.0009922698,0.0005938901,0.00045601194,0.00036173625,0.00068192976,0.0012451137,0.00093483337,0.0053472663],"category_scores_gemma":[0.0025318458,0.00034647452,0.00062251254,0.0005967905,0.0003472061,0.0013966616,0.0014926468,0.0022852828,0.00524782],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00052123546,0.00019639455,0.0010068278,0.00016395816,0.00013208023,0.00015174733,0.00013431639,0.083426744,0.067057975,0.0059231776,0.016147116,0.8251384],"study_design_scores_gemma":[0.000014019638,0.000068132584,0.00072752946,0.000013354204,0.000023618679,0.00021019162,0.000024282512,0.962737,0.025007319,0.0038132872,0.0073336246,0.000027630578],"about_ca_topic_score_codex":0.003129293,"about_ca_topic_score_gemma":0.005445018,"teacher_disagreement_score":0.0053472663,"about_ca_system_score_codex":0.00045966398,"about_ca_system_score_gemma":0.00063552277,"threshold_uncertainty_score":0.017888367},"labels":[],"label_agreement":null},{"id":"W3147246185","doi":"10.21203/rs.3.rs-16425/v1","title":"WITHDRAWN: A robust speaker recognition based on Data augmentation","year":2020,"lang":"en","type":"preprint","venue":"Research Square","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"National Natural Science Foundation of China; Fundamental Research Funds for the Central Universities; National Science Foundation","keywords":"Computer science; Speech recognition; Artificial intelligence","score_opus":0.4058160311411746,"score_gpt":0.42449921906336013,"score_spread":0.01868318792218554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3147246185","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029559817,0.010260209,0.68794185,0.02681333,0.07233204,0.0016766528,0.036597844,0.05370609,0.08111224],"genre_scores_gemma":[0.19765085,0.0038035,0.3128453,0.004137436,0.016401656,0.00084443466,0.059725627,0.0071937027,0.39739758],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986083,0.0002162594,0.00012712384,0.00029844648,0.0006598719,0.000090040514],"domain_scores_gemma":[0.9973086,0.0004443683,0.00006413777,0.0005045558,0.0014057511,0.00027271098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018176871,0.0018206743,0.0012508616,0.0011803253,0.00088543276,0.0017163018,0.001784404,0.0020619496,0.09935066],"category_scores_gemma":[0.0050893966,0.0005752622,0.0008483912,0.00070963625,0.0005620514,0.0019006433,0.0014506232,0.001927526,0.062709816],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030949882,0.00022203506,0.0007115391,0.00079659163,0.00018645471,0.00067580584,0.00014439666,0.0028564064,0.13052343,0.0073389695,0.38823518,0.46521428],"study_design_scores_gemma":[0.00079390523,0.0009172648,0.0043826015,0.00015846036,0.0002803602,0.0017079706,0.000113597074,0.09237571,0.31636474,0.015457378,0.5672317,0.00021627548],"about_ca_topic_score_codex":0.003204251,"about_ca_topic_score_gemma":0.0027377491,"teacher_disagreement_score":0.09935066,"about_ca_system_score_codex":0.0005541323,"about_ca_system_score_gemma":0.001433556,"threshold_uncertainty_score":0.33236104},"labels":[],"label_agreement":null},{"id":"W3149444771","doi":"10.18280/ts.380124","title":"Classification of Pitch and Gender of Speakers for Forensic Speaker Recognition from Disguised Voices Using Novel Features Learned by Deep Convolutional Neural Networks","year":2021,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Spectrogram; Mel-frequency cepstrum; Speech recognition; Convolutional neural network; Computer science; Pattern recognition (psychology); Support vector machine; Artificial intelligence; Classifier (UML); Feature extraction; Artificial neural network","score_opus":0.08201919839413377,"score_gpt":0.27523834011215603,"score_spread":0.19321914171802226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3149444771","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58093244,0.0010943925,0.4107212,0.00031761284,0.00028946841,0.00010297581,0.0005765327,0.0016355389,0.0043299086],"genre_scores_gemma":[0.94029105,0.00030855363,0.05529639,0.00007607601,0.000051835563,0.000043064723,0.0007354091,0.00004770209,0.0031499586],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9998117,0.000023208644,0.000010343086,0.000053129374,0.000060816423,0.000040822197],"domain_scores_gemma":[0.9997919,0.0000556745,0.000025490832,0.000021866123,0.00008589457,0.000019100202],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033304884,0.0005501366,0.00027461225,0.0006324195,0.00020785317,0.00034610575,0.00035513903,0.000409209,0.0011915421],"category_scores_gemma":[0.0008069297,0.00014226028,0.00037271925,0.00022065558,0.00020601093,0.00043812787,0.0004365534,0.0005161328,0.00048529293],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007519885,0.00021297601,0.01491865,0.00014487487,0.00010961236,0.00046934828,0.00025717242,0.04228776,0.18825246,0.0009589019,0.003619251,0.74801713],"study_design_scores_gemma":[0.000015320964,0.00020184241,0.020258198,0.000034989225,0.00008734381,0.00042945455,0.00015430227,0.900367,0.07496998,0.0010437751,0.0023994548,0.000038298338],"about_ca_topic_score_codex":0.00250622,"about_ca_topic_score_gemma":0.0043149255,"teacher_disagreement_score":0.00250622,"about_ca_system_score_codex":0.00031154533,"about_ca_system_score_gemma":0.00029852998,"threshold_uncertainty_score":0.0049832463},"labels":[],"label_agreement":null},{"id":"W3157651102","doi":"10.3389/fnagi.2021.635945","title":"Comparing Pre-trained and Feature-Based Models for Prediction of Alzheimer's Disease Based on Speech","year":2021,"lang":"en","type":"article","venue":"Frontiers in Aging Neuroscience","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":92,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Transfer of learning; Speech recognition; Natural language processing; Encoder; Set (abstract data type); Feature (linguistics); Speech processing; Machine learning","score_opus":0.04272635931665986,"score_gpt":0.2557115942008928,"score_spread":0.21298523488423293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3157651102","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9411625,0.00091146276,0.054808952,0.00029251276,0.00010397608,0.0001716666,0.00041409407,0.00070239935,0.0014323072],"genre_scores_gemma":[0.9834231,0.00021700552,0.014305357,0.000048770326,0.00003901135,0.00010991181,0.0009315298,0.00002594004,0.00089931185],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99941945,0.00021087684,0.00004746573,0.00020392372,0.000059744503,0.000058717702],"domain_scores_gemma":[0.99503064,0.0038564543,0.0001886857,0.00027292123,0.0005426171,0.00010858066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036578006,0.0010490803,0.0005800444,0.00086353044,0.00028934673,0.0009104381,0.0008562376,0.0008952995,0.0010947112],"category_scores_gemma":[0.0069851065,0.00032045864,0.0008042763,0.0003286388,0.00031591573,0.000910632,0.00073480426,0.001263838,0.00053033815],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018377559,0.0011496269,0.05655006,0.00019434639,0.000625244,0.00014322279,0.0002704997,0.6855934,0.008157575,0.00037047378,0.0013503428,0.24375738],"study_design_scores_gemma":[0.000025254289,0.00030985565,0.00893246,0.000015137184,0.000068054185,0.000026823585,0.000049082,0.98785585,0.0022328668,0.00033936126,0.000127374,0.00001781354],"about_ca_topic_score_codex":0.01240121,"about_ca_topic_score_gemma":0.006704044,"teacher_disagreement_score":0.01240121,"about_ca_system_score_codex":0.0011580135,"about_ca_system_score_gemma":0.00086800044,"threshold_uncertainty_score":0.024658084},"labels":[],"label_agreement":null},{"id":"W3160325739","doi":"10.1109/icassp39728.2021.9414670","title":"A Capsule Network Based Approach for Detection of Audio Spoofing Attacks","year":2021,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":80,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Spoofing attack; Computer science; Replay attack; Convolutional neural network; Generalization; Artificial intelligence; Speech recognition; Computer security; Authentication (law)","score_opus":0.030080943366938517,"score_gpt":0.23999549081306323,"score_spread":0.20991454744612473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160325739","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0421334,0.00023577074,0.95385456,0.00009529487,0.000050454633,0.0000611876,0.00010280668,0.0008607053,0.0026058631],"genre_scores_gemma":[0.7764247,0.00048304306,0.21725334,0.00012830041,0.000066824,0.00009532141,0.00054640195,0.00009353471,0.00490861],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995534,0.0000988121,0.000023793511,0.00011646441,0.00012935241,0.00007812671],"domain_scores_gemma":[0.9993044,0.00019537141,0.000113311406,0.000115573486,0.00022126726,0.000050119426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000549634,0.0008746856,0.00062018464,0.0012371541,0.00037171203,0.0008446951,0.0010839481,0.0008208871,0.0013216056],"category_scores_gemma":[0.0015900515,0.00026023184,0.00050786743,0.00079665816,0.0004992047,0.0014232938,0.0011207232,0.00077086594,0.0006157605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00096843473,0.00025887348,0.008648436,0.00017083035,0.00017021887,0.0006859324,0.0001912277,0.295374,0.0990973,0.017673701,0.004113228,0.5726479],"study_design_scores_gemma":[0.0000034292254,0.00007799345,0.0009198898,0.000004481353,0.000021654902,0.00014123987,0.000021444865,0.98543537,0.011346737,0.0010769949,0.00093637407,0.000014485932],"about_ca_topic_score_codex":0.0028284006,"about_ca_topic_score_gemma":0.0025950589,"teacher_disagreement_score":0.0028284006,"about_ca_system_score_codex":0.00061957346,"about_ca_system_score_gemma":0.0004741035,"threshold_uncertainty_score":0.0056239367},"labels":[],"label_agreement":null},{"id":"W3161411634","doi":"10.1109/icassp39728.2021.9413680","title":"A Comparison of Discrete Latent Variable Models for Speech Representation Learning","year":2021,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Latent variable; Speech recognition; Artificial intelligence; Representation (politics); Encoding (memory); Word error rate; Variable (mathematics); Latent variable model; Word (group theory); Pattern recognition (psychology); Mathematics","score_opus":0.09678490460931576,"score_gpt":0.3466243956047883,"score_spread":0.24983949099547254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3161411634","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058429245,0.0079541225,0.92462003,0.001628399,0.00032819752,0.00011378389,0.0011397917,0.0027181958,0.003068234],"genre_scores_gemma":[0.64967537,0.0066283783,0.33219922,0.00046540826,0.00024130422,0.00038457988,0.005468884,0.0005026176,0.0044343444],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99730957,0.0013983415,0.00017411723,0.00041182252,0.00058015395,0.00012589271],"domain_scores_gemma":[0.99289954,0.0052431985,0.0001878533,0.0007562057,0.00074537506,0.00016787622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0057470603,0.0009752236,0.0008989049,0.0014490671,0.00030237695,0.0019583167,0.0017813507,0.0013271259,0.002315915],"category_scores_gemma":[0.013945616,0.000470852,0.0012343592,0.0014536994,0.0004977963,0.0034196118,0.00148356,0.0024585696,0.0011733354],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015275843,0.0003837736,0.0053484924,0.00054284796,0.00061852066,0.00006123141,0.00025148343,0.36763832,0.0031693026,0.027608374,0.0060796407,0.58677036],"study_design_scores_gemma":[0.000030880292,0.000112045935,0.0007433904,0.000033849155,0.000025028596,0.0000227896,0.00003292087,0.9905255,0.00066936604,0.006789523,0.0009949006,0.0000198559],"about_ca_topic_score_codex":0.00791219,"about_ca_topic_score_gemma":0.0077514173,"teacher_disagreement_score":0.00791219,"about_ca_system_score_codex":0.0015547645,"about_ca_system_score_gemma":0.0011325501,"threshold_uncertainty_score":0.03039372},"labels":[],"label_agreement":null},{"id":"W3162773681","doi":"10.18280/ts.380232","title":"HMM Based Language Identification from Speech Utterances of Popular Indic Languages Using Spectral and Prosodic Features","year":2021,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Hidden Markov model; Utterance; Computer science; Speech recognition; Mel-frequency cepstrum; Feature (linguistics); Artificial intelligence; Identification (biology); Natural language processing; Feature extraction; Linguistics","score_opus":0.01633622496964346,"score_gpt":0.25978347560542053,"score_spread":0.24344725063577707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3162773681","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5471045,0.00070387503,0.435939,0.00019777464,0.00012015623,0.00015532727,0.0016452294,0.007503212,0.0066309418],"genre_scores_gemma":[0.8788204,0.00036312322,0.11225876,0.000054688157,0.000022064427,0.00011258778,0.0024913244,0.0001798969,0.0056970343],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99975973,0.00006157295,0.000016368367,0.00007605494,0.00005301754,0.0000332598],"domain_scores_gemma":[0.99966013,0.00013155265,0.000034004253,0.00003184683,0.000120878365,0.000021624812],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034750762,0.00034093537,0.00037436353,0.00043666665,0.00023203436,0.00045790547,0.00024270397,0.0002619055,0.0023690173],"category_scores_gemma":[0.0009176308,0.00015483878,0.00029962405,0.00026435955,0.00015355801,0.0006191968,0.00028633437,0.00034776545,0.001360233],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013219727,0.0002598551,0.022014996,0.00071071397,0.00014957038,0.00070436584,0.0011007648,0.019638205,0.4264554,0.0012727882,0.0053114356,0.52105993],"study_design_scores_gemma":[0.00007055456,0.00093326025,0.06680547,0.00011143776,0.00024570693,0.0012713532,0.0013198026,0.62300545,0.29455772,0.0017247855,0.0097901225,0.00016439399],"about_ca_topic_score_codex":0.002053004,"about_ca_topic_score_gemma":0.0033097854,"teacher_disagreement_score":0.0023690173,"about_ca_system_score_codex":0.00014695064,"about_ca_system_score_gemma":0.0003560338,"threshold_uncertainty_score":0.007925153},"labels":[],"label_agreement":null},{"id":"W3162841994","doi":"10.18653/v1/2021.findings-acl.312","title":"Learning Robust Latent Representations for Controllable Speech Synthesis","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vanguard College","funders":"","keywords":"Computer science; Transformer; Speech recognition; Latent variable; Artificial intelligence; Encoder; Probabilistic latent semantic analysis; Mutual information; Pattern recognition (psychology)","score_opus":0.058973699644019335,"score_gpt":0.28078634362666927,"score_spread":0.22181264398264994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3162841994","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013446771,0.000146623,0.98474103,0.0000838122,0.000020765241,0.000015580683,0.0001302439,0.0008311153,0.0005841333],"genre_scores_gemma":[0.668323,0.00034098947,0.32436034,0.00018417613,0.00006947993,0.00020923956,0.001391292,0.0005583658,0.0045631547],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994605,0.00018449716,0.000031386255,0.00017000662,0.00010108155,0.000052603504],"domain_scores_gemma":[0.9990854,0.0005501752,0.00007150866,0.0001634201,0.00009156089,0.000037924758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008799914,0.0008407067,0.000686403,0.0003823564,0.00022233983,0.0007181383,0.00095468166,0.00071288843,0.002518993],"category_scores_gemma":[0.0030829022,0.00056110614,0.00085248175,0.0004149808,0.00077588734,0.0014527432,0.0016524398,0.0018310656,0.0008313155],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002651858,0.00010742161,0.00061731564,0.00017362493,0.00012308224,0.00011750974,0.00016757198,0.6863913,0.050331574,0.044079326,0.0027620008,0.2148642],"study_design_scores_gemma":[0.0000061914843,0.000014766503,0.00004646019,0.000003757711,0.0000048703446,0.000010195744,0.000006020913,0.9879583,0.0041391766,0.0074750264,0.00033046992,0.000004674264],"about_ca_topic_score_codex":0.001811735,"about_ca_topic_score_gemma":0.0032248546,"teacher_disagreement_score":0.002518993,"about_ca_system_score_codex":0.0005845783,"about_ca_system_score_gemma":0.00067292596,"threshold_uncertainty_score":0.008426845},"labels":[],"label_agreement":null},{"id":"W3163865502","doi":"10.1109/icassp39728.2021.9413952","title":"Multi-Dialect Speech Recognition in English Using Attention on Ensemble of Experts","year":2021,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Task (project management); Word error rate; Artificial intelligence; Speech recognition; Ensemble forecasting; Baseline (sea); Variety (cybernetics); Ensemble learning; Language model; Word (group theory); Natural language processing; Training set; Machine learning; Linguistics","score_opus":0.085878234083952,"score_gpt":0.28859020752999937,"score_spread":0.20271197344604736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3163865502","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6407076,0.00093086687,0.35145387,0.00026758085,0.00012560892,0.000056043933,0.00026753222,0.003022715,0.0031681755],"genre_scores_gemma":[0.9598615,0.00014816828,0.036458932,0.000116151314,0.000029838602,0.000025404557,0.00047605482,0.000061269406,0.0028227395],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99944836,0.000117845775,0.000023409437,0.00026311545,0.00006141118,0.000085919535],"domain_scores_gemma":[0.9993284,0.00030106443,0.00002960207,0.000089200184,0.00018808013,0.00006372491],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001059419,0.00087591074,0.0007977951,0.0005663278,0.00029317458,0.0005335578,0.00066424784,0.000650575,0.0009342212],"category_scores_gemma":[0.0015625063,0.00037350942,0.00087773125,0.0003061132,0.0002545728,0.0012093835,0.0010239385,0.0011016866,0.0007488856],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000905299,0.00040265854,0.009475685,0.0001068017,0.0003642549,0.0004370698,0.0008803187,0.31256983,0.07347402,0.0008150582,0.0031339033,0.59743506],"study_design_scores_gemma":[0.000007398619,0.000092333765,0.0023716313,0.000005232471,0.000045166482,0.00006834448,0.00008485265,0.9886225,0.007699986,0.0006145094,0.0003711508,0.000016882424],"about_ca_topic_score_codex":0.011550808,"about_ca_topic_score_gemma":0.019453099,"teacher_disagreement_score":0.011550808,"about_ca_system_score_codex":0.00047014563,"about_ca_system_score_gemma":0.0004623003,"threshold_uncertainty_score":0.02296716},"labels":[],"label_agreement":null},{"id":"W3165143153","doi":"10.31234/osf.io/bm2uq","title":"How do voices become familiar? Speech intelligibility and voice recognition are differentially sensitive to voice training","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Intelligibility (philosophy); Psychology; Speech recognition; Computer science","score_opus":0.09017087775657101,"score_gpt":0.28423595413564184,"score_spread":0.19406507637907083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3165143153","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99606293,0.0003624076,0.0016691248,0.00016551984,0.00004912525,0.000025461843,0.0000415896,0.00004692905,0.0015768646],"genre_scores_gemma":[0.99660134,0.00025406177,0.0014549651,0.00017533933,0.000037046786,0.000027060358,0.00007303942,0.0000472645,0.0013297719],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99897647,0.00022017727,0.000079194375,0.00033902362,0.00022947011,0.00015565362],"domain_scores_gemma":[0.99473155,0.0024553575,0.0009836222,0.0007574564,0.00045976133,0.00061225554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011742952,0.00036929798,0.00054552854,0.00027736853,0.00029342037,0.0012147902,0.00039882548,0.0013828758,0.0034293171],"category_scores_gemma":[0.015855106,0.00045849115,0.00036055053,0.00009511541,0.00086609734,0.0022073132,0.0011786782,0.0010372151,0.00064640533],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029998212,0.0004988628,0.059972696,0.00039602793,0.0002124075,0.0013847644,0.0060230927,0.00070683757,0.7943784,0.00035003747,0.00043996118,0.1326371],"study_design_scores_gemma":[0.00013189836,0.00553735,0.807178,0.00023320407,0.00037110996,0.0046249027,0.007226872,0.0028796764,0.16386855,0.0031751813,0.0046367976,0.00013640868],"about_ca_topic_score_codex":0.00052758097,"about_ca_topic_score_gemma":0.0008507156,"teacher_disagreement_score":0.0034293171,"about_ca_system_score_codex":0.00017729538,"about_ca_system_score_gemma":0.00018551084,"threshold_uncertainty_score":0.011472225},"labels":[],"label_agreement":null},{"id":"W3167533889","doi":"10.48550/arxiv.2106.04624","title":"SpeechBrain: A General-Purpose Speech Toolkit","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":513,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; McGill University","funders":"","keywords":"Computer science; Scripting language; Python (programming language); Inference; Architecture; Speech processing; Speech recognition; Speech technology; Natural language processing; Artificial intelligence; Programming language","score_opus":0.09161433237207015,"score_gpt":0.1896422480167848,"score_spread":0.09802791564471466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3167533889","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003940797,0.0006761044,0.41373047,0.0002890175,0.00045061207,0.00030444973,0.035023753,0.5330475,0.012537354],"genre_scores_gemma":[0.08356533,0.0010918288,0.5462098,0.001310982,0.00029400893,0.0023138984,0.16252361,0.15789913,0.04479146],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99921405,0.00015143999,0.00008377009,0.00021172248,0.00026520365,0.00007382525],"domain_scores_gemma":[0.9987925,0.00055806956,0.000061369596,0.00022400847,0.0002697583,0.00009428856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009344483,0.002090762,0.0010354725,0.0011829975,0.00059692306,0.0018393418,0.0025733097,0.0013901262,0.0647307],"category_scores_gemma":[0.0048274253,0.0011405499,0.001072719,0.0006692912,0.00048138923,0.0022359288,0.003017886,0.0020671417,0.06926867],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008782633,0.000112425034,0.0011651581,0.0024388817,0.00023584398,0.00058262155,0.0007605764,0.009395744,0.028514374,0.009969153,0.66659844,0.27934852],"study_design_scores_gemma":[0.00038737935,0.00019941884,0.003524977,0.00041336365,0.00014572049,0.0019149932,0.00042156017,0.18081872,0.06135092,0.043270346,0.70712566,0.00042685022],"about_ca_topic_score_codex":0.0033367423,"about_ca_topic_score_gemma":0.006060784,"teacher_disagreement_score":0.0647307,"about_ca_system_score_codex":0.0004591332,"about_ca_system_score_gemma":0.0012895879,"threshold_uncertainty_score":0.21654576},"labels":[],"label_agreement":null},{"id":"W3175990969","doi":"10.21428/594757db.930ce165","title":"Learning to Model Prosodic and Spectral Features for Non-parallel Emotive Speech Conversion","year":2021,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Dalhousie University","funders":"Vector Institute; Natural Sciences and Engineering Research Council of Canada; Government of Canada; Canadian Institute for Advanced Research","keywords":"Emotive; Computer science; Speech recognition; Generative grammar; Speech synthesis; Artificial neural network; Convolutional neural network; Kernel (algebra); Artificial intelligence; Speech enhancement","score_opus":0.0176946675514212,"score_gpt":0.25114540375258565,"score_spread":0.23345073620116444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3175990969","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039157208,0.00025703973,0.9581244,0.00010833481,0.000059131315,0.000043884782,0.00008051121,0.000571824,0.0015975744],"genre_scores_gemma":[0.8243012,0.00042421083,0.1678273,0.00021982974,0.00006198945,0.00015407772,0.0005520814,0.00017968196,0.0062795873],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99982256,0.000047590733,0.000006866847,0.0000666207,0.00003294022,0.0000234388],"domain_scores_gemma":[0.99970645,0.00015506451,0.000029961882,0.000042856496,0.0000514071,0.000014289483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005450488,0.0008646544,0.00033658117,0.00027708412,0.00014339859,0.00029794427,0.000572998,0.00043395697,0.0014614607],"category_scores_gemma":[0.0011396485,0.00031424977,0.00055273937,0.00019836078,0.00035735557,0.00060723355,0.00060610863,0.0010778661,0.00051247276],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022244584,0.00018577115,0.0016537072,0.00008540278,0.0001252238,0.00016019087,0.000096743766,0.66805404,0.053203028,0.0058281734,0.0020013903,0.26838395],"study_design_scores_gemma":[0.0000020977227,0.000020963515,0.00023245595,0.0000023989596,0.000007867844,0.000019932211,0.0000039508163,0.99508274,0.0032476736,0.0010403596,0.00033540698,0.000004132223],"about_ca_topic_score_codex":0.0017067865,"about_ca_topic_score_gemma":0.0031176095,"teacher_disagreement_score":0.0017067865,"about_ca_system_score_codex":0.00028718245,"about_ca_system_score_gemma":0.00030915343,"threshold_uncertainty_score":0.0048890114},"labels":[],"label_agreement":null},{"id":"W3176272988","doi":"10.23641/asha.14167058.v1","title":"Forced alignment of child speech (Mahr et al., 2021)","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Speech recognition; Phone; Two-alternative forced choice; Sample (material); Segmentation; Natural language processing; Artificial intelligence; Linguistics; Mathematics; Statistics","score_opus":0.03463776890904033,"score_gpt":0.26468767655305236,"score_spread":0.23004990764401204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176272988","genre_codex":"methods","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32936972,0.0048630834,0.5789277,0.00095881516,0.0012370601,0.002134249,0.028362444,0.0135731725,0.040573765],"genre_scores_gemma":[0.35040227,0.0013316154,0.60837764,0.000555956,0.00013821006,0.0018062999,0.016443534,0.0028042844,0.018140133],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971046,0.00077357906,0.00026643692,0.0009362852,0.0008000906,0.0001189764],"domain_scores_gemma":[0.9928508,0.0022351467,0.0007754128,0.00138741,0.0026054345,0.00014592873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037290354,0.00097443315,0.0004468799,0.0012494178,0.000689717,0.0014266362,0.00093537156,0.00075105723,0.015886996],"category_scores_gemma":[0.016116517,0.0005212392,0.0007620789,0.0012270877,0.0005663934,0.0011582462,0.0011664713,0.00079509744,0.00836789],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011052045,0.00008092791,0.026109187,0.0012900986,0.00022511405,0.00046296293,0.002797381,0.0026323884,0.10225627,0.0034645617,0.026160331,0.8334157],"study_design_scores_gemma":[0.00022431795,0.0013503303,0.51668125,0.00075987633,0.00051957025,0.007318592,0.0031772722,0.039895643,0.18929358,0.0055937087,0.2346452,0.00054059434],"about_ca_topic_score_codex":0.01243517,"about_ca_topic_score_gemma":0.030511389,"teacher_disagreement_score":0.015886996,"about_ca_system_score_codex":0.00079321954,"about_ca_system_score_gemma":0.0017442262,"threshold_uncertainty_score":0.053147256},"labels":[],"label_agreement":null},{"id":"W3176722102","doi":"10.18429/jacow-linac2018-tu1a03","title":"Status and Issues (Microphonics, LFD, MPS) with TRIUMF ARIEL e-Linac Commissioning","year":2018,"lang":"en","type":"article","venue":"JACOW","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"TRIUMF","funders":"","keywords":"Microphonics; Linear particle accelerator; Nuclear engineering; Nuclear physics; Physics; Engineering; Beam (structure)","score_opus":0.01715254033419223,"score_gpt":0.2598099494333721,"score_spread":0.24265740909917988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176722102","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25032255,0.075716145,0.22267087,0.022779798,0.004818378,0.002283021,0.014970448,0.027190302,0.37924847],"genre_scores_gemma":[0.6640358,0.01623272,0.16584277,0.0024785234,0.0021473963,0.001096665,0.025563225,0.003257344,0.11934553],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956454,0.0005170852,0.00021813462,0.00043369833,0.002777349,0.00040834688],"domain_scores_gemma":[0.9937523,0.0006834392,0.0005877669,0.00079464127,0.0034781203,0.00070363254],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008350529,0.0007753163,0.00060027913,0.002084978,0.0013430575,0.0029751812,0.0015634336,0.0013481978,0.020515837],"category_scores_gemma":[0.0052182046,0.00041692713,0.00051553466,0.0013646107,0.0008589485,0.0029180022,0.0012582535,0.0013548912,0.0073092515],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015738482,0.00033420758,0.016448462,0.0020553588,0.00014659089,0.0006369519,0.0007559519,0.009002203,0.09134014,0.017721277,0.08109311,0.778892],"study_design_scores_gemma":[0.0000820078,0.0018367816,0.023501894,0.00037525772,0.000095039584,0.0012744163,0.00031896314,0.0074986373,0.09626309,0.0016650921,0.8669793,0.00010956904],"about_ca_topic_score_codex":0.0062164855,"about_ca_topic_score_gemma":0.0069591906,"teacher_disagreement_score":0.020515837,"about_ca_system_score_codex":0.0033245792,"about_ca_system_score_gemma":0.00438916,"threshold_uncertainty_score":0.068632305},"labels":[],"label_agreement":null},{"id":"W3177268625","doi":"10.21467/proceedings.115.20","title":"End-to-End Speech Recognition Using Recurrent Neural Network (RNN)","year":2021,"lang":"en","type":"article","venue":"AIJR Proceedings","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University of Edmonton","funders":"","keywords":"Computer science; Recurrent neural network; End-to-end principle; Deep learning; Speech recognition; Artificial intelligence; Long short term memory; Language model; Artificial neural network; Deep neural networks; Voice activity detection; Acoustic model; Speech processing","score_opus":0.056511863445194516,"score_gpt":0.27158804131575,"score_spread":0.21507617787055547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3177268625","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0776862,0.0008200932,0.8660062,0.00025034137,0.00031096177,0.00018906365,0.002114432,0.046500597,0.0061221085],"genre_scores_gemma":[0.428744,0.0005485018,0.5427583,0.00049089163,0.00011855493,0.00024426926,0.00799724,0.0009539107,0.018144406],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995173,0.000052745443,0.000032286644,0.00018616662,0.00015348519,0.00005798039],"domain_scores_gemma":[0.9995722,0.00009728839,0.00003225918,0.000102546735,0.00016358099,0.00003202994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005402742,0.00110637,0.0008526256,0.0005734723,0.000356775,0.0007888122,0.001330664,0.0008292814,0.004954486],"category_scores_gemma":[0.0013863537,0.0002930723,0.0005285315,0.00030923242,0.00025956676,0.0012058665,0.0009842931,0.0009855636,0.00625717],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006975347,0.00037492625,0.0025585787,0.00029428664,0.0002161746,0.0007421409,0.00017838003,0.029452229,0.23131412,0.0019266357,0.022494419,0.7097506],"study_design_scores_gemma":[0.00006784532,0.00034931223,0.003408485,0.000042056672,0.00010404591,0.00052502926,0.00007775138,0.72060406,0.25994536,0.0027832368,0.012001187,0.00009165125],"about_ca_topic_score_codex":0.004205795,"about_ca_topic_score_gemma":0.009148514,"teacher_disagreement_score":0.004954486,"about_ca_system_score_codex":0.00037027858,"about_ca_system_score_gemma":0.0004831759,"threshold_uncertainty_score":0.016574383},"labels":[],"label_agreement":null},{"id":"W3178196694","doi":"10.18280/ria.350307","title":"Usage of Prosody Modification and Acoustic Adaptation for Robust Automatic Speech Recognition (ASR) System","year":2021,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Prosody; Speech recognition; Naturalness; Computer science; Word error rate; Adaptation (eye); Speech processing; Psychology","score_opus":0.10538573665782153,"score_gpt":0.27794781039062283,"score_spread":0.1725620737328013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3178196694","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4411578,0.0025518741,0.53270096,0.0004094466,0.000308134,0.00050935656,0.00037727022,0.008373395,0.013611789],"genre_scores_gemma":[0.81242615,0.0008329252,0.17864248,0.00026145545,0.00007113344,0.00034073272,0.00055303454,0.00030874202,0.006563337],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993717,0.00012684935,0.000055205484,0.00022441278,0.00017853329,0.000043327113],"domain_scores_gemma":[0.9995646,0.00012181816,0.00005118243,0.00008050636,0.0001623727,0.00001942966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056479365,0.0006089244,0.00047855856,0.00044668972,0.00026561343,0.0004985542,0.00070649374,0.000468162,0.002233882],"category_scores_gemma":[0.0012119735,0.00023375126,0.0003564247,0.00024200174,0.00023842143,0.0005239235,0.000375751,0.00039765352,0.001443789],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044340416,0.00018601344,0.0029596384,0.00033306045,0.0000954225,0.00044832288,0.00033516617,0.0056334278,0.6141489,0.0004493275,0.0011339044,0.37383342],"study_design_scores_gemma":[0.00010294647,0.0021905312,0.044930413,0.00009654164,0.0003798042,0.003963466,0.00026497824,0.17544836,0.7438934,0.0007392479,0.027824767,0.00016555494],"about_ca_topic_score_codex":0.0008459605,"about_ca_topic_score_gemma":0.00077365653,"teacher_disagreement_score":0.002233882,"about_ca_system_score_codex":0.00014744709,"about_ca_system_score_gemma":0.00027091661,"threshold_uncertainty_score":0.007473111},"labels":[],"label_agreement":null},{"id":"W3184647894","doi":"10.3390/s21155097","title":"A Two-Level Speaker Identification System via Fusion of Heterogeneous Classifiers and Complementary Feature Cooperation","year":2021,"lang":"en","type":"article","venue":"Sensors","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Mel-frequency cepstrum; Classifier (UML); Mixture model; Discriminative model; Artificial intelligence; Pattern recognition (psychology); Computer science; Speech recognition; Support vector machine; Speaker recognition; Feature extraction","score_opus":0.03279552816942155,"score_gpt":0.2527752848545654,"score_spread":0.21997975668514386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3184647894","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03071605,0.0003221927,0.9598012,0.0002202654,0.00015363868,0.00013905988,0.00008825101,0.005043284,0.0035160736],"genre_scores_gemma":[0.6073149,0.00017958584,0.38143554,0.00042356364,0.00016183172,0.00027757033,0.00036065967,0.00013187816,0.009714424],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991134,0.00013172255,0.00004625202,0.00030319006,0.00027014155,0.00013531439],"domain_scores_gemma":[0.9995474,0.000073455834,0.000042745232,0.00006855343,0.00020976749,0.000058000383],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010688356,0.0007051673,0.0010936637,0.0006304522,0.000603733,0.0010097601,0.0018817631,0.0013624539,0.0029141563],"category_scores_gemma":[0.0010891425,0.0005364241,0.00069132214,0.00039462207,0.0003708369,0.0012728379,0.0019008758,0.0013188092,0.0025444091],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00079752953,0.00039548782,0.0036246607,0.00019987804,0.00026955156,0.0005452053,0.0004475406,0.029263075,0.20670241,0.006332052,0.0069251917,0.74449754],"study_design_scores_gemma":[0.000054798253,0.0004101885,0.0031080502,0.00003278994,0.00018116402,0.0005471342,0.00007461344,0.9179538,0.0637245,0.0050755437,0.008748998,0.00008838218],"about_ca_topic_score_codex":0.0020319624,"about_ca_topic_score_gemma":0.002330926,"teacher_disagreement_score":0.0029141563,"about_ca_system_score_codex":0.00051792787,"about_ca_system_score_gemma":0.00080943183,"threshold_uncertainty_score":0.0097488165},"labels":[],"label_agreement":null},{"id":"W3186939564","doi":"10.18280/isi.260304","title":"Optimized Features Extraction from Spectral and Temporal Features for Identifying the Telugu Dialects by Using GMM and HMM","year":2021,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Telugu; Mel-frequency cepstrum; Hidden Markov model; Computer science; Artificial intelligence; Dimensionality reduction; Speech recognition; Feature extraction; Pattern recognition (psychology); Curse of dimensionality; Identification (biology); Feature (linguistics); Linguistics","score_opus":0.0278661034268363,"score_gpt":0.2684506857284297,"score_spread":0.24058458230159344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3186939564","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.069450594,0.0005425955,0.9259397,0.0000792632,0.000077211975,0.00006248286,0.00032848842,0.0017877498,0.0017319362],"genre_scores_gemma":[0.59213036,0.0006669437,0.39806426,0.000051981937,0.00004220471,0.00020748118,0.0017057075,0.00021945543,0.006911731],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9997936,0.00003755463,0.00001417565,0.00006909586,0.0000457435,0.000039839713],"domain_scores_gemma":[0.99988246,0.00003455355,0.000008885706,0.000013211082,0.00005445517,0.0000063843754],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002754537,0.0005107608,0.0004361003,0.00060722226,0.00023501927,0.0003603627,0.00026272956,0.00033244575,0.0014346575],"category_scores_gemma":[0.0004971194,0.00022734534,0.00065896363,0.0003995689,0.00012824667,0.00040069665,0.00024463344,0.00042261946,0.0010634647],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003977625,0.0001306245,0.004986762,0.00016096074,0.00012531117,0.0001978592,0.00022833672,0.060881566,0.17678763,0.002592486,0.004092745,0.74941784],"study_design_scores_gemma":[0.000022456885,0.00016985126,0.023421222,0.000031075586,0.00011798083,0.00027327263,0.0002106996,0.8927951,0.07356533,0.0017953156,0.0075309607,0.00006672978],"about_ca_topic_score_codex":0.0071192207,"about_ca_topic_score_gemma":0.0060647265,"teacher_disagreement_score":0.0071192207,"about_ca_system_score_codex":0.000259797,"about_ca_system_score_gemma":0.00041066317,"threshold_uncertainty_score":0.014155567},"labels":[],"label_agreement":null},{"id":"W3187244867","doi":"10.21437/interspeech.2021-1755","title":"The Zero Resource Speech Challenge 2021: Spoken Language Modelling","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Agence Nationale de la Recherche","keywords":"Computer science; Encoder; Natural language processing; ABX test; Zero (linguistics); Coding (social sciences); Speech recognition; Pipeline (software); Artificial intelligence; Baseline (sea); Word (group theory); Language model; Linguistics; Mathematics","score_opus":0.03830097918852758,"score_gpt":0.25625806829496617,"score_spread":0.21795708910643857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3187244867","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.116193585,0.018215084,0.30751666,0.01548987,0.01174232,0.004121928,0.31908682,0.14197747,0.065656215],"genre_scores_gemma":[0.111781925,0.0019298783,0.15127389,0.0026078515,0.0011066264,0.0035078155,0.68049675,0.004981196,0.042314053],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99443626,0.0024157194,0.00032855425,0.0012393196,0.0010757059,0.00050433166],"domain_scores_gemma":[0.99291754,0.0033529007,0.00015211459,0.0016994575,0.0013226707,0.000555329],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0055655795,0.0043614563,0.0030194016,0.0009945967,0.001355543,0.0035330313,0.0044137137,0.005466733,0.02571841],"category_scores_gemma":[0.016051212,0.0008698766,0.0017523182,0.0009927267,0.0011200384,0.0044245725,0.0065983334,0.004921693,0.03919101],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001495413,0.0008196731,0.00096176396,0.0022014207,0.00035781553,0.00043963024,0.00047385707,0.013923411,0.01253018,0.0039961906,0.6758694,0.28693125],"study_design_scores_gemma":[0.0019924603,0.0016583389,0.0063447375,0.00082473224,0.0003681662,0.0015366849,0.00169813,0.3658085,0.049421035,0.027282294,0.54248625,0.0005786634],"about_ca_topic_score_codex":0.015031484,"about_ca_topic_score_gemma":0.018349146,"teacher_disagreement_score":0.02571841,"about_ca_system_score_codex":0.0015441175,"about_ca_system_score_gemma":0.0031050593,"threshold_uncertainty_score":0.08603668},"labels":[],"label_agreement":null},{"id":"W3191044189","doi":"10.48550/arxiv.2107.14642","title":"Practical Attacks on Voice Spoofing Countermeasures","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Spoofing attack; Computer science; Computer security; Authentication (law); Adversarial system; Key (lock); Vulnerability (computing); Artificial intelligence","score_opus":0.17514551471353124,"score_gpt":0.23951261841909008,"score_spread":0.06436710370555884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3191044189","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14205787,0.0007616994,0.83899176,0.00087226054,0.0001882968,0.00016782864,0.00011742189,0.0023617612,0.014481083],"genre_scores_gemma":[0.9590517,0.00020510383,0.038455147,0.00021189018,0.000041845822,0.00007432734,0.000067274595,0.00006094777,0.0018316113],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99714845,0.00096043537,0.0001169304,0.0003184399,0.0011110618,0.00034462346],"domain_scores_gemma":[0.99621385,0.0020269984,0.00039495406,0.00092947116,0.0003247502,0.000109864566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017599285,0.0010600459,0.00055616704,0.0006361339,0.0004426383,0.0008841113,0.00076288363,0.0012379887,0.0019425609],"category_scores_gemma":[0.0066319876,0.00022673834,0.00049887743,0.0002619602,0.0012854995,0.0014908911,0.0025043613,0.0014655099,0.0007786753],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008419482,0.00027288462,0.0033310433,0.0002919241,0.00019129949,0.0007388339,0.00032170457,0.5050717,0.16395454,0.08715571,0.005601534,0.23222673],"study_design_scores_gemma":[0.000039256465,0.00036121096,0.00088404544,0.000058672973,0.00003579356,0.0006879961,0.000077295736,0.91162336,0.06350458,0.016317273,0.006373117,0.000037375423],"about_ca_topic_score_codex":0.00019016166,"about_ca_topic_score_gemma":0.00015542308,"teacher_disagreement_score":0.0019425609,"about_ca_system_score_codex":0.00046899906,"about_ca_system_score_gemma":0.0003250628,"threshold_uncertainty_score":0.009307504},"labels":[],"label_agreement":null},{"id":"W3195948749","doi":"10.1109/jiot.2021.3097266","title":"Efficient and Privacy-Preserving Speaker Recognition for Cybertwin-Driven 6G","year":2021,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Euclidean distance; Biometrics; Speaker recognition; Cosine similarity; Random projection; Computation; Computer security; Speech recognition; Data mining; Artificial intelligence; Algorithm; Pattern recognition (psychology)","score_opus":0.03617530084013353,"score_gpt":0.2618438795747483,"score_spread":0.22566857873461477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3195948749","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07475556,0.000816739,0.9182477,0.0004193666,0.00026553703,0.00013590428,0.0002178305,0.0019914405,0.0031498214],"genre_scores_gemma":[0.87628055,0.00039685742,0.11898011,0.00029634658,0.00012240453,0.00008613647,0.00039882277,0.000045442488,0.0033932815],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982798,0.00037312822,0.000106388194,0.00030122043,0.00073234516,0.00020710613],"domain_scores_gemma":[0.9990722,0.00019565767,0.00010836501,0.0003909742,0.00017826511,0.000054422617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008689041,0.0006767004,0.000777818,0.0004955336,0.0006330135,0.00078405754,0.0008579723,0.0007542752,0.0014066637],"category_scores_gemma":[0.002333508,0.00018733727,0.00044795743,0.00050711137,0.0006690434,0.0016560663,0.0017051761,0.0011205492,0.00087933266],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015073015,0.0002831636,0.002631177,0.00025116254,0.00017445302,0.0008855051,0.0004297038,0.086996436,0.21623786,0.04195876,0.00876937,0.6398751],"study_design_scores_gemma":[0.000060194474,0.00045180615,0.0015945232,0.000027634202,0.00006008687,0.001523584,0.00013621346,0.8718428,0.09854973,0.016288236,0.009371542,0.000093637165],"about_ca_topic_score_codex":0.0007485164,"about_ca_topic_score_gemma":0.0008306068,"teacher_disagreement_score":0.0014066637,"about_ca_system_score_codex":0.00045562568,"about_ca_system_score_gemma":0.0005888792,"threshold_uncertainty_score":0.0047057867},"labels":[],"label_agreement":null},{"id":"W3198750786","doi":"","title":"Malayalam three-way rhotics contrast: Articulatory modelling based on MRI data","year":2020,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"","keywords":"Malayalam; Contrast (vision); Computer science; Artificial intelligence; Speech recognition; Natural language processing","score_opus":0.0532952881399329,"score_gpt":0.2398904879386189,"score_spread":0.186595199798686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3198750786","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47279134,0.0006168985,0.51334393,0.00034197915,0.00011191511,0.00010655819,0.0012178109,0.0015557766,0.00991377],"genre_scores_gemma":[0.9094886,0.00048264812,0.082011454,0.00004602852,0.000031999996,0.000051271112,0.0010270576,0.00032502945,0.0065359324],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99991274,0.000020633772,0.000004988537,0.000017052556,0.000028376877,0.000016227403],"domain_scores_gemma":[0.9997029,0.00013367426,0.000025533816,0.000036846024,0.00007992497,0.000021122965],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002984429,0.00039378818,0.00027694204,0.00049252727,0.00019356296,0.0007613363,0.000344977,0.0005850912,0.0026800372],"category_scores_gemma":[0.0012136677,0.00016422397,0.0005333905,0.0004007702,0.00019741282,0.0003634575,0.00035205446,0.0005609679,0.0016424365],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016860766,0.00020669572,0.0071131396,0.0005762157,0.00020544349,0.0014899048,0.00053716276,0.27884847,0.30801895,0.0066599348,0.0032133549,0.39144462],"study_design_scores_gemma":[0.000020289286,0.00012745353,0.012966507,0.000040373583,0.0000734529,0.00056616066,0.00008411375,0.9317945,0.05033306,0.00086989347,0.0030712918,0.000052794952],"about_ca_topic_score_codex":0.0062045283,"about_ca_topic_score_gemma":0.00866243,"teacher_disagreement_score":0.0062045283,"about_ca_system_score_codex":0.00016558882,"about_ca_system_score_gemma":0.0004904783,"threshold_uncertainty_score":0.012336791},"labels":[],"label_agreement":null},{"id":"W3200111860","doi":"10.1007/978-3-030-87802-3_1","title":"Text-Independent Speaker Verification Employing CNN-LSTM-TDNN Hybrid Networks","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Speech recognition; NIST; Artificial neural network; Time delay neural network; Speaker recognition; Artificial intelligence; Pattern recognition (psychology); Utterance; Pooling; Convolutional neural network","score_opus":0.023570762265196613,"score_gpt":0.2391657481355195,"score_spread":0.21559498587032289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200111860","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04848864,0.0017579561,0.9297771,0.00030708913,0.0008856139,0.00015946744,0.00088790565,0.008526504,0.009209638],"genre_scores_gemma":[0.5384581,0.0011990562,0.42389527,0.0004063901,0.0003433095,0.00018592938,0.0033562824,0.000657886,0.03149784],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99934477,0.000082690385,0.000039464783,0.00023535932,0.00018565884,0.00011212811],"domain_scores_gemma":[0.99923396,0.00017499525,0.000049912134,0.00013121334,0.0003712811,0.00003868389],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092699716,0.0011240725,0.0009530953,0.0005795609,0.0005195237,0.0009159654,0.0011937647,0.001140576,0.0070190104],"category_scores_gemma":[0.0015542404,0.00044125417,0.0009201952,0.0004760952,0.0002582215,0.0012968143,0.0011152995,0.0014207818,0.0074231788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007316186,0.000104390696,0.0008760438,0.00017541791,0.00016529874,0.00017527994,0.000045938457,0.01960722,0.18035872,0.00096550083,0.006325971,0.7904686],"study_design_scores_gemma":[0.000023699786,0.00015905678,0.0020581593,0.000044248663,0.000160252,0.00031032055,0.000047629972,0.8405095,0.1510859,0.0011863491,0.004367374,0.000047488185],"about_ca_topic_score_codex":0.004992909,"about_ca_topic_score_gemma":0.0102827335,"teacher_disagreement_score":0.0070190104,"about_ca_system_score_codex":0.00045877622,"about_ca_system_score_gemma":0.0010060334,"threshold_uncertainty_score":0.023480952},"labels":[],"label_agreement":null},{"id":"W3200812870","doi":"","title":"Alzheimers Dementia Detection using Acoustic & Linguistic features and Pre-Trained BERT.","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Dementia; Task (project management); Artificial intelligence; Set (abstract data type); Feature (linguistics); Natural language processing; Conjunction (astronomy); Speech recognition; Linguistics; Disease; Medicine; Engineering","score_opus":0.06678901600204276,"score_gpt":0.2035636742655412,"score_spread":0.13677465826349844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200812870","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6363525,0.0032243447,0.30260894,0.0013951159,0.0009900555,0.00047306408,0.017128136,0.016873054,0.020954806],"genre_scores_gemma":[0.8487768,0.0007142506,0.10368501,0.00021382814,0.00023992994,0.00029819622,0.031387966,0.00023284077,0.014451174],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995303,0.00010466278,0.000020917108,0.00015544935,0.00010821606,0.00008041137],"domain_scores_gemma":[0.99934405,0.0002996841,0.000044131044,0.00007834894,0.00018256796,0.00005126345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001148593,0.0015110414,0.00045898423,0.0012482521,0.00033042007,0.0006693486,0.0005470346,0.0008228598,0.0020247484],"category_scores_gemma":[0.002562857,0.00025131422,0.0006188939,0.00044362934,0.00025429964,0.0008302353,0.00080994767,0.0010169569,0.0037162106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017410486,0.0007175159,0.035266843,0.00043681657,0.00025334512,0.0010524404,0.00043156368,0.07192706,0.04957064,0.0021361436,0.045801163,0.79066545],"study_design_scores_gemma":[0.000081551334,0.0006176311,0.040141676,0.0001117476,0.000116562944,0.0012285281,0.0004363526,0.90290123,0.034418847,0.003937284,0.015914477,0.0000941677],"about_ca_topic_score_codex":0.0072809462,"about_ca_topic_score_gemma":0.010183188,"teacher_disagreement_score":0.0072809462,"about_ca_system_score_codex":0.00061027665,"about_ca_system_score_gemma":0.0007197017,"threshold_uncertainty_score":0.014477134},"labels":[],"label_agreement":null},{"id":"W3201237299","doi":"10.1007/978-3-030-87802-3_2","title":"End-to-End Voice Spoofing Detection Employing Time Delay Neural Networks and Higher Order Statistics","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Spoofing attack; Speech recognition; Artificial neural network; Higher-order statistics; Artificial intelligence; Computer network; Telecommunications; Signal processing","score_opus":0.018339856872574663,"score_gpt":0.23781070371785273,"score_spread":0.21947084684527807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3201237299","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06713439,0.0005489538,0.92484665,0.000114889546,0.00013350163,0.000047747242,0.0003262403,0.0024153285,0.0044322726],"genre_scores_gemma":[0.5459833,0.00069304864,0.43370637,0.00013072486,0.00009737019,0.000056146793,0.00095955597,0.00018826139,0.018185185],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998363,0.000017571609,0.000010013376,0.00003469507,0.00007324793,0.00002811094],"domain_scores_gemma":[0.99961567,0.0001776015,0.000025004092,0.000031944117,0.00013329953,0.000016331633],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029373722,0.00063739746,0.00045976933,0.0004934834,0.0002857892,0.00078929414,0.00048129013,0.0007049305,0.0021105232],"category_scores_gemma":[0.00072433724,0.00024714592,0.00024484273,0.00038317853,0.00019570735,0.000982539,0.00045974678,0.0006003567,0.0014656535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00062247535,0.00023793882,0.0026919676,0.00013388156,0.00006637049,0.00028875924,0.0000518913,0.044385727,0.29222745,0.003713436,0.0029737265,0.6526063],"study_design_scores_gemma":[0.000009803482,0.00011869145,0.002995249,0.000016518601,0.000027458726,0.0002736669,0.00002530644,0.87319607,0.11950715,0.0019726167,0.0018314243,0.000025973655],"about_ca_topic_score_codex":0.0015211311,"about_ca_topic_score_gemma":0.0050823754,"teacher_disagreement_score":0.0021105232,"about_ca_system_score_codex":0.00031702363,"about_ca_system_score_gemma":0.00039191754,"threshold_uncertainty_score":0.007060349},"labels":[],"label_agreement":null},{"id":"W3201401182","doi":"10.3390/app11188412","title":"Accented Speech Recognition Based on End-to-End Domain Adversarial Training of Neural Networks","year":2021,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Speech recognition; Computer science; Classifier (UML); Artificial neural network; Stress (linguistics); Connectionism; Artificial intelligence","score_opus":0.05449696249940805,"score_gpt":0.2641169772131821,"score_spread":0.20962001471377406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3201401182","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042179495,0.00020138694,0.954204,0.00013912597,0.00007227245,0.00006458301,0.0000369296,0.00087384606,0.0022283338],"genre_scores_gemma":[0.8645503,0.0001888461,0.12937877,0.00021198567,0.00004132576,0.0001394259,0.00020415158,0.000055214186,0.005229923],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993825,0.00018368557,0.000028646931,0.0001815272,0.000148086,0.000075603486],"domain_scores_gemma":[0.99921584,0.00038288365,0.00006352891,0.000107645115,0.00019281631,0.000037318736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012491785,0.00092379784,0.00066680176,0.00022342616,0.00032544605,0.00045375523,0.0008974599,0.00070473563,0.0012340255],"category_scores_gemma":[0.0019881148,0.00032911848,0.00056025933,0.00017862947,0.0007161627,0.000820864,0.0011023333,0.0017440794,0.000535089],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021186267,0.000103476006,0.00068279385,0.000037746908,0.00004537818,0.00012644565,0.000091880785,0.8573606,0.015017248,0.0040958216,0.0010299115,0.12119694],"study_design_scores_gemma":[0.0000015972544,0.000023530716,0.0000735787,0.000001379306,0.0000032771657,0.0000126477335,0.0000033330937,0.9967636,0.0024760002,0.000514334,0.00012297239,0.000003757812],"about_ca_topic_score_codex":0.0025535368,"about_ca_topic_score_gemma":0.00269691,"teacher_disagreement_score":0.0025535368,"about_ca_system_score_codex":0.0005021749,"about_ca_system_score_gemma":0.00053528615,"threshold_uncertainty_score":0.0066064},"labels":[],"label_agreement":null},{"id":"W3202995775","doi":"10.48550/arxiv.2110.00678","title":"Speech Technology for Everyone: Automatic Speech Recognition for Non-Native English with Transfer Learning","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Speech recognition; Computer science; Transfer of learning; Transfer (computing); Natural language processing; Speech technology; Artificial intelligence; Speech processing","score_opus":0.05550620059544906,"score_gpt":0.1950521161755607,"score_spread":0.13954591558011165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3202995775","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49006572,0.0045757843,0.34823397,0.0015615874,0.0027789022,0.00092374464,0.01739049,0.104657196,0.02981258],"genre_scores_gemma":[0.7707244,0.0007534576,0.1546337,0.0009975611,0.00030318092,0.0007939495,0.043951105,0.0026474278,0.025195237],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985233,0.00042454494,0.00007225241,0.0005919973,0.00022327421,0.00016464778],"domain_scores_gemma":[0.9988404,0.00036613212,0.000027432947,0.00035213164,0.00032023145,0.000093741655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002524698,0.002096601,0.0009994645,0.0007680609,0.0006531105,0.0013532232,0.0015504136,0.0012517745,0.007932656],"category_scores_gemma":[0.0041329353,0.00041404943,0.00079759856,0.0004969415,0.00054645375,0.0024744892,0.0026175552,0.002406613,0.01177616],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002049403,0.0012897582,0.0070227073,0.00079106796,0.0005743871,0.00057348364,0.0010023117,0.040181167,0.06474093,0.002665519,0.09662696,0.78248215],"study_design_scores_gemma":[0.00042032287,0.0019076937,0.014230796,0.00013918332,0.00026107352,0.0012398326,0.0011599512,0.76668656,0.1590548,0.007887221,0.046743583,0.00026905333],"about_ca_topic_score_codex":0.008351579,"about_ca_topic_score_gemma":0.013066412,"teacher_disagreement_score":0.008351579,"about_ca_system_score_codex":0.0005539256,"about_ca_system_score_gemma":0.0009038829,"threshold_uncertainty_score":0.026537418},"labels":[],"label_agreement":null},{"id":"W3206189675","doi":"10.1109/icassp43922.2022.9747814","title":"Large-Scale Self-Supervised Speech Representation Learning for Automatic Speaker Verification","year":2022,"lang":"en","type":"article","venue":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":102,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Generalizability theory; Computer science; Speech recognition; Word error rate; Speaker recognition; Artificial intelligence; Representation (politics); Artificial neural network; Scale (ratio); Feature (linguistics); Pattern recognition (psychology); Machine learning; Mathematics","score_opus":0.0517667352431102,"score_gpt":0.3075118367600685,"score_spread":0.2557451015169583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3206189675","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.105989754,0.0015670863,0.87893015,0.00026106165,0.00020100054,0.00014321842,0.00056121417,0.00980564,0.0025408536],"genre_scores_gemma":[0.8104081,0.00035461478,0.18097953,0.00020582185,0.000119257296,0.00021208049,0.0030084362,0.00029030434,0.0044219713],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984571,0.0005954118,0.0000569385,0.00047526127,0.00031890097,0.00009643196],"domain_scores_gemma":[0.998173,0.00055955857,0.00012981136,0.0006718581,0.00040967137,0.000056047338],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020938853,0.0009885173,0.00083061395,0.00047837087,0.0003475823,0.00055410084,0.0013617254,0.0009018201,0.0015832711],"category_scores_gemma":[0.003927257,0.00029224728,0.00060377613,0.00038066143,0.00048018576,0.0016078998,0.0013038521,0.0013411324,0.001739394],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049681653,0.00033242613,0.0015558398,0.00013389435,0.00013830939,0.00006363054,0.00011679075,0.09967714,0.042110663,0.001947413,0.008189127,0.845238],"study_design_scores_gemma":[0.000015363514,0.00011662253,0.0008712773,0.000008662662,0.000023725299,0.00006243444,0.000024917093,0.9729192,0.023200328,0.0015288213,0.0012129843,0.000015738351],"about_ca_topic_score_codex":0.0022835894,"about_ca_topic_score_gemma":0.0030387607,"teacher_disagreement_score":0.0022835894,"about_ca_system_score_codex":0.00043841926,"about_ca_system_score_gemma":0.00077707344,"threshold_uncertainty_score":0.011073649},"labels":[],"label_agreement":null},{"id":"W3207572704","doi":"10.1109/icassp43922.2022.9746260","title":"Continual Learning Using Lattice-Free MMI for Speech Recognition","year":2022,"lang":"en","type":"article","venue":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"NeuroRx Research (Canada)","funders":"","keywords":"Forgetting; Computer science; Regularization (linguistics); Artificial neural network; Exploit; Speech recognition; Word error rate; Artificial intelligence; Acoustic model; Domain adaptation; Machine learning; Speech processing","score_opus":0.09276504634484213,"score_gpt":0.3157352333647936,"score_spread":0.22297018701995147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3207572704","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051103286,0.00042931642,0.94481796,0.00018971317,0.000053962594,0.000045042096,0.00006565566,0.0019488606,0.001346208],"genre_scores_gemma":[0.71623373,0.0001834114,0.28041622,0.00018679393,0.000055994155,0.00014075736,0.00030061486,0.00020847075,0.0022739996],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993862,0.00019241123,0.000037598835,0.00017920608,0.00014491144,0.00005964966],"domain_scores_gemma":[0.9979894,0.0010165315,0.00018189759,0.00040933478,0.00030371407,0.00009913377],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017689269,0.00087791024,0.0008221137,0.0005783949,0.00039015297,0.0006681624,0.0018004786,0.0009534013,0.0018838834],"category_scores_gemma":[0.005306642,0.0004816729,0.00070148316,0.00056361675,0.0010406828,0.0018442993,0.001630142,0.0021550644,0.00087625795],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023566965,0.00027434638,0.0021225365,0.00010145484,0.000086305845,0.00010080577,0.0001431922,0.6508461,0.013778351,0.00847843,0.0018141776,0.32201853],"study_design_scores_gemma":[0.000004944629,0.000035668043,0.00008122279,0.0000024823496,0.0000026284229,0.00001402492,0.000005573804,0.9962955,0.0017880726,0.0015920906,0.0001731367,0.000004641763],"about_ca_topic_score_codex":0.002790275,"about_ca_topic_score_gemma":0.0045491015,"teacher_disagreement_score":0.002790275,"about_ca_system_score_codex":0.00066920405,"about_ca_system_score_gemma":0.0007509102,"threshold_uncertainty_score":0.009355128},"labels":[],"label_agreement":null},{"id":"W3208368542","doi":"10.5281/zenodo.4309193","title":"Humelo/Prosody-API-Document: First release for zenodo connect test","year":2020,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Humber College","funders":"","keywords":"Prosody; Test (biology); Computer science; Natural language processing; Speech recognition; Geology","score_opus":0.045376276028887316,"score_gpt":0.23300364903911477,"score_spread":0.18762737301022747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208368542","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030831788,0.00071204023,0.07827735,0.0006124062,0.001169683,0.0019201972,0.29434764,0.4952106,0.09691835],"genre_scores_gemma":[0.095304854,0.00027403273,0.032781236,0.0006257159,0.0002737911,0.0026412236,0.6541707,0.1278011,0.086127356],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986966,0.00022341181,0.00014283718,0.0002465227,0.0005421907,0.00014841827],"domain_scores_gemma":[0.99669707,0.0006663604,0.00012722175,0.0009881189,0.0011805602,0.00034068554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016377362,0.0032714116,0.0015296225,0.0016784223,0.0006455696,0.0022332794,0.0028716049,0.001995699,0.26162425],"category_scores_gemma":[0.0047433963,0.0011304498,0.0007076525,0.0008556752,0.0004615735,0.0029027343,0.0025337671,0.0020059252,0.22069144],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0047128797,0.0006670635,0.0018891427,0.0016477774,0.00016113382,0.0004619043,0.00036841098,0.0014922887,0.057314403,0.0030883893,0.7671912,0.1610054],"study_design_scores_gemma":[0.0020445634,0.0016564319,0.016127216,0.00039399936,0.00015598835,0.0017149254,0.00040823346,0.029813189,0.1767753,0.007709475,0.76264256,0.00055822113],"about_ca_topic_score_codex":0.0026035344,"about_ca_topic_score_gemma":0.00200812,"teacher_disagreement_score":0.26162425,"about_ca_system_score_codex":0.00039862195,"about_ca_system_score_gemma":0.0006918922,"threshold_uncertainty_score":0.8752203},"labels":[],"label_agreement":null},{"id":"W3209371554","doi":"10.1109/icassp43922.2022.9747760","title":"Optimizing Alignment of Speech and Language Latent Spaces for End-To-End Speech Recognition and Understanding","year":2022,"lang":"en","type":"article","venue":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Speech recognition; Encoder; Language model; Embedding; Word error rate; Context (archaeology); Connectionism; End-to-end principle; Task (project management); Natural language processing; Artificial intelligence; Artificial neural network","score_opus":0.10644103280632176,"score_gpt":0.3075885950457152,"score_spread":0.2011475622393934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209371554","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01812629,0.00025606263,0.9766309,0.00015493055,0.000058066886,0.00004953139,0.00014316535,0.0036584486,0.0009226035],"genre_scores_gemma":[0.4726577,0.00047569638,0.51437235,0.0004207501,0.00013093921,0.00034371027,0.0020778466,0.0008214117,0.008699557],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989378,0.0003229029,0.000057248406,0.0003747347,0.00018445309,0.00012289954],"domain_scores_gemma":[0.99919003,0.00037363835,0.000068635,0.00014241347,0.00016936583,0.000055950455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010932086,0.0015436868,0.00082398497,0.000577522,0.00039290794,0.0009043791,0.0010082523,0.0012787064,0.004214373],"category_scores_gemma":[0.003103561,0.00047073778,0.00084367674,0.0006672534,0.000597094,0.002260559,0.001730274,0.0022426995,0.0037307031],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050966785,0.00045968045,0.0012123996,0.00014690323,0.000104529536,0.00022171593,0.00027617952,0.13078667,0.09805091,0.006518027,0.0072014933,0.75451183],"study_design_scores_gemma":[0.0000186075,0.00009309261,0.00053728255,0.000009189198,0.000025270287,0.000081322825,0.00008022859,0.9654831,0.026803574,0.0053849984,0.0014656311,0.000017601102],"about_ca_topic_score_codex":0.0037415794,"about_ca_topic_score_gemma":0.0061799004,"teacher_disagreement_score":0.004214373,"about_ca_system_score_codex":0.00056826137,"about_ca_system_score_gemma":0.0012646803,"threshold_uncertainty_score":0.014098465},"labels":[],"label_agreement":null},{"id":"W3209976096","doi":"10.1109/icassp43922.2022.9746832","title":"Pseudo-Labeling for Massively Multilingual Speech Recognition","year":2022,"lang":"en","type":"article","venue":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Natural language processing; Speech recognition; Artificial intelligence; Language model","score_opus":0.08598030702419207,"score_gpt":0.3185981659794001,"score_spread":0.23261785895520803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209976096","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008749971,0.00017923716,0.9800514,0.0001841143,0.00011082793,0.00009856301,0.00039838345,0.008730046,0.0014974305],"genre_scores_gemma":[0.21454053,0.00015285656,0.7733205,0.000563492,0.00013118691,0.0006326283,0.0041887676,0.0016200001,0.004850006],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9976495,0.001070474,0.00013124863,0.0006624317,0.00036262345,0.00012369182],"domain_scores_gemma":[0.99532384,0.0019095348,0.00022777753,0.0015685519,0.00079731934,0.00017299736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002543429,0.0016003037,0.0009094463,0.0008320355,0.0010499611,0.0013580685,0.0026974704,0.0013272087,0.0054763444],"category_scores_gemma":[0.007083763,0.00082194374,0.0010257908,0.0008283131,0.0015841026,0.003338422,0.0036287333,0.002798351,0.0047891387],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009545847,0.00037960004,0.0025292432,0.00043980862,0.00016549892,0.00043368057,0.00070384913,0.21189165,0.043023624,0.030963628,0.026007358,0.68250746],"study_design_scores_gemma":[0.00004248732,0.00009649493,0.00032199136,0.000025637348,0.000017218732,0.00012508959,0.00006921318,0.9341763,0.016009657,0.039011925,0.010053775,0.000050211427],"about_ca_topic_score_codex":0.0032520306,"about_ca_topic_score_gemma":0.0074797235,"teacher_disagreement_score":0.0054763444,"about_ca_system_score_codex":0.0009118405,"about_ca_system_score_gemma":0.0015787858,"threshold_uncertainty_score":0.018320262},"labels":[],"label_agreement":null},{"id":"W3210306132","doi":"10.1109/rteict52294.2021.9573848","title":"Emotional Speech Cloning using GANs","year":2021,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Speech recognition; Discriminator; Sadness; Speech synthesis; Context (archaeology); Generator (circuit theory); Cloning (programming); Artificial neural network; Anger; Active listening; Field (mathematics); Natural language processing; Artificial intelligence; Psychology; Telecommunications","score_opus":0.05172122108534818,"score_gpt":0.2743723135183435,"score_spread":0.22265109243299533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210306132","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03320793,0.0005147641,0.958235,0.00025042586,0.00019785471,0.00004980643,0.00012432273,0.0023156942,0.005104144],"genre_scores_gemma":[0.78138554,0.0004614733,0.20435107,0.00047163226,0.00013831227,0.00013389204,0.00069295906,0.00035336157,0.012011743],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99976665,0.00006927994,0.000009011122,0.000070689624,0.00005385184,0.000030481035],"domain_scores_gemma":[0.9996635,0.00019320167,0.000018108081,0.00004954826,0.000062087485,0.000013628644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057956256,0.0006630509,0.00037358084,0.00019840068,0.00013661012,0.00044194222,0.0005855411,0.00051357184,0.0023370918],"category_scores_gemma":[0.0013879786,0.00023961144,0.0005518729,0.0001419351,0.00036071832,0.0005984103,0.000617657,0.00097487005,0.0007438914],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032162116,0.000097518365,0.0012540852,0.00013432275,0.000119865246,0.00025757286,0.00016340616,0.5665167,0.046862993,0.013370439,0.0064162794,0.36448523],"study_design_scores_gemma":[0.0000062885456,0.00003265893,0.00016720247,0.000007169447,0.000011919436,0.00004495912,0.000009909267,0.98999035,0.005915991,0.0024672917,0.0013411088,0.0000051068696],"about_ca_topic_score_codex":0.0012479775,"about_ca_topic_score_gemma":0.0019842358,"teacher_disagreement_score":0.0023370918,"about_ca_system_score_codex":0.00033920349,"about_ca_system_score_gemma":0.0002490171,"threshold_uncertainty_score":0.007818401},"labels":[],"label_agreement":null},{"id":"W3210530853","doi":"10.1109/icassp43922.2022.9746484","title":"A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion","year":2022,"lang":"en","type":"article","venue":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":107,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ubisoft (Canada)","funders":"","keywords":"Computer science; Speech recognition","score_opus":0.07575626700609553,"score_gpt":0.3305673919311458,"score_spread":0.2548111249250503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210530853","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49260107,0.002761368,0.48966724,0.00043941403,0.00030625635,0.00013052781,0.0001777188,0.0027638262,0.011152612],"genre_scores_gemma":[0.9221697,0.00029428428,0.07466713,0.00011680717,0.000041514173,0.00005273872,0.00020505245,0.0001183467,0.0023344175],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993349,0.000222741,0.000050935596,0.0001270294,0.00020704701,0.00005732515],"domain_scores_gemma":[0.9986725,0.00076918915,0.00006103824,0.00020409064,0.00020807469,0.000085104584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012090384,0.0004504875,0.00047123298,0.0005503509,0.00016299917,0.00092964666,0.0005874094,0.0005066113,0.0034318995],"category_scores_gemma":[0.0038033035,0.00014185514,0.00039265535,0.0003563632,0.00048635388,0.0011495901,0.0008019529,0.0008565289,0.0007035811],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021420058,0.00040102832,0.0014757629,0.00029436618,0.00009428184,0.00014089141,0.00014004746,0.104853064,0.08213743,0.0055633103,0.0009909287,0.8017669],"study_design_scores_gemma":[0.00010640378,0.001197722,0.0032148447,0.00003844069,0.00007135707,0.00019815737,0.00011681701,0.91319686,0.07586293,0.0038463664,0.0021079779,0.000042108662],"about_ca_topic_score_codex":0.0005619076,"about_ca_topic_score_gemma":0.0006469668,"teacher_disagreement_score":0.0034318995,"about_ca_system_score_codex":0.00029746655,"about_ca_system_score_gemma":0.00030033878,"threshold_uncertainty_score":0.011480808},"labels":[],"label_agreement":null},{"id":"W3214993239","doi":"10.1121/10.0008538","title":"APhL aligner: A neural network forced-alignment system","year":2021,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Phone; Speech recognition; Interval (graph theory); Interpolation (computer graphics); Pronunciation; Boundary (topology); Artificial neural network; Point (geometry); TIMIT; Artificial intelligence; Acoustics; Hidden Markov model; Mathematics; Linguistics","score_opus":0.014738017954428346,"score_gpt":0.23123460596303078,"score_spread":0.21649658800860244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214993239","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05698018,0.0006118572,0.76260865,0.00058015675,0.0007184313,0.0005763472,0.0057166056,0.15701099,0.01519682],"genre_scores_gemma":[0.25124982,0.0001398995,0.7079453,0.0008327778,0.00012316111,0.0006160071,0.00808355,0.0028857342,0.028123777],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993954,0.00006567383,0.000032114924,0.00030350796,0.00015341437,0.000049877744],"domain_scores_gemma":[0.99953413,0.00012566855,0.00003820857,0.00012801534,0.0001400337,0.00003394693],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008203208,0.0010294297,0.0007016824,0.0005657818,0.0007104533,0.0008595265,0.0018598436,0.0012713592,0.02125014],"category_scores_gemma":[0.0023041898,0.00062133954,0.00040574625,0.0004579284,0.00048392886,0.0018857761,0.0016993055,0.0017993922,0.0074860463],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00093875587,0.00021038267,0.0016458232,0.00032596235,0.000118531585,0.00048285606,0.0002538738,0.022651982,0.16820626,0.00324273,0.046296846,0.755626],"study_design_scores_gemma":[0.00029959477,0.0003833433,0.0042595426,0.00004587064,0.00008924327,0.0005963494,0.00011264958,0.7911993,0.15508819,0.0058922926,0.0418885,0.00014503582],"about_ca_topic_score_codex":0.0073937555,"about_ca_topic_score_gemma":0.013296666,"teacher_disagreement_score":0.02125014,"about_ca_system_score_codex":0.00083266204,"about_ca_system_score_gemma":0.00113814,"threshold_uncertainty_score":0.07108879},"labels":[],"label_agreement":null},{"id":"W3217533145","doi":"10.1121/10.0008580","title":"Exploring the variable efficacy of Google speech-to-text with spontaneous bilingual speech in Cantonese and English","year":2021,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Context (archaeology); Variation (astronomy); Variable (mathematics); Matching (statistics); Speech recognition; Multilingualism; Natural language processing; Linguistics; Psychology; Mathematics; History; Statistics","score_opus":0.026358114819322445,"score_gpt":0.23888731842026484,"score_spread":0.2125292036009424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3217533145","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99814355,0.000027673252,0.0003485697,0.000032038835,0.000006492005,0.000050331822,0.0001267881,0.000027339034,0.0012371554],"genre_scores_gemma":[0.9972383,0.000039834118,0.0011089604,0.00002536917,0.000010316828,0.000064516964,0.0004986676,0.000024712628,0.0009892794],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9940796,0.0033265816,0.00042807308,0.0008406761,0.0010548359,0.0002703884],"domain_scores_gemma":[0.96751696,0.021852935,0.0026645462,0.0023364746,0.0043489495,0.0012802818],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009092648,0.00080563483,0.00045105084,0.0009488943,0.0008982534,0.002428101,0.0006699635,0.0005658465,0.0019989994],"category_scores_gemma":[0.039288923,0.00028600427,0.00033396613,0.00047534745,0.001197587,0.0016498978,0.0015189686,0.0004823198,0.0009241232],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008303967,0.0031135203,0.5569717,0.0015277491,0.00047381883,0.0016873768,0.10229663,0.0075421887,0.09846865,0.0010580402,0.0030120672,0.21554428],"study_design_scores_gemma":[0.00023806188,0.0057057417,0.90066546,0.00014441578,0.00031423132,0.00085260475,0.035330612,0.024841832,0.02754546,0.0006711165,0.0034358855,0.00025455712],"about_ca_topic_score_codex":0.035189234,"about_ca_topic_score_gemma":0.050449863,"teacher_disagreement_score":0.035189234,"about_ca_system_score_codex":0.0012757368,"about_ca_system_score_gemma":0.0010501166,"threshold_uncertainty_score":0.06996882},"labels":[],"label_agreement":null},{"id":"W4200004927","doi":"10.1109/pst52912.2021.9647775","title":"SegmentPerturb: Effective Black-Box Hidden Voice Attack on Commercial ASR Systems via Selective Deletion","year":2021,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Voice command device; Speech recognition; Voice activity detection; Speaker recognition; Black box; Control (management); Mobile device; Smartwatch; Human–computer interaction; Speech processing; Artificial intelligence; Embedded system; Operating system","score_opus":0.025661827251802424,"score_gpt":0.26884072239596746,"score_spread":0.24317889514416502,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200004927","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21908282,0.00039396543,0.76908207,0.00026363638,0.00008556816,0.00017734533,0.000096046264,0.0074071437,0.0034114155],"genre_scores_gemma":[0.87067467,0.00011635766,0.12560934,0.00013298402,0.00004210885,0.00006077453,0.00016197903,0.00019108741,0.0030106986],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991522,0.00021677083,0.000043850614,0.00015015993,0.00032253694,0.00011451161],"domain_scores_gemma":[0.99882084,0.00048178012,0.00013061486,0.00038883951,0.00011824232,0.000059645376],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061004783,0.0008106507,0.0007009355,0.00055677595,0.00048319413,0.00053936755,0.00067310844,0.0008289496,0.0016726085],"category_scores_gemma":[0.0019955463,0.00021454645,0.00036323653,0.00024851307,0.00082015444,0.00156884,0.0013748732,0.0006775942,0.000781763],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027354,0.0002791139,0.004073063,0.00022054031,0.00013104406,0.00096166687,0.0006552541,0.091483355,0.35217673,0.015475915,0.006066864,0.5257411],"study_design_scores_gemma":[0.00008304596,0.0008008177,0.0013695549,0.000015863934,0.000042422114,0.0009664773,0.00015273571,0.8049107,0.18070726,0.0052657197,0.0056466535,0.000038764603],"about_ca_topic_score_codex":0.00043340444,"about_ca_topic_score_gemma":0.00051664247,"teacher_disagreement_score":0.0016726085,"about_ca_system_score_codex":0.00032012153,"about_ca_system_score_gemma":0.00037599468,"threshold_uncertainty_score":0.005595386},"labels":[],"label_agreement":null},{"id":"W4200153536","doi":"10.31234/osf.io/y6gnh","title":"Intelligibility benefit for familiar voices does not depend on better discrimination of fundamental frequency or vocal tract length","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Timbre; Psychology; Formant; Vocal tract; Intelligibility (philosophy); Perception; Acoustics; Audiology; Cognitive psychology; Speech recognition; Vowel; Computer science; Musical","score_opus":0.06553322139946756,"score_gpt":0.31607531447158044,"score_spread":0.2505420930721129,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200153536","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99749184,0.00019830719,0.0012030508,0.000053435586,0.000017852208,0.000008537886,0.000038682057,0.000049883693,0.00093840796],"genre_scores_gemma":[0.9983265,0.00004989973,0.00085393566,0.00006536047,0.000020623012,0.000009741288,0.00008248309,0.000022760989,0.00056880066],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99960846,0.000064421,0.000053309133,0.0001000209,0.00012950321,0.000044305852],"domain_scores_gemma":[0.99720085,0.001246458,0.00051230815,0.00039372817,0.0001957734,0.00045089098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079567754,0.00030814,0.000441213,0.00028198486,0.00013165789,0.0005076697,0.00021931154,0.00047742724,0.0039652805],"category_scores_gemma":[0.0024831588,0.00022230165,0.00021806006,0.00005259552,0.00047872626,0.0005710119,0.00064154726,0.0005588479,0.00057348213],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001548635,0.00014242435,0.008125825,0.000111783425,0.000059294685,0.00033108622,0.0001633802,0.000045953377,0.9775754,0.00007761836,0.00008715896,0.011731351],"study_design_scores_gemma":[0.00016589763,0.0069950395,0.7011357,0.00002788547,0.00018820241,0.0037586393,0.0005805812,0.0009240292,0.2833188,0.00071214326,0.0021416387,0.000051568102],"about_ca_topic_score_codex":0.00010035095,"about_ca_topic_score_gemma":0.00027903076,"teacher_disagreement_score":0.0039652805,"about_ca_system_score_codex":0.00008697706,"about_ca_system_score_gemma":0.00008111609,"threshold_uncertainty_score":0.0132651925},"labels":[],"label_agreement":null},{"id":"W4200300291","doi":"10.21105/joss.03958","title":"Phonemizer: Text to Phones Transcription for Multiple Languages in Python","year":2021,"lang":"en","type":"article","venue":"The Journal of Open Source Software","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":82,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Agence Nationale de la Recherche; Canadian Institute for Advanced Research; Microsoft Research","keywords":"Python (programming language); Computer science; Transcription (linguistics); Programming language; World Wide Web; Linguistics; Philosophy","score_opus":0.034780526084438636,"score_gpt":0.30247217448345226,"score_spread":0.2676916483990136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200300291","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026424883,0.00012929992,0.26396155,0.00019898031,0.00022341832,0.00024543438,0.022699902,0.6992526,0.010646355],"genre_scores_gemma":[0.082340255,0.00046929985,0.3089526,0.0013126147,0.0002722187,0.0019972406,0.09078325,0.46244025,0.051432252],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989887,0.0001267647,0.00009387242,0.00025501163,0.00038165055,0.00015401222],"domain_scores_gemma":[0.999042,0.00023813146,0.00008934197,0.00025667585,0.00025710533,0.00011676996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008546281,0.0016061387,0.00087630557,0.0008385421,0.00056031754,0.0014843153,0.002404663,0.00076396065,0.11103091],"category_scores_gemma":[0.0032673217,0.0010715419,0.0010114483,0.0006981954,0.0006681828,0.0023373922,0.0031473716,0.002380206,0.08090364],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012373382,0.0001836235,0.0016069667,0.0018594231,0.00018509933,0.00078163296,0.0009972798,0.0041318405,0.047572613,0.010766812,0.692952,0.23772538],"study_design_scores_gemma":[0.00048528225,0.00019643916,0.004425052,0.00027817948,0.0000819574,0.0011038107,0.00022529144,0.04514148,0.11019729,0.025273444,0.81220955,0.00038212637],"about_ca_topic_score_codex":0.0011566652,"about_ca_topic_score_gemma":0.001472998,"teacher_disagreement_score":0.11103091,"about_ca_system_score_codex":0.00044045591,"about_ca_system_score_gemma":0.0013332423,"threshold_uncertainty_score":0.3714354},"labels":[],"label_agreement":null},{"id":"W4200482297","doi":"10.1145/3494987","title":"SpeeChin","year":2021,"lang":"en","type":"article","venue":"Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Speech recognition; Session (web analytics); Convolutional neural network; Natural language processing; Syllable; Chin; Artificial intelligence; World Wide Web","score_opus":0.013344885097684268,"score_gpt":0.2456831710635254,"score_spread":0.23233828596584113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200482297","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04797128,0.005732238,0.25351217,0.002888875,0.004458013,0.0010592557,0.026701426,0.2660829,0.39159387],"genre_scores_gemma":[0.22544298,0.0039925533,0.15194878,0.005606821,0.0010774842,0.001193535,0.074658304,0.021598097,0.5144814],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993926,0.0000879181,0.000048600057,0.00016992798,0.00021362398,0.00008733706],"domain_scores_gemma":[0.9991922,0.00018627493,0.00005020531,0.00020293535,0.0002519574,0.00011649052],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007472902,0.0014841859,0.00057593425,0.0007535822,0.0006194589,0.0016281767,0.0014165612,0.0009852782,0.091658235],"category_scores_gemma":[0.0019911977,0.00038040947,0.0005116335,0.00043542444,0.00038574298,0.0026644925,0.0024590106,0.0007367847,0.066185094],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021625762,0.00022489691,0.0024629314,0.0013090795,0.00007716873,0.00070179626,0.000783092,0.0012071462,0.03454939,0.01370457,0.4374037,0.5054136],"study_design_scores_gemma":[0.00011672662,0.0003858085,0.0023762763,0.00013732917,0.00006415292,0.0011737059,0.00026918226,0.009063441,0.029984657,0.0050739166,0.9512534,0.000101463665],"about_ca_topic_score_codex":0.0011962809,"about_ca_topic_score_gemma":0.0024649515,"teacher_disagreement_score":0.091658235,"about_ca_system_score_codex":0.00043091844,"about_ca_system_score_gemma":0.0006740392,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W4205101752","doi":"10.18280/ts.380623","title":"Dialect Identification in Telugu Language Speech Utterance Using Modified Features with Deep Neural Network","year":2021,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Telugu; Computer science; Mel-frequency cepstrum; Hidden Markov model; Artificial neural network; Artificial intelligence; Identification (biology); Speech recognition; Language identification; Utterance; Natural language processing; Feature (linguistics); Feature extraction; Natural language; Linguistics","score_opus":0.020629811216508243,"score_gpt":0.245858799548895,"score_spread":0.22522898833238675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205101752","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6771667,0.0018465846,0.30937356,0.0004268393,0.00043672504,0.00013926129,0.001233826,0.0024873856,0.006889129],"genre_scores_gemma":[0.94373804,0.0004316058,0.047702886,0.00007688099,0.00004307384,0.000060317194,0.0017210772,0.00006097793,0.0061651603],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9998332,0.000025310228,0.000011579868,0.000054899512,0.000042417225,0.00003250911],"domain_scores_gemma":[0.9998616,0.0000349636,0.000010694836,0.000009662781,0.000071138726,0.000011876495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002241497,0.00043421699,0.00032836132,0.00047684097,0.00020589292,0.00035528737,0.00032008337,0.0003187034,0.0016867933],"category_scores_gemma":[0.0005930385,0.00014150645,0.0003835813,0.00026029412,0.0001233494,0.0004417428,0.00039695116,0.0005394182,0.0005941647],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009309935,0.00033901428,0.01192882,0.00023265893,0.00014959574,0.0006300709,0.0004216086,0.05006382,0.09609936,0.00073131546,0.006227099,0.8322456],"study_design_scores_gemma":[0.000014944425,0.00022208139,0.017072419,0.000027708162,0.00006735829,0.00023053797,0.00023501858,0.9489084,0.03014259,0.00057209353,0.002472619,0.000034293775],"about_ca_topic_score_codex":0.008336741,"about_ca_topic_score_gemma":0.01080067,"teacher_disagreement_score":0.008336741,"about_ca_system_score_codex":0.00031681274,"about_ca_system_score_gemma":0.0002802922,"threshold_uncertainty_score":0.016576469},"labels":[],"label_agreement":null},{"id":"W4210486131","doi":"10.1109/asru51503.2021.9687877","title":"Hybrid Network with Multi-Level Global-Local Statistics Pooling for Robust Text-Independent Speaker Recognition","year":2021,"lang":"en","type":"article","venue":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Pooling; NIST; Speech recognition; Speaker recognition; Context (archaeology); Artificial intelligence; Set (abstract data type); Speaker diarisation; Hybrid system; Pattern recognition (psychology); Machine learning","score_opus":0.14976837305959667,"score_gpt":0.283479670430947,"score_spread":0.13371129737135035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210486131","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04235844,0.0017842634,0.9480122,0.0002030893,0.00026763877,0.00010083425,0.0003147678,0.0043385425,0.002620224],"genre_scores_gemma":[0.654555,0.0007941129,0.33046082,0.00047916695,0.000347242,0.00024702054,0.0014436992,0.00030512974,0.0113677895],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99938285,0.000113361806,0.000030220977,0.0002540043,0.00013382148,0.00008574201],"domain_scores_gemma":[0.99968386,0.00009609335,0.00002949355,0.000054926077,0.00011324205,0.000022527647],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012222246,0.0013433606,0.00079881365,0.0006930128,0.00037521368,0.0006018396,0.0013288998,0.000814872,0.0027089461],"category_scores_gemma":[0.0010902149,0.0003893809,0.00073957787,0.00055090006,0.00037618002,0.0018712549,0.001296087,0.000904327,0.0016208135],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010448004,0.00026739814,0.0013990672,0.00021465111,0.00048601683,0.00027273304,0.00018429638,0.053512536,0.17570485,0.0025123311,0.0067298673,0.7576715],"study_design_scores_gemma":[0.000028791215,0.00027218464,0.0021357967,0.00001856599,0.0002078889,0.000223693,0.00004092178,0.9297901,0.061016273,0.002269837,0.0039314386,0.00006454732],"about_ca_topic_score_codex":0.0034865427,"about_ca_topic_score_gemma":0.005258228,"teacher_disagreement_score":0.0034865427,"about_ca_system_score_codex":0.0004488307,"about_ca_system_score_gemma":0.00044883107,"threshold_uncertainty_score":0.00906229},"labels":[],"label_agreement":null},{"id":"W4213101158","doi":"10.5220/0010816800003122","title":"Dynamic Latent Scale for GAN Inversion","year":2022,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Inversion (geology); Computer science; Scale (ratio); Geology; Physics; Geomorphology","score_opus":0.018830950667661762,"score_gpt":0.23235755396200458,"score_spread":0.2135266032943428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213101158","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023601407,0.00016364423,0.99473023,0.00011886278,0.000064011685,0.000020294048,0.00014468489,0.00086397846,0.0015341245],"genre_scores_gemma":[0.3248356,0.0006012183,0.6521557,0.00059751375,0.00022949943,0.0003216112,0.0021322297,0.0010781764,0.018048404],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99970347,0.00008645253,0.000009599672,0.00008576739,0.0000763419,0.000038210816],"domain_scores_gemma":[0.9996332,0.00015936383,0.000018245373,0.00009578016,0.00006889148,0.000024568653],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004839335,0.0009631577,0.0006147373,0.0003303114,0.00021821147,0.0006612171,0.00091375574,0.0010110885,0.007957643],"category_scores_gemma":[0.0019384227,0.00044894617,0.0006464553,0.00044701283,0.0004250416,0.0009206013,0.0010851595,0.0021997686,0.0033519906],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029518222,0.00012192964,0.0008373842,0.00017065516,0.0001235962,0.0001675123,0.00010926983,0.2924021,0.034167558,0.07037227,0.02750387,0.5737287],"study_design_scores_gemma":[0.000010402079,0.000019283383,0.00015750104,0.000009684733,0.0000072627636,0.000047618083,0.000010657181,0.97766477,0.0028563305,0.015673418,0.003533806,0.000009357609],"about_ca_topic_score_codex":0.00309082,"about_ca_topic_score_gemma":0.0075770444,"teacher_disagreement_score":0.007957643,"about_ca_system_score_codex":0.00038221062,"about_ca_system_score_gemma":0.000625668,"threshold_uncertainty_score":0.026620924},"labels":[],"label_agreement":null},{"id":"W4213234291","doi":"10.1186/s13634-022-00844-9","title":"Free resources for forced phonetic alignment in Brazilian Portuguese based on Kaldi toolkit","year":2022,"lang":"en","type":"article","venue":"EURASIP Journal on Advances in Signal Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Pró-Reitoria de Pesquisa e Pós-Graduação, Universidade Federal do Pará; Nvidia; Universidade Federal do Pará; Fundação Amazônia Paraense de Amparo à Pesquisa; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Computer science; Scripting language; Speech recognition; Phone; Portuguese; Natural language processing; Process (computing); Intersection (aeronautics); Artificial intelligence; Brazilian Portuguese; Linguistics; Programming language","score_opus":0.017650564225092733,"score_gpt":0.2759942747064355,"score_spread":0.25834371048134275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213234291","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028972061,0.0014546318,0.45503968,0.00064650027,0.0006316982,0.0006996224,0.07955144,0.40852112,0.024483277],"genre_scores_gemma":[0.19385372,0.0007472759,0.4730629,0.00051700475,0.0001156431,0.0019491338,0.26743236,0.050374463,0.0119473925],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99731356,0.0005642099,0.0005102416,0.000785894,0.0006174047,0.00020864143],"domain_scores_gemma":[0.99530965,0.0016510397,0.00026349004,0.0016584615,0.0008810098,0.00023635587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023648164,0.0023050562,0.0012312416,0.0025324372,0.0011787405,0.0021019503,0.0029069367,0.0012561136,0.026311146],"category_scores_gemma":[0.012742909,0.0013019708,0.001183349,0.0017531393,0.0008497949,0.003562519,0.0056190183,0.0022320133,0.025613856],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002698827,0.00039528945,0.0062684296,0.003994049,0.0002817364,0.0027090013,0.00339775,0.021293754,0.06478884,0.018806364,0.26644915,0.60891676],"study_design_scores_gemma":[0.00051351317,0.0003094556,0.011176566,0.00072884426,0.00021568216,0.0021641217,0.0012555514,0.16994116,0.13661838,0.024711588,0.65168506,0.00068003556],"about_ca_topic_score_codex":0.009823193,"about_ca_topic_score_gemma":0.01320727,"teacher_disagreement_score":0.026311146,"about_ca_system_score_codex":0.0009873088,"about_ca_system_score_gemma":0.002608476,"threshold_uncertainty_score":0.08801961},"labels":[],"label_agreement":null},{"id":"W4220982091","doi":"10.1080/15434303.2022.2038172","title":"Investigating the Effects of Task Type and Linguistic Background on Accuracy in Automated Speech Recognition Systems: Implications for Use in Language Assessment of Young Learners","year":2022,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Christian Studies; University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Task (project management); Computer science; Natural language processing; Artificial intelligence; Meaning (existential); Task analysis; Language proficiency; Test (biology); Psychology; Speech recognition","score_opus":0.03373161378752211,"score_gpt":0.33916975486964335,"score_spread":0.30543814108212125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220982091","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9975151,0.00009934288,0.0015405599,0.00004908243,0.000007638987,0.00003830981,0.000029425748,0.000012744455,0.0007077893],"genre_scores_gemma":[0.99676204,0.00006673537,0.0025210814,0.000050725786,0.000014296887,0.00006319594,0.00007304451,0.000016400983,0.0004325242],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98045087,0.011827575,0.0014291393,0.0018505128,0.0039930767,0.00044880062],"domain_scores_gemma":[0.71413535,0.24428588,0.019041682,0.00793962,0.011002743,0.0035947177],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027601201,0.00057076843,0.00061613834,0.0008754489,0.00052795577,0.0020893766,0.0006898741,0.0005519352,0.0013209978],"category_scores_gemma":[0.12513876,0.00033795962,0.0005875561,0.00069947215,0.00082292885,0.0018952234,0.0012771963,0.00068387704,0.0004997022],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002799876,0.0012154937,0.9232199,0.00012953869,0.00027382546,0.000120400444,0.0040192124,0.0010971172,0.01186227,0.00018945281,0.0001485276,0.054924257],"study_design_scores_gemma":[0.000028931625,0.003095093,0.9895056,0.00002535039,0.00005838739,0.00008529557,0.0010240942,0.0016761915,0.004172727,0.00015721371,0.00014743417,0.000023630897],"about_ca_topic_score_codex":0.0022451656,"about_ca_topic_score_gemma":0.0038311386,"teacher_disagreement_score":0.027601201,"about_ca_system_score_codex":0.0005326518,"about_ca_system_score_gemma":0.0007736636,"threshold_uncertainty_score":0.14597082},"labels":[],"label_agreement":null},{"id":"W4221140961","doi":"10.1109/jstsp.2022.3200909","title":"Are Discrete Units Necessary for Spoken Language Modeling?","year":2022,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Signal Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Grand Équipement National De Calcul Intensif; Agence Nationale de la Recherche; École des Hautes Etudes en Sciences Sociales; Canadian Institute for Advanced Research","keywords":"Computer science; Spoken language; Natural language processing; Linguistics","score_opus":0.04163231579509832,"score_gpt":0.2834469320030519,"score_spread":0.24181461620795355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221140961","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046616293,0.0034565937,0.9364214,0.004282621,0.0005293175,0.00006309961,0.00069640833,0.00086491194,0.007069382],"genre_scores_gemma":[0.84683067,0.002021729,0.145199,0.0009147361,0.00033983978,0.00023458706,0.0008963965,0.00032601136,0.0032370933],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99793905,0.0007911911,0.00014156166,0.00061494217,0.00038121577,0.00013206051],"domain_scores_gemma":[0.99338174,0.004311427,0.00043460642,0.0011672117,0.0004602446,0.00024469238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015840628,0.00054420106,0.0011053302,0.00036513407,0.00049826293,0.0021971485,0.0014435126,0.0015182161,0.005094769],"category_scores_gemma":[0.014308004,0.0006089761,0.0006316478,0.0006425502,0.0026580468,0.006223135,0.0014234708,0.0034304124,0.0023442942],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00090881356,0.0002108985,0.0063640573,0.0012704702,0.00020204813,0.00044543418,0.0017660101,0.12659109,0.036974654,0.46826088,0.008306048,0.34869963],"study_design_scores_gemma":[0.000085383224,0.00023244564,0.0025413749,0.00017892935,0.000059646896,0.0002866201,0.00053390727,0.42328373,0.012481459,0.5473362,0.012894462,0.0000857933],"about_ca_topic_score_codex":0.0021972791,"about_ca_topic_score_gemma":0.0012515784,"teacher_disagreement_score":0.005094769,"about_ca_system_score_codex":0.0007021674,"about_ca_system_score_gemma":0.0009603839,"threshold_uncertainty_score":0.01704371},"labels":[],"label_agreement":null},{"id":"W4224917505","doi":"10.1109/icassp43922.2022.9747452","title":"Robust Self-Supervised Speaker Representation Learning Via Instance Mix Regularization","year":2022,"lang":"en","type":"article","venue":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Embedding; Regularization (linguistics); Speech recognition; Feature learning; Utterance; Artificial intelligence; Supervised learning; Speaker recognition; Pattern recognition (psychology); Machine learning; Artificial neural network","score_opus":0.05941694244909695,"score_gpt":0.2801079894117903,"score_spread":0.22069104696269337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224917505","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033779997,0.0003551151,0.96067125,0.00015876202,0.000057267975,0.000055933895,0.00016808014,0.0036978847,0.0010556857],"genre_scores_gemma":[0.5878234,0.00025766363,0.39922127,0.000433205,0.00015850914,0.00022258009,0.0022467468,0.00068143354,0.008955092],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867094,0.0005022391,0.000044980487,0.00041668344,0.00026455944,0.00010067136],"domain_scores_gemma":[0.99876773,0.0004412141,0.00013504666,0.00030673124,0.00029219667,0.000057199697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019849543,0.0013251139,0.0011843921,0.0006350514,0.0003115967,0.0006624209,0.001969204,0.001163132,0.0016831005],"category_scores_gemma":[0.0030241106,0.0004639419,0.0010329231,0.00043435488,0.00068026705,0.0014036823,0.0017009426,0.0022037788,0.0012904787],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00057688507,0.00033583207,0.0017479681,0.0001795063,0.00031353917,0.00012603795,0.00020494396,0.2797608,0.047577344,0.007578396,0.013001999,0.64859676],"study_design_scores_gemma":[0.000008197692,0.000026900996,0.00014064378,0.0000029900232,0.0000079981455,0.000029928318,0.0000061659,0.9930233,0.0050551286,0.0013078131,0.0003839824,0.0000069748958],"about_ca_topic_score_codex":0.001605278,"about_ca_topic_score_gemma":0.002260471,"teacher_disagreement_score":0.0019849543,"about_ca_system_score_codex":0.00050249137,"about_ca_system_score_gemma":0.0006801705,"threshold_uncertainty_score":0.01049757},"labels":[],"label_agreement":null},{"id":"W4229455725","doi":"10.1121/10.0010882","title":"Evaluating the accuracy of forced alignment across Mandarin varieties","year":2022,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mandarin Chinese; Variety (cybernetics); Computer science; Phone; Variation (astronomy); Speech recognition; Beijing; Artificial intelligence; Acoustics; Linguistics; History; Physics; Philosophy","score_opus":0.04716307972668853,"score_gpt":0.33734243633737404,"score_spread":0.2901793566106855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229455725","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9306303,0.0017583565,0.04648769,0.00026109678,0.00034128362,0.00012466457,0.0040348414,0.004846406,0.01151533],"genre_scores_gemma":[0.95835906,0.00019600477,0.028873585,0.00012101904,0.000053554988,0.000117062795,0.0087539125,0.0014275224,0.002098256],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99275357,0.0021496597,0.00078569556,0.002741178,0.0011890017,0.00038089312],"domain_scores_gemma":[0.9758202,0.014044172,0.001182741,0.0037487054,0.00463753,0.00056673953],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0067342836,0.001243152,0.00086043694,0.0016378164,0.0010579877,0.0017680278,0.0011143379,0.0015847975,0.0036803442],"category_scores_gemma":[0.027860768,0.00046369561,0.000649954,0.0011478886,0.0010091681,0.0016923025,0.0016121684,0.00096306915,0.0037672834],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0059033185,0.0005834715,0.20704316,0.0017578102,0.0018437854,0.0016240018,0.008873609,0.06769794,0.2324556,0.0032813686,0.018231766,0.45070404],"study_design_scores_gemma":[0.00028583116,0.0020349023,0.4645314,0.00027286584,0.0005614628,0.0025942556,0.004994461,0.3013832,0.19765885,0.0046465187,0.020585673,0.00045063245],"about_ca_topic_score_codex":0.007939625,"about_ca_topic_score_gemma":0.011212083,"teacher_disagreement_score":0.007939625,"about_ca_system_score_codex":0.00049751665,"about_ca_system_score_gemma":0.000721372,"threshold_uncertainty_score":0.03561473},"labels":[],"label_agreement":null},{"id":"W4229458071","doi":"10.18280/ts.390235","title":"Speaker Identification Based on Physical Variation of Speech Signal","year":2022,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mel-frequency cepstrum; Speech recognition; Cepstrum; Speaker recognition; Computer science; Variation (astronomy); Identification (biology); Classifier (UML); Pattern recognition (psychology); Feature (linguistics); SIGNAL (programming language); Artificial intelligence; Feature extraction","score_opus":0.020835860932413106,"score_gpt":0.23737903835082555,"score_spread":0.21654317741841245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229458071","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20844807,0.0013006373,0.78352726,0.00012175963,0.00017730423,0.00010017221,0.00018162646,0.0015215826,0.0046216156],"genre_scores_gemma":[0.8216579,0.0007230961,0.17329808,0.000039665003,0.00010999211,0.000071183866,0.00032516522,0.00012969115,0.0036451996],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993148,0.000121363126,0.000028537395,0.00020602375,0.00028528867,0.000043922253],"domain_scores_gemma":[0.99944943,0.00019190292,0.000056050227,0.000051966977,0.00023121503,0.000019411753],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005025937,0.00032658334,0.00043184697,0.0009868353,0.00027271904,0.0005522307,0.0002689604,0.00031680157,0.0013343813],"category_scores_gemma":[0.0014516452,0.00011997128,0.00029998878,0.00038250498,0.00026387203,0.000762925,0.00032632035,0.00034540496,0.00089781696],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004129334,0.000047261783,0.0068226415,0.00025427088,0.00011252534,0.00025394798,0.00026690468,0.007692198,0.3976408,0.0020090586,0.0011621475,0.5833253],"study_design_scores_gemma":[0.00003361781,0.0008617978,0.08152739,0.000070018774,0.00027112407,0.003991388,0.00043808547,0.46271032,0.43249208,0.0043673264,0.013025997,0.00021081541],"about_ca_topic_score_codex":0.00036291513,"about_ca_topic_score_gemma":0.0003843463,"teacher_disagreement_score":0.0013343813,"about_ca_system_score_codex":0.00016139552,"about_ca_system_score_gemma":0.00016924914,"threshold_uncertainty_score":0.004463911},"labels":[],"label_agreement":null},{"id":"W4230248116","doi":"10.1007/978-1-4899-7502-7_984-1","title":"Privacy-Preserving Speech Recognition","year":2021,"lang":"en","type":"book-chapter","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Biometrics; Cloud computing; Internet privacy; Authentication (law); Computer security; Information privacy; Process (computing); World Wide Web","score_opus":0.059787939742645575,"score_gpt":0.24620604243606511,"score_spread":0.18641810269341955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230248116","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032348137,0.005667602,0.77222943,0.0019296235,0.001074615,0.000063350635,0.0005005757,0.0023113023,0.21298864],"genre_scores_gemma":[0.24166626,0.015558398,0.18857948,0.002051244,0.0021394838,0.00016160401,0.0015605661,0.0012040383,0.54707885],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990496,0.00016201718,0.000042618096,0.00018241446,0.00047730576,0.000086018124],"domain_scores_gemma":[0.99904007,0.00033037228,0.000034279954,0.00046852848,0.00010806864,0.000018742568],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067092676,0.0007707807,0.0005306137,0.0004919968,0.0006011173,0.0026917835,0.0010997489,0.0011638064,0.019560993],"category_scores_gemma":[0.0020314578,0.0004789259,0.000430054,0.0007362075,0.001416168,0.0026825212,0.0016350144,0.0017907924,0.016741201],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009155758,0.000045847275,0.00009255921,0.00023648495,0.000018829507,0.00014784574,0.00015011297,0.008892505,0.009716276,0.4555322,0.058341306,0.4667345],"study_design_scores_gemma":[0.000015018824,0.00007013541,0.00024237976,0.00012898017,0.000029693376,0.0012634918,0.00009109296,0.05144689,0.04284012,0.4769861,0.42684907,0.00003709602],"about_ca_topic_score_codex":0.0003556174,"about_ca_topic_score_gemma":0.00040653377,"teacher_disagreement_score":0.019560993,"about_ca_system_score_codex":0.0006707563,"about_ca_system_score_gemma":0.0005761846,"threshold_uncertainty_score":0.06543803},"labels":[],"label_agreement":null},{"id":"W4231504173","doi":"10.31234/osf.io/y8xcf","title":"Mixed-effects design analysis for experimental phonetics","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Statistical power; Sample size determination; Sign (mathematics); Phonetics; Null hypothesis; Magnitude (astronomy); Type I and type II errors; Statistics; Value (mathematics); Econometrics; Null (SQL); Sample (material); Computer science; Mathematics; Psychology; Linguistics; Data mining","score_opus":0.09505999670829285,"score_gpt":0.3023379607484315,"score_spread":0.20727796404013865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231504173","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024368817,0.0006872361,0.9612757,0.0011267199,0.0031800044,0.014882154,0.0048751393,0.0060250424,0.00551117],"genre_scores_gemma":[0.00854916,0.000238758,0.910336,0.00075722433,0.00024110264,0.07643486,0.00061762874,0.0011264456,0.0016988429],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.74580127,0.19590427,0.010629546,0.017395278,0.027524877,0.002744709],"domain_scores_gemma":[0.6357331,0.27850205,0.01852,0.05226304,0.013699861,0.0012819284],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14011876,0.006191555,0.0072556376,0.0062205144,0.0043275263,0.0075090425,0.007784509,0.0071314895,0.08632675],"category_scores_gemma":[0.39142263,0.0031036069,0.011862121,0.00862879,0.00566739,0.0060518803,0.006529158,0.013118179,0.014405668],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004849212,0.0016711826,0.0048269266,0.018571839,0.0067407903,0.0011556209,0.007386172,0.010151127,0.0077123987,0.42903912,0.19198939,0.31590623],"study_design_scores_gemma":[0.0043502706,0.009629115,0.008734814,0.0066516204,0.0031897144,0.0007851496,0.001710586,0.07417198,0.0139625585,0.3455263,0.5302053,0.0010825705],"about_ca_topic_score_codex":0.0021137896,"about_ca_topic_score_gemma":0.002692914,"teacher_disagreement_score":0.14011876,"about_ca_system_score_codex":0.0062584896,"about_ca_system_score_gemma":0.007999478,"threshold_uncertainty_score":0.7410277},"labels":[],"label_agreement":null},{"id":"W4233027766","doi":"10.1109/tasl.2013.2273045","title":"IEEE Transactions on Audio, Speech, and Language Processing publication information","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"University of Texas at Dallas; Korea Advanced Institute of Science and Technology; Hong Kong Polytechnic University; Tsinghua University; Aalborg Universitet; Nanyang Technological University; York University; Ben-Gurion University of the Negev; Bar-Ilan University; University of Cambridge; National Cheng Kung University; Institut national de recherche en informatique et en automatique (INRIA); Ohio State University","keywords":"Computer science; Speech recognition; Natural language processing","score_opus":0.012180034270205904,"score_gpt":0.2406691442479533,"score_spread":0.2284891099777474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233027766","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019376032,0.03964166,0.41537264,0.01114549,0.05948234,0.0007802887,0.0055787032,0.0049063805,0.44371647],"genre_scores_gemma":[0.09491786,0.026755087,0.070896514,0.0023883544,0.008283977,0.0003296196,0.012412121,0.00055221166,0.7834643],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99942183,0.00006078001,0.00004912268,0.0000641993,0.00034395198,0.00006018389],"domain_scores_gemma":[0.9989342,0.00016882374,0.000033811084,0.00014512548,0.00062368927,0.00009434691],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008596088,0.00080533925,0.00075455307,0.0010031349,0.000512851,0.0018012311,0.0006434157,0.0012018048,0.14073786],"category_scores_gemma":[0.0018116771,0.00018334299,0.00043328918,0.00083151914,0.00048268566,0.001332411,0.00076850236,0.0011559222,0.0646145],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000420794,0.00015493673,0.00092684885,0.00036877222,0.00006605322,0.00037596043,0.00008712658,0.0014473784,0.014629081,0.011001768,0.38790587,0.5826154],"study_design_scores_gemma":[0.000052299838,0.00018514109,0.0025041315,0.00019584585,0.000078447665,0.00076807453,0.000114025584,0.017981267,0.0070976648,0.009537867,0.961449,0.000036274785],"about_ca_topic_score_codex":0.0018329255,"about_ca_topic_score_gemma":0.0029218115,"teacher_disagreement_score":0.14073786,"about_ca_system_score_codex":0.00033051835,"about_ca_system_score_gemma":0.0011310122,"threshold_uncertainty_score":0.47081506},"labels":[],"label_agreement":null},{"id":"W4233734240","doi":"10.3390/cryptography1020016","title":"A Text-Independent Speaker Authentication System for Mobile Devices","year":2017,"lang":"en","type":"article","venue":"Cryptography","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Computer science; Authentication (law); Classifier (UML); Biometrics; Naive Bayes classifier; Reliability (semiconductor); Mobile device; Artificial intelligence; Speaker recognition; Speech recognition; Data mining; Computer security; Support vector machine; World Wide Web","score_opus":0.023812572285493803,"score_gpt":0.274783175883733,"score_spread":0.2509706035982392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233734240","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052833837,0.000824962,0.930131,0.00018135218,0.00050841016,0.0004480991,0.00036985683,0.01124302,0.0034594198],"genre_scores_gemma":[0.5554342,0.0005179737,0.42757118,0.0002792577,0.0002840547,0.00045702772,0.0009942661,0.0002192588,0.014242676],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994272,0.00011634182,0.000050572526,0.00015549648,0.00020511214,0.00004527334],"domain_scores_gemma":[0.9996327,0.00006235004,0.000026992073,0.000072138566,0.00017315014,0.000032627224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060314836,0.00054351526,0.00060719333,0.0004948402,0.00050666975,0.00054319855,0.00080710434,0.00083785487,0.0039801616],"category_scores_gemma":[0.0010094945,0.0002199146,0.00040715022,0.00027655813,0.00021133777,0.0007541199,0.0006791995,0.0006431034,0.0035796033],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00080952793,0.000113489994,0.001079533,0.0003312809,0.00010823118,0.00037508554,0.00023583353,0.0026060664,0.5336639,0.0028547049,0.005479058,0.45234329],"study_design_scores_gemma":[0.0002313991,0.0018428417,0.010895982,0.000112003836,0.00040336288,0.0035140656,0.00013596157,0.3781782,0.52883625,0.002375424,0.0732303,0.00024419365],"about_ca_topic_score_codex":0.0005605339,"about_ca_topic_score_gemma":0.0005010649,"teacher_disagreement_score":0.0039801616,"about_ca_system_score_codex":0.00021916917,"about_ca_system_score_gemma":0.00031149125,"threshold_uncertainty_score":0.013314962},"labels":[],"label_agreement":null},{"id":"W4233773279","doi":"10.1007/978-0-387-39940-9_2076","title":"Audio Parsing","year":2009,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Database Systems","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Parsing; Natural language processing","score_opus":0.02394974643188112,"score_gpt":0.2335670174814805,"score_spread":0.2096172710495994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233773279","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035399294,0.0024655028,0.47534084,0.0005324349,0.0014182442,0.0004653085,0.011460841,0.06132198,0.44345486],"genre_scores_gemma":[0.054662816,0.003181617,0.3827543,0.0010956425,0.00069448486,0.00038603303,0.037274037,0.013426288,0.50652486],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99964523,0.000017324373,0.000022238146,0.00011551801,0.00015812406,0.000041527554],"domain_scores_gemma":[0.99954766,0.00007737853,0.000015339027,0.00013386615,0.0001914403,0.000034167213],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032125428,0.0015792901,0.0007467997,0.002219449,0.00089441583,0.0027016825,0.0017809143,0.0009930587,0.19959795],"category_scores_gemma":[0.0011867293,0.000653781,0.00068438554,0.0016368093,0.00047654222,0.0019707135,0.001959812,0.001065185,0.17737621],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014223838,0.000041367046,0.000200731,0.0003768013,0.000016179574,0.00023255467,0.00012164923,0.00080896984,0.04204373,0.013797521,0.14340429,0.798814],"study_design_scores_gemma":[0.000029181967,0.000050729785,0.0008562644,0.00016248757,0.00004840042,0.0009126029,0.00013128911,0.0053589586,0.059778217,0.013792574,0.9188222,0.000057038007],"about_ca_topic_score_codex":0.0023099114,"about_ca_topic_score_gemma":0.0028301564,"teacher_disagreement_score":0.19959795,"about_ca_system_score_codex":0.00044380824,"about_ca_system_score_gemma":0.0008646762,"threshold_uncertainty_score":0.6677217},"labels":[],"label_agreement":null},{"id":"W4236361712","doi":"10.1121/1.3654817","title":"Perception of speaker sex in children's voices","year":2011,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Sentence; Psychology; Perception; Context (archaeology); Phrase; Age groups; Audiology; Linguistics; Medicine; Demography","score_opus":0.01817659713404111,"score_gpt":0.2361441229514645,"score_spread":0.2179675258174234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236361712","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99931276,0.00006630828,0.00019960241,0.0000066881357,0.0000030015092,0.000002965341,0.000034705285,0.0000069825255,0.00036704363],"genre_scores_gemma":[0.99888617,0.00008143873,0.00061804184,0.0000116906,0.000004000878,0.00000781186,0.00004811167,0.0000050018893,0.00033772064],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9996625,0.000056269146,0.000036548186,0.000063671796,0.00012059057,0.00006032609],"domain_scores_gemma":[0.9978694,0.0009835438,0.00051988463,0.000109420085,0.000325302,0.00019248266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006799864,0.0002618281,0.00030845834,0.00027268264,0.00013228988,0.0005400703,0.00014836225,0.0003002071,0.002191566],"category_scores_gemma":[0.003501112,0.00014122041,0.00017218562,0.00007946724,0.00032471624,0.00042975706,0.00045894267,0.00028215753,0.00027878108],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002457779,0.00014009024,0.40669087,0.0003071474,0.000074322015,0.0017883562,0.013922042,0.00044626262,0.5288462,0.00028363205,0.0002910596,0.04475215],"study_design_scores_gemma":[0.00003187809,0.0017063349,0.92859113,0.000042107542,0.000069500245,0.00217342,0.0046686386,0.00063776306,0.060471915,0.00017638018,0.0013863457,0.000044548928],"about_ca_topic_score_codex":0.0009810401,"about_ca_topic_score_gemma":0.0011285922,"teacher_disagreement_score":0.002191566,"about_ca_system_score_codex":0.00013184446,"about_ca_system_score_gemma":0.000107203894,"threshold_uncertainty_score":0.00733155},"labels":[],"label_agreement":null},{"id":"W4236397392","doi":"10.1145/1979742.1979724","title":"Performance","year":2011,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Emily Carr University of Art and Design; University of British Columbia","funders":"","keywords":"Computer science","score_opus":0.06481581633554469,"score_gpt":0.20672975120550138,"score_spread":0.14191393486995668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236397392","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07186842,0.002251073,0.117207624,0.0018304933,0.001969679,0.0009217617,0.017164323,0.0699525,0.71683407],"genre_scores_gemma":[0.28247437,0.0011345441,0.049371254,0.0019092377,0.00060644926,0.00046630125,0.04743042,0.0073209777,0.6092865],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99875927,0.000106988235,0.000051769002,0.00032092875,0.0005190084,0.00024204675],"domain_scores_gemma":[0.9986401,0.00018809944,0.000040816685,0.00037335439,0.00060946366,0.00014807947],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078516104,0.0012570245,0.0006639352,0.0012501534,0.0012612182,0.0020505572,0.0014218139,0.001152492,0.22149867],"category_scores_gemma":[0.0029197703,0.0002493295,0.0005847371,0.001181211,0.0003035019,0.0013216202,0.0014213191,0.0006961202,0.17658281],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018484088,0.00061294483,0.0025956044,0.00031880976,0.000073532654,0.00018331473,0.00012898332,0.005842909,0.061385512,0.005188541,0.22492394,0.69689745],"study_design_scores_gemma":[0.0003084087,0.0011841143,0.016505836,0.00015488504,0.00017786912,0.0012230912,0.0003868109,0.035509847,0.16899128,0.004973834,0.7704508,0.00013326178],"about_ca_topic_score_codex":0.005001409,"about_ca_topic_score_gemma":0.004658589,"teacher_disagreement_score":0.22149867,"about_ca_system_score_codex":0.0008717647,"about_ca_system_score_gemma":0.0016010398,"threshold_uncertainty_score":0.7409868},"labels":[],"label_agreement":null},{"id":"W4236464389","doi":"10.1109/tasl.2013.2273049","title":"IEEE Transactions on Audio, Speech, and Language Processing publication information","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"University of Texas at Dallas; Korea Advanced Institute of Science and Technology; Hong Kong Polytechnic University; Tsinghua University; Aalborg Universitet; Nanyang Technological University; York University; Ben-Gurion University of the Negev; Bar-Ilan University; University of Cambridge; National Cheng Kung University; Institut national de recherche en informatique et en automatique (INRIA); Ohio State University","keywords":"Computer science; Speech recognition; Audio mining; Speech processing; Natural language processing; Voice activity detection","score_opus":0.012180034270205904,"score_gpt":0.2406691442479533,"score_spread":0.2284891099777474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236464389","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019376032,0.03964166,0.41537264,0.01114549,0.05948234,0.0007802887,0.0055787032,0.0049063805,0.44371647],"genre_scores_gemma":[0.09491786,0.026755087,0.070896514,0.0023883544,0.008283977,0.0003296196,0.012412121,0.00055221166,0.7834643],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99942183,0.00006078001,0.00004912268,0.0000641993,0.00034395198,0.00006018389],"domain_scores_gemma":[0.9989342,0.00016882374,0.000033811084,0.00014512548,0.00062368927,0.00009434691],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008596088,0.00080533925,0.00075455307,0.0010031349,0.000512851,0.0018012311,0.0006434157,0.0012018048,0.14073786],"category_scores_gemma":[0.0018116771,0.00018334299,0.00043328918,0.00083151914,0.00048268566,0.001332411,0.00076850236,0.0011559222,0.0646145],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000420794,0.00015493673,0.00092684885,0.00036877222,0.00006605322,0.00037596043,0.00008712658,0.0014473784,0.014629081,0.011001768,0.38790587,0.5826154],"study_design_scores_gemma":[0.000052299838,0.00018514109,0.0025041315,0.00019584585,0.000078447665,0.00076807453,0.000114025584,0.017981267,0.0070976648,0.009537867,0.961449,0.000036274785],"about_ca_topic_score_codex":0.0018329255,"about_ca_topic_score_gemma":0.0029218115,"teacher_disagreement_score":0.8592621,"about_ca_system_score_codex":0.00033051835,"about_ca_system_score_gemma":0.0011310122,"threshold_uncertainty_score":0.47081506},"labels":[],"label_agreement":null},{"id":"W4238168884","doi":"10.1109/tasl.2013.2263986","title":"IEEE Transactions on Audio, Speech, and Language Processing publication information","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"University of Texas at Dallas; Korea Advanced Institute of Science and Technology; Hong Kong Polytechnic University; Tsinghua University; Aalborg Universitet; Nanyang Technological University; York University; Ben-Gurion University of the Negev; Bar-Ilan University; University of Cambridge; National Cheng Kung University; Institut national de recherche en informatique et en automatique (INRIA); Ohio State University","keywords":"Computer science; Speech recognition; Speech processing; Audio mining; Natural language processing; Voice activity detection","score_opus":0.012180034270205904,"score_gpt":0.2406691442479533,"score_spread":0.2284891099777474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4238168884","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019376032,0.03964166,0.41537264,0.01114549,0.05948234,0.0007802887,0.0055787032,0.0049063805,0.44371647],"genre_scores_gemma":[0.09491786,0.026755087,0.070896514,0.0023883544,0.008283977,0.0003296196,0.012412121,0.00055221166,0.7834643],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99942183,0.00006078001,0.00004912268,0.0000641993,0.00034395198,0.00006018389],"domain_scores_gemma":[0.9989342,0.00016882374,0.000033811084,0.00014512548,0.00062368927,0.00009434691],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008596088,0.00080533925,0.00075455307,0.0010031349,0.000512851,0.0018012311,0.0006434157,0.0012018048,0.14073786],"category_scores_gemma":[0.0018116771,0.00018334299,0.00043328918,0.00083151914,0.00048268566,0.001332411,0.00076850236,0.0011559222,0.0646145],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000420794,0.00015493673,0.00092684885,0.00036877222,0.00006605322,0.00037596043,0.00008712658,0.0014473784,0.014629081,0.011001768,0.38790587,0.5826154],"study_design_scores_gemma":[0.000052299838,0.00018514109,0.0025041315,0.00019584585,0.000078447665,0.00076807453,0.000114025584,0.017981267,0.0070976648,0.009537867,0.961449,0.000036274785],"about_ca_topic_score_codex":0.0018329255,"about_ca_topic_score_gemma":0.0029218115,"teacher_disagreement_score":0.8592621,"about_ca_system_score_codex":0.00033051835,"about_ca_system_score_gemma":0.0011310122,"threshold_uncertainty_score":0.47081506},"labels":[],"label_agreement":null},{"id":"W4239839560","doi":"10.1109/tasl.2013.2264640","title":"IEEE Transactions on Audio, Speech, and Language Processing publication information","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"University of Texas at Dallas; Korea Advanced Institute of Science and Technology; Hong Kong Polytechnic University; Tsinghua University; Aalborg Universitet; Nanyang Technological University; York University; Ben-Gurion University of the Negev; Bar-Ilan University; University of Cambridge; National Cheng Kung University; Institut national de recherche en informatique et en automatique (INRIA); Ohio State University","keywords":"Computer science; Speech recognition; Audio mining; Speech processing; Natural language processing; Voice activity detection","score_opus":0.012180034270205904,"score_gpt":0.2406691442479533,"score_spread":0.2284891099777474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239839560","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019376032,0.03964166,0.41537264,0.01114549,0.05948234,0.0007802887,0.0055787032,0.0049063805,0.44371647],"genre_scores_gemma":[0.09491786,0.026755087,0.070896514,0.0023883544,0.008283977,0.0003296196,0.012412121,0.00055221166,0.7834643],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99942183,0.00006078001,0.00004912268,0.0000641993,0.00034395198,0.00006018389],"domain_scores_gemma":[0.9989342,0.00016882374,0.000033811084,0.00014512548,0.00062368927,0.00009434691],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008596088,0.00080533925,0.00075455307,0.0010031349,0.000512851,0.0018012311,0.0006434157,0.0012018048,0.14073786],"category_scores_gemma":[0.0018116771,0.00018334299,0.00043328918,0.00083151914,0.00048268566,0.001332411,0.00076850236,0.0011559222,0.0646145],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000420794,0.00015493673,0.00092684885,0.00036877222,0.00006605322,0.00037596043,0.00008712658,0.0014473784,0.014629081,0.011001768,0.38790587,0.5826154],"study_design_scores_gemma":[0.000052299838,0.00018514109,0.0025041315,0.00019584585,0.000078447665,0.00076807453,0.000114025584,0.017981267,0.0070976648,0.009537867,0.961449,0.000036274785],"about_ca_topic_score_codex":0.0018329255,"about_ca_topic_score_gemma":0.0029218115,"teacher_disagreement_score":0.14073786,"about_ca_system_score_codex":0.00033051835,"about_ca_system_score_gemma":0.0011310122,"threshold_uncertainty_score":0.47081506},"labels":[],"label_agreement":null},{"id":"W4241475234","doi":"10.1002/0471219282.eot138","title":"Speech Processing","year":2003,"lang":"en","type":"other","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Naturalness; Computer science; Speech recognition; Voice activity detection; Speech synthesis; Speech technology; Vocabulary; Speech processing; Speech corpus; Speech analytics; Natural (archaeology); Natural language processing; Artificial intelligence; Linguistics","score_opus":0.021271344167064023,"score_gpt":0.2468486355925819,"score_spread":0.22557729142551788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4241475234","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0104007935,0.010124078,0.33807513,0.0045791212,0.005414369,0.0013936008,0.014276683,0.015483241,0.60025305],"genre_scores_gemma":[0.14656521,0.010047549,0.18731907,0.0038074127,0.002889808,0.0010869656,0.035084233,0.0026736262,0.61052614],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99904174,0.00015859658,0.00010900318,0.00024129552,0.00039328192,0.00005616094],"domain_scores_gemma":[0.99844944,0.000251993,0.000051325038,0.0003028057,0.0008883284,0.000056146917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010792773,0.0010727977,0.0007043647,0.0019012439,0.0008342107,0.004260886,0.0009917741,0.0010586018,0.1502922],"category_scores_gemma":[0.0036367609,0.0002203146,0.0005276212,0.0014197734,0.000494541,0.0011728538,0.0012483835,0.00091814285,0.140007],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026234167,0.000047347152,0.0005147554,0.0005567927,0.00004319971,0.00032349766,0.00024531552,0.0011704721,0.013245056,0.011806451,0.15390976,0.81787497],"study_design_scores_gemma":[0.00006868143,0.00015049495,0.0023929703,0.00043509773,0.000053823653,0.00092154334,0.00037388023,0.009153674,0.014301934,0.021535492,0.95055306,0.00005940766],"about_ca_topic_score_codex":0.0012124544,"about_ca_topic_score_gemma":0.00086746505,"teacher_disagreement_score":0.1502922,"about_ca_system_score_codex":0.00055983604,"about_ca_system_score_gemma":0.0008976395,"threshold_uncertainty_score":0.5027775},"labels":[],"label_agreement":null},{"id":"W4246248617","doi":"10.31234/osf.io/jb4wh","title":"Evaluating generalised additive mixed modelling strategies for dynamic speech analysis","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Set (abstract data type); Range (aeronautics); Formant; Focus (optics); Data set; Data mining; Artificial intelligence; Speech recognition","score_opus":0.1663628758113608,"score_gpt":0.36711043957423445,"score_spread":0.20074756376287364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246248617","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008188698,0.0007694283,0.98813397,0.0003990459,0.0000899948,0.00028889248,0.00023068415,0.0006046966,0.0012946498],"genre_scores_gemma":[0.07502903,0.0006286499,0.9204509,0.00028125744,0.000070069495,0.0011482702,0.0006230321,0.0005706854,0.0011981237],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9517645,0.04276841,0.0012199901,0.0019118548,0.002028829,0.00030631607],"domain_scores_gemma":[0.65879023,0.3274693,0.0030377854,0.005215874,0.0048552426,0.00063154555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.086060464,0.0030443117,0.00207149,0.0038994763,0.0012388758,0.0050528836,0.004041439,0.003397626,0.008523004],"category_scores_gemma":[0.22109523,0.0017358714,0.004923017,0.0026551182,0.0018045255,0.004079221,0.00488098,0.0038458505,0.0020582823],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013770191,0.00026181876,0.008972984,0.001822395,0.003957278,0.00046825878,0.0020598967,0.50347227,0.0019726974,0.15545161,0.0052079633,0.3149757],"study_design_scores_gemma":[0.00016795582,0.00037590822,0.0013037173,0.0004382317,0.0003458941,0.00013569384,0.00041986877,0.87263,0.0014589744,0.11694706,0.00564233,0.00013441745],"about_ca_topic_score_codex":0.0086173965,"about_ca_topic_score_gemma":0.009523277,"teacher_disagreement_score":0.086060464,"about_ca_system_score_codex":0.0024813323,"about_ca_system_score_gemma":0.0026216889,"threshold_uncertainty_score":0.45513666},"labels":[],"label_agreement":null},{"id":"W4247179283","doi":"10.1109/tasl.2013.2282066","title":"IEEE Transactions on Audio, Speech, and Language Processing publication information","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Texas at Dallas; Korea Advanced Institute of Science and Technology; Hong Kong Polytechnic University; Tsinghua University; Institute for Infocomm Research; Aalborg Universitet; York University; Bar-Ilan University; Facebook; National Cheng Kung University; Institut national de recherche en informatique et en automatique (INRIA); Ohio State University; Nanyang Technological University; Ben-Gurion University of the Negev; University of Missouri; RWTH Aachen University; Microsoft Research","keywords":"Computer science; Speech recognition; Speech processing","score_opus":0.012180034270205904,"score_gpt":0.2406691442479533,"score_spread":0.2284891099777474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247179283","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019376032,0.03964166,0.41537264,0.01114549,0.05948234,0.0007802887,0.0055787032,0.0049063805,0.44371647],"genre_scores_gemma":[0.09491786,0.026755087,0.070896514,0.0023883544,0.008283977,0.0003296196,0.012412121,0.00055221166,0.7834643],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99942183,0.00006078001,0.00004912268,0.0000641993,0.00034395198,0.00006018389],"domain_scores_gemma":[0.9989342,0.00016882374,0.000033811084,0.00014512548,0.00062368927,0.00009434691],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008596088,0.00080533925,0.00075455307,0.0010031349,0.000512851,0.0018012311,0.0006434157,0.0012018048,0.14073786],"category_scores_gemma":[0.0018116771,0.00018334299,0.00043328918,0.00083151914,0.00048268566,0.001332411,0.00076850236,0.0011559222,0.0646145],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000420794,0.00015493673,0.00092684885,0.00036877222,0.00006605322,0.00037596043,0.00008712658,0.0014473784,0.014629081,0.011001768,0.38790587,0.5826154],"study_design_scores_gemma":[0.000052299838,0.00018514109,0.0025041315,0.00019584585,0.000078447665,0.00076807453,0.000114025584,0.017981267,0.0070976648,0.009537867,0.961449,0.000036274785],"about_ca_topic_score_codex":0.0018329255,"about_ca_topic_score_gemma":0.0029218115,"teacher_disagreement_score":0.14073786,"about_ca_system_score_codex":0.00033051835,"about_ca_system_score_gemma":0.0011310122,"threshold_uncertainty_score":0.47081506},"labels":[],"label_agreement":null},{"id":"W4248245387","doi":"10.1109/tasl.2013.2282071","title":"IEEE Transactions on Audio, Speech, and Language Processing publication information","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Texas at Dallas; Korea Advanced Institute of Science and Technology; Hong Kong Polytechnic University; Tsinghua University; Institute for Infocomm Research; Aalborg Universitet; York University; Bar-Ilan University; Facebook; National Cheng Kung University; Institut national de recherche en informatique et en automatique (INRIA); Ohio State University; Nanyang Technological University; Ben-Gurion University of the Negev; University of Missouri; RWTH Aachen University; Microsoft Research","keywords":"Computer science; Speech recognition; Audio mining; Speech processing; Multimedia; Voice activity detection","score_opus":0.012180034270205904,"score_gpt":0.2406691442479533,"score_spread":0.2284891099777474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248245387","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019376032,0.03964166,0.41537264,0.01114549,0.05948234,0.0007802887,0.0055787032,0.0049063805,0.44371647],"genre_scores_gemma":[0.09491786,0.026755087,0.070896514,0.0023883544,0.008283977,0.0003296196,0.012412121,0.00055221166,0.7834643],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99942183,0.00006078001,0.00004912268,0.0000641993,0.00034395198,0.00006018389],"domain_scores_gemma":[0.9989342,0.00016882374,0.000033811084,0.00014512548,0.00062368927,0.00009434691],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008596088,0.00080533925,0.00075455307,0.0010031349,0.000512851,0.0018012311,0.0006434157,0.0012018048,0.14073786],"category_scores_gemma":[0.0018116771,0.00018334299,0.00043328918,0.00083151914,0.00048268566,0.001332411,0.00076850236,0.0011559222,0.0646145],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000420794,0.00015493673,0.00092684885,0.00036877222,0.00006605322,0.00037596043,0.00008712658,0.0014473784,0.014629081,0.011001768,0.38790587,0.5826154],"study_design_scores_gemma":[0.000052299838,0.00018514109,0.0025041315,0.00019584585,0.000078447665,0.00076807453,0.000114025584,0.017981267,0.0070976648,0.009537867,0.961449,0.000036274785],"about_ca_topic_score_codex":0.0018329255,"about_ca_topic_score_gemma":0.0029218115,"teacher_disagreement_score":0.14073786,"about_ca_system_score_codex":0.00033051835,"about_ca_system_score_gemma":0.0011310122,"threshold_uncertainty_score":0.47081506},"labels":[],"label_agreement":null},{"id":"W4250163740","doi":"10.1109/tasl.2013.2253678","title":"IEEE Transactions on Audio, Speech, and Language Processing publication information","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"University of Texas at Dallas; Korea Advanced Institute of Science and Technology; Hong Kong Polytechnic University; Tsinghua University; Aalborg Universitet; Nanyang Technological University; York University; Ben-Gurion University of the Negev; Bar-Ilan University; University of Cambridge; National Cheng Kung University; Ohio State University; Institut national de recherche en informatique et en automatique (INRIA); Northwestern University","keywords":"Computer science; Speech recognition; Audio mining; Speech processing; Multimedia; Natural language processing; World Wide Web; Voice activity detection","score_opus":0.012180034270205904,"score_gpt":0.2406691442479533,"score_spread":0.2284891099777474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250163740","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019376032,0.03964166,0.41537264,0.01114549,0.05948234,0.0007802887,0.0055787032,0.0049063805,0.44371647],"genre_scores_gemma":[0.09491786,0.026755087,0.070896514,0.0023883544,0.008283977,0.0003296196,0.012412121,0.00055221166,0.7834643],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99942183,0.00006078001,0.00004912268,0.0000641993,0.00034395198,0.00006018389],"domain_scores_gemma":[0.9989342,0.00016882374,0.000033811084,0.00014512548,0.00062368927,0.00009434691],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008596088,0.00080533925,0.00075455307,0.0010031349,0.000512851,0.0018012311,0.0006434157,0.0012018048,0.14073786],"category_scores_gemma":[0.0018116771,0.00018334299,0.00043328918,0.00083151914,0.00048268566,0.001332411,0.00076850236,0.0011559222,0.0646145],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000420794,0.00015493673,0.00092684885,0.00036877222,0.00006605322,0.00037596043,0.00008712658,0.0014473784,0.014629081,0.011001768,0.38790587,0.5826154],"study_design_scores_gemma":[0.000052299838,0.00018514109,0.0025041315,0.00019584585,0.000078447665,0.00076807453,0.000114025584,0.017981267,0.0070976648,0.009537867,0.961449,0.000036274785],"about_ca_topic_score_codex":0.0018329255,"about_ca_topic_score_gemma":0.0029218115,"teacher_disagreement_score":0.14073786,"about_ca_system_score_codex":0.00033051835,"about_ca_system_score_gemma":0.0011310122,"threshold_uncertainty_score":0.47081506},"labels":[],"label_agreement":null},{"id":"W4251756105","doi":"10.31234/osf.io/97jp4","title":"Performance of forced-alignment algorithms on children’s speech","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Speech recognition; Two-alternative forced choice; Sample (material); Phone; Electroglottograph; Natural language processing; Artificial intelligence; Algorithm; Mathematics; Audiology; Linguistics; Statistics; Phonation","score_opus":0.033852122633258354,"score_gpt":0.2521861475258069,"score_spread":0.21833402489254858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251756105","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6877897,0.005783829,0.26713312,0.00037174835,0.00081403035,0.0004751395,0.006952894,0.020372937,0.010306655],"genre_scores_gemma":[0.5984484,0.00072753744,0.37968132,0.00018423064,0.00008559868,0.00043464694,0.013444885,0.003116875,0.0038765178],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9934274,0.002157927,0.00065686484,0.0022801883,0.0011684215,0.00030921047],"domain_scores_gemma":[0.97926944,0.011733454,0.0010429721,0.0020993655,0.0053840065,0.00047088962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0074250894,0.0017645169,0.0011489941,0.0018626826,0.0011169487,0.0023380884,0.0017098864,0.0014240667,0.006135518],"category_scores_gemma":[0.024271308,0.0005995313,0.0010897616,0.001695603,0.0007476734,0.0021563629,0.0016887689,0.0011533437,0.0045214985],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0040043998,0.00021292838,0.035310514,0.0017251732,0.0010344845,0.0003950546,0.0023169797,0.023752138,0.07843222,0.0016921603,0.009610381,0.8415136],"study_design_scores_gemma":[0.00062972965,0.0029840497,0.24562383,0.0005324603,0.0010045543,0.0033381502,0.0031370418,0.39143008,0.3028128,0.0046875123,0.043132156,0.0006876706],"about_ca_topic_score_codex":0.011905982,"about_ca_topic_score_gemma":0.016614651,"teacher_disagreement_score":0.011905982,"about_ca_system_score_codex":0.0012415065,"about_ca_system_score_gemma":0.001966903,"threshold_uncertainty_score":0.039268076},"labels":[],"label_agreement":null},{"id":"W4253290035","doi":"10.1121/2.0000395","title":"Towards real-time two-dimensional wave propagation for articulatory speech synthesis","year":2016,"lang":"en","type":"article","venue":"Proceedings of meetings on acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Nvidia","keywords":"Computer science; Formant; Solver; Discretization; Speech recognition; Speech enhancement; Acoustics; Artificial intelligence","score_opus":0.02041344907479455,"score_gpt":0.2419891075239956,"score_spread":0.22157565844920105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253290035","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024161419,0.00010483047,0.9721391,0.00007244351,0.00004712178,0.000033342403,0.00005485837,0.0019444949,0.0014424499],"genre_scores_gemma":[0.2580328,0.00021737449,0.7384744,0.00004437347,0.000024363539,0.00010569887,0.00021412116,0.00039556623,0.002491271],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99979407,0.00004703113,0.000011342115,0.00002562729,0.00010801157,0.000013972158],"domain_scores_gemma":[0.99962354,0.00020154372,0.000027311298,0.000049523656,0.00007438708,0.000023728875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041026162,0.00058014394,0.00032538062,0.00021371142,0.00018725135,0.00090324663,0.0007133999,0.0007844465,0.0030118865],"category_scores_gemma":[0.0012581281,0.00036227168,0.0003009734,0.00019335434,0.00034109905,0.0006176926,0.00067262043,0.0005514401,0.0010443616],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038974977,0.0001288733,0.0015460469,0.0003632909,0.000058795962,0.00036770137,0.0005384351,0.4540719,0.36496183,0.015555087,0.0024678018,0.15955049],"study_design_scores_gemma":[0.000021130061,0.000045885423,0.0001421496,0.000011468095,0.0000040260566,0.000055772645,0.000018585431,0.9748906,0.019926636,0.001126676,0.0037478996,0.0000091967095],"about_ca_topic_score_codex":0.0012278968,"about_ca_topic_score_gemma":0.0013423586,"teacher_disagreement_score":0.0030118865,"about_ca_system_score_codex":0.00029687272,"about_ca_system_score_gemma":0.0004209011,"threshold_uncertainty_score":0.010075748},"labels":[],"label_agreement":null},{"id":"W4255090931","doi":"10.22215/etd/2011-09074","title":"A speech recognition enabled ambulance call report system for paramedics","year":2011,"lang":"en","type":"dissertation","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Heritage; Library and Archives Canada","funders":"","keywords":"Engineering; Computer science; Telecommunications; Speech recognition; Aeronautics","score_opus":0.043796933631790595,"score_gpt":0.27081536340810214,"score_spread":0.22701842977631154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255090931","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4224196,0.0018871027,0.24001597,0.0013578641,0.0010018323,0.0021190713,0.019639838,0.28435683,0.02720186],"genre_scores_gemma":[0.7437156,0.00097303645,0.16976702,0.0012255897,0.00044678815,0.0016444948,0.024122173,0.002510746,0.05559466],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9996538,0.000053643307,0.000038754068,0.00009627199,0.0001228881,0.00003470356],"domain_scores_gemma":[0.9994172,0.0001511,0.000050729293,0.0000683243,0.00021692741,0.0000956994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046449126,0.0006895922,0.00067840767,0.0006181361,0.00029040466,0.0007810727,0.00075105723,0.0007011213,0.012877178],"category_scores_gemma":[0.0012531625,0.00022893432,0.00022154204,0.00023241741,0.00011055698,0.00046942686,0.0006002331,0.00047361592,0.012102238],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004234219,0.0008095801,0.0070798905,0.00050145894,0.00014437328,0.0016510489,0.00051307445,0.0025952433,0.2883034,0.00056608155,0.098473854,0.59512776],"study_design_scores_gemma":[0.002245828,0.0047985693,0.07579673,0.00037927274,0.00083510973,0.006203796,0.001293927,0.25549033,0.46793067,0.0014078191,0.18301222,0.00060572015],"about_ca_topic_score_codex":0.0026124364,"about_ca_topic_score_gemma":0.0029619697,"teacher_disagreement_score":0.012877178,"about_ca_system_score_codex":0.00029028536,"about_ca_system_score_gemma":0.00056437904,"threshold_uncertainty_score":0.043078423},"labels":[],"label_agreement":null},{"id":"W4255779616","doi":"10.1121/1.4800662","title":"Nonlinearities in block-type reduced-order vocal fold models with asymmetric tissue properties","year":2013,"lang":"en","type":"article","venue":"Proceedings of meetings on acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Phonation; Vocal folds; Fold (higher-order function); Nonlinear system; Bifurcation; Sensitivity (control systems); Control theory (sociology); Computer science; Speech recognition; Mathematics; Physics; Artificial intelligence; Larynx; Engineering","score_opus":0.02415733067456152,"score_gpt":0.22200372047738967,"score_spread":0.19784638980282815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255779616","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5190175,0.0012375114,0.4517642,0.00057507935,0.00009408279,0.00010634261,0.00043886813,0.00042663942,0.026339721],"genre_scores_gemma":[0.98097587,0.0005453845,0.009175491,0.00004570291,0.000027688351,0.000102321785,0.00015569094,0.000054338543,0.008917531],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999881,0.00004034786,0.000006349883,0.000018228713,0.0000345154,0.000019507637],"domain_scores_gemma":[0.9996917,0.00012792175,0.00008126706,0.000031660624,0.00004394108,0.000023445793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025465802,0.0004876044,0.00059768243,0.00040696087,0.00024052679,0.00063210796,0.0007253153,0.000936417,0.0014887006],"category_scores_gemma":[0.0008562526,0.00034926107,0.0007579571,0.00019738008,0.0006419711,0.0006216413,0.00041595567,0.00046005807,0.00045997236],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004373195,0.000027186668,0.00068584067,0.00005187437,0.000021619671,0.00015540577,0.00009839642,0.9702304,0.010502919,0.015506617,0.00024096703,0.0024350958],"study_design_scores_gemma":[0.0000024509873,0.000009814494,0.00013086178,0.0000023350044,0.0000031107854,0.0000129853,0.0000054589686,0.9980433,0.00020181261,0.0014586085,0.0001259977,0.0000032729847],"about_ca_topic_score_codex":0.005273359,"about_ca_topic_score_gemma":0.0039725075,"teacher_disagreement_score":0.005273359,"about_ca_system_score_codex":0.0005217188,"about_ca_system_score_gemma":0.00039731798,"threshold_uncertainty_score":0.010485351},"labels":[],"label_agreement":null},{"id":"W4255932031","doi":"10.1075/bct.16.15kan","title":"Speech transformation solutions","year":2008,"lang":"en","type":"book-chapter","venue":"Benjamins current topics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cape Breton University","funders":"","keywords":"Transformation (genetics); Computer science; Speech recognition; Biology","score_opus":0.08945794588131091,"score_gpt":0.2647568369040798,"score_spread":0.1752988910227689,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255932031","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0059184185,0.0031975403,0.7694093,0.0017581803,0.0015627411,0.00042101057,0.00093202986,0.019913765,0.19688702],"genre_scores_gemma":[0.09519745,0.00501128,0.39416963,0.0023947025,0.00097369275,0.00070405606,0.007333753,0.0037643507,0.49045104],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99900085,0.00009181169,0.00006509206,0.00023721569,0.000499789,0.000105224484],"domain_scores_gemma":[0.99928695,0.00011837932,0.000033745506,0.0001946299,0.0003216911,0.000044765045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006573128,0.0011381226,0.00053801225,0.001283303,0.00096591143,0.0025467966,0.0022305534,0.0019186211,0.09032988],"category_scores_gemma":[0.0016238496,0.0004119488,0.0006530225,0.0010466435,0.00051154796,0.002567232,0.0024394544,0.0017636006,0.06816174],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019181812,0.00017481719,0.00021325516,0.0003166705,0.00002515456,0.0002626946,0.0003718892,0.0026785447,0.036589824,0.07145331,0.054401323,0.8333206],"study_design_scores_gemma":[0.000048677273,0.000121500285,0.0003115665,0.000120663455,0.00002660656,0.0009752331,0.0003236524,0.021356693,0.05342602,0.03169637,0.89154714,0.000045880784],"about_ca_topic_score_codex":0.00087038946,"about_ca_topic_score_gemma":0.0008659728,"teacher_disagreement_score":0.09032988,"about_ca_system_score_codex":0.000861306,"about_ca_system_score_gemma":0.0009787085,"threshold_uncertainty_score":0.30218357},"labels":[],"label_agreement":null},{"id":"W4285242026","doi":"10.51542/ijscia.v3i3.25","title":"ArmSpeech: Armenian Spoken Language Corpus","year":2022,"lang":"en","type":"article","venue":"International Journal Of Scientific Advances","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Armenian; Stress (linguistics); The Republic; Diaspora; Linguistics; Speech corpus; Spoken language; Identification (biology); History; Computer science; Natural language processing; Artificial intelligence; Political science; Speech synthesis; Law","score_opus":0.014031201442583113,"score_gpt":0.27713340186773505,"score_spread":0.2631022004251519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285242026","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061291978,0.0033160304,0.010598549,0.0006227666,0.0008870236,0.0012308714,0.89576393,0.00602874,0.02026009],"genre_scores_gemma":[0.037990224,0.000666282,0.010980859,0.00017033922,0.00010426837,0.0021721087,0.94119084,0.0004824964,0.00624264],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979802,0.0004974169,0.00036535482,0.0005418339,0.0004680042,0.00014717321],"domain_scores_gemma":[0.9983412,0.0005558425,0.00010395706,0.00030462682,0.00060856837,0.00008568034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001518042,0.0021472669,0.0010808583,0.0032104496,0.0013242214,0.0016616131,0.0016497548,0.001737237,0.020878898],"category_scores_gemma":[0.004123894,0.00045262123,0.00057830504,0.003094469,0.00056961406,0.0013625226,0.0022551655,0.0012651139,0.02138389],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016023393,0.00050007366,0.0031434738,0.0050381077,0.0002040742,0.002432882,0.00192447,0.0040868847,0.026458928,0.0033631148,0.7594019,0.19184376],"study_design_scores_gemma":[0.0007148543,0.0002867782,0.05442372,0.0008470048,0.00022138491,0.001984495,0.0021554586,0.012545665,0.0150808655,0.0027213115,0.9087657,0.0002527697],"about_ca_topic_score_codex":0.014515874,"about_ca_topic_score_gemma":0.013423714,"teacher_disagreement_score":0.020878898,"about_ca_system_score_codex":0.0011100501,"about_ca_system_score_gemma":0.0020473357,"threshold_uncertainty_score":0.06984693},"labels":[],"label_agreement":null},{"id":"W4285813846","doi":"10.1109/iwcmc55113.2022.9824220","title":"A Study Of Voiceprint Recognition Technology Based on Deep Learning","year":2022,"lang":"en","type":"article","venue":"2022 International Wireless Communications and Mobile Computing (IWCMC)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Realization (probability); Process (computing); Facial recognition system; Artificial intelligence; Feature extraction","score_opus":0.02877269869195719,"score_gpt":0.285629063645942,"score_spread":0.2568563649539848,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285813846","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14376383,0.010256225,0.799829,0.0029657693,0.00032891813,0.000067114466,0.0001043456,0.00041099495,0.04227385],"genre_scores_gemma":[0.9303816,0.0047003753,0.04938309,0.00029301125,0.00012803388,0.000036795594,0.000072325485,0.0000396859,0.014965223],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9997894,0.00003622986,0.0000103619095,0.0000506857,0.00008111232,0.00003218809],"domain_scores_gemma":[0.99977213,0.00010114595,0.00002314396,0.000016004285,0.00007126667,0.000016293363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032796242,0.00024210999,0.00026607877,0.00035388753,0.00026984114,0.00083591306,0.00045838824,0.00062786153,0.0015891063],"category_scores_gemma":[0.0008962811,0.00016748624,0.00040305327,0.0003719068,0.00044257398,0.0019858077,0.0003831513,0.0006677216,0.00022836817],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017072608,0.00018323379,0.012680445,0.00075558,0.00015268856,0.0010423842,0.00062541204,0.2609577,0.062686056,0.2829975,0.005509655,0.3722387],"study_design_scores_gemma":[0.0000056775166,0.00007909066,0.0032135951,0.000034543784,0.000031579155,0.00026101602,0.000074493415,0.95238304,0.008073089,0.028215457,0.0076048058,0.00002355351],"about_ca_topic_score_codex":0.0021094107,"about_ca_topic_score_gemma":0.0012148735,"teacher_disagreement_score":0.0021094107,"about_ca_system_score_codex":0.0005821732,"about_ca_system_score_gemma":0.00048385462,"threshold_uncertainty_score":0.0053161383},"labels":[],"label_agreement":null},{"id":"W4287591426","doi":"10.48550/arxiv.2011.11588","title":"The Zero Resource Speech Benchmark 2021: Metrics and baselines for unsupervised spoken language modeling","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"","keywords":"Computer science; Natural language processing; Benchmark (surveying); Artificial intelligence; Cluster analysis; Spoken language; Language model; Syntax; Speech recognition; Concatenation (mathematics); Pipeline (software); Representation (politics)","score_opus":0.0971620928814873,"score_gpt":0.20497678732253022,"score_spread":0.10781469444104291,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287591426","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28748685,0.010627283,0.49184182,0.0019161936,0.0026796905,0.0031509046,0.08132084,0.077054605,0.04392176],"genre_scores_gemma":[0.39886189,0.0011929707,0.33616298,0.00085752003,0.00034414727,0.004548833,0.2341766,0.00796861,0.015886355],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.988299,0.0051521463,0.0010687164,0.0019025711,0.0028634286,0.00071408227],"domain_scores_gemma":[0.98721826,0.0049841553,0.00064408046,0.0033755854,0.0031838294,0.0005939764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007830624,0.0043317485,0.001719558,0.0038035454,0.0014716716,0.0027945482,0.0036040468,0.0038038164,0.006544],"category_scores_gemma":[0.0326134,0.0006266396,0.001184935,0.0024106002,0.0014922644,0.0034713259,0.0045526205,0.0028367578,0.006665818],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0042269435,0.0028405136,0.010256464,0.0035767567,0.0009877479,0.00072226155,0.00082392676,0.13708827,0.03846437,0.013844654,0.21977322,0.56739485],"study_design_scores_gemma":[0.0007716849,0.003937421,0.020779936,0.00064615865,0.00035659838,0.001642585,0.0011519012,0.71616113,0.12509888,0.034441136,0.09443035,0.00058219396],"about_ca_topic_score_codex":0.012214976,"about_ca_topic_score_gemma":0.014473126,"teacher_disagreement_score":0.012214976,"about_ca_system_score_codex":0.0018724371,"about_ca_system_score_gemma":0.0022184872,"threshold_uncertainty_score":0.04141277},"labels":[],"label_agreement":null},{"id":"W4287692747","doi":"10.48550/arxiv.2008.01504","title":"\"This is Houston. Say again, please\". The Behavox system for the\\n Apollo-11 Fearless Steps Challenge (phase II)","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ventix (Canada)","funders":"","keywords":"Computer science; Speech recognition; Word error rate; Apollo; Variety (cybernetics); Ranking (information retrieval); Lexicon; Segmentation; Baseline (sea); Word (group theory); Speaker diarisation; Vocal tract; Artificial intelligence; Natural language processing; Speaker recognition; Linguistics","score_opus":0.13355590728972452,"score_gpt":0.2203934630769101,"score_spread":0.08683755578718558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287692747","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03009241,0.0015067664,0.05893546,0.026021596,0.015579142,0.0011831528,0.08545097,0.14101507,0.6402155],"genre_scores_gemma":[0.07176028,0.0006799033,0.031659417,0.008580447,0.0010747092,0.0004485353,0.13525248,0.007962855,0.74258125],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993268,0.00014430968,0.000024893621,0.00017713157,0.0002327689,0.00009412548],"domain_scores_gemma":[0.9991265,0.00012490281,0.000027958713,0.00015927684,0.0003262786,0.00023515447],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009833154,0.0013621132,0.0005347696,0.00047242414,0.0017135459,0.002192613,0.0010899585,0.0013570918,0.24631222],"category_scores_gemma":[0.0028031347,0.00027012816,0.00046581947,0.00037015098,0.000493166,0.002794855,0.0026172067,0.0016067015,0.22980027],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011761692,0.000032229495,0.0003794377,0.00008271281,0.0000048757643,0.00005552382,0.00012171615,0.0000604076,0.0018589675,0.0005659461,0.96175116,0.034969255],"study_design_scores_gemma":[0.000041355353,0.00008890542,0.0019149813,0.00006142632,0.000009713588,0.00012965032,0.0005494842,0.0028802184,0.0040374864,0.0013976019,0.98885006,0.00003915883],"about_ca_topic_score_codex":0.011775224,"about_ca_topic_score_gemma":0.032757338,"teacher_disagreement_score":0.24631222,"about_ca_system_score_codex":0.0005855249,"about_ca_system_score_gemma":0.0009914733,"threshold_uncertainty_score":0.8239964},"labels":[],"label_agreement":null},{"id":"W4287889742","doi":"10.18653/v1/2022.deeplo-1.9","title":"Punctuation Restoration in Spanish Customer Support Transcripts using Transfer Learning","year":2022,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Stornoway Diamond (Canada)","funders":"","keywords":"Punctuation; Transfer of learning; Computer science; Natural language processing; Artificial intelligence","score_opus":0.04942122317982497,"score_gpt":0.2564283702834163,"score_spread":0.20700714710359133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287889742","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33830482,0.00041878276,0.63398415,0.00051851466,0.00040387604,0.00038074848,0.0009276621,0.018897733,0.0061637387],"genre_scores_gemma":[0.7450468,0.0002784773,0.24024694,0.00024293462,0.00016474783,0.00033268536,0.0037170465,0.0010461623,0.008924174],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99876356,0.00036924568,0.00006766432,0.00044406694,0.0002439078,0.00011161835],"domain_scores_gemma":[0.9979844,0.0006789565,0.00016737096,0.00047053242,0.0005857435,0.00011302001],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012983481,0.0010346747,0.000607143,0.0008300794,0.0005867036,0.0008710332,0.00079940795,0.0007128742,0.0032603738],"category_scores_gemma":[0.004463347,0.00023034765,0.00058345223,0.00060538953,0.00071627705,0.0009825367,0.0014803319,0.0012270649,0.0041316818],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010603814,0.00025007274,0.0030204677,0.00028571326,0.00007184513,0.00073189207,0.0010719199,0.020678677,0.24933133,0.0008082801,0.0067154057,0.715974],"study_design_scores_gemma":[0.00017866428,0.0008567609,0.011366014,0.00007204828,0.00014388267,0.0011939349,0.002182977,0.51240957,0.4424393,0.0038019747,0.025182437,0.00017246928],"about_ca_topic_score_codex":0.0019861024,"about_ca_topic_score_gemma":0.0021474345,"teacher_disagreement_score":0.0032603738,"about_ca_system_score_codex":0.00042203232,"about_ca_system_score_gemma":0.0007896782,"threshold_uncertainty_score":0.010907054},"labels":[],"label_agreement":null},{"id":"W4288087689","doi":"10.48550/arxiv.1910.13923","title":"Lightweight and Efficient End-to-End Speech Recognition Using Low-Rank\\n Transformer","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Transformer; End-to-end principle; Inference; Computer science; Language model; Software deployment; Artificial neural network; Speech recognition; Artificial intelligence; Engineering","score_opus":0.07597558586763042,"score_gpt":0.1964255653594453,"score_spread":0.12044997949181488,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288087689","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012738284,0.00040689154,0.95655113,0.00021502415,0.00018013359,0.00010771995,0.0008249646,0.02555766,0.0034181443],"genre_scores_gemma":[0.3743667,0.0007252107,0.5866216,0.00054409966,0.00017971461,0.00036704322,0.007916275,0.0015260148,0.027753323],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992797,0.000111143934,0.000040170373,0.00020854996,0.0002578964,0.00010257237],"domain_scores_gemma":[0.99930453,0.00018690537,0.000033995435,0.00022978925,0.00020313304,0.000041711348],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071453786,0.0017812185,0.0009962664,0.0006684895,0.00045081426,0.0015035177,0.0022628738,0.0011226572,0.012816072],"category_scores_gemma":[0.002696993,0.00059095287,0.00087312347,0.0006004053,0.0005136288,0.0025839969,0.0021276553,0.0022498895,0.013880935],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006807694,0.0002935037,0.00082730205,0.00022191805,0.00014873873,0.0002738781,0.00009534188,0.07144845,0.060158543,0.007079348,0.026407816,0.8323644],"study_design_scores_gemma":[0.000038475984,0.000080925136,0.00026749942,0.000013235709,0.000022458216,0.00014498863,0.000035308894,0.9514693,0.03781372,0.0049050725,0.0051836506,0.000025398498],"about_ca_topic_score_codex":0.00848981,"about_ca_topic_score_gemma":0.020430768,"teacher_disagreement_score":0.012816072,"about_ca_system_score_codex":0.00065676705,"about_ca_system_score_gemma":0.0016393469,"threshold_uncertainty_score":0.04287404},"labels":[],"label_agreement":null},{"id":"W4288107168","doi":"10.48550/arxiv.1909.06805","title":"Many-to-Many Voice Conversion using Cycle-Consistent Variational\\n Autoencoder with Multiple Decoders","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Autoencoder; Computer science; Speech recognition; Path (computing); Task (project management); Consistency (knowledge bases); Artificial intelligence; Deep learning; Engineering","score_opus":0.07116699081042,"score_gpt":0.19414457001423718,"score_spread":0.12297757920381719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288107168","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011728449,0.00022704825,0.9863107,0.00007178552,0.00003244365,0.00002577793,0.000025238269,0.0005268458,0.0010515921],"genre_scores_gemma":[0.46759945,0.00036760702,0.5234638,0.0002585663,0.00006691735,0.00015301448,0.00039844975,0.00027567727,0.007416538],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99965715,0.00008366861,0.000021830632,0.00010625625,0.000094701594,0.000036372327],"domain_scores_gemma":[0.9996164,0.0002122113,0.000024837393,0.00006130645,0.00006304909,0.000022186709],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000712701,0.00079379714,0.0008078988,0.00036298676,0.0002958688,0.00057809945,0.0011207904,0.0009506213,0.0020271568],"category_scores_gemma":[0.0013952047,0.0005964228,0.00080430007,0.00031770318,0.0006704106,0.0009259361,0.0011779969,0.0015620199,0.00058320124],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017828814,0.00010869534,0.0006508176,0.0001046,0.00012581577,0.00013642984,0.000112635964,0.6655849,0.02347262,0.011580539,0.0012802501,0.2966644],"study_design_scores_gemma":[0.0000049918654,0.000016116413,0.000046055662,0.0000034241414,0.0000050997623,0.0000193868,0.000003682744,0.99608225,0.002197328,0.0012789458,0.00033801512,0.0000046905234],"about_ca_topic_score_codex":0.004015748,"about_ca_topic_score_gemma":0.005813444,"teacher_disagreement_score":0.004015748,"about_ca_system_score_codex":0.0004075092,"about_ca_system_score_gemma":0.00075936905,"threshold_uncertainty_score":0.007984757},"labels":[],"label_agreement":null},{"id":"W4289792473","doi":"10.1109/jstsp.2022.3196562","title":"L-Mix: A Latent-Level Instance Mixup Regularization for Robust Self-Supervised Speaker Representation Learning","year":2022,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Signal Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Feature learning; Embedding; Speech recognition; Artificial intelligence; Regularization (linguistics); Speaker recognition; Pattern recognition (psychology); Supervised learning; Semi-supervised learning; Machine learning; Artificial neural network","score_opus":0.05517068553173211,"score_gpt":0.2693890251686757,"score_spread":0.2142183396369436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289792473","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019863108,0.0003604475,0.9766258,0.00015692487,0.000041891806,0.00006192306,0.00011166271,0.00187751,0.0009008417],"genre_scores_gemma":[0.5141505,0.00031594955,0.47519737,0.00059360184,0.00013027962,0.00039599053,0.0012310036,0.00069980323,0.007285496],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910295,0.0003559563,0.000039087234,0.00022036795,0.00020400071,0.00007771587],"domain_scores_gemma":[0.9992955,0.00027683307,0.000077099976,0.0001368074,0.00016059316,0.000053171774],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019399334,0.0013416045,0.0010514456,0.000580781,0.0003691588,0.00069088745,0.0020188256,0.001367176,0.0021381015],"category_scores_gemma":[0.0025717658,0.00051711616,0.000944818,0.00045400512,0.00083984353,0.001605077,0.0021895438,0.0021227985,0.00092283584],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005876059,0.00044701845,0.002127016,0.00027990897,0.00038552933,0.00015367329,0.00023818301,0.37648404,0.050396655,0.014519084,0.012048475,0.54233277],"study_design_scores_gemma":[0.000008474327,0.000044984343,0.000113626185,0.000005081355,0.000008859412,0.000023989636,0.0000071947843,0.99379313,0.003900702,0.0015395212,0.0005464081,0.000008115004],"about_ca_topic_score_codex":0.0013107873,"about_ca_topic_score_gemma":0.00248825,"teacher_disagreement_score":0.0021381015,"about_ca_system_score_codex":0.000570661,"about_ca_system_score_gemma":0.00071138015,"threshold_uncertainty_score":0.010259509},"labels":[],"label_agreement":null},{"id":"W4291746033","doi":"10.3390/app12094419","title":"Automatic Speech Recognition (ASR) Systems for Children: A Systematic Literature Review","year":2022,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":124,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Speech recognition; Computer science; Task (project management); Speech technology; Field (mathematics); Process (computing); Speech processing; Engineering","score_opus":0.028251749218005794,"score_gpt":0.2559027336825049,"score_spread":0.22765098446449908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4291746033","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00032151426,0.998912,0.00015403621,0.0001589489,0.000047097314,0.00006193731,0.00012336891,0.0000058644164,0.00021524723],"genre_scores_gemma":[0.0026426988,0.9962263,0.0006610153,0.00016237599,0.00003207506,0.00011102021,0.000110539826,0.0000029767439,0.000051048282],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.99513113,0.0011484601,0.0019345161,0.00051548,0.0011479437,0.00012248576],"domain_scores_gemma":[0.9732527,0.021117765,0.0024620448,0.00029656733,0.002707454,0.00016349414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005884323,0.0013553979,0.004006503,0.009729762,0.0005657581,0.0019418779,0.0019933204,0.0017318248,0.0053062774],"category_scores_gemma":[0.023900028,0.00079618994,0.004379223,0.007480117,0.0009545198,0.0028031587,0.0011803883,0.0010308513,0.00085856754],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000109082124,0.00003644578,0.000850371,0.6787756,0.001390012,0.00014528971,0.00026087955,0.00017816994,0.00026446368,0.0004967311,0.0038551565,0.31363776],"study_design_scores_gemma":[0.000103859355,0.00036235305,0.0065292413,0.8805122,0.017461773,0.001204843,0.00063984765,0.0002165868,0.0005401264,0.00067850674,0.09168706,0.00006357586],"about_ca_topic_score_codex":0.008622719,"about_ca_topic_score_gemma":0.0194846,"teacher_disagreement_score":0.009729762,"about_ca_system_score_codex":0.002118867,"about_ca_system_score_gemma":0.01020455,"threshold_uncertainty_score":0.031119645},"labels":[],"label_agreement":null},{"id":"W4295308567","doi":"10.1109/jstsp.2022.3206084","title":"Self-Supervised Language Learning From Raw Audio: Lessons From the Zero Resource Speech Challenge","year":2022,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Signal Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; Connaught Fund; Agence Nationale de la Recherche; École des Hautes Etudes en Sciences Sociales","keywords":"Computer science; Speech recognition; Zero (linguistics); Resource (disambiguation); Artificial intelligence; Natural language processing; Linguistics","score_opus":0.030685832581785723,"score_gpt":0.26361765352844096,"score_spread":0.23293182094665524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295308567","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03442206,0.03891567,0.84397113,0.058108125,0.0029375886,0.00015696668,0.0024285787,0.0033176949,0.015742205],"genre_scores_gemma":[0.39912316,0.023692876,0.53059435,0.0097338995,0.008100796,0.0005127578,0.011550533,0.0020581568,0.014633564],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99340713,0.0034340576,0.0003189661,0.0012405867,0.0014240657,0.00017528345],"domain_scores_gemma":[0.9500929,0.040127948,0.00044402815,0.0036658484,0.0047708033,0.00089847395],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017231517,0.0011129318,0.001837911,0.0010883616,0.0008750057,0.0034066555,0.0029140066,0.0025667641,0.0018628343],"category_scores_gemma":[0.04081148,0.00046600375,0.0007150406,0.0011514012,0.0034025756,0.0068674874,0.0036712408,0.0066686156,0.0021847996],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048505762,0.00030390362,0.0039463816,0.0012400628,0.00023200653,0.0002662943,0.0010802099,0.07520425,0.0027885358,0.08698076,0.118932314,0.7085403],"study_design_scores_gemma":[0.00010183792,0.00024423056,0.002225201,0.00038875462,0.000041531526,0.00034615136,0.0008544107,0.46051958,0.0061192764,0.44091663,0.08809896,0.00014343095],"about_ca_topic_score_codex":0.004151074,"about_ca_topic_score_gemma":0.0052068974,"teacher_disagreement_score":0.017231517,"about_ca_system_score_codex":0.001167994,"about_ca_system_score_gemma":0.0020639314,"threshold_uncertainty_score":0.09113002},"labels":[],"label_agreement":null},{"id":"W4297804082","doi":"10.55630/dipp.2020.10.5","title":"Cross-Cultural Emotion Recognition and Comparison Using Convolutional Neural Networks","year":2020,"lang":"en","type":"article","venue":"Digital Presentation and Preservation of Cultural and Scientific Heritage","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Convolutional neural network; Emotion recognition; Computer science; Task (project management); Feature (linguistics); Subject (documents); Speech recognition; Natural language processing; Cultural heritage; Psychology; Artificial intelligence; Linguistics; History","score_opus":0.18286233500905522,"score_gpt":0.32968336606741977,"score_spread":0.14682103105836455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297804082","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9498658,0.0009581353,0.040656235,0.00013090993,0.00021369409,0.0000564239,0.0004238362,0.00041955104,0.0072754864],"genre_scores_gemma":[0.9879006,0.00023979084,0.0096968245,0.000029752753,0.000022856433,0.000020189398,0.0005438657,0.00002983521,0.0015161984],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991954,0.00024089552,0.000067518726,0.00018178736,0.00017989373,0.00013447077],"domain_scores_gemma":[0.9992206,0.00025361814,0.000052729236,0.000088717534,0.0003405759,0.000043763586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012004457,0.00054283184,0.0002980673,0.0010725739,0.0002866466,0.0008294916,0.00028517327,0.0003964941,0.0012460331],"category_scores_gemma":[0.0026881376,0.000105916886,0.0005401511,0.00058987184,0.00023020692,0.00063453143,0.0007485278,0.00032336157,0.0005421338],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002626931,0.0004097137,0.074547134,0.0004003464,0.00084409514,0.0009266607,0.0016801081,0.045761023,0.11466103,0.001681061,0.0036453714,0.75281656],"study_design_scores_gemma":[0.00004301604,0.00082591036,0.23057076,0.00012283662,0.0006266636,0.0009825908,0.003295721,0.65268046,0.10173989,0.0021860052,0.0067926976,0.00013344118],"about_ca_topic_score_codex":0.005194203,"about_ca_topic_score_gemma":0.0048117526,"teacher_disagreement_score":0.005194203,"about_ca_system_score_codex":0.00046291013,"about_ca_system_score_gemma":0.00017818176,"threshold_uncertainty_score":0.010327995},"labels":[],"label_agreement":null},{"id":"W4297841830","doi":"10.21437/interspeech.2022-11066","title":"SoundChoice: Grapheme-to-Phoneme Models with Semantic Disambiguation","year":2022,"lang":"en","type":"article","venue":"Interspeech 2022","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Grapheme; Computer science; Natural language processing; Artificial intelligence","score_opus":0.01880117531733043,"score_gpt":0.23215500689416602,"score_spread":0.21335383157683557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297841830","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032687325,0.00084785634,0.94683695,0.00041248047,0.00031267598,0.00010335286,0.000885305,0.014091294,0.0038228624],"genre_scores_gemma":[0.65066046,0.0005174534,0.3298153,0.0006997507,0.00012090232,0.00027853993,0.0036678123,0.00087158487,0.013368097],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997147,0.000054663822,0.000013284195,0.00014091015,0.00004734483,0.000029234583],"domain_scores_gemma":[0.9996916,0.00014737976,0.000018599349,0.00006208089,0.000054376957,0.000025974956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005575834,0.0013087116,0.0006085241,0.00047878874,0.00036777515,0.00082684326,0.0018330675,0.0012737396,0.004003125],"category_scores_gemma":[0.0014477583,0.00044127018,0.00080799044,0.0006124548,0.00053251424,0.0018552117,0.0013273818,0.0019166014,0.0022837417],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006628533,0.00026382066,0.001635847,0.00021191005,0.0001702461,0.00035158294,0.00023438147,0.36231568,0.031568654,0.010815186,0.017607896,0.57416195],"study_design_scores_gemma":[0.000037862654,0.00007184809,0.00024918863,0.000010029801,0.000022721068,0.00004821633,0.000026713913,0.9771527,0.006528786,0.012764061,0.0030676255,0.00002020129],"about_ca_topic_score_codex":0.006591864,"about_ca_topic_score_gemma":0.013655712,"teacher_disagreement_score":0.006591864,"about_ca_system_score_codex":0.000533464,"about_ca_system_score_gemma":0.0011097239,"threshold_uncertainty_score":0.013391852},"labels":[],"label_agreement":null},{"id":"W4297841867","doi":"10.21437/interspeech.2022-10761","title":"Daft-Exprt: Cross-Speaker Prosody Transfer on Any Text for Expressive Speech Synthesis","year":2022,"lang":"en","type":"article","venue":"Interspeech 2022","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ubisoft (Canada)","funders":"","keywords":"Prosody; Computer science; Speech synthesis; Speech recognition; Transfer (computing); Natural language processing","score_opus":0.02503636111819494,"score_gpt":0.28065545976882816,"score_spread":0.2556190986506332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297841867","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024709249,0.00064914476,0.95603156,0.00023266161,0.00040490704,0.00019043658,0.0005085266,0.011439923,0.0058336034],"genre_scores_gemma":[0.58360815,0.0006115011,0.3837751,0.0006375303,0.00021228183,0.0006794605,0.0029538579,0.0022014545,0.025320698],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996499,0.000084128056,0.000017234514,0.00012227843,0.00009508589,0.000031317442],"domain_scores_gemma":[0.99960154,0.0002002753,0.000019107805,0.00009710409,0.00005237169,0.000029614679],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009278741,0.0012333755,0.0005582059,0.0002489874,0.00026664813,0.0006383726,0.0014814776,0.0009852932,0.008162303],"category_scores_gemma":[0.0020341442,0.0003246837,0.0009129012,0.00012273437,0.00046285897,0.0010680243,0.0021104298,0.0019495432,0.0034247919],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061505876,0.00029496028,0.00065917685,0.00036686074,0.00022390978,0.00058833475,0.000287843,0.39550757,0.095704265,0.008225786,0.012054127,0.48547214],"study_design_scores_gemma":[0.000045451543,0.0002125647,0.00018292009,0.000022938844,0.00002784206,0.000199974,0.000022532138,0.96399486,0.024137747,0.0049718497,0.0061545568,0.000026668056],"about_ca_topic_score_codex":0.000951498,"about_ca_topic_score_gemma":0.0014312977,"teacher_disagreement_score":0.008162303,"about_ca_system_score_codex":0.00029775058,"about_ca_system_score_gemma":0.0004375832,"threshold_uncertainty_score":0.027305603},"labels":[],"label_agreement":null},{"id":"W4298028408","doi":"10.48550/arxiv.1803.02551","title":"Extracting Domain Invariant Features by Unsupervised Learning for Robust\\n Automatic Speech Recognition","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Autoencoder; Computer science; Robustness (evolution); Invariant (physics); Speech recognition; Word error rate; Artificial intelligence; Pattern recognition (psychology); Latent variable; Encoder; Domain (mathematical analysis); Deep learning; Mathematics","score_opus":0.093970308576222,"score_gpt":0.20312589556715785,"score_spread":0.10915558699093585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298028408","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028961712,0.00021225346,0.9683823,0.00006675648,0.000027420489,0.000024295337,0.000115693656,0.0014652363,0.0007443876],"genre_scores_gemma":[0.5238842,0.0003751372,0.469278,0.00015361977,0.0000914295,0.00011822122,0.0018871828,0.00034468493,0.0038675144],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994247,0.00015510539,0.000027824835,0.00019209374,0.00014023433,0.0000599739],"domain_scores_gemma":[0.9991418,0.00033703746,0.00008618414,0.00025453774,0.000153513,0.000026787075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007430235,0.00058983447,0.00050728035,0.0007549177,0.00025878145,0.0004559298,0.00066073425,0.00046380944,0.0008755712],"category_scores_gemma":[0.0020716488,0.0002866463,0.0005296561,0.000682393,0.0006356073,0.00094118546,0.00073360646,0.00088899594,0.0008498054],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020513791,0.00018443276,0.0020990171,0.00008917752,0.000098564706,0.000105524276,0.00009216077,0.1284842,0.07237033,0.0067686904,0.0041825837,0.7853201],"study_design_scores_gemma":[0.000007524616,0.000051573472,0.0010883607,0.000004789227,0.000013848099,0.00004715375,0.000025125531,0.9717157,0.019862153,0.0053824345,0.0017881611,0.0000131924935],"about_ca_topic_score_codex":0.002267816,"about_ca_topic_score_gemma":0.0040719802,"teacher_disagreement_score":0.002267816,"about_ca_system_score_codex":0.0003678446,"about_ca_system_score_gemma":0.0007581139,"threshold_uncertainty_score":0.00450927},"labels":[],"label_agreement":null},{"id":"W4299884656","doi":"10.1007/978-3-031-01599-1_5","title":"Speech Synthesis","year":2016,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on assistive, rehabilitative, and health-preserving technologies","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Toronto Rehabilitation Institute","funders":"","keywords":"Phone; Speech synthesis; Computer science; Symbol (formal); Speech recognition; Section (typography); Linguistics; Programming language; Philosophy","score_opus":0.040224558404532165,"score_gpt":0.2880119932924299,"score_spread":0.24778743488789773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4299884656","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006319029,0.004150973,0.4395066,0.0010488925,0.0058971937,0.00064728607,0.007654109,0.015775442,0.5190004],"genre_scores_gemma":[0.08669587,0.0034582082,0.16004972,0.0014703231,0.001368889,0.000850119,0.013680155,0.0047482755,0.72767854],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994153,0.000058252906,0.00003523009,0.00020031132,0.00024389826,0.000047023],"domain_scores_gemma":[0.9995382,0.00008931468,0.000012313647,0.000090630645,0.00023877858,0.00003087036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004888859,0.0015534245,0.0008347931,0.0010813134,0.00085896446,0.002746398,0.0010016875,0.0013579743,0.16931215],"category_scores_gemma":[0.0014325299,0.00042745314,0.0005941389,0.0006405837,0.0004303634,0.0010665049,0.0014736616,0.00113099,0.13244845],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033213166,0.000052965548,0.00014259393,0.0007058134,0.00002948806,0.00030988632,0.00033912776,0.0019008499,0.0935605,0.02011819,0.105841376,0.77666706],"study_design_scores_gemma":[0.000059632126,0.00013537843,0.0006271083,0.00020348503,0.000045373865,0.0009792799,0.00025569688,0.007363982,0.079020046,0.008812454,0.90243953,0.00005802183],"about_ca_topic_score_codex":0.0010586178,"about_ca_topic_score_gemma":0.0012914311,"teacher_disagreement_score":0.16931215,"about_ca_system_score_codex":0.0004972464,"about_ca_system_score_gemma":0.00074647384,"threshold_uncertainty_score":0.56640553},"labels":[],"label_agreement":null},{"id":"W4307680525","doi":"10.1162/tacl_a_00545","title":"Generative Spoken Dialogue Language Modeling","year":2023,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Centre National de la Recherche Scientifique; Agence Nationale de la Recherche; École des Hautes Etudes en Sciences Sociales; Canadian Institute for Advanced Research","keywords":"Paralanguage; Computer science; Transformer; Spoken language; Generative grammar; Speech recognition; Natural language processing; Laughter; Language model; Artificial intelligence; Communication; Psychology","score_opus":0.03106876500409547,"score_gpt":0.2777580017736145,"score_spread":0.246689236769519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307680525","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023002263,0.00042965912,0.9671104,0.00049681804,0.00012103909,0.00006603313,0.00083720003,0.0025696952,0.00536694],"genre_scores_gemma":[0.81064475,0.00028495124,0.17178015,0.00038248836,0.00013653177,0.00028184318,0.0021113798,0.00055173214,0.013826091],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99958843,0.00016568485,0.000014808523,0.000121512305,0.000071107825,0.000038510923],"domain_scores_gemma":[0.99944645,0.00035493073,0.00002593448,0.00006309454,0.00007718395,0.00003228414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049640134,0.00071427744,0.00052026653,0.00045562137,0.00025790583,0.0008967351,0.0015859085,0.001001605,0.006105737],"category_scores_gemma":[0.0018760302,0.00044770577,0.0010897991,0.00029563645,0.0005971885,0.0007330337,0.0012271286,0.0013124814,0.0014856282],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011820755,0.00006031333,0.0008217345,0.00012561846,0.00009771445,0.00023384659,0.00036048205,0.8972139,0.0056109745,0.036701065,0.004247938,0.054408234],"study_design_scores_gemma":[0.0000053985214,0.0000060641546,0.000036983718,0.0000035122453,0.0000037941345,0.000016078844,0.0000070137903,0.9925356,0.0004099288,0.006069771,0.00090235216,0.0000034788727],"about_ca_topic_score_codex":0.003346221,"about_ca_topic_score_gemma":0.003912078,"teacher_disagreement_score":0.006105737,"about_ca_system_score_codex":0.00065837236,"about_ca_system_score_gemma":0.0005910396,"threshold_uncertainty_score":0.020425797},"labels":[],"label_agreement":null},{"id":"W4307783259","doi":"10.48550/arxiv.2210.15775","title":"Evaluating context-invariance in unsupervised speech representations","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Connaught Fund; Agence Nationale de la Recherche; Natural Sciences and Engineering Research Council of Canada; Morgan Family Foundation","keywords":"Computer science; Context (archaeology); Benchmark (surveying); Word (group theory); Independence (probability theory); Artificial intelligence; Speech recognition; Natural language processing; Linguistics; Mathematics","score_opus":0.23756314595082362,"score_gpt":0.2724413548986045,"score_spread":0.034878208947780875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307783259","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74142057,0.0023363025,0.24092504,0.0008080558,0.00029608211,0.00025490057,0.0027688323,0.0033707886,0.0078194225],"genre_scores_gemma":[0.9548439,0.00026355634,0.036260553,0.00016071528,0.000107742846,0.00013392813,0.0062955986,0.00029014098,0.0016438687],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960896,0.0015832591,0.00025784998,0.0011432546,0.0006512239,0.00027496877],"domain_scores_gemma":[0.986199,0.009083844,0.0008874952,0.0019860957,0.0014450559,0.0003984636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004543667,0.0013674066,0.00093924825,0.001569079,0.00066281395,0.0016445256,0.0011371537,0.0016501859,0.0016633477],"category_scores_gemma":[0.026200632,0.00036119643,0.00092776545,0.0009658456,0.0011386208,0.0023805131,0.0021915617,0.0021164948,0.0008739217],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020328658,0.0007344826,0.020251505,0.0005077855,0.0006884974,0.00020344298,0.0003872724,0.55266404,0.019738987,0.0052829995,0.0072115897,0.39029655],"study_design_scores_gemma":[0.000041643023,0.00033776026,0.005158942,0.00002449559,0.00004489469,0.00007558266,0.0000872026,0.9782599,0.009285831,0.005857726,0.0007975986,0.000028294831],"about_ca_topic_score_codex":0.005059919,"about_ca_topic_score_gemma":0.006277471,"teacher_disagreement_score":0.005059919,"about_ca_system_score_codex":0.0011284981,"about_ca_system_score_gemma":0.0008952611,"threshold_uncertainty_score":0.024029493},"labels":[],"label_agreement":null},{"id":"W4310184971","doi":"10.3390/app122312159","title":"Arabic Emotional Voice Conversion Using English Pre-Trained StarGANv2-VC-Based Model","year":2022,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"King Saud University","keywords":"Prosody; Computer science; Speech recognition; Identity (music); Arabic; Natural language processing; Generative grammar; Artificial intelligence; Psychology; Linguistics","score_opus":0.040328397784666285,"score_gpt":0.25196903258446324,"score_spread":0.21164063479979695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310184971","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24391899,0.0014296868,0.7326569,0.0005520258,0.00043704212,0.00018911285,0.00038097682,0.0037030666,0.016732212],"genre_scores_gemma":[0.9205015,0.00025982817,0.066407524,0.00025596,0.0000454518,0.00013695509,0.00073594117,0.00015957464,0.011497278],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99986255,0.000034545752,0.0000057809752,0.000042493215,0.000032052994,0.000022517324],"domain_scores_gemma":[0.9997961,0.00009113721,0.000010465722,0.000017175465,0.00007408427,0.000010989299],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004004173,0.0006770526,0.000288122,0.0002747136,0.00017615074,0.00036660547,0.0004883019,0.0005053186,0.0021406258],"category_scores_gemma":[0.00083235785,0.00016645427,0.00050683203,0.000098745215,0.00024287944,0.00034811956,0.00039782247,0.000820749,0.0006980551],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002191423,0.000114412614,0.0019449005,0.00009903286,0.00009399665,0.0002472352,0.00011726767,0.77566373,0.027489359,0.0028148268,0.0040178085,0.18717825],"study_design_scores_gemma":[0.0000035496164,0.000029717994,0.000242877,0.000005617211,0.000007487811,0.000029486053,0.000008113917,0.99539846,0.0034349854,0.00030694887,0.00052742707,0.0000052617856],"about_ca_topic_score_codex":0.004020723,"about_ca_topic_score_gemma":0.005600699,"teacher_disagreement_score":0.004020723,"about_ca_system_score_codex":0.00036809556,"about_ca_system_score_gemma":0.00036333522,"threshold_uncertainty_score":0.007994652},"labels":[],"label_agreement":null},{"id":"W4310892144","doi":"10.14705/rpnet.2022.61.1459","title":"Using Google Voice Typing to automatically assess pronunciation","year":2022,"lang":"en","type":"book-chapter","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; Concordia University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Pronunciation; Typing; Computer science; Speech recognition; Natural language processing; Test (biology); Artificial intelligence; Linguistics","score_opus":0.12220048908798234,"score_gpt":0.30215750724548485,"score_spread":0.1799570181575025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310892144","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8984331,0.0021329338,0.05722481,0.00019470236,0.00029642845,0.00020113515,0.0015652415,0.0025959746,0.037355635],"genre_scores_gemma":[0.9233879,0.0010697902,0.054245923,0.00010206856,0.000095834715,0.00013144728,0.0014034127,0.0003599401,0.019203607],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99811137,0.0006721992,0.000085081345,0.00028764893,0.00078428496,0.000059412097],"domain_scores_gemma":[0.99323106,0.0047115986,0.00043462586,0.0003860807,0.001115595,0.00012100796],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016822545,0.00059794687,0.00038132333,0.0015587385,0.00015688658,0.0013798316,0.0005438985,0.00044202167,0.0035661568],"category_scores_gemma":[0.00726923,0.00013841357,0.00017696571,0.0008037362,0.0003432946,0.0007621595,0.00060279836,0.00025885648,0.002989642],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049052224,0.00013525442,0.07835302,0.0005019729,0.00008109892,0.0003889711,0.0031144347,0.0017215206,0.10402028,0.0008306105,0.0067691547,0.8035931],"study_design_scores_gemma":[0.00015199166,0.004357885,0.6716566,0.00045417194,0.00035967043,0.010590014,0.00908811,0.0445243,0.1871619,0.0029295583,0.06822044,0.0005054637],"about_ca_topic_score_codex":0.001063253,"about_ca_topic_score_gemma":0.0034746807,"teacher_disagreement_score":0.0035661568,"about_ca_system_score_codex":0.00022932778,"about_ca_system_score_gemma":0.00022030431,"threshold_uncertainty_score":0.011929929},"labels":[],"label_agreement":null},{"id":"W4312330812","doi":"10.56828/jser.2022.1.1.3","title":"Voiceprint Recognition based on Machine Learning Methods","year":2022,"lang":"en","type":"article","venue":"Journal of Science and Engineering Research","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Computer science; Speech recognition; Speaker recognition; Identification (biology); Feature (linguistics); Biometrics; Task (project management); Artificial intelligence; Pattern recognition (psychology); Engineering","score_opus":0.10591997324467936,"score_gpt":0.3791078615026312,"score_spread":0.2731878882579518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312330812","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0073099844,0.0018778356,0.98592573,0.00019114578,0.00011066996,0.00003072438,0.00005674992,0.0013595272,0.003137614],"genre_scores_gemma":[0.519078,0.0038624865,0.45855206,0.0005343515,0.00036989411,0.00014787859,0.0005400128,0.00022147397,0.016693827],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994869,0.00007901119,0.00003150443,0.00013308726,0.00022879636,0.00004074026],"domain_scores_gemma":[0.9996413,0.00013810987,0.000033150034,0.0000552757,0.00011881712,0.000013328052],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040781056,0.0005879096,0.00057180977,0.0009969581,0.00022005281,0.0007121816,0.00071533537,0.00068802654,0.0026262503],"category_scores_gemma":[0.0012714505,0.0001780829,0.00058962393,0.0007831984,0.00029218235,0.0010830186,0.0005244406,0.0008247265,0.0013853882],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007778746,0.00004814206,0.00080916984,0.00012682714,0.00004801409,0.000083158615,0.000026970965,0.06503832,0.01932003,0.007045493,0.0027154519,0.90466064],"study_design_scores_gemma":[0.0000065644376,0.000035736975,0.00088787026,0.000018201139,0.000015605734,0.00011989576,0.000010013688,0.9763749,0.011941707,0.005552101,0.0050186045,0.000018790262],"about_ca_topic_score_codex":0.001752854,"about_ca_topic_score_gemma":0.0014532759,"teacher_disagreement_score":0.0026262503,"about_ca_system_score_codex":0.00047144011,"about_ca_system_score_gemma":0.0004660011,"threshold_uncertainty_score":0.008785665},"labels":[],"label_agreement":null},{"id":"W4312451460","doi":"10.1109/aike55402.2022.00016","title":"The Effects of Model Capacity in Modelling Variability between Training and Testing Environments for Automatic Speech Recognition","year":2022,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Automation; Training (meteorology); Training set; Human–computer interaction; Home automation; Degradation (telecommunications); Speech recognition; Artificial intelligence; Engineering","score_opus":0.14311974578024658,"score_gpt":0.2510602895614192,"score_spread":0.1079405437811726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312451460","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6131272,0.0032320453,0.3757816,0.0017497833,0.0002747884,0.00022757621,0.0008239718,0.0016895602,0.0030934827],"genre_scores_gemma":[0.972627,0.00041015833,0.025333839,0.00020354097,0.0000348866,0.00011703075,0.0007285583,0.00021495647,0.00033011002],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98708504,0.007118278,0.0012151208,0.0023657966,0.0016751222,0.0005405595],"domain_scores_gemma":[0.87234306,0.106612585,0.0038682192,0.0131326625,0.0033005578,0.0007429712],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015409749,0.0020450358,0.0013111064,0.0007641525,0.0010378951,0.0022291224,0.0018268905,0.0023888985,0.0007880665],"category_scores_gemma":[0.105117336,0.0012549955,0.0013154328,0.00082530006,0.0022703153,0.0053695496,0.0032908202,0.0037561166,0.00049913925],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002636374,0.0004796791,0.025413215,0.0006062278,0.00043842534,0.00050855393,0.0011919348,0.8657456,0.022966728,0.002400898,0.0007764604,0.076835915],"study_design_scores_gemma":[0.00008738523,0.00097532454,0.01558944,0.00026024447,0.00029456904,0.0006937378,0.0005215876,0.94715315,0.027332451,0.005000436,0.0018613084,0.00023031814],"about_ca_topic_score_codex":0.008047134,"about_ca_topic_score_gemma":0.0047078673,"teacher_disagreement_score":0.015409749,"about_ca_system_score_codex":0.0012829547,"about_ca_system_score_gemma":0.0016716287,"threshold_uncertainty_score":0.08149552},"labels":[],"label_agreement":null},{"id":"W4312729122","doi":"10.1121/2.0001664","title":"The Speech and Language Resource Bank: A central index of resources for speech science research and education","year":2020,"lang":"en","type":"article","venue":"Proceedings of meetings on acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Documentation; Resource (disambiguation); Field (mathematics); Fragmentation (computing); Data science; World Wide Web","score_opus":0.030542299761338536,"score_gpt":0.3016588962468001,"score_spread":0.27111659648546155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312729122","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00614549,0.0057191267,0.2738578,0.006287333,0.001726196,0.0021026805,0.48249438,0.12890743,0.09275949],"genre_scores_gemma":[0.023001933,0.0044931304,0.3107742,0.0015203261,0.0009571994,0.0027500987,0.554706,0.04366807,0.05812904],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99027,0.0025061832,0.0025017345,0.0010029012,0.0032092012,0.00050999026],"domain_scores_gemma":[0.9241414,0.020800617,0.005301606,0.01625218,0.023402201,0.010101993],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017065886,0.0020822652,0.0030460923,0.024084188,0.0032652093,0.010372106,0.005128432,0.0028692067,0.09660716],"category_scores_gemma":[0.055097267,0.0019395401,0.00093099487,0.024957571,0.0020890525,0.013511922,0.011043605,0.0042304946,0.14781865],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041842155,0.00018397605,0.0024443804,0.0017077842,0.000054084627,0.00020966488,0.0012340345,0.00089013844,0.0041258307,0.01947483,0.61896735,0.35028958],"study_design_scores_gemma":[0.00008226864,0.00003841558,0.0027223246,0.00061708846,0.000048736612,0.00023431463,0.00034471496,0.0020748866,0.0041244156,0.010034495,0.97954136,0.00013700155],"about_ca_topic_score_codex":0.0072565507,"about_ca_topic_score_gemma":0.0058003073,"teacher_disagreement_score":0.09660716,"about_ca_system_score_codex":0.0027956418,"about_ca_system_score_gemma":0.022318287,"threshold_uncertainty_score":0.32318318},"labels":[],"label_agreement":null},{"id":"W4312904577","doi":"10.1007/978-3-031-20980-2_29","title":"An Analytic Study on Clustering-Based Pseudo-labels for Self-supervised Deep Speaker Verification","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Overfitting; Computer science; Cluster analysis; Discriminative model; Artificial intelligence; Embedding; Pattern recognition (psychology); Set (abstract data type); Speaker recognition; Scheme (mathematics); Speech recognition; Machine learning; Artificial neural network; Mathematics","score_opus":0.03380490464928443,"score_gpt":0.2764592676533605,"score_spread":0.24265436300407606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312904577","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01796114,0.0008106633,0.9767651,0.00032374327,0.000046460907,0.00005630978,0.00009484281,0.00020978221,0.0037318363],"genre_scores_gemma":[0.6586372,0.0014263091,0.3236694,0.00036464655,0.00037906648,0.00021890803,0.0007141431,0.0005424217,0.014047762],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972263,0.001121426,0.000083769606,0.00057217677,0.0007938885,0.00020236676],"domain_scores_gemma":[0.9704351,0.023150275,0.0011658337,0.0018628637,0.0030620454,0.0003237795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004421866,0.0007986047,0.00097345514,0.0014978867,0.00091707223,0.0019695284,0.0031670718,0.0016114939,0.0045057097],"category_scores_gemma":[0.037629057,0.00073346874,0.0008361147,0.0014405072,0.0025862358,0.0056231553,0.0020782612,0.002273134,0.00082870707],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037363646,0.00014532985,0.002762671,0.0004860674,0.00010751338,0.00020947975,0.0008914091,0.34227288,0.014049037,0.44103178,0.0074793096,0.19019091],"study_design_scores_gemma":[0.0000030957792,0.00003201917,0.00062004046,0.000032820742,0.000015304602,0.00008414891,0.000053378284,0.953626,0.0015105144,0.04307495,0.0009306857,0.000017098384],"about_ca_topic_score_codex":0.0036393376,"about_ca_topic_score_gemma":0.003835423,"teacher_disagreement_score":0.0045057097,"about_ca_system_score_codex":0.0022757028,"about_ca_system_score_gemma":0.0013772662,"threshold_uncertainty_score":0.023385286},"labels":[],"label_agreement":null},{"id":"W4313042211","doi":"10.1109/ijcnn55064.2022.9892054","title":"Fine-grained Early Frequency Attention for Deep Speaker Recognition","year":2022,"lang":"en","type":"article","venue":"2022 International Joint Conference on Neural Networks (IJCNN)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Focus (optics); Deep neural networks; Deep learning; Artificial intelligence; Key (lock); Artificial neural network; Speech recognition; Pattern recognition (psychology)","score_opus":0.054296543505739286,"score_gpt":0.2565625299664059,"score_spread":0.2022659864606666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313042211","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10760337,0.0040042456,0.85946167,0.0008937825,0.0004642307,0.00010592377,0.0012979616,0.019858724,0.0063100643],"genre_scores_gemma":[0.7852023,0.0010098203,0.19876003,0.00066029566,0.0001732167,0.00012732977,0.003462397,0.0004115044,0.010193047],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996562,0.000067014465,0.00001282209,0.00011606657,0.00007076295,0.00007701579],"domain_scores_gemma":[0.99962735,0.00013685675,0.000027427634,0.00008497288,0.00008794555,0.000035467434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085607974,0.0013112164,0.00058808614,0.00058450474,0.00036156524,0.00060190563,0.001340536,0.00091622904,0.0052200863],"category_scores_gemma":[0.0015497649,0.0003481119,0.00057694403,0.00047455973,0.00036471226,0.0016995877,0.0015373132,0.0020746358,0.0019194849],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006445996,0.00034200915,0.0027288327,0.0002008845,0.00017384821,0.00016672678,0.0001624104,0.12286444,0.08692648,0.0062064664,0.021249495,0.75833386],"study_design_scores_gemma":[0.000034770288,0.0001350575,0.0013468856,0.00002244245,0.000046281068,0.00008639675,0.00003507208,0.94748664,0.036445584,0.009200965,0.005136097,0.000023799652],"about_ca_topic_score_codex":0.008406718,"about_ca_topic_score_gemma":0.01472137,"teacher_disagreement_score":0.008406718,"about_ca_system_score_codex":0.00078956084,"about_ca_system_score_gemma":0.0007592302,"threshold_uncertainty_score":0.01746291},"labels":[],"label_agreement":null},{"id":"W4313148067","doi":"10.1007/978-3-031-20980-2_21","title":"CRIM’s Speech Recognition System for OpenASR21 Evaluation with Conformer and Voice Activity Detector Embeddings","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Speech recognition; Computer science; Hidden Markov model; Mel-frequency cepstrum; Word error rate; Sentence; Artificial intelligence; Language model; Natural language processing; Pattern recognition (psychology); Feature extraction","score_opus":0.04380244650141289,"score_gpt":0.27454648629349643,"score_spread":0.23074403979208352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313148067","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1969144,0.0039004113,0.36418074,0.0011517049,0.0045887087,0.003041306,0.055669997,0.30113685,0.069415845],"genre_scores_gemma":[0.3020822,0.0009843989,0.39878014,0.0009339107,0.0004558463,0.0027288224,0.20339322,0.012295327,0.0783462],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99648476,0.00086477434,0.00030153105,0.0008113428,0.0012518811,0.00028570747],"domain_scores_gemma":[0.99689263,0.0006175333,0.000081386184,0.00067862094,0.0014952081,0.00023462267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042520626,0.0024174075,0.0015182463,0.0018497918,0.001055196,0.0021267708,0.0022350661,0.002083519,0.024750678],"category_scores_gemma":[0.0054482906,0.000636573,0.00093872804,0.0010899444,0.0004750947,0.0019145008,0.0020387725,0.0013968319,0.0330814],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027681168,0.0007242631,0.0023497702,0.0007792007,0.00038853913,0.0005855235,0.0002570503,0.007412699,0.07175879,0.002112895,0.20829533,0.7025677],"study_design_scores_gemma":[0.0013951027,0.0029227037,0.017923068,0.00022078815,0.00058522896,0.0024332602,0.00082708354,0.30185682,0.38796124,0.0036663637,0.2797527,0.00045570076],"about_ca_topic_score_codex":0.009911119,"about_ca_topic_score_gemma":0.010583987,"teacher_disagreement_score":0.024750678,"about_ca_system_score_codex":0.00087814656,"about_ca_system_score_gemma":0.0014756037,"threshold_uncertainty_score":0.082799256},"labels":[],"label_agreement":null},{"id":"W4313228380","doi":"10.1561/116.00000017","title":"An Application-Oriented Taxonomy on Spoofing, D isguise and Countermeasures in Speaker Recognition","year":2022,"lang":"en","type":"article","venue":"APSIPA Transactions on Signal and Information Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Spoofing attack; Taxonomy (biology); Computer science; Speaker recognition; Speech recognition; Computer security; Biology; Botany","score_opus":0.019150673068162115,"score_gpt":0.22176721218037682,"score_spread":0.2026165391122147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313228380","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008762762,0.7914813,0.11831564,0.008698151,0.0034146172,0.0008858645,0.0006385891,0.00056565716,0.06723732],"genre_scores_gemma":[0.058773763,0.8230563,0.083645545,0.006943354,0.004177602,0.0011764459,0.0016647174,0.00016253952,0.02039986],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9953961,0.0010045025,0.00080413016,0.0005636563,0.0018896637,0.00034192012],"domain_scores_gemma":[0.9919526,0.0045864526,0.0010948678,0.00043111917,0.0017291678,0.00020573716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028011217,0.0021893992,0.0013444301,0.015705066,0.0016334367,0.0054315347,0.0021619885,0.0041160113,0.0038258375],"category_scores_gemma":[0.0075823567,0.0006577524,0.0013713372,0.010692023,0.0031447844,0.010034121,0.0026800842,0.0031850303,0.002347918],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001202146,0.0002401461,0.0040893666,0.015484967,0.000100686666,0.0008216572,0.0038076218,0.0029992806,0.0060074897,0.2167848,0.03523457,0.7143092],"study_design_scores_gemma":[0.0000122369065,0.00032306454,0.0042944564,0.009852531,0.0001320253,0.0032263454,0.002311752,0.004939857,0.0025895555,0.06677365,0.905401,0.00014350208],"about_ca_topic_score_codex":0.0027258925,"about_ca_topic_score_gemma":0.0018522295,"teacher_disagreement_score":0.015705066,"about_ca_system_score_codex":0.002354253,"about_ca_system_score_gemma":0.0029536856,"threshold_uncertainty_score":0.01708138},"labels":[],"label_agreement":null},{"id":"W4315645596","doi":"10.18280/isi.270614","title":"Indonesian Automatic Speech Recognition with XLSR-53","year":2022,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Indonesian; Word error rate; Speech recognition; Computer science; MAGIC (telescope); Word (group theory); Natural language processing; Language model; Training set; Artificial intelligence; Linguistics","score_opus":0.01775987249685566,"score_gpt":0.21229777143432518,"score_spread":0.19453789893746953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315645596","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19615324,0.00088976,0.6591105,0.0003679944,0.0004591533,0.00040070218,0.005651553,0.10824157,0.02872553],"genre_scores_gemma":[0.5578943,0.00036290562,0.38532323,0.00026995104,0.000057513887,0.0005465901,0.022157632,0.0026002626,0.030787684],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99903774,0.00022179671,0.00008930326,0.00027842209,0.00029266864,0.00008008231],"domain_scores_gemma":[0.9992698,0.0001876615,0.000039020382,0.00022319707,0.0002532497,0.00002700544],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011514297,0.0007227534,0.00057346106,0.0004628124,0.00020023978,0.0007303864,0.0007497543,0.0004267254,0.011938105],"category_scores_gemma":[0.0014384154,0.00035340525,0.00064152153,0.00033230826,0.00022876785,0.00085823017,0.0010101021,0.00079723157,0.011628192],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011877222,0.0005069708,0.0039304546,0.00038984398,0.00020115676,0.00052509346,0.00035366454,0.063697174,0.16349785,0.0031394588,0.022309044,0.74026155],"study_design_scores_gemma":[0.00011852557,0.0008991571,0.008107288,0.000064398235,0.0000922148,0.00083237793,0.0001417916,0.7787597,0.17105216,0.0010314522,0.038801678,0.00009925979],"about_ca_topic_score_codex":0.0034323677,"about_ca_topic_score_gemma":0.003398122,"teacher_disagreement_score":0.011938105,"about_ca_system_score_codex":0.0003204406,"about_ca_system_score_gemma":0.0006690762,"threshold_uncertainty_score":0.0399369},"labels":[],"label_agreement":null},{"id":"W4315700151","doi":"","title":"I-vector based Representation of Highly Imperfect Automatic Transcriptions","year":2014,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Imperfect; Representation (politics); Artificial intelligence; Natural language processing; Linguistics","score_opus":0.015819957402144164,"score_gpt":0.2273022812769938,"score_spread":0.21148232387484964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315700151","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.059815794,0.0008534173,0.9095665,0.0008022996,0.00073984574,0.00014273044,0.0072531127,0.009847019,0.010979226],"genre_scores_gemma":[0.53626275,0.0012755187,0.4058956,0.0002815134,0.00048135256,0.00035288214,0.02373769,0.0018288221,0.02988385],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99939907,0.00012564736,0.000042387204,0.000105174404,0.00023502557,0.000092620234],"domain_scores_gemma":[0.99830556,0.000606555,0.00012019947,0.000324785,0.0005813534,0.00006149266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004940265,0.0010962172,0.0006707081,0.00092999486,0.00030344777,0.0014293023,0.00096679945,0.0011778611,0.015983846],"category_scores_gemma":[0.0029609797,0.00028243772,0.0004300466,0.0015310912,0.00038864106,0.0011296517,0.0008827279,0.0010829675,0.007615298],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018652797,0.00018352224,0.00083488435,0.00055386976,0.00005654195,0.000757073,0.00025448698,0.10365293,0.16488689,0.01501091,0.025934188,0.6860094],"study_design_scores_gemma":[0.00005681074,0.00027435183,0.0017457185,0.00008280526,0.00004797879,0.00040573807,0.00020257507,0.8996146,0.07315298,0.0048230886,0.019538684,0.000054825698],"about_ca_topic_score_codex":0.0030129275,"about_ca_topic_score_gemma":0.003605658,"teacher_disagreement_score":0.015983846,"about_ca_system_score_codex":0.0004166468,"about_ca_system_score_gemma":0.000797857,"threshold_uncertainty_score":0.053471327},"labels":[],"label_agreement":null},{"id":"W4318003022","doi":"10.1109/gcaiot57150.2022.10019087","title":"Mitigating the effects of temporal distortion in a copy-detection based playback attack detector","year":2022,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Distortion (music); Computer science; Detector; Similarity (geometry); Speech recognition; Measure (data warehouse); Channel (broadcasting); Similarity measure; Artificial intelligence; Pattern recognition (psychology); Data mining; Telecommunications; Bandwidth (computing)","score_opus":0.014833054637465586,"score_gpt":0.2341417956944769,"score_spread":0.2193087410570113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318003022","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21694866,0.0008838661,0.7778394,0.00020648849,0.00020657119,0.00017438107,0.000088673914,0.0019446121,0.0017073668],"genre_scores_gemma":[0.79554975,0.00045297827,0.20044553,0.00016096281,0.00010042716,0.00007748355,0.00024822442,0.00010622143,0.0028585184],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998553,0.00017029131,0.00011371912,0.00020919838,0.0008538652,0.00009994569],"domain_scores_gemma":[0.99687296,0.0009952768,0.00043718866,0.00053270103,0.0009905852,0.00017129013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011780832,0.0009064616,0.0010481967,0.0012956619,0.00039408318,0.00096192065,0.001063295,0.00074284547,0.0010434545],"category_scores_gemma":[0.0053363265,0.0002620169,0.0003273146,0.00061796285,0.0005772482,0.001718447,0.0012056448,0.0009498527,0.0007437032],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015772474,0.00040319387,0.0071625537,0.00025568204,0.00016763766,0.0009328622,0.00026872888,0.018853419,0.36826727,0.0034809266,0.0018629624,0.5967675],"study_design_scores_gemma":[0.000057160945,0.0011820226,0.008757306,0.00003398895,0.00014577626,0.002882809,0.00017662258,0.545507,0.43623683,0.0012278876,0.0037184148,0.000074249874],"about_ca_topic_score_codex":0.0010390279,"about_ca_topic_score_gemma":0.0013990327,"teacher_disagreement_score":0.0012956619,"about_ca_system_score_codex":0.00034692255,"about_ca_system_score_gemma":0.0006922797,"threshold_uncertainty_score":0.006230414},"labels":[],"label_agreement":null},{"id":"W4318148717","doi":"10.1109/tai.2023.3240113","title":"Fine-Grained Early Frequency Attention for Deep Speaker Representation Learning","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Artificial Intelligence","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Robustness (evolution); Speech recognition; Deep learning; Convolutional neural network; Artificial intelligence; Speaker recognition; Feature learning; Speech processing; Transfer of learning","score_opus":0.09106019514806173,"score_gpt":0.32258037748894486,"score_spread":0.23152018234088312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318148717","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07080113,0.0033630934,0.9149412,0.00062283454,0.0003072948,0.00008242283,0.00035334373,0.005443691,0.004085009],"genre_scores_gemma":[0.8431839,0.0013126369,0.14525206,0.0005732206,0.00021042506,0.00012591839,0.0008717959,0.00022370425,0.008246378],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997335,0.000050863087,0.0000118540875,0.00008975715,0.000056943536,0.00005715092],"domain_scores_gemma":[0.9996619,0.00013628215,0.000029657027,0.0000715921,0.000072650124,0.000027819022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069370726,0.00110021,0.00051999313,0.0005688542,0.00031497082,0.0005015126,0.0013280793,0.00089607656,0.0033956005],"category_scores_gemma":[0.0013684012,0.0002767024,0.0007235273,0.0004738103,0.0004250345,0.0013397972,0.0011804427,0.0018124499,0.0013281975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040382924,0.00036242438,0.0024498985,0.00018750096,0.00015721655,0.0001725723,0.00015925844,0.20429796,0.07347737,0.008133707,0.009022817,0.7011755],"study_design_scores_gemma":[0.00001618688,0.000118079355,0.00110158,0.00001811735,0.000050491584,0.00007828639,0.000017091292,0.97153723,0.016814029,0.0071026688,0.003127646,0.000018592273],"about_ca_topic_score_codex":0.0062646666,"about_ca_topic_score_gemma":0.010818847,"teacher_disagreement_score":0.0062646666,"about_ca_system_score_codex":0.0007994445,"about_ca_system_score_gemma":0.0006822057,"threshold_uncertainty_score":0.0124563575},"labels":[],"label_agreement":null},{"id":"W4319862473","doi":"10.1109/slt54892.2023.10022470","title":"A Comprehensive Study on Self-Supervised Distillation for Speaker Representation Learning","year":2023,"lang":"en","type":"article","venue":"2022 IEEE Spoken Language Technology Workshop (SLT)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Benchmark (surveying); Representation (politics); Speaker recognition; Speech recognition; Artificial intelligence; Word error rate; Training set; Feature learning; Machine learning","score_opus":0.037294017843743366,"score_gpt":0.32256218263729897,"score_spread":0.2852681647935556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319862473","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02308675,0.009466736,0.9612085,0.00065234903,0.00016210317,0.00009059976,0.00009382643,0.0009831393,0.004255979],"genre_scores_gemma":[0.5702087,0.009813893,0.40210786,0.0011279493,0.0008895111,0.00031257476,0.0013985229,0.0006469625,0.013493936],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99767214,0.0010238516,0.00008962523,0.0006526966,0.0004602716,0.00010130651],"domain_scores_gemma":[0.99567986,0.002698632,0.00013166406,0.0007178902,0.0006687007,0.00010327297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036050586,0.001065298,0.0010173827,0.0006946272,0.0004862181,0.0011022998,0.001354877,0.0011657714,0.0017728201],"category_scores_gemma":[0.008264349,0.0005193373,0.001037522,0.0007800667,0.0011359282,0.0026745116,0.0017358831,0.0028315575,0.00081610517],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037325034,0.00043806445,0.0014990405,0.0006666543,0.00031132207,0.00010824479,0.0003100211,0.22199486,0.024150213,0.03697198,0.0073095425,0.70586675],"study_design_scores_gemma":[0.00001001232,0.00019197658,0.0005754688,0.000044384153,0.000036221558,0.00009654514,0.000030628846,0.97504133,0.009256453,0.009560162,0.0051281094,0.000028670558],"about_ca_topic_score_codex":0.0019449606,"about_ca_topic_score_gemma":0.0017643421,"teacher_disagreement_score":0.0036050586,"about_ca_system_score_codex":0.0007435746,"about_ca_system_score_gemma":0.0010432965,"threshold_uncertainty_score":0.019065559},"labels":[],"label_agreement":null},{"id":"W4319862706","doi":"10.1109/slt54892.2023.10022986","title":"Flow-ER: A Flow-Based Embedding Regularization Strategy for Robust Speech Representation Learning","year":2023,"lang":"en","type":"article","venue":"2022 IEEE Spoken Language Technology Workshop (SLT)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Embedding; Computer science; Regularization (linguistics); Artificial intelligence; Machine learning; Deep learning; Speech recognition; Representation (politics); Feature learning; Bottleneck; Task (project management)","score_opus":0.03353607308453113,"score_gpt":0.30544206453765,"score_spread":0.2719059914531189,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319862706","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001545307,0.00012776218,0.9972474,0.00005828358,0.000027714483,0.00003136296,0.00003263895,0.00049790274,0.00043158347],"genre_scores_gemma":[0.14286755,0.00064377097,0.8449152,0.00040436987,0.00018212783,0.00035758287,0.0007751561,0.00062408386,0.0092301415],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99946827,0.00016026535,0.000030200858,0.00013224749,0.00015737985,0.000051723113],"domain_scores_gemma":[0.99949396,0.00021139355,0.000053049007,0.000072505456,0.0001358342,0.000033285254],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017667506,0.0015628143,0.0009916844,0.0009059579,0.000369178,0.00058751303,0.0017511218,0.0015157365,0.0036906465],"category_scores_gemma":[0.0024077718,0.00057752174,0.0009811326,0.0006532223,0.0007109183,0.0018124551,0.0015547614,0.001999963,0.0014391601],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025755767,0.0002516914,0.00041487915,0.00022201949,0.0001225506,0.00013884497,0.0001396745,0.29150087,0.043602943,0.032941252,0.011481087,0.6189266],"study_design_scores_gemma":[0.000009179236,0.00004177257,0.000056400153,0.0000069123967,0.0000068344584,0.000033698245,0.0000040072478,0.99081707,0.0038939568,0.0034608494,0.0016587174,0.000010610189],"about_ca_topic_score_codex":0.0023737848,"about_ca_topic_score_gemma":0.0023198614,"teacher_disagreement_score":0.0036906465,"about_ca_system_score_codex":0.0005441116,"about_ca_system_score_gemma":0.0008777839,"threshold_uncertainty_score":0.012346506},"labels":[],"label_agreement":null},{"id":"W4320086272","doi":"10.48550/arxiv.2206.01685","title":"Toward a realistic model of speech processing in the brain with\\n self-supervised learning","year":2022,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"","keywords":"Computer science; Functional magnetic resonance imaging; Artificial intelligence; Hierarchy; Speech recognition; Benchmark (surveying); Neuroimaging; Natural language processing; Machine learning; Psychology; Neuroscience","score_opus":0.13240354466124338,"score_gpt":0.20674851802463984,"score_spread":0.07434497336339646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320086272","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055961385,0.00018196274,0.9397599,0.00087493757,0.000045963614,0.00004618666,0.00017593092,0.000597557,0.0023562005],"genre_scores_gemma":[0.77098846,0.00036706368,0.21971475,0.0004270573,0.00011951109,0.0002799738,0.00041351118,0.00015908522,0.0075306133],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99985147,0.00004515631,0.0000049787545,0.00004824141,0.00003313273,0.000016988874],"domain_scores_gemma":[0.99967587,0.00016426628,0.000033002736,0.00004126857,0.00006325859,0.000022343122],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052185036,0.00040221005,0.00035787615,0.00023286948,0.00020947526,0.00070909946,0.0012717806,0.0010213047,0.0010380218],"category_scores_gemma":[0.0012833409,0.00037928205,0.0006232665,0.00021480396,0.00078448164,0.0010511166,0.0006172062,0.0014437841,0.00041554507],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003653905,0.000039353017,0.00056192663,0.000036756544,0.00003208186,0.000035092646,0.00006786343,0.9677036,0.0035542084,0.012960132,0.001013454,0.01395905],"study_design_scores_gemma":[0.0000015079606,0.000004450411,0.000045666216,9.616201e-7,9.2378497e-7,0.0000035272155,0.0000015796014,0.99692863,0.00014289141,0.0027506698,0.00011815865,9.4523574e-7],"about_ca_topic_score_codex":0.0039899447,"about_ca_topic_score_gemma":0.0060045174,"teacher_disagreement_score":0.0039899447,"about_ca_system_score_codex":0.0007855563,"about_ca_system_score_gemma":0.00084591133,"threshold_uncertainty_score":0.007933438},"labels":[],"label_agreement":null},{"id":"W4321513043","doi":"10.1007/978-3-031-11035-1_2","title":"Improving Automatic Speech Recognition for Non-native English with Transfer Learning and Language Model Decoding","year":2022,"lang":"en","type":"book-chapter","venue":"Signals and communication technology","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Decoding methods; Computer science; Speech recognition; Transfer of learning; Voice activity detection; Acoustic model; Language model; Speech processing; Set (abstract data type); Natural language processing; Artificial intelligence; Telecommunications","score_opus":0.020601723571282447,"score_gpt":0.24169538823306397,"score_spread":0.2210936646617815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321513043","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025646785,0.0016449539,0.9412262,0.00022793413,0.0004167961,0.00006898329,0.0004151563,0.0121778315,0.018175364],"genre_scores_gemma":[0.18716244,0.0021148494,0.7127527,0.00037581043,0.00032275662,0.0002111679,0.0036906323,0.0022718455,0.091097824],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99964046,0.00006194619,0.00002514192,0.00008940641,0.0001430952,0.000039953342],"domain_scores_gemma":[0.9993894,0.0002806376,0.000013792393,0.00008411272,0.00021662429,0.000015366877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004094246,0.0011524567,0.0007554398,0.0005658946,0.0002961544,0.001046782,0.0008781571,0.0008336572,0.01302738],"category_scores_gemma":[0.001372129,0.00031078054,0.0007003656,0.0005858109,0.00029800535,0.001309953,0.00079209486,0.0012869763,0.014003528],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000091388596,0.00008329165,0.00024129316,0.00015809142,0.00003744523,0.0001087129,0.00009190225,0.008413583,0.09682481,0.0032494671,0.00992879,0.8807712],"study_design_scores_gemma":[0.000029977786,0.00028323437,0.0022366198,0.00005608707,0.00013864232,0.0009667649,0.00018575371,0.5628142,0.37814942,0.00950908,0.045571316,0.00005894209],"about_ca_topic_score_codex":0.0025014302,"about_ca_topic_score_gemma":0.0038902394,"teacher_disagreement_score":0.01302738,"about_ca_system_score_codex":0.00030151533,"about_ca_system_score_gemma":0.0004624325,"threshold_uncertainty_score":0.04358089},"labels":[],"label_agreement":null},{"id":"W4324269592","doi":"10.1007/978-981-19-6406-0_9","title":"Overview of Incorporating Nonlinear Functions into Recurrent Neural Network Models","year":2022,"lang":"en","type":"book-chapter","venue":"Springer proceedings in mathematics & statistics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Recurrent neural network; Computer science; Artificial neural network; Artificial intelligence; Range (aeronautics); Nonlinear system; Time delay neural network; Long short term memory; Machine learning; Speech recognition; Engineering","score_opus":0.06969708072922273,"score_gpt":0.28067170098954985,"score_spread":0.21097462026032712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4324269592","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010022945,0.014470784,0.97360307,0.00021614501,0.00025999438,0.000048648744,0.00016680123,0.0014509622,0.008781353],"genre_scores_gemma":[0.050363604,0.04506388,0.86112607,0.00039516555,0.0009400037,0.0002355711,0.0014377374,0.0009801395,0.03945785],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99979955,0.000044525794,0.000021911295,0.00004890687,0.000071868424,0.000013261007],"domain_scores_gemma":[0.99975663,0.00009757546,0.000013249705,0.000038709295,0.000082413746,0.000011364861],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072448223,0.0012044304,0.0008006746,0.00055137894,0.00017890494,0.0012207296,0.0014164755,0.0010512362,0.008869523],"category_scores_gemma":[0.0009475825,0.0008618725,0.0009602613,0.0008998853,0.00023228627,0.0018197396,0.0006886681,0.0014699888,0.0059074583],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000983426,0.000111774694,0.00033554278,0.0014781491,0.00024226645,0.00017986038,0.000095731964,0.17404547,0.018291174,0.09446523,0.015196325,0.69546014],"study_design_scores_gemma":[0.000021065036,0.00013708006,0.00031648748,0.00026579242,0.00014078578,0.00023920757,0.000016078126,0.74466276,0.008907571,0.06136177,0.18386893,0.000062428466],"about_ca_topic_score_codex":0.0026122862,"about_ca_topic_score_gemma":0.0038489283,"teacher_disagreement_score":0.008869523,"about_ca_system_score_codex":0.00039550092,"about_ca_system_score_gemma":0.00040526982,"threshold_uncertainty_score":0.02967155},"labels":[],"label_agreement":null},{"id":"W4324386959","doi":"10.1007/s11042-023-14412-2","title":"The voice as a material clue: a new forensic Algerian Corpus","year":2023,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Stress (linguistics); Arabic; Session (web analytics); Speech recognition; Natural language processing; Feature (linguistics); Linguistics; World Wide Web","score_opus":0.02979908837243485,"score_gpt":0.26438318273401457,"score_spread":0.2345840943615797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4324386959","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85204685,0.0050439774,0.032217883,0.0017299271,0.0008563703,0.0005698398,0.0155425975,0.0009777095,0.091014825],"genre_scores_gemma":[0.9166374,0.001510214,0.027485752,0.00033260687,0.00055640115,0.00046299116,0.021839464,0.0005272026,0.030648014],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9994066,0.00018980798,0.00004730438,0.000101285186,0.0001839112,0.00007103403],"domain_scores_gemma":[0.99886835,0.000390909,0.00006388587,0.00021908358,0.00038233315,0.00007543895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010247759,0.0005665041,0.00033173087,0.0031895358,0.0018835687,0.0012035542,0.0007103376,0.0009822348,0.008088904],"category_scores_gemma":[0.0019522392,0.00016292583,0.00021190799,0.0016961957,0.0011161041,0.0008104329,0.0017491691,0.00055871875,0.002048351],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017391931,0.0007715753,0.012567328,0.002056118,0.000120739816,0.00785099,0.017989941,0.006067724,0.08666282,0.021041073,0.067283675,0.77584887],"study_design_scores_gemma":[0.00020041,0.0003509672,0.14616036,0.00071148516,0.0001874687,0.012863603,0.017299522,0.011181673,0.045460578,0.005846852,0.75959134,0.00014568186],"about_ca_topic_score_codex":0.005581344,"about_ca_topic_score_gemma":0.0089932745,"teacher_disagreement_score":0.008088904,"about_ca_system_score_codex":0.000675127,"about_ca_system_score_gemma":0.0009847601,"threshold_uncertainty_score":0.027060151},"labels":[],"label_agreement":null},{"id":"W4361795437","doi":"10.2139/ssrn.4394373","title":"Domain-General Vs. Domain-Specific Pre-Trained Models Binary Patch Grouping for Improved WSI Representation","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"William Osler Health System; University of Waterloo; McMaster University","funders":"","keywords":"Domain (mathematical analysis); Representation (politics); Binary number; Computer science; Artificial intelligence; Pattern recognition (psychology); Mathematics; Arithmetic; Mathematical analysis","score_opus":0.04305255522905972,"score_gpt":0.2867782409578404,"score_spread":0.24372568572878067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361795437","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.063258536,0.00054929336,0.9273484,0.000202616,0.00012723039,0.00006796501,0.0005533912,0.003964909,0.0039276807],"genre_scores_gemma":[0.6191132,0.000724776,0.3572538,0.0002577093,0.00011861621,0.00016290639,0.004490627,0.0009963299,0.016882045],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998078,0.000039446863,0.000009676822,0.00006468363,0.000037198173,0.000041251504],"domain_scores_gemma":[0.9997178,0.0000512858,0.000015377642,0.00011830337,0.000072027484,0.00002526284],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034076447,0.00065375824,0.00065430393,0.00046957147,0.00019369958,0.00062482356,0.0007470577,0.000677363,0.0055560204],"category_scores_gemma":[0.00093913195,0.00020830292,0.0006299402,0.0006164502,0.00029130033,0.0008365175,0.00069743,0.0010640561,0.0038752824],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008370154,0.000195291,0.0011874352,0.00015332205,0.00009005631,0.00010939891,0.00012035201,0.13085717,0.11542023,0.006148988,0.010300376,0.7345804],"study_design_scores_gemma":[0.000020090867,0.00011268296,0.0013293838,0.000020273039,0.000055432844,0.00009806549,0.00006602713,0.953404,0.036971685,0.0027075447,0.0051966165,0.000018187875],"about_ca_topic_score_codex":0.004015706,"about_ca_topic_score_gemma":0.0062082843,"teacher_disagreement_score":0.0055560204,"about_ca_system_score_codex":0.00021668615,"about_ca_system_score_gemma":0.0005942103,"threshold_uncertainty_score":0.018586755},"labels":[],"label_agreement":null},{"id":"W4362558814","doi":"10.58837/chula.the.2020.141","title":"Using automatic speech recognition to assess Thai speech language fluency in montreal cognitive assessment (MoCA)","year":2020,"lang":"en","type":"dissertation","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Speech recognition; Hidden Markov model; Fluency; Language model; Artificial intelligence; Natural language processing; Test set; Psychology","score_opus":0.072513247186501,"score_gpt":0.35510322075969214,"score_spread":0.28258997357319116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362558814","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78003985,0.0006055003,0.21126448,0.00014630292,0.00011791634,0.00048987,0.0012635324,0.002498536,0.00357404],"genre_scores_gemma":[0.92090374,0.0002148797,0.07599765,0.00008776017,0.000036453555,0.00033722344,0.0010075836,0.000078814286,0.0013358347],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99907386,0.00029869613,0.00008816659,0.00022393612,0.00025021198,0.00006509086],"domain_scores_gemma":[0.9989459,0.0003708832,0.00010433797,0.00007310032,0.00045878463,0.00004698236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012344533,0.00069836277,0.00032349446,0.00095344364,0.00020906422,0.00060319836,0.000379044,0.0005272406,0.0012853863],"category_scores_gemma":[0.0039429753,0.00012884669,0.00048342173,0.00041232165,0.00024751519,0.0005113047,0.0004621908,0.00027822904,0.00050125737],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012297389,0.0003189364,0.044490736,0.0005064157,0.00037333395,0.0009387257,0.0007412495,0.028231693,0.21457899,0.0008815745,0.0032143004,0.7044944],"study_design_scores_gemma":[0.00024161336,0.0028911573,0.23232937,0.00010274917,0.00054064125,0.004697314,0.0007529052,0.512955,0.23662506,0.0015863129,0.0068444135,0.00043343587],"about_ca_topic_score_codex":0.009761353,"about_ca_topic_score_gemma":0.010286927,"teacher_disagreement_score":0.009761353,"about_ca_system_score_codex":0.00027994343,"about_ca_system_score_gemma":0.00055059616,"threshold_uncertainty_score":0.01940912},"labels":[],"label_agreement":null},{"id":"W4367145625","doi":"10.1121/10.0019208","title":"Using the Corpus of North American Spoken English to explore regional variation in millions of eɪ diphthongs","year":2023,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; American English; Python (programming language); Diphthong; Speech recognition; Speech corpus; Coarticulation; Natural language processing; Variation (astronomy); Variety (cybernetics); Artificial intelligence; Speech synthesis; Linguistics; Vowel","score_opus":0.06297583373034152,"score_gpt":0.2886126725932716,"score_spread":0.2256368388629301,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367145625","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6205829,0.0047795395,0.038704444,0.0015246067,0.00085255987,0.0012283059,0.25527343,0.0026771822,0.07437702],"genre_scores_gemma":[0.56645447,0.0024294292,0.064988926,0.00063584634,0.00037668593,0.0037871227,0.33118543,0.0015698526,0.028572299],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99891126,0.00022136948,0.00012067843,0.00034904762,0.0003056152,0.00009212709],"domain_scores_gemma":[0.9967038,0.0012213598,0.00018272629,0.00031541756,0.001417655,0.000159102],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008256189,0.00045541747,0.0003599418,0.0028641748,0.0014830756,0.0010415586,0.0005803646,0.0003691748,0.009693717],"category_scores_gemma":[0.0038425385,0.00024823885,0.00028647637,0.0035845626,0.0006750797,0.00079965824,0.0015252155,0.0006463536,0.004587185],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008601849,0.00039679187,0.04885095,0.0049456977,0.00020518043,0.003466028,0.039152425,0.0022270672,0.09769169,0.0071952473,0.27390066,0.52110803],"study_design_scores_gemma":[0.00006620983,0.00012762278,0.44475153,0.00037621774,0.00014784116,0.0016231431,0.016680172,0.003959698,0.013174602,0.0014792895,0.5174512,0.00016250591],"about_ca_topic_score_codex":0.05985274,"about_ca_topic_score_gemma":0.14680678,"teacher_disagreement_score":0.05985274,"about_ca_system_score_codex":0.0008991097,"about_ca_system_score_gemma":0.0020159197,"threshold_uncertainty_score":0.11900872},"labels":[],"label_agreement":null},{"id":"W4367280348","doi":"10.1121/10.0018553","title":"Perception error variation in masking contexts","year":2023,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Masking (illustration); Noise (video); Confusion; Variation (astronomy); Perception; Speech perception; Speech recognition; Computer science; Word (group theory); Mathematics; Psychology; Artificial intelligence; Physics","score_opus":0.024518950563863617,"score_gpt":0.2736917242615607,"score_spread":0.24917277369769708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367280348","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98954225,0.0006336304,0.0064078984,0.00004156248,0.00003622376,0.000036697304,0.0015008677,0.00018872229,0.001612135],"genre_scores_gemma":[0.9943264,0.000112034075,0.002737043,0.000029450166,0.00001276362,0.00004700691,0.002299792,0.00006873808,0.00036679686],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9944918,0.0014419962,0.0007183074,0.0016040312,0.0015136048,0.00023030235],"domain_scores_gemma":[0.97087336,0.019730736,0.0022439812,0.003639268,0.003050128,0.00046251688],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029119293,0.0006304949,0.00063595054,0.0010168358,0.00037034156,0.001379404,0.000496659,0.00062952185,0.0013504443],"category_scores_gemma":[0.03469828,0.00021508985,0.0003441679,0.00088554964,0.00065931794,0.0011700429,0.002245297,0.0005643424,0.0005440955],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0096168555,0.00039176078,0.3832725,0.0022552963,0.0009812746,0.0012527072,0.011817338,0.019264592,0.26536393,0.0020261009,0.0064875344,0.29727006],"study_design_scores_gemma":[0.00008730716,0.00086232706,0.90357715,0.00018678233,0.00035223327,0.0021546471,0.00266533,0.02813156,0.051265385,0.003977345,0.006488424,0.00025148407],"about_ca_topic_score_codex":0.0014996706,"about_ca_topic_score_gemma":0.0015578119,"teacher_disagreement_score":0.0029119293,"about_ca_system_score_codex":0.0003232466,"about_ca_system_score_gemma":0.00029966404,"threshold_uncertainty_score":0.015399933},"labels":[],"label_agreement":null},{"id":"W4367627905","doi":"10.3390/electronics12092055","title":"Knowledge-Based Features for Speech Analysis and Classification: Pronunciation Diagnoses","year":2023,"lang":"en","type":"article","venue":"Electronics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Pronunciation; Computer science; Articulation (sociology); Speech recognition; Speech production; Natural language processing; Artificial intelligence; Linguistics","score_opus":0.03250779710277582,"score_gpt":0.2931780798860759,"score_spread":0.26067028278330007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367627905","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10914945,0.0011349644,0.8763809,0.0005189189,0.00018477389,0.0003945536,0.0021454117,0.0037116436,0.006379288],"genre_scores_gemma":[0.74318767,0.0005186356,0.2502256,0.00011552184,0.00009727284,0.00035460023,0.0022077416,0.00009555895,0.0031974693],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993362,0.000079232115,0.00008994731,0.00015935098,0.00023888452,0.00009637972],"domain_scores_gemma":[0.998979,0.00043607038,0.00010217486,0.00010834901,0.00032767907,0.000046754263],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006662034,0.0008874163,0.0006980763,0.0028256932,0.00041737626,0.001175209,0.00087761163,0.0012925516,0.0031197963],"category_scores_gemma":[0.00376374,0.00014931838,0.0005252718,0.001087013,0.0003955373,0.0010343962,0.00076504116,0.0007655603,0.0018345166],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030685743,0.00023233722,0.009538766,0.00016648979,0.000046827336,0.00047934017,0.0001493027,0.0098865,0.03929092,0.0021353457,0.0035117976,0.9342556],"study_design_scores_gemma":[0.00005858827,0.0004499384,0.05324597,0.00021715021,0.00017825363,0.0022296999,0.0006945434,0.8109609,0.10422365,0.013483498,0.01412292,0.00013493531],"about_ca_topic_score_codex":0.0029756862,"about_ca_topic_score_gemma":0.0020993114,"teacher_disagreement_score":0.0031197963,"about_ca_system_score_codex":0.0005380684,"about_ca_system_score_gemma":0.0006271594,"threshold_uncertainty_score":0.010436773},"labels":[],"label_agreement":null},{"id":"W4372259784","doi":"10.1109/icassp49357.2023.10095515","title":"Grad-StyleSpeech: Any-Speaker Adaptive Text-to-Speech Synthesis with Diffusion Models","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Speech recognition; Speech synthesis; Similarity (geometry); Speech processing; Generative grammar; Generative model; Artificial intelligence","score_opus":0.04366180071214854,"score_gpt":0.23850837105092526,"score_spread":0.19484657033877673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4372259784","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01467829,0.0013381685,0.92206883,0.00029642848,0.0005159146,0.00017274646,0.0019588028,0.04969534,0.009275545],"genre_scores_gemma":[0.31010246,0.0010422582,0.64185995,0.0006261767,0.0002740974,0.000522458,0.011215104,0.0077732108,0.026584283],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995271,0.000079910234,0.000027647333,0.00015588207,0.00016985137,0.000039643746],"domain_scores_gemma":[0.99962926,0.0001495499,0.000018213488,0.000091534144,0.00007357038,0.000037894126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000791225,0.0014514392,0.0007203082,0.0005242654,0.00028636304,0.00077860185,0.0012924985,0.0009975967,0.014296414],"category_scores_gemma":[0.0018436295,0.00032761053,0.0007277438,0.00038132042,0.00038139554,0.0010530977,0.0018051956,0.0014830113,0.0075063314],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00095894065,0.00027402307,0.0007987835,0.0004801208,0.00018481571,0.00041450778,0.00025287416,0.108206876,0.11152679,0.009868595,0.04411468,0.722919],"study_design_scores_gemma":[0.00023880071,0.0003386545,0.0006387056,0.00004643176,0.000052040745,0.00043285376,0.00006903799,0.8594557,0.07284107,0.012870508,0.052928496,0.00008782575],"about_ca_topic_score_codex":0.0027415166,"about_ca_topic_score_gemma":0.005222023,"teacher_disagreement_score":0.014296414,"about_ca_system_score_codex":0.00035475564,"about_ca_system_score_gemma":0.0006394553,"threshold_uncertainty_score":0.04782629},"labels":[],"label_agreement":null},{"id":"W4372266975","doi":"10.1109/icassp49357.2023.10096406","title":"On Unsupervised Uncertainty-Driven Speech Pseudo-Label Filtering and Model Calibration","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Calibration; Speech recognition; Artificial intelligence; Pattern recognition (psychology); Mathematics; Statistics","score_opus":0.0494052664186122,"score_gpt":0.26795665898778115,"score_spread":0.21855139256916895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4372266975","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01617168,0.0002978756,0.9808014,0.000286682,0.00003530295,0.000044879434,0.00008885544,0.0016070274,0.0006662706],"genre_scores_gemma":[0.5937362,0.00035114333,0.3964986,0.0009329584,0.00022102466,0.00028278894,0.0018420875,0.00080568297,0.0053294767],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99740076,0.001200592,0.00011012646,0.0006356782,0.0004511022,0.00020179273],"domain_scores_gemma":[0.99012357,0.006332464,0.00059943326,0.0016826094,0.0010239385,0.00023791383],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004547642,0.0018098723,0.0014822404,0.0011160069,0.0010729413,0.0014484567,0.003028651,0.0024831588,0.0018439605],"category_scores_gemma":[0.01576959,0.0009823228,0.0012272887,0.0008682131,0.0019382816,0.0032757416,0.0030318233,0.004152979,0.0010411151],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037443166,0.00018053984,0.002656425,0.00013514486,0.00014427865,0.00016291418,0.00050105015,0.7558735,0.006678978,0.016015973,0.003642118,0.21363467],"study_design_scores_gemma":[0.000008928861,0.000022498054,0.00018206963,0.000010105305,0.000005408546,0.000022272214,0.00001408968,0.99229455,0.0016148208,0.0053599738,0.00045489095,0.000010480931],"about_ca_topic_score_codex":0.008179004,"about_ca_topic_score_gemma":0.010644347,"teacher_disagreement_score":0.008179004,"about_ca_system_score_codex":0.0014919931,"about_ca_system_score_gemma":0.001748177,"threshold_uncertainty_score":0.024050534},"labels":[],"label_agreement":null},{"id":"W4375869393","doi":"10.1109/icassp49357.2023.10096040","title":"Hybrid Neural Network with Cross- and Self-Module Attention Pooling for Text-Independent Speaker Verification","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Pooling; Time delay neural network; Artificial neural network; Artificial intelligence; Speech recognition; Feature extraction; Pattern recognition (psychology); Convolutional neural network; Hybrid neural network; Neocognitron; Speaker recognition","score_opus":0.020656171329763155,"score_gpt":0.25866326936253015,"score_spread":0.23800709803276698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4375869393","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11654772,0.00142972,0.8737517,0.00019091951,0.00020820969,0.00010388661,0.0002767001,0.0047338977,0.0027571733],"genre_scores_gemma":[0.8020406,0.00031677162,0.18986358,0.00023957182,0.000078039404,0.00010322119,0.00080330763,0.00014104843,0.0064138826],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99954826,0.00008554465,0.000023287677,0.00016208152,0.00010380421,0.00007703112],"domain_scores_gemma":[0.99964166,0.000112848094,0.00003172865,0.000065762346,0.00012682662,0.000021264359],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011369154,0.0008031004,0.0006944342,0.00053140405,0.00031557676,0.00046904403,0.0011906072,0.0008041246,0.002223501],"category_scores_gemma":[0.0011164045,0.00035527296,0.0005349564,0.0003865512,0.0003016844,0.0014491321,0.0011612561,0.00085767306,0.00082281826],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00094320066,0.0002789729,0.0019218059,0.00012496886,0.00029458723,0.00021915365,0.000113346156,0.077098444,0.13394104,0.0022172881,0.0044192323,0.778428],"study_design_scores_gemma":[0.000016403665,0.00009366634,0.0012621018,0.00000747936,0.000064796244,0.00008201511,0.000015053911,0.9557181,0.04076678,0.0008907884,0.0010648106,0.000018094779],"about_ca_topic_score_codex":0.0054975664,"about_ca_topic_score_gemma":0.008300405,"teacher_disagreement_score":0.0054975664,"about_ca_system_score_codex":0.000620278,"about_ca_system_score_gemma":0.00058600475,"threshold_uncertainty_score":0.010931134},"labels":[],"label_agreement":null},{"id":"W4376869488","doi":"10.18280/isi.280208","title":"Comparative Study of CNN Structures for Arabic Speech Recognition","year":2023,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Arabic; Speech recognition; Computer science; Natural language processing; Linguistics; Artificial intelligence; Philosophy","score_opus":0.06243161467872856,"score_gpt":0.2909166329288379,"score_spread":0.22848501825010933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376869488","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86288744,0.014174548,0.07305573,0.0010014045,0.0009433963,0.00019396827,0.002396723,0.0044176965,0.04092919],"genre_scores_gemma":[0.9496799,0.0037203014,0.033018168,0.00017713476,0.00008764651,0.00009211944,0.003623149,0.00018812896,0.00941344],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99950624,0.00009023371,0.000044758264,0.00010296358,0.00015666227,0.00009909658],"domain_scores_gemma":[0.9989599,0.0003857624,0.00005473592,0.00009784206,0.0004404982,0.000061264494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010550397,0.0012357138,0.00046431902,0.001075425,0.00037656358,0.0008368276,0.00079458725,0.0007259744,0.0038717003],"category_scores_gemma":[0.0032882516,0.00024796068,0.0005248787,0.000694833,0.00026698242,0.001485158,0.00045895996,0.00064332166,0.0016439524],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022337718,0.0002899502,0.010464422,0.000929886,0.0004276531,0.00050929794,0.00023261145,0.22882098,0.039435025,0.004229194,0.013034381,0.69939286],"study_design_scores_gemma":[0.000053443913,0.00071222545,0.009931034,0.00013524397,0.00023484687,0.00023275362,0.00032524992,0.93317163,0.045096833,0.0014457868,0.008606347,0.000054661854],"about_ca_topic_score_codex":0.017182553,"about_ca_topic_score_gemma":0.018291822,"teacher_disagreement_score":0.017182553,"about_ca_system_score_codex":0.001258109,"about_ca_system_score_gemma":0.00081819046,"threshold_uncertainty_score":0.034165084},"labels":[],"label_agreement":null},{"id":"W4378505314","doi":"10.48550/arxiv.2305.15096","title":"Dynamic Masking Rate Schedules for MLM Pretraining","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Samsung; York University; Samsung Advanced Institute of Technology","keywords":"Masking (illustration); Computer science; Speedup; Transformer; Pareto principle; Schedule; Speech recognition; Real-time computing; Parallel computing; Mathematical optimization; Mathematics; Operating system; Engineering; Electrical engineering; Voltage","score_opus":0.1660565028958392,"score_gpt":0.22019851642282345,"score_spread":0.05414201352698425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378505314","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20922735,0.001190143,0.7593113,0.00074816635,0.00036468144,0.0002456832,0.0004761158,0.018712837,0.0097236745],"genre_scores_gemma":[0.81747055,0.00021457602,0.17483057,0.00037373466,0.00006549518,0.0002606298,0.0007823396,0.0015044467,0.0044975886],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995315,0.00013097256,0.000032985005,0.0001324611,0.00009590908,0.00007618594],"domain_scores_gemma":[0.998054,0.0010741525,0.00011550717,0.00040275883,0.00024698768,0.000106526764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012172335,0.0015059034,0.000611107,0.0004002149,0.0004932668,0.00071643613,0.0015768597,0.0008602885,0.0082288645],"category_scores_gemma":[0.0062665488,0.00070756214,0.00058074837,0.00026050862,0.0005402752,0.0018693756,0.0013609936,0.001961108,0.0030655568],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015322709,0.00044668512,0.0044618575,0.00031492536,0.00011958201,0.00023951745,0.00044382122,0.46986732,0.11249495,0.006119905,0.009024256,0.3949349],"study_design_scores_gemma":[0.00007850187,0.00025380863,0.0010227731,0.000032683216,0.000040996085,0.00007507707,0.000085160085,0.95458233,0.035745706,0.0045738546,0.0034692287,0.000039946593],"about_ca_topic_score_codex":0.0045540403,"about_ca_topic_score_gemma":0.010372091,"teacher_disagreement_score":0.0082288645,"about_ca_system_score_codex":0.0008286135,"about_ca_system_score_gemma":0.0013785042,"threshold_uncertainty_score":0.027528286},"labels":[],"label_agreement":null},{"id":"W4380449787","doi":"10.5267/j.ijdns.2023.5.004","title":"A framework for pronunciation error detection and correction for non-native Arab speakers of English language","year":2023,"lang":"en","type":"article","venue":"International Journal of Data and Network Science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Pronunciation; Computer science; Classifier (UML); Artificial intelligence; Speech recognition; Natural language processing; Confusion; Decision tree; Confusion matrix; Error detection and correction; Construct (python library); Linguistics; Psychology; Algorithm","score_opus":0.042945068011124465,"score_gpt":0.3388800272419896,"score_spread":0.29593495923086516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380449787","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036986205,0.000106066684,0.99313253,0.00014689614,0.00003653721,0.00013481145,0.00012901096,0.002094664,0.0005208594],"genre_scores_gemma":[0.08549198,0.00012713904,0.9121243,0.000081613165,0.000036582813,0.00026429503,0.0005869108,0.00010524277,0.0011819409],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99706984,0.0007306083,0.00026292395,0.00079982926,0.000943593,0.00019321014],"domain_scores_gemma":[0.9958877,0.0013038545,0.00051784824,0.00036836226,0.0017610508,0.0001611696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00446943,0.0013150459,0.00093002897,0.0037721687,0.0012821254,0.0017847015,0.002249727,0.0011970926,0.0018031191],"category_scores_gemma":[0.009335799,0.00041386078,0.0013888262,0.0008252178,0.000971359,0.0017882804,0.001825506,0.0012875294,0.0012276277],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028141227,0.00062940887,0.012678786,0.00038878436,0.00024910356,0.0007911166,0.0014510066,0.101429805,0.025512151,0.037125204,0.008548747,0.8109144],"study_design_scores_gemma":[0.000031236763,0.0002755527,0.004776999,0.00014146182,0.0000876732,0.000523801,0.00054175756,0.9439554,0.015261059,0.020766279,0.01352118,0.000117587864],"about_ca_topic_score_codex":0.021804791,"about_ca_topic_score_gemma":0.02489488,"teacher_disagreement_score":0.021804791,"about_ca_system_score_codex":0.0013228069,"about_ca_system_score_gemma":0.0047289575,"threshold_uncertainty_score":0.043355703},"labels":[],"label_agreement":null},{"id":"W4382053133","doi":"10.1109/iwbf57495.2023.10157564","title":"On the Use of Cross-module Attention Statistics Pooling for Speaker Verification","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Computer science; Pooling; Artificial neural network; Speech recognition; Artificial intelligence; Time delay neural network; Feature extraction; Pattern recognition (psychology); Convolutional neural network; Speaker recognition","score_opus":0.1666763134449241,"score_gpt":0.33124857941475017,"score_spread":0.16457226596982608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382053133","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061199352,0.0010156068,0.930622,0.0001694385,0.00011055655,0.00008816077,0.000113392125,0.0032473176,0.0034342122],"genre_scores_gemma":[0.81100976,0.0004966238,0.18086086,0.00032582108,0.00007363405,0.000062635125,0.00045810486,0.00012957041,0.006582941],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994305,0.00014867968,0.000026934264,0.00021070508,0.0001114134,0.00007174673],"domain_scores_gemma":[0.99946564,0.00016606486,0.000040306488,0.000121909055,0.00018037639,0.000025733396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015789398,0.0008595487,0.00058231165,0.00059555605,0.0003473155,0.0006072292,0.0011097468,0.00079152203,0.0023621751],"category_scores_gemma":[0.0015327309,0.00034825315,0.0005439265,0.00047791805,0.000417463,0.0014839789,0.0013034305,0.0008003372,0.0008947618],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007049005,0.00016412951,0.002470041,0.000110646564,0.0002890264,0.00021528706,0.00015203867,0.04128028,0.154034,0.0044640033,0.0026111035,0.79350454],"study_design_scores_gemma":[0.000019183017,0.0002529514,0.003494415,0.000018245184,0.00012834244,0.00022209491,0.000035169887,0.89463943,0.095031746,0.0026665232,0.0034588508,0.000033054934],"about_ca_topic_score_codex":0.005245657,"about_ca_topic_score_gemma":0.008106082,"teacher_disagreement_score":0.005245657,"about_ca_system_score_codex":0.0005056886,"about_ca_system_score_gemma":0.00063491554,"threshold_uncertainty_score":0.010430217},"labels":[],"label_agreement":null},{"id":"W4382053191","doi":"10.1109/iwbf57495.2023.10157651","title":"On the influence of the quality of pseudo-labels on the self-supervised speaker verification task: a thorough analysis","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Overfitting; Computer science; Discriminative model; Task (project management); Artificial intelligence; Noise (video); Memorization; Speech recognition; Quality (philosophy); Cluster analysis; Embedding; Pattern recognition (psychology); Machine learning; Artificial neural network; Mathematics; Image (mathematics); Engineering","score_opus":0.05485249341111849,"score_gpt":0.294590206193768,"score_spread":0.23973771278264955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382053191","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5963906,0.006132765,0.38667616,0.001056687,0.0002650039,0.00025288708,0.00033508564,0.0013286753,0.007562111],"genre_scores_gemma":[0.97131854,0.00075673516,0.025799695,0.00017213279,0.00008350551,0.000055034885,0.00032599366,0.00026019174,0.0012281648],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9946197,0.002539294,0.00024745255,0.0009582318,0.0012712543,0.00036401974],"domain_scores_gemma":[0.9509424,0.04076109,0.0017471157,0.002916423,0.0031688672,0.00046403977],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009023852,0.0013422244,0.0009607697,0.000637259,0.00060602,0.0014084197,0.0007603097,0.0012661888,0.001344416],"category_scores_gemma":[0.047107406,0.0004440031,0.0004972775,0.00039144442,0.0015505643,0.002553962,0.0015186549,0.0015303362,0.00053562963],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032698587,0.000532047,0.028588163,0.0015704829,0.0007003835,0.0006230626,0.0009784718,0.34855798,0.1993525,0.007413563,0.00431979,0.40409362],"study_design_scores_gemma":[0.000047625643,0.0019113978,0.029296072,0.00020181098,0.00022830504,0.0006932197,0.00041743153,0.8237675,0.13460268,0.0062327124,0.0024515323,0.00014960748],"about_ca_topic_score_codex":0.002214171,"about_ca_topic_score_gemma":0.003100637,"teacher_disagreement_score":0.009023852,"about_ca_system_score_codex":0.0005579242,"about_ca_system_score_gemma":0.00074948714,"threshold_uncertainty_score":0.047723234},"labels":[],"label_agreement":null},{"id":"W4382862298","doi":"10.3390/electronics12132887","title":"Review of Advances in Speech Processing with Focus on Artificial Neural Networks","year":2023,"lang":"en","type":"article","venue":"Electronics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Focus (optics); Computer science; Speech processing; Artificial neural network; Hidden Markov model; Coding (social sciences); Artificial intelligence; Speech recognition","score_opus":0.019845192751302896,"score_gpt":0.2754517902035622,"score_spread":0.2556065974522593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382862298","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00038108023,0.9896639,0.0029594828,0.001063263,0.0011951572,0.000009943973,0.00004669983,0.00002867082,0.00465185],"genre_scores_gemma":[0.0021237186,0.99165946,0.0024256296,0.0004927045,0.0014168598,0.000012005642,0.000078805875,0.000013394578,0.0017773979],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9996092,0.000070329,0.00006235713,0.00007076421,0.00016637977,0.00002108315],"domain_scores_gemma":[0.9985682,0.0008809643,0.00008625977,0.000038638434,0.00038730062,0.00003857172],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073349033,0.0007799036,0.00073915126,0.0020831581,0.00031275622,0.0010483734,0.00089515245,0.0010338514,0.0052683237],"category_scores_gemma":[0.00203931,0.0003431608,0.0004016039,0.0028483854,0.00055663165,0.0019440195,0.00053319096,0.0012235215,0.0026309444],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006608532,0.00006503588,0.0002978538,0.013829335,0.00008208035,0.00013992023,0.000095791765,0.001497613,0.002163471,0.015414171,0.04278102,0.92356753],"study_design_scores_gemma":[0.000006094183,0.00009363369,0.0011198083,0.005269754,0.000086569016,0.00053899555,0.000079552774,0.0009972418,0.0010330197,0.0091454,0.9815958,0.00003406315],"about_ca_topic_score_codex":0.0010796834,"about_ca_topic_score_gemma":0.0015114285,"teacher_disagreement_score":0.0052683237,"about_ca_system_score_codex":0.0006267056,"about_ca_system_score_gemma":0.0009504325,"threshold_uncertainty_score":0.017624319},"labels":[],"label_agreement":null},{"id":"W4383217247","doi":"10.22541/au.168857312.29438464/v1","title":"Bidirectional Long short-term memory and Recurrent Neural Network model for speech recognition","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"International Development Research Centre; Styrelsen för Internationellt Utvecklingssamarbete","keywords":"Computer science; Recurrent neural network; Speech recognition; Word error rate; Artificial neural network; Long short term memory; Term (time); Short-term memory; Transformer; Artificial intelligence; Language model; Working memory; Cognition","score_opus":0.13743307712226754,"score_gpt":0.3105569811471613,"score_spread":0.17312390402489375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383217247","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0646354,0.0033429111,0.92262995,0.00043995515,0.0003118265,0.0000750648,0.00040063492,0.0020517856,0.0061123297],"genre_scores_gemma":[0.8472365,0.0021762357,0.13202234,0.00022152832,0.00013768775,0.0001753296,0.0011687452,0.0001839667,0.016677635],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996772,0.00006612706,0.000027032946,0.00010237965,0.000086449014,0.000040840765],"domain_scores_gemma":[0.9996551,0.00010904826,0.000043041222,0.000046101693,0.0001325973,0.000014084889],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060751574,0.00080635253,0.0005699758,0.00038148166,0.0001859722,0.0006841378,0.0011314447,0.0006580505,0.0022149023],"category_scores_gemma":[0.001385096,0.00024091765,0.0007439272,0.0005080328,0.00026549824,0.00091037265,0.0003675713,0.0010276821,0.001027942],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042255878,0.00025374774,0.0027703044,0.00036107708,0.00032885332,0.00037574876,0.00017192535,0.5002207,0.04153166,0.016339324,0.005475581,0.43174854],"study_design_scores_gemma":[0.0000048326883,0.000059956255,0.00031945104,0.0000068456225,0.0000316799,0.000041920644,0.0000066961184,0.99323845,0.0035227663,0.0019716136,0.00078610325,0.000009771733],"about_ca_topic_score_codex":0.0076807067,"about_ca_topic_score_gemma":0.008671054,"teacher_disagreement_score":0.0076807067,"about_ca_system_score_codex":0.0005093793,"about_ca_system_score_gemma":0.0005767604,"threshold_uncertainty_score":0.015272021},"labels":[],"label_agreement":null},{"id":"W4383746897","doi":"10.1109/memea57477.2023.10171898","title":"Performance of Speech Recognition Algorithms in Musical Speech used for Speech-Language Pathology Rehabilitation","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Speech recognition; Speech processing; Natural language processing; Artificial intelligence","score_opus":0.03338750530970448,"score_gpt":0.28691131119752716,"score_spread":0.2535238058878227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383746897","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9422024,0.0008630954,0.052017078,0.00008782432,0.00017414577,0.00011190038,0.0002444609,0.0023391584,0.001960088],"genre_scores_gemma":[0.9250817,0.0003157542,0.07169171,0.00005739909,0.0000364412,0.00012817777,0.00087774184,0.00027384044,0.0015374357],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99766505,0.00051504764,0.00038888198,0.00073747477,0.00050804944,0.0001854748],"domain_scores_gemma":[0.9953028,0.002765129,0.00024313405,0.0003172775,0.001260256,0.00011138317],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001983287,0.0010263773,0.00087838346,0.0011574201,0.0004140423,0.0010503378,0.0006953888,0.00085792487,0.0016677076],"category_scores_gemma":[0.007834562,0.00022417429,0.00057679723,0.0005988354,0.00032947355,0.0008634622,0.00049553026,0.0004767935,0.001210935],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003978213,0.0006990512,0.023405282,0.0006277326,0.00045396734,0.000570734,0.00096342,0.047423862,0.22047743,0.00075218896,0.0022481221,0.69839996],"study_design_scores_gemma":[0.00016466268,0.0028561235,0.057151973,0.00007330159,0.00047200205,0.0015563952,0.00073375134,0.5577572,0.37407595,0.0006248594,0.0043702456,0.00016350081],"about_ca_topic_score_codex":0.0030548223,"about_ca_topic_score_gemma":0.001655029,"teacher_disagreement_score":0.0030548223,"about_ca_system_score_codex":0.0005051654,"about_ca_system_score_gemma":0.0005960586,"threshold_uncertainty_score":0.010488749},"labels":[],"label_agreement":null},{"id":"W4384615840","doi":"10.48550/arxiv.2307.07359","title":"From Multilayer Perceptron to GPT: A Reflection on Deep Learning Research for Wireless Physical Layer","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Division of Electrical, Communications and Cyber Systems; Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Wireless; Computer science; Wireless network; Physical layer; Wireless broadband; Perceptron; Context (archaeology); Artificial intelligence; Machine learning; Empirical research; Telecommunications; Artificial neural network","score_opus":0.37201008105183087,"score_gpt":0.32566992425717856,"score_spread":0.04634015679465231,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384615840","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007312861,0.026313022,0.8481329,0.09631583,0.0016879177,0.00007391791,0.00025948827,0.0006710703,0.019232927],"genre_scores_gemma":[0.3684347,0.050319903,0.5333153,0.024023332,0.0050020935,0.0004072345,0.0003235842,0.001069563,0.017104357],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9947694,0.0023487427,0.00034515373,0.0009405123,0.0013558781,0.00024026775],"domain_scores_gemma":[0.98555285,0.010288879,0.00031522408,0.0014542498,0.0019442815,0.0004445003],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012763158,0.0015118977,0.0013368247,0.0016639172,0.00081868883,0.007222677,0.0029360515,0.0047598756,0.003248751],"category_scores_gemma":[0.03181159,0.0010635417,0.0009163486,0.0022661726,0.010135156,0.020014947,0.004101672,0.019813411,0.0013499086],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012175677,0.00012399704,0.0010059132,0.00052896223,0.00008362708,0.0001122925,0.00045980376,0.046731185,0.0010612409,0.77537537,0.015440058,0.15895578],"study_design_scores_gemma":[0.000022645163,0.00009910934,0.00032316,0.00037087698,0.000020920177,0.000117981595,0.00013140439,0.17142798,0.0021287065,0.79085547,0.034444086,0.000057693254],"about_ca_topic_score_codex":0.0072980924,"about_ca_topic_score_gemma":0.0042729666,"teacher_disagreement_score":0.012763158,"about_ca_system_score_codex":0.0056337076,"about_ca_system_score_gemma":0.0025140846,"threshold_uncertainty_score":0.06749886},"labels":[],"label_agreement":null},{"id":"W4384828046","doi":"10.1057/s41599-023-01931-4","title":"Using a forced aligner for prosody research","year":2023,"lang":"en","type":"article","venue":"Humanities and Social Sciences Communications","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Georgia Institute of Technology","keywords":"Computer science; Prosody; Mandarin Chinese; Syllable; Phrase; Natural language processing; Speech recognition; Sentence; Annotation; Artificial intelligence; Linguistics","score_opus":0.7762389046443241,"score_gpt":0.5030580593464857,"score_spread":0.27318084529783837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384828046","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08689433,0.00045237463,0.8823618,0.00024359509,0.00039014433,0.0005523437,0.0022739896,0.021446468,0.005384908],"genre_scores_gemma":[0.18503292,0.00009687013,0.8083236,0.00013813212,0.000055162884,0.0004894239,0.0014626877,0.001937679,0.002463527],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99707806,0.00084930024,0.00027309914,0.0009581505,0.0007172473,0.0001242059],"domain_scores_gemma":[0.9923219,0.0032311094,0.0005190199,0.0014463657,0.0022869362,0.00019455138],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034013093,0.0012966637,0.00059424003,0.001607407,0.0009050735,0.0012159315,0.0011844909,0.0011661947,0.015070292],"category_scores_gemma":[0.012547017,0.00043923684,0.00062728015,0.0011694239,0.00062842487,0.0015924892,0.0011791943,0.0009144533,0.004651115],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010206647,0.00011225561,0.003949708,0.00065670075,0.00013871056,0.0006874799,0.0014372955,0.004096799,0.46789643,0.0023926233,0.006880072,0.5107312],"study_design_scores_gemma":[0.00020939574,0.0010853455,0.024379738,0.00014869792,0.00019659582,0.0015608822,0.0012436203,0.1998671,0.7125834,0.004724013,0.05364747,0.00035376346],"about_ca_topic_score_codex":0.0022289783,"about_ca_topic_score_gemma":0.003675775,"teacher_disagreement_score":0.015070292,"about_ca_system_score_codex":0.00049541786,"about_ca_system_score_gemma":0.0010004324,"threshold_uncertainty_score":0.05041516},"labels":[],"label_agreement":null},{"id":"W4384936706","doi":"10.1016/j.csl.2023.101538","title":"Trends and developments in automatic speech recognition research","year":2023,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Computer science; Discriminative model; Exploit; Variety (cybernetics); Artificial intelligence; Speech recognition; Natural language; Deep learning; SIGNAL (programming language); Machine learning; Natural language processing","score_opus":0.07391361334822268,"score_gpt":0.34104259928551184,"score_spread":0.2671289859372892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384936706","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029608384,0.81075585,0.06329128,0.025257993,0.0035699662,0.00012912962,0.000891842,0.001140388,0.065355174],"genre_scores_gemma":[0.14576894,0.6880602,0.11064969,0.0061450773,0.009207552,0.00014714901,0.0022319953,0.00031903552,0.03747039],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99788755,0.00042935938,0.00023422696,0.0004890285,0.0008165288,0.00014335455],"domain_scores_gemma":[0.98454237,0.007720276,0.0008892201,0.00047372322,0.005798618,0.00057583227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004845304,0.0005369485,0.00079680583,0.0038431387,0.00043949258,0.0033932147,0.001265455,0.0016786068,0.012778999],"category_scores_gemma":[0.0067300173,0.00037722522,0.00055254815,0.0046215155,0.0013303922,0.0044539496,0.0006883715,0.0017227468,0.006671648],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023415458,0.0001735318,0.0039294576,0.0023387102,0.000028402541,0.00006843449,0.00021801911,0.00077521557,0.0144280605,0.019140296,0.0121985935,0.9464672],"study_design_scores_gemma":[0.000044306824,0.0006987044,0.01829924,0.0022671253,0.00015314037,0.0015550549,0.0014615315,0.014171195,0.021457436,0.024239706,0.91552866,0.0001239692],"about_ca_topic_score_codex":0.0018734264,"about_ca_topic_score_gemma":0.002196464,"teacher_disagreement_score":0.012778999,"about_ca_system_score_codex":0.0011239782,"about_ca_system_score_gemma":0.002335317,"threshold_uncertainty_score":0.04275},"labels":[],"label_agreement":null},{"id":"W4385080277","doi":"10.1109/sp46215.2023.10179374","title":"Breaking Security-Critical Voice Authentication","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Spoofing attack; Computer science; Computer security; Vulnerability (computing); Authentication (law); Adversarial system; Key (lock); Task (project management); Artificial intelligence","score_opus":0.028324428021169017,"score_gpt":0.29898535245972496,"score_spread":0.27066092443855594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385080277","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1958421,0.0015826016,0.7548458,0.0050892644,0.0009450439,0.0003301728,0.00021320404,0.009106324,0.032045532],"genre_scores_gemma":[0.9721228,0.00028351354,0.023186406,0.0006037966,0.00011884337,0.000058336784,0.000059108766,0.0002193116,0.0033478106],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9929516,0.001607606,0.0003658957,0.0011569498,0.0027086872,0.0012093147],"domain_scores_gemma":[0.9875415,0.0047698445,0.0010452446,0.0052039577,0.0010288332,0.00041067676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029095267,0.0011313569,0.00084380934,0.0009626563,0.0014144286,0.002724204,0.0015727316,0.002868154,0.004577237],"category_scores_gemma":[0.018352903,0.0008560744,0.00086915586,0.0003379306,0.003725294,0.0065362607,0.0075306576,0.0046718004,0.0023939721],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016966581,0.00031702235,0.0059031644,0.00057790603,0.0002343975,0.001602876,0.0022097793,0.0813018,0.14840391,0.4429454,0.021497432,0.29330963],"study_design_scores_gemma":[0.00009822113,0.00047403263,0.0011380222,0.00023339789,0.00010532706,0.0014813484,0.00041696217,0.6043784,0.11671137,0.22830288,0.04650599,0.00015410544],"about_ca_topic_score_codex":0.0008682403,"about_ca_topic_score_gemma":0.00044618818,"teacher_disagreement_score":0.004577237,"about_ca_system_score_codex":0.0012551239,"about_ca_system_score_gemma":0.001071717,"threshold_uncertainty_score":0.015387237},"labels":[],"label_agreement":null},{"id":"W4385489013","doi":"10.1109/icasspw59220.2023.10193304","title":"Investigation Of The Quality Of Pseudo-Labels For The Self-Supervised Speaker Verification Task","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Computer science; Overfitting; Cluster analysis; Discriminative model; Artificial intelligence; Task (project management); Speech recognition; Noise (video); Speaker recognition; Speaker verification; Pattern recognition (psychology); Embedding; Quality (philosophy); Machine learning; Artificial neural network","score_opus":0.10024304657006006,"score_gpt":0.2985688427223572,"score_spread":0.19832579615229712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385489013","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34481072,0.0004883629,0.64957774,0.00039770434,0.00013160767,0.00014854112,0.0001918798,0.0018289865,0.0024244601],"genre_scores_gemma":[0.8511216,0.000121494224,0.14608063,0.00013604942,0.000038430095,0.000087204004,0.0005072476,0.0002546032,0.0016527523],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9973506,0.0013539222,0.00009160323,0.00057522074,0.00048876513,0.00013993036],"domain_scores_gemma":[0.9882996,0.007520285,0.0007122022,0.0015250596,0.0016590251,0.00028374547],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0053706323,0.0010129276,0.0006272449,0.00045020573,0.000533034,0.0010451807,0.001277419,0.0013591672,0.0013675414],"category_scores_gemma":[0.020700973,0.00036291702,0.0003961937,0.0002786907,0.001100209,0.0020066395,0.0013728772,0.0017472401,0.00074806897],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032226914,0.0006115476,0.010884656,0.0005379569,0.0002832398,0.0002845898,0.000783943,0.38061604,0.14719617,0.007121306,0.0039098775,0.44454804],"study_design_scores_gemma":[0.000025532798,0.00026810291,0.0019417255,0.000018466384,0.00002417565,0.00012769943,0.0000776123,0.9527614,0.042223677,0.0019142844,0.000587419,0.000029874018],"about_ca_topic_score_codex":0.0012819843,"about_ca_topic_score_gemma":0.0022943956,"teacher_disagreement_score":0.0053706323,"about_ca_system_score_codex":0.00052615226,"about_ca_system_score_gemma":0.0008022525,"threshold_uncertainty_score":0.028402984},"labels":[],"label_agreement":null},{"id":"W4385573061","doi":"10.18653/v1/2022.emnlp-industry.29","title":"SpeechNet: Weakly Supervised, End-to-End Speech Recognition at Industrial Scale","year":2022,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"End-to-end principle; Computer science; Speech recognition; Scale (ratio); Natural language processing; Artificial intelligence; Cartography; Geography","score_opus":0.05790377424567948,"score_gpt":0.24210331265645219,"score_spread":0.1841995384107727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385573061","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052695464,0.0017989255,0.61747354,0.00087233516,0.0011821027,0.0006737034,0.03841577,0.27546167,0.011426528],"genre_scores_gemma":[0.27432653,0.0009609177,0.49750265,0.00072961126,0.00041916297,0.0021710352,0.17785867,0.007367766,0.038663708],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99851185,0.0003916858,0.000086010616,0.00046934548,0.00041956085,0.00012148542],"domain_scores_gemma":[0.99841714,0.0006035736,0.00006291162,0.0003578832,0.0004399787,0.00011847294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018608512,0.0022764662,0.0015021396,0.0016018488,0.0006613661,0.0014186247,0.002045909,0.0014584679,0.012213816],"category_scores_gemma":[0.0037428217,0.00087067473,0.0005774312,0.0010998982,0.0005570132,0.0027212312,0.0025116534,0.0015743738,0.019595422],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025106277,0.00090248795,0.0029760965,0.0005585771,0.00038261167,0.00044528156,0.00023825682,0.023054121,0.04875241,0.0030351507,0.320278,0.5968664],"study_design_scores_gemma":[0.0004226601,0.0006601155,0.0066118976,0.00006893153,0.00011613325,0.00034930484,0.00028120776,0.84886193,0.07083806,0.010657205,0.060988188,0.00014433678],"about_ca_topic_score_codex":0.0060274573,"about_ca_topic_score_gemma":0.011570332,"teacher_disagreement_score":0.012213816,"about_ca_system_score_codex":0.00052052346,"about_ca_system_score_gemma":0.0012620643,"threshold_uncertainty_score":0.04085934},"labels":[],"label_agreement":null},{"id":"W4385822952","doi":"10.21437/interspeech.2023-1087","title":"Speech Self-Supervised Representation Benchmarking: Are We Doing it Right?","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"Grand Équipement National De Calcul Intensif","keywords":"Benchmarking; Computer science; Representation (politics); Artificial intelligence; Speech recognition; Natural language processing","score_opus":0.05260799574573499,"score_gpt":0.29073518130807524,"score_spread":0.23812718556234025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385822952","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07974807,0.016357811,0.8001277,0.040640786,0.0112603875,0.0004708155,0.0040867766,0.024602214,0.022705473],"genre_scores_gemma":[0.6131751,0.005332646,0.30030033,0.012249561,0.0068373177,0.0004627545,0.02042206,0.006841626,0.034378514],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98934036,0.0046052733,0.0004446271,0.0023609824,0.0024218804,0.00082688325],"domain_scores_gemma":[0.97960836,0.0060410993,0.000669081,0.004262053,0.0076184175,0.0018010252],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01911605,0.0019860684,0.0028789928,0.0010062313,0.0010518979,0.005110569,0.003094519,0.0042091734,0.01417939],"category_scores_gemma":[0.045113087,0.00055298285,0.0011789842,0.000875955,0.0016819623,0.007199361,0.0030823469,0.004756134,0.008960153],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010601663,0.0006251681,0.0067486675,0.00058962475,0.0004749422,0.00009201556,0.00018431153,0.019743973,0.01433633,0.0064782724,0.11613395,0.8335325],"study_design_scores_gemma":[0.00035941062,0.0020501583,0.013995719,0.0010008448,0.00044846692,0.0006072943,0.0009814961,0.728712,0.062258672,0.0779788,0.11130031,0.0003067317],"about_ca_topic_score_codex":0.0026353274,"about_ca_topic_score_gemma":0.004022419,"teacher_disagreement_score":0.98088396,"about_ca_system_score_codex":0.001074558,"about_ca_system_score_gemma":0.002060797,"threshold_uncertainty_score":0.10109651},"labels":[],"label_agreement":null},{"id":"W4386074659","doi":"10.11159/mhci23.111","title":"GAN-Based Fine-Grained Feature Modeling For Zero-Shot Voice Cloning","year":2023,"lang":"en","type":"article","venue":"Proceedings of the World Congress on Electrical Engineering and Computer Systems and Science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cloning (programming); Computer science; Zero (linguistics); Shot (pellet); Feature (linguistics); Speech recognition; Materials science; Programming language","score_opus":0.019463419043084445,"score_gpt":0.23164629502604334,"score_spread":0.2121828759829589,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386074659","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0073511545,0.0002034943,0.9910942,0.000041734555,0.00002882664,0.00001343462,0.000029796602,0.0006344744,0.00060286326],"genre_scores_gemma":[0.76091594,0.00034886517,0.23222591,0.00022997068,0.00007760182,0.0001211345,0.00035653307,0.0002737021,0.0054503847],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997198,0.000064328466,0.0000117526615,0.000098662895,0.000072380266,0.000033065586],"domain_scores_gemma":[0.99971086,0.00015553736,0.000026514363,0.000043173746,0.000047498957,0.000016375454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005077304,0.00077925285,0.0006831618,0.00025052045,0.00019131014,0.00033032717,0.0009425567,0.0005906054,0.0014665199],"category_scores_gemma":[0.0009794015,0.0003709313,0.0008499985,0.00022322153,0.00043961487,0.0006644723,0.00061602733,0.0011645245,0.0004963126],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017137601,0.00005548546,0.00056568295,0.00007572155,0.00007509488,0.00017784395,0.000101313286,0.78907555,0.032327052,0.0075239264,0.0016651307,0.16818573],"study_design_scores_gemma":[0.000001920053,0.000013152302,0.00005401069,0.0000015879106,0.000004399004,0.00002123578,0.0000016676604,0.99712104,0.0017052839,0.00080206955,0.0002702276,0.0000033729875],"about_ca_topic_score_codex":0.0026482013,"about_ca_topic_score_gemma":0.0033279194,"teacher_disagreement_score":0.0026482013,"about_ca_system_score_codex":0.00041844428,"about_ca_system_score_gemma":0.0003985262,"threshold_uncertainty_score":0.005265534},"labels":[],"label_agreement":null},{"id":"W4386105229","doi":"10.1109/is3c57901.2023.00051","title":"Performance Evaluation of Indonesian Language Forced Alignment Using Montreal Forced Aligner","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Indonesian; Speech recognition; Transcription (linguistics); Natural language processing; Segmentation; Language model; Process (computing); Speech corpus; Set (abstract data type); Artificial intelligence; Speech synthesis; Linguistics; Programming language","score_opus":0.05697551244489023,"score_gpt":0.3030025896258461,"score_spread":0.24602707718095584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386105229","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65680045,0.0040624565,0.26059264,0.00064946886,0.00079895556,0.00040881365,0.003897285,0.049153727,0.023636185],"genre_scores_gemma":[0.7970256,0.0007116636,0.17089458,0.00026762154,0.00008200265,0.00029173307,0.014670119,0.0016213169,0.014435351],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9980635,0.00055573514,0.00014272131,0.00058549724,0.00042826255,0.00022424496],"domain_scores_gemma":[0.99767953,0.00087938487,0.00009369363,0.00029788073,0.0008948604,0.00015465157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002271937,0.0019374036,0.0011471676,0.0012056045,0.00090224546,0.0012725658,0.0015232757,0.00104766,0.007451666],"category_scores_gemma":[0.0051945057,0.0003653146,0.00068676285,0.0010648317,0.00043755188,0.0015102301,0.0010922368,0.00083191897,0.0045745657],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034318175,0.00054819084,0.011384399,0.0006055932,0.0004398473,0.00079608994,0.0006613743,0.12191649,0.12160077,0.001263943,0.021118995,0.7162325],"study_design_scores_gemma":[0.00017825198,0.0014324691,0.017447665,0.00004270087,0.00018437409,0.0005727989,0.00075931224,0.87134296,0.09718715,0.000549413,0.01013668,0.00016632349],"about_ca_topic_score_codex":0.059117362,"about_ca_topic_score_gemma":0.05353941,"teacher_disagreement_score":0.059117362,"about_ca_system_score_codex":0.00092760945,"about_ca_system_score_gemma":0.0017421684,"threshold_uncertainty_score":0.11754656},"labels":[],"label_agreement":null},{"id":"W4386273179","doi":"10.2139/ssrn.4733627","title":"Speech Self-Supervised Representations Benchmarking: A Case for Larger Probing Heads","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Benchmarking; Computer science; Ranking (information retrieval); Inference; Downstream (manufacturing); Task (project management); Generalization; Feature (linguistics); Set (abstract data type); Artificial intelligence; Architecture; Machine learning; Natural language processing; Engineering; Mathematics; Geography","score_opus":0.02543416354791751,"score_gpt":0.2923444770256426,"score_spread":0.2669103134777251,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386273179","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31758004,0.002197563,0.6356847,0.0026096257,0.001083264,0.000567033,0.0031203835,0.022880673,0.014276712],"genre_scores_gemma":[0.8180303,0.0001971386,0.16718869,0.0008286976,0.00017059052,0.00038223236,0.005790458,0.0028221004,0.0045898296],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.987357,0.0061751697,0.000733373,0.0025886146,0.0023944494,0.0007514155],"domain_scores_gemma":[0.9584442,0.020959223,0.00071718585,0.013052589,0.0058169174,0.0010098487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014392351,0.001224056,0.0020488806,0.0009287573,0.0013493295,0.0027716851,0.004049137,0.0038428777,0.013061647],"category_scores_gemma":[0.06787573,0.0004874058,0.00079744466,0.0014052324,0.001890971,0.005323101,0.005474724,0.003115617,0.0035931708],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003956913,0.0012095411,0.009962489,0.0010219235,0.00050614343,0.0007807676,0.0014694118,0.14587176,0.05514231,0.014879597,0.03265017,0.732549],"study_design_scores_gemma":[0.00026011758,0.0015554351,0.009200254,0.00019170668,0.00022648361,0.0009757577,0.0016006907,0.8188267,0.089360036,0.041378785,0.03623619,0.00018788368],"about_ca_topic_score_codex":0.0032171248,"about_ca_topic_score_gemma":0.0049250876,"teacher_disagreement_score":0.014392351,"about_ca_system_score_codex":0.0009672928,"about_ca_system_score_gemma":0.0015412971,"threshold_uncertainty_score":0.07611489},"labels":[],"label_agreement":null},{"id":"W4386609311","doi":"10.1109/lsp.2023.3313515","title":"Rhythm Modeling for Voice Conversion","year":2023,"lang":"en","type":"article","venue":"IEEE Signal Processing Letters","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ubisoft (Canada)","funders":"","keywords":"Speech recognition; Rhythm; Computer science; Prosody; Speech processing; Artificial intelligence; Pattern recognition (psychology); Acoustics","score_opus":0.04954250797524673,"score_gpt":0.2673340634600034,"score_spread":0.21779155548475665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386609311","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011038643,0.0005185469,0.98445636,0.00010982151,0.00008790238,0.000031539825,0.00022428404,0.0008502522,0.0026826141],"genre_scores_gemma":[0.7127435,0.0018880678,0.2694748,0.000280962,0.00040224227,0.00025932328,0.0023156807,0.00077327737,0.011862139],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997807,0.000058582013,0.00001073168,0.00006692898,0.00006192086,0.000021035128],"domain_scores_gemma":[0.99975556,0.0000994436,0.000028172648,0.000040794213,0.0000624683,0.000013628431],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003307324,0.0005695153,0.0004210273,0.0003921457,0.00023619346,0.0006582456,0.0007331228,0.00045552538,0.0020329703],"category_scores_gemma":[0.0013603204,0.00023016347,0.00079237786,0.00038167232,0.0002632353,0.00056689646,0.000488943,0.0009871926,0.0011852466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014102347,0.00011923586,0.0016716005,0.00014491648,0.00012998891,0.00013792072,0.00011736859,0.69258446,0.03632232,0.01775081,0.0056658504,0.24521446],"study_design_scores_gemma":[0.000004986108,0.000018747804,0.00045577175,0.00000840382,0.000008883606,0.000042483283,0.000010004197,0.9894595,0.0020455008,0.005143219,0.0027934585,0.000009006256],"about_ca_topic_score_codex":0.003264722,"about_ca_topic_score_gemma":0.0037457584,"teacher_disagreement_score":0.003264722,"about_ca_system_score_codex":0.00033633565,"about_ca_system_score_gemma":0.00043033288,"threshold_uncertainty_score":0.0068009496},"labels":[],"label_agreement":null},{"id":"W4386626719","doi":"10.18280/isi.280429","title":"A Fractional Ebola Optimization Search Algorithm Approach for Enhanced Speaker Diarization","year":2023,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Speaker diarisation; Computer science; Algorithm; Speech recognition; Speaker verification; Speaker recognition","score_opus":0.025713677455891173,"score_gpt":0.2521937344669724,"score_spread":0.22648005701108123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386626719","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051007243,0.00011642723,0.9936655,0.00007588523,0.000020748934,0.000018941913,0.000012197727,0.00025007155,0.0007394473],"genre_scores_gemma":[0.23781592,0.00019869683,0.75711787,0.00028383292,0.000062260035,0.00019854512,0.00014515735,0.00020008838,0.003977592],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99953055,0.00012235131,0.00002974799,0.00012422547,0.00014347558,0.000049689304],"domain_scores_gemma":[0.999382,0.0003506585,0.000058697533,0.000053336462,0.00013013976,0.000025078578],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011267263,0.00085832505,0.0008492076,0.0009127994,0.0005376519,0.00087604264,0.0011113166,0.0011636135,0.0023578596],"category_scores_gemma":[0.0033181342,0.00035379187,0.00077392603,0.00067701645,0.0007515244,0.0010325109,0.000950759,0.0009822358,0.00070356467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023138887,0.00009478176,0.00088569993,0.000096084215,0.00008181692,0.000098451565,0.00020269938,0.6731728,0.016819382,0.01904122,0.0024238653,0.28685182],"study_design_scores_gemma":[0.0000064823957,0.00001699933,0.00008202207,0.000003865511,0.000005319084,0.000021387186,0.0000064497012,0.99609226,0.0012009116,0.001928177,0.0006307091,0.0000054870966],"about_ca_topic_score_codex":0.004637398,"about_ca_topic_score_gemma":0.0049281055,"teacher_disagreement_score":0.004637398,"about_ca_system_score_codex":0.0006432091,"about_ca_system_score_gemma":0.0012273366,"threshold_uncertainty_score":0.009220779},"labels":[],"label_agreement":null},{"id":"W4386729029","doi":"10.1007/978-3-031-42823-4_20","title":"A Novel Self-supervised Representation Learning Model for an Open-Set Speaker Recognition","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Speaker recognition; Speech recognition; Artificial intelligence; Cluster analysis; Biometrics; Feature learning; Pattern recognition (psychology); Generalization; Cosine similarity; Representation (politics)","score_opus":0.1366916856664875,"score_gpt":0.32034331849955155,"score_spread":0.18365163283306404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386729029","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005266764,0.00026736147,0.9917419,0.00015117785,0.000092198374,0.000039855342,0.00011858686,0.0015927921,0.00072938815],"genre_scores_gemma":[0.30922157,0.00051304686,0.6667799,0.0006983418,0.00045735412,0.00049346057,0.0019617018,0.0005180811,0.019356597],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989164,0.0002500571,0.00005106501,0.00040034915,0.00026431223,0.000117795535],"domain_scores_gemma":[0.9990146,0.00036896075,0.00006268562,0.00016046966,0.0003440601,0.000049207152],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015306197,0.00089171325,0.0014375199,0.00062733365,0.00053239823,0.00095710147,0.0033566293,0.0017973155,0.0035805593],"category_scores_gemma":[0.002314719,0.00055901625,0.0013429079,0.00070865423,0.0005617033,0.0020023326,0.0019238245,0.0027953014,0.0030860151],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036213754,0.00032060314,0.0006691314,0.000104037405,0.0001949965,0.00009183038,0.00010455223,0.16769257,0.01847189,0.009694515,0.0117314095,0.7905623],"study_design_scores_gemma":[0.0000056532426,0.000024908213,0.00008935939,0.0000031190234,0.00001213956,0.00002693762,0.000003393063,0.99620336,0.0016506535,0.0014187003,0.00055452774,0.000007245103],"about_ca_topic_score_codex":0.006096799,"about_ca_topic_score_gemma":0.008325799,"teacher_disagreement_score":0.006096799,"about_ca_system_score_codex":0.0007396227,"about_ca_system_score_gemma":0.00095343776,"threshold_uncertainty_score":0.012122631},"labels":[],"label_agreement":null},{"id":"W4386764306","doi":"10.1109/waspaa58266.2023.10248132","title":"Robust Audio Anti-Spoofing System Based on Low-Frequency Sub-Band Information","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Spectrogram; Discriminative model; Spoofing attack; Computer science; Robustness (evolution); Detector; Focus (optics); Speech recognition; Artificial intelligence; Computer security; Telecommunications","score_opus":0.02636678921615326,"score_gpt":0.20617658468781888,"score_spread":0.17980979547166562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386764306","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35556215,0.001397846,0.5885029,0.00036353082,0.0005347556,0.0004246508,0.001541329,0.04228389,0.009389004],"genre_scores_gemma":[0.8091954,0.000302176,0.1813596,0.00032226712,0.00012203193,0.000189118,0.0015389466,0.00031010277,0.0066603515],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99944645,0.000043029817,0.00002654783,0.00019200194,0.00021278657,0.00007912833],"domain_scores_gemma":[0.9994727,0.000094967625,0.00006443523,0.00011055452,0.00020572211,0.00005163581],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006017806,0.00078692095,0.0011308495,0.0010704634,0.00041356575,0.00075136835,0.0009041766,0.00078470074,0.0043074545],"category_scores_gemma":[0.0014691058,0.0002621888,0.00032688954,0.0003317527,0.00025718464,0.0010444357,0.000990825,0.0006199131,0.0041666855],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016704104,0.00028558442,0.0038891283,0.00027479793,0.00014452056,0.00031630447,0.00013558063,0.005932913,0.396179,0.0010272156,0.007192898,0.58295166],"study_design_scores_gemma":[0.00019062836,0.00085734593,0.013840957,0.00007235948,0.00021529247,0.0012380286,0.000092919814,0.52422464,0.44370812,0.0018377968,0.013592297,0.00012967322],"about_ca_topic_score_codex":0.0008545622,"about_ca_topic_score_gemma":0.0013647291,"teacher_disagreement_score":0.0043074545,"about_ca_system_score_codex":0.00030497304,"about_ca_system_score_gemma":0.00045952754,"threshold_uncertainty_score":0.01440984},"labels":[],"label_agreement":null},{"id":"W4387800211","doi":"10.48550/arxiv.2310.11541","title":"MUST&P-SRL: Multi-lingual and Unified Syllabification in Text and Phonetic Domains for Speech Representation Learning","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Syllabification; Computer science; Natural language processing; Artificial intelligence; Representation (politics); Speech recognition; Stress (linguistics); Linguistics; Syllable","score_opus":0.2157484087785792,"score_gpt":0.25914638130662127,"score_spread":0.04339797252804206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387800211","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009649545,0.00051928207,0.8544203,0.00041169187,0.00035161388,0.00042263654,0.019758653,0.107138865,0.0073273852],"genre_scores_gemma":[0.059359286,0.0002860606,0.854714,0.00027933516,0.00016715535,0.001108452,0.07065373,0.0054337387,0.007998261],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99787736,0.00052739494,0.00013644801,0.00085698173,0.00042752124,0.00017435798],"domain_scores_gemma":[0.99741495,0.0008894139,0.00013391636,0.0009617238,0.00045427575,0.00014564916],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021134466,0.0019806724,0.00080057705,0.0034945605,0.0012145957,0.0021997092,0.0027621042,0.0015870173,0.025670338],"category_scores_gemma":[0.006289115,0.000825829,0.0014492163,0.0020292685,0.00079270604,0.0030119137,0.0039303675,0.002891571,0.026486373],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002855806,0.00019625535,0.0016664325,0.0006081467,0.0000815471,0.00021817768,0.00039769046,0.0046839505,0.028530473,0.007719212,0.09935314,0.8562593],"study_design_scores_gemma":[0.00022064263,0.00038303106,0.009414364,0.00027921755,0.00012978917,0.00090935966,0.00072936504,0.558128,0.101463,0.043823164,0.28428522,0.00023483566],"about_ca_topic_score_codex":0.007859153,"about_ca_topic_score_gemma":0.017696312,"teacher_disagreement_score":0.025670338,"about_ca_system_score_codex":0.0009749649,"about_ca_system_score_gemma":0.0026408187,"threshold_uncertainty_score":0.08587587},"labels":[],"label_agreement":null},{"id":"W4388097452","doi":"10.18280/ts.400518","title":"A Comprehensive Examination of Phoneme Recognition in Automatic Speech Recognition Systems","year":2023,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Speech recognition; Computer science; Artificial intelligence; Pattern recognition (psychology); Natural language processing","score_opus":0.06636515426379523,"score_gpt":0.25613746559120476,"score_spread":0.18977231132740952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388097452","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022696725,0.95476955,0.022750633,0.0016565492,0.0014264284,0.00008505641,0.00025175366,0.00014858722,0.016641822],"genre_scores_gemma":[0.01908418,0.9481939,0.022650145,0.0016313369,0.001216469,0.00012335021,0.0006174853,0.000066634275,0.006416473],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9986375,0.00024797374,0.00020931367,0.00019914782,0.0006470124,0.00005910053],"domain_scores_gemma":[0.9973068,0.0014692384,0.00015587332,0.00009541011,0.00093577156,0.000036936646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001309408,0.00086899684,0.00096896646,0.0021006793,0.00038155154,0.0015871942,0.0008742136,0.0014547714,0.004870462],"category_scores_gemma":[0.0041596973,0.0004762757,0.00065689225,0.0022734671,0.00048053398,0.002858151,0.00065568887,0.0013164913,0.0030075484],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000428618,0.00004574243,0.00050716614,0.015623112,0.000097049735,0.00021594967,0.00023014683,0.0018905967,0.008560653,0.009602913,0.016006498,0.94717735],"study_design_scores_gemma":[0.0000055422665,0.00024832756,0.002695086,0.007320643,0.00016952309,0.0013954946,0.00020385032,0.0016096962,0.006373093,0.0063641015,0.9735488,0.000065881766],"about_ca_topic_score_codex":0.0016292854,"about_ca_topic_score_gemma":0.0016922565,"teacher_disagreement_score":0.004870462,"about_ca_system_score_codex":0.00071079127,"about_ca_system_score_gemma":0.002315568,"threshold_uncertainty_score":0.016293347},"labels":[],"label_agreement":null},{"id":"W4388104645","doi":"10.18280/ts.400529","title":"A Comprehensive Review on Machine Learning Approaches for Enhancing Human Speech Recognition","year":2023,"lang":"en","type":"review","venue":"Traitement du signal","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Speech recognition; Artificial intelligence; Machine learning; Natural language processing","score_opus":0.30327594934148594,"score_gpt":0.3540698144114672,"score_spread":0.05079386506998124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388104645","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016526005,0.99709976,0.0006486036,0.00018599053,0.0002111514,0.000011377741,0.0000549765,0.000024431829,0.0015984515],"genre_scores_gemma":[0.00075686135,0.997454,0.0006861662,0.00016228424,0.00014533615,0.000014494366,0.00008348676,0.000004236961,0.00069322216],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9997739,0.000033604803,0.000040259365,0.000048397516,0.00008654607,0.000017289232],"domain_scores_gemma":[0.99943644,0.0003462757,0.00006184336,0.000016188875,0.00011569033,0.00002351414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056337076,0.0010829696,0.0011485985,0.0025240544,0.00024978895,0.0008291422,0.0007953543,0.0009368981,0.0065834317],"category_scores_gemma":[0.0011055756,0.00037579253,0.0006445484,0.0023808188,0.00029279082,0.0012890777,0.00049386785,0.0011380527,0.0036073958],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000411857,0.00006868975,0.00010920104,0.031877536,0.000094419775,0.000099145,0.000055185763,0.00048106004,0.002405323,0.0025063923,0.024956783,0.93730503],"study_design_scores_gemma":[0.000010780133,0.00013456284,0.0008613175,0.0077513773,0.00021970288,0.0006578929,0.00004573631,0.00022323635,0.0010281762,0.00158602,0.9874467,0.000034330034],"about_ca_topic_score_codex":0.0010041638,"about_ca_topic_score_gemma":0.0017193338,"teacher_disagreement_score":0.0065834317,"about_ca_system_score_codex":0.00035842965,"about_ca_system_score_gemma":0.0011119716,"threshold_uncertainty_score":0.022023737},"labels":[],"label_agreement":null},{"id":"W4388380244","doi":"10.1007/s10772-023-10059-4","title":"Attention-based factorized TDNN for a noise-robust and spoof-aware speaker verification system","year":2023,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Spoofing attack; Speech recognition; Speaker verification; Encoder; Speaker recognition; Artificial neural network; Context (archaeology); Mel-frequency cepstrum; Artificial intelligence; Word error rate; Frame (networking); Pattern recognition (psychology); Feature extraction; Telecommunications","score_opus":0.02756174976548047,"score_gpt":0.27208361846283263,"score_spread":0.24452186869735215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388380244","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.096314035,0.0014484735,0.8951883,0.00026161142,0.0004662087,0.00009307338,0.00027784432,0.0029873615,0.0029629974],"genre_scores_gemma":[0.8156336,0.0006064271,0.1767054,0.00025144467,0.00014835774,0.00007733767,0.00044776706,0.00010699022,0.006022633],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99967015,0.00004534048,0.000024368876,0.000109783155,0.0000883696,0.00006203257],"domain_scores_gemma":[0.99960214,0.00008574382,0.000023745752,0.00003191801,0.0002336643,0.000022789725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054931553,0.0005609195,0.0006070452,0.0004133502,0.00041884521,0.00044268096,0.0007791077,0.00067272905,0.0027790202],"category_scores_gemma":[0.00073168747,0.00021493959,0.000499081,0.00031515403,0.00019718277,0.0006561039,0.0005208225,0.00064520637,0.0010126213],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009929306,0.0001768036,0.0012336263,0.00012769712,0.00008661102,0.0001439487,0.00006582738,0.027131885,0.19907957,0.0008085289,0.0027876312,0.7673649],"study_design_scores_gemma":[0.000023919181,0.00026388888,0.002444819,0.000019940693,0.00009328317,0.00025678021,0.000029278093,0.9287469,0.065181196,0.000554322,0.0023511997,0.00003443846],"about_ca_topic_score_codex":0.009221364,"about_ca_topic_score_gemma":0.01299119,"teacher_disagreement_score":0.009221364,"about_ca_system_score_codex":0.00042804112,"about_ca_system_score_gemma":0.00069292623,"threshold_uncertainty_score":0.018335402},"labels":[],"label_agreement":null},{"id":"W4388483000","doi":"10.1109/ase56229.2023.00107","title":"ASTER: Automatic Speech Recognition System Accessibility Testing for Stutterers","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Research Foundation Singapore; Neurosciences Research Foundation","keywords":"Computer science; Stuttering; Advanced Spaceborne Thermal Emission and Reflection Radiometer; Speech recognition; Test (biology); Rendering (computer graphics); Natural language processing; Artificial intelligence","score_opus":0.1166057641101622,"score_gpt":0.3060882649432736,"score_spread":0.1894825008331114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388483000","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5361851,0.0010561876,0.31413785,0.00041453773,0.00031449436,0.000709456,0.003975432,0.13877155,0.0044354666],"genre_scores_gemma":[0.88092405,0.00017407529,0.10682533,0.00027317283,0.00003397858,0.0005329305,0.0064651133,0.0018510199,0.002920306],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9969484,0.0009570443,0.00040484287,0.0006001821,0.00090766547,0.000181922],"domain_scores_gemma":[0.9931779,0.0035673047,0.00070363306,0.0010494394,0.0012980171,0.00020380471],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002277465,0.0018862258,0.00093030185,0.0010855555,0.0003292045,0.00069454603,0.0018522781,0.0011238578,0.003845133],"category_scores_gemma":[0.011322803,0.00047032855,0.000855059,0.00033912295,0.0006921049,0.001684795,0.001419247,0.0008693616,0.0019780593],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0051921075,0.0017612387,0.04323793,0.0018975401,0.0007986463,0.0028273358,0.001281079,0.26632774,0.19341436,0.0030407163,0.034762792,0.44545853],"study_design_scores_gemma":[0.00036790545,0.0019691105,0.012658661,0.00007168819,0.0001462114,0.0010287699,0.0002126536,0.86231357,0.11317581,0.00188608,0.006033914,0.0001356656],"about_ca_topic_score_codex":0.0040982417,"about_ca_topic_score_gemma":0.0038170188,"teacher_disagreement_score":0.0040982417,"about_ca_system_score_codex":0.00056746847,"about_ca_system_score_gemma":0.000938107,"threshold_uncertainty_score":0.012863219},"labels":[],"label_agreement":null},{"id":"W4388854325","doi":"10.1007/978-3-031-48312-7_44","title":"Self-supervised Speaker Verification Employing Augmentation Mix and Self-augmented Training-Based Clustering","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Cluster analysis; Embedding; Artificial intelligence; Dependency (UML); Noise (video); Speaker recognition; Representation (politics); Pattern recognition (psychology); Data mining; Machine learning; Speech recognition; Image (mathematics)","score_opus":0.0421863035107793,"score_gpt":0.25844806115425595,"score_spread":0.21626175764347666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388854325","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02861932,0.0003521745,0.96406156,0.00007436642,0.00015531476,0.00008932417,0.00016942246,0.0039812615,0.002497327],"genre_scores_gemma":[0.29571462,0.0002534228,0.68939424,0.00014596882,0.00011644331,0.00015352132,0.0011933522,0.00062274706,0.012405652],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986064,0.00026645858,0.00006551006,0.0004871357,0.00042900332,0.00014548493],"domain_scores_gemma":[0.99875534,0.00026925787,0.00007442276,0.00045710077,0.00039395367,0.000049972983],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012025486,0.0010001485,0.0013998775,0.00074424455,0.00068321906,0.0009587343,0.0016126267,0.0011595843,0.003208265],"category_scores_gemma":[0.0015681104,0.0005906617,0.001378614,0.0006848812,0.00058891013,0.0014900309,0.0021142773,0.0012414639,0.0044123414],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000686304,0.00025484458,0.001161453,0.00014484958,0.00017461865,0.00009349061,0.00015796903,0.031710826,0.21473,0.0020245952,0.004262501,0.74459857],"study_design_scores_gemma":[0.000018763076,0.00017084471,0.0020993608,0.000015469228,0.00007890515,0.0003525392,0.00005017181,0.8674537,0.12503123,0.0013249838,0.0033557308,0.000048349943],"about_ca_topic_score_codex":0.0017016813,"about_ca_topic_score_gemma":0.0045147943,"teacher_disagreement_score":0.003208265,"about_ca_system_score_codex":0.0003127002,"about_ca_system_score_gemma":0.0009530322,"threshold_uncertainty_score":0.01073277},"labels":[],"label_agreement":null},{"id":"W4388878572","doi":"10.1007/978-3-031-48312-7_36","title":"Multi-task Learning over Mixup Variants for the Speaker Verification Task","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Speech recognition; Robustness (evolution); Artificial intelligence; Regularization (linguistics); Machine learning","score_opus":0.041228708833597756,"score_gpt":0.2696667201367999,"score_spread":0.22843801130320213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388878572","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025888545,0.0017028162,0.9677839,0.00016881055,0.000188928,0.000065980195,0.00024968886,0.0018423664,0.002108932],"genre_scores_gemma":[0.48999137,0.0013059751,0.48478147,0.00041862062,0.00054635195,0.0002572282,0.0025370086,0.00093278213,0.019229313],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99880326,0.00037609547,0.00007903941,0.0003609776,0.00021748581,0.00016302423],"domain_scores_gemma":[0.99790466,0.0012885524,0.00007313131,0.00032410055,0.00029234844,0.00011714559],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022660615,0.0016322263,0.001396526,0.00065334555,0.00049442647,0.0009692158,0.0015093992,0.0012845852,0.006585743],"category_scores_gemma":[0.0032849354,0.0005056011,0.0011487117,0.0008238099,0.0004438114,0.0020025917,0.0022133926,0.0023263588,0.0033389295],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009976128,0.00020324958,0.0006299962,0.00020408712,0.00017511054,0.000111091744,0.00006147087,0.04047851,0.040901743,0.002763397,0.0058555817,0.9076182],"study_design_scores_gemma":[0.000040179006,0.00029756554,0.0009996892,0.000023393803,0.00010938642,0.00023378828,0.000041501422,0.9639511,0.022648351,0.007851917,0.0037685125,0.00003459705],"about_ca_topic_score_codex":0.0019882983,"about_ca_topic_score_gemma":0.00314878,"teacher_disagreement_score":0.006585743,"about_ca_system_score_codex":0.00027137858,"about_ca_system_score_gemma":0.00073043094,"threshold_uncertainty_score":0.022031546},"labels":[],"label_agreement":null},{"id":"W4388878685","doi":"10.1007/978-3-031-48312-7_25","title":"Audio DeepFake Detection Employing Multiple Parametric Exponential Linear Units","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Activation function; Parametric statistics; Process (computing); Residual; Exponential function; Artificial intelligence; Speech recognition; Function (biology); Deep learning; Task (project management); Parametric model; Sign (mathematics); Pattern recognition (psychology); Artificial neural network; Algorithm; Mathematics","score_opus":0.052630643896907775,"score_gpt":0.2539528112894271,"score_spread":0.20132216739251932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388878685","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018962033,0.00052431773,0.9759907,0.00009209911,0.00010379026,0.000037142232,0.000105565865,0.001253762,0.0029306954],"genre_scores_gemma":[0.3805337,0.00071512704,0.592814,0.00027741605,0.0001332706,0.00009084842,0.00056866487,0.00021257967,0.024654418],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99975795,0.000030475365,0.000012944731,0.00005034424,0.000104390514,0.000043843447],"domain_scores_gemma":[0.99959356,0.00017162989,0.000024212386,0.000059682523,0.00012278487,0.00002825485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044453522,0.00088076864,0.00047654883,0.0006528778,0.00028947587,0.00076959433,0.00070904545,0.0008451581,0.006756983],"category_scores_gemma":[0.0008715982,0.00032058943,0.00044420373,0.00046313214,0.00028244226,0.0010920266,0.0012791242,0.00089231157,0.0031065575],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045420154,0.00007285565,0.0006036093,0.00014730023,0.000040612238,0.00011907061,0.00003787434,0.008332494,0.16777568,0.0035295698,0.0017810204,0.81710577],"study_design_scores_gemma":[0.00004416575,0.00043180786,0.002668362,0.0000865158,0.00008720001,0.00072905986,0.00006967563,0.6933302,0.28324872,0.005241507,0.01401072,0.000052052128],"about_ca_topic_score_codex":0.0008379502,"about_ca_topic_score_gemma":0.003255334,"teacher_disagreement_score":0.006756983,"about_ca_system_score_codex":0.00026270328,"about_ca_system_score_gemma":0.00041917994,"threshold_uncertainty_score":0.022604406},"labels":[],"label_agreement":null},{"id":"W4389115567","doi":"10.48550/arxiv.2311.15077","title":"Multilingual self-supervised speech representations improve the speech recognition of low-resource African languages with codeswitching","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institute for Advanced Research; National Science Foundation","keywords":"Computer science; Bespoke; Code (set theory); Natural language processing; Artificial intelligence; Speech recognition; Language model; Scratch; Programming language","score_opus":0.07033471131280217,"score_gpt":0.22219515293901865,"score_spread":0.15186044162621648,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389115567","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5214196,0.0009451097,0.4473115,0.0007872524,0.00056464365,0.00014481871,0.0017876127,0.017824052,0.009215419],"genre_scores_gemma":[0.8844242,0.00019712621,0.10266307,0.000305623,0.00008479707,0.00010877564,0.0044505596,0.0007580366,0.0070077786],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99939406,0.00018722202,0.000028479544,0.00023994684,0.000075698365,0.00007464406],"domain_scores_gemma":[0.9988073,0.0005197226,0.00006549775,0.0002682249,0.0002658537,0.00007343716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074157625,0.00096555904,0.00037584774,0.00041373732,0.00029389272,0.00078516407,0.0005671173,0.00052008085,0.0025192401],"category_scores_gemma":[0.0032712298,0.00025223868,0.0005222094,0.00030284634,0.00046082766,0.0013071004,0.0013754665,0.0014689658,0.0029931306],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007941676,0.0004811493,0.009663893,0.00026244594,0.00022630577,0.00023905524,0.00070993725,0.08404378,0.13588853,0.0017591296,0.011674909,0.75425667],"study_design_scores_gemma":[0.000047228383,0.00035070573,0.0074968426,0.000054587126,0.00008105512,0.00021138959,0.0004692048,0.87672853,0.10205514,0.0035966965,0.008836906,0.00007165625],"about_ca_topic_score_codex":0.0047036037,"about_ca_topic_score_gemma":0.009775554,"teacher_disagreement_score":0.0047036037,"about_ca_system_score_codex":0.00030879286,"about_ca_system_score_gemma":0.000737959,"threshold_uncertainty_score":0.009352446},"labels":[],"label_agreement":null},{"id":"W4389191800","doi":"10.22215/etd/2023-15803","title":"Differentiation of Dry and Wet Cough Sounds using A Deep Learning Model and Data Augmentation","year":2023,"lang":"en","type":"dissertation","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"AGE-WELL","keywords":"Reverberation; Dry cough; Noise (video); Computer science; Speech recognition; Deep learning; Task (project management); Artificial intelligence; Test data; Training set; Machine learning; Pattern recognition (psychology); Image (mathematics); Engineering; Medicine","score_opus":0.08115625648407646,"score_gpt":0.32814461729633004,"score_spread":0.2469883608122536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389191800","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4335594,0.0011725663,0.55201054,0.00097195356,0.0003536836,0.00020378927,0.0011243505,0.0033791414,0.0072246403],"genre_scores_gemma":[0.86095154,0.00048301212,0.12652409,0.0003159888,0.00008553258,0.00016808212,0.0020805302,0.00015937432,0.009231825],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998055,0.000033528555,0.000010938743,0.00006574766,0.00004257094,0.00004167594],"domain_scores_gemma":[0.9996717,0.00014154262,0.000031113013,0.000038789298,0.0000865808,0.000030264848],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004904608,0.0008742857,0.00043843975,0.00040472025,0.00022533297,0.000785365,0.00068256404,0.00074168964,0.0014494275],"category_scores_gemma":[0.0014145809,0.00031785556,0.00085231324,0.00025498672,0.00031779648,0.000782019,0.000985073,0.0015571809,0.000879566],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008430633,0.0005786337,0.0096260775,0.00022663445,0.00014078576,0.00040738803,0.00028962424,0.3469202,0.09099878,0.0023047286,0.0059315525,0.5417325],"study_design_scores_gemma":[0.000008814698,0.000116162606,0.0017389696,0.0000250681,0.000020060084,0.00004434146,0.000040019382,0.98621583,0.009910756,0.0009907207,0.00087463565,0.0000146239345],"about_ca_topic_score_codex":0.0035508384,"about_ca_topic_score_gemma":0.0055926084,"teacher_disagreement_score":0.0035508384,"about_ca_system_score_codex":0.0004198868,"about_ca_system_score_gemma":0.00070858677,"threshold_uncertainty_score":0.0070602894},"labels":[],"label_agreement":null},{"id":"W4389518264","doi":"10.18653/v1/2023.calcs-1.8","title":"Multilingual self-supervised speech representations improve the speech recognition of low-resource African languages with codeswitching","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institute for Advanced Research; National Science Foundation","keywords":"Computer science; Bespoke; Code (set theory); Natural language processing; Artificial intelligence; Speech recognition; Language model; Programming language","score_opus":0.023251246850451306,"score_gpt":0.27282881387348334,"score_spread":0.24957756702303205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389518264","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5414225,0.0008927368,0.4277168,0.0006901746,0.000530944,0.00015450099,0.0017931799,0.017688492,0.009110757],"genre_scores_gemma":[0.8890374,0.00018736353,0.09842346,0.00029109404,0.000072981384,0.000114123824,0.0044617224,0.0007044694,0.0067074522],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99947983,0.00014731579,0.000025560055,0.0002069057,0.0000694485,0.00007093931],"domain_scores_gemma":[0.9989784,0.00042885263,0.00005849939,0.00022033059,0.00024870623,0.000065367174],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006496648,0.00093408325,0.00037480117,0.00038634895,0.0002812363,0.00070637965,0.000543508,0.00044318696,0.0024900793],"category_scores_gemma":[0.0029823596,0.00023577832,0.0005071234,0.00027907707,0.00042817765,0.0012378225,0.0012379705,0.001403594,0.0028755427],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007565424,0.00047177105,0.009654268,0.00025241997,0.0002078236,0.00024581666,0.0007134095,0.08202528,0.14344206,0.0016000058,0.010816237,0.7498144],"study_design_scores_gemma":[0.000044668006,0.00037857852,0.008608477,0.000057283076,0.000086372216,0.00024427904,0.0005143887,0.8668135,0.11022338,0.0032283282,0.0097227935,0.00007793531],"about_ca_topic_score_codex":0.0049849767,"about_ca_topic_score_gemma":0.010868596,"teacher_disagreement_score":0.0049849767,"about_ca_system_score_codex":0.0002933032,"about_ca_system_score_gemma":0.0007396402,"threshold_uncertainty_score":0.009911895},"labels":[],"label_agreement":null},{"id":"W4389518357","doi":"10.18653/v1/2023.arabicnlp-1.38","title":"VoxArabica: A Robust Dialect-Aware Arabic Speech Recognition System","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Alliance de recherche numérique du Canada; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Arabic; Computer science; Upload; Natural language processing; Interface (matter); Speech recognition; Range (aeronautics); Artificial intelligence; Language model; Linguistics; World Wide Web; Engineering","score_opus":0.05897081501115145,"score_gpt":0.23440623216464804,"score_spread":0.1754354171534966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389518357","genre_codex":"software","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11330789,0.0030646988,0.33787328,0.00063489104,0.000956799,0.0007627191,0.016158385,0.5072437,0.01999766],"genre_scores_gemma":[0.536824,0.0007622079,0.36359024,0.00152984,0.00038019076,0.0008514834,0.056550145,0.0051111523,0.034400705],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994898,0.0000720775,0.000047223984,0.00022727145,0.00011446011,0.000049130886],"domain_scores_gemma":[0.9995635,0.000064877415,0.000031501346,0.00009845894,0.00019478665,0.000046875626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006318414,0.0014106077,0.0010728488,0.001083242,0.00050499785,0.0010031224,0.0011910786,0.0008769321,0.009770142],"category_scores_gemma":[0.0014916842,0.0003858921,0.00056362536,0.0003058623,0.00028836553,0.0012593595,0.0017561861,0.0010361405,0.016729055],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015672282,0.00032332703,0.004277132,0.00064996956,0.00028428232,0.0012632764,0.00077118835,0.011155624,0.18509936,0.002213327,0.13133234,0.661063],"study_design_scores_gemma":[0.00057569944,0.0009470683,0.012265831,0.00022885921,0.00033892394,0.0027791997,0.00084240665,0.565635,0.20973562,0.0088111665,0.19732016,0.0005201375],"about_ca_topic_score_codex":0.0027239707,"about_ca_topic_score_gemma":0.0024632297,"teacher_disagreement_score":0.009770142,"about_ca_system_score_codex":0.0003725638,"about_ca_system_score_gemma":0.0005625075,"threshold_uncertainty_score":0.032684445},"labels":[],"label_agreement":null},{"id":"W4389518772","doi":"10.18653/v1/2023.emnlp-main.323","title":"PromptMix: A Class Boundary Augmentation Method for Large Language Model Distillation","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; McGill University; Canadian Institute for Advanced Research","funders":"","keywords":"Class (philosophy); Distillation; Computer science; Boundary (topology); Programming language; Artificial intelligence; Mathematics; Chemistry; Chromatography; Mathematical analysis","score_opus":0.03956160061057078,"score_gpt":0.34672870365444136,"score_spread":0.30716710304387057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389518772","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018547924,0.00042764758,0.9541172,0.00032772246,0.00025836861,0.00019194945,0.00089045765,0.023769429,0.0014692355],"genre_scores_gemma":[0.18249077,0.00020465453,0.8008963,0.0006963341,0.00023908926,0.00078071974,0.0058863936,0.0018210971,0.0069847144],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986557,0.0003986014,0.00006851684,0.00045233645,0.00031845292,0.00010638401],"domain_scores_gemma":[0.9978265,0.0010692711,0.00013750541,0.00053825637,0.00031247284,0.00011594841],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016930664,0.0017968914,0.0011605297,0.0011858174,0.000889528,0.0011351234,0.0023420893,0.0015821785,0.005786676],"category_scores_gemma":[0.006275106,0.00059672253,0.0012227043,0.0008503011,0.0010320619,0.0028663217,0.0030674022,0.003870615,0.0042165066],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000656747,0.00038721698,0.0013638698,0.00029227752,0.00007173978,0.00029653922,0.0005362038,0.037495207,0.041215673,0.0074169924,0.027948897,0.8823186],"study_design_scores_gemma":[0.000090587186,0.00020816374,0.00046989133,0.00003596217,0.000023838646,0.0001819035,0.00014399856,0.93759143,0.031433042,0.016542897,0.013219988,0.00005828791],"about_ca_topic_score_codex":0.0020320485,"about_ca_topic_score_gemma":0.004582121,"teacher_disagreement_score":0.005786676,"about_ca_system_score_codex":0.00063566025,"about_ca_system_score_gemma":0.0013558794,"threshold_uncertainty_score":0.019358397},"labels":[],"label_agreement":null},{"id":"W4389519335","doi":"10.18653/v1/2023.emnlp-industry.8","title":"MUST&P-SRL: Multi-lingual and Unified Syllabification in Text and Phonetic Domains for Speech Representation Learning","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Syllabification; Natural language processing; Artificial intelligence; Speech recognition; Representation (politics); Stress (linguistics); Linguistics; Syllable","score_opus":0.08676770552050438,"score_gpt":0.3358065862145701,"score_spread":0.2490388806940657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389519335","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015150901,0.0006942226,0.8098425,0.00046978155,0.0004763945,0.000596976,0.03614992,0.1272599,0.009359376],"genre_scores_gemma":[0.06751512,0.00031084346,0.8029752,0.00027710182,0.00016322338,0.001386088,0.1141353,0.005217221,0.008019985],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99796367,0.0004702683,0.00013592263,0.00085022807,0.00040394632,0.00017598689],"domain_scores_gemma":[0.9975846,0.00082110136,0.00013205288,0.00083450234,0.00048506926,0.00014268683],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019570384,0.0020734023,0.00077878434,0.0034649412,0.0012319707,0.002013839,0.0026191778,0.001559688,0.022753526],"category_scores_gemma":[0.006190537,0.00077484146,0.00141381,0.0019880892,0.0007185774,0.002765612,0.0036593925,0.0029170103,0.025674691],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034508156,0.00023387185,0.0024137823,0.00069570116,0.00009478907,0.00025525215,0.0004844269,0.005114877,0.033251394,0.006112169,0.11819871,0.8327999],"study_design_scores_gemma":[0.00024983365,0.0004172584,0.013811768,0.00031165613,0.00015162848,0.0010338522,0.0009800474,0.53324825,0.10889638,0.032664046,0.30795527,0.00027994937],"about_ca_topic_score_codex":0.009582985,"about_ca_topic_score_gemma":0.021919765,"teacher_disagreement_score":0.022753526,"about_ca_system_score_codex":0.0009557237,"about_ca_system_score_gemma":0.002658923,"threshold_uncertainty_score":0.07611817},"labels":[],"label_agreement":null},{"id":"W4389524018","doi":"10.18653/v1/2023.emnlp-main.182","title":"Generative Spoken Language Model based on continuous word-sized audio tokens","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Grand Équipement National De Calcul Intensif; Agence Nationale de la Recherche; Canadian Institute for Advanced Research","keywords":"Computer science; Natural language processing; Language model; Word (group theory); Speech recognition; Artificial intelligence; Generative grammar; Spoken language; Generative model; Bridging (networking); Linguistics","score_opus":0.027014318475177688,"score_gpt":0.26470486781931507,"score_spread":0.2376905493441374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389524018","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02471211,0.00032315697,0.9687262,0.0002650127,0.00013259237,0.00006775004,0.00045389615,0.0026378436,0.0026814502],"genre_scores_gemma":[0.80123514,0.00045460268,0.17637126,0.0003256572,0.000120155346,0.0004202882,0.001311113,0.0005105543,0.019251218],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996666,0.00009476329,0.000020393689,0.000112713125,0.000073162126,0.000032453485],"domain_scores_gemma":[0.9992969,0.0004421281,0.0000440837,0.000069170026,0.000117341704,0.000030418114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003802278,0.00058303645,0.0005818634,0.00032591584,0.00018586601,0.00075260043,0.001245931,0.0007452158,0.0052782437],"category_scores_gemma":[0.0016046942,0.00034461674,0.00082006137,0.0003275181,0.00057525176,0.00095018884,0.0007012763,0.0010011662,0.0023842803],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036696965,0.000087976514,0.00084616477,0.00027008113,0.00010251926,0.00046829347,0.00043873987,0.79242826,0.0420756,0.037031338,0.00393882,0.12194529],"study_design_scores_gemma":[0.0000106083135,0.000029686253,0.000074648095,0.000005103505,0.000011430147,0.000049110713,0.000010436061,0.99271977,0.002370115,0.004004211,0.0007061171,0.000008718275],"about_ca_topic_score_codex":0.0026806744,"about_ca_topic_score_gemma":0.0031588343,"teacher_disagreement_score":0.0052782437,"about_ca_system_score_codex":0.00045021684,"about_ca_system_score_gemma":0.0005620878,"threshold_uncertainty_score":0.017657459},"labels":[],"label_agreement":null},{"id":"W4390037801","doi":"10.1162/tacl_a_00627","title":"AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASR","year":2023,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Benchmark (surveying); Computer science; Speech recognition; Domain (mathematical analysis); Set (abstract data type); Productivity; Natural language processing; Test set; Test (biology); Artificial intelligence; Biology","score_opus":0.05812305070298272,"score_gpt":0.34878724945583334,"score_spread":0.2906641987528506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390037801","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14853415,0.0039276625,0.019514978,0.0015491768,0.0026000205,0.0019123617,0.7791665,0.022266991,0.020528192],"genre_scores_gemma":[0.05424718,0.00052610616,0.00978362,0.00028511763,0.0002632073,0.0009302304,0.9259215,0.00039623753,0.007646847],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983625,0.00037097587,0.0002008902,0.00037789083,0.00045097686,0.00023675954],"domain_scores_gemma":[0.9982704,0.0004125146,0.0000833612,0.00045719725,0.0005982194,0.00017835508],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016123172,0.0028517502,0.0011601378,0.002197735,0.0010394328,0.0011759597,0.001630493,0.0022900007,0.014187371],"category_scores_gemma":[0.0041284985,0.00038602753,0.0010450572,0.0012722858,0.0006244834,0.0011204819,0.0018897491,0.0013747273,0.024796717],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027296648,0.00096390885,0.0062846714,0.0019522682,0.00031569687,0.0020890012,0.0004693149,0.0072908266,0.037050962,0.00079659675,0.7566945,0.18336253],"study_design_scores_gemma":[0.0021069949,0.0027000117,0.12753895,0.001002795,0.000568519,0.011015433,0.003192896,0.08682817,0.0729942,0.0037324035,0.68748283,0.0008367677],"about_ca_topic_score_codex":0.016124586,"about_ca_topic_score_gemma":0.022277288,"teacher_disagreement_score":0.016124586,"about_ca_system_score_codex":0.0007158857,"about_ca_system_score_gemma":0.0015242398,"threshold_uncertainty_score":0.04746145},"labels":[],"label_agreement":null},{"id":"W4390126565","doi":"10.18280/isi.280612","title":"Enhanced Dialectal Speech Recognition in Punjabi Using Pitch-Based Acoustic Modeling","year":2023,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Speech recognition; Computer science; Acoustic model; Natural language processing; Acoustics; Speech processing; Physics","score_opus":0.0453817229647579,"score_gpt":0.25765321074589137,"score_spread":0.21227148778113347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390126565","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70925653,0.00066581374,0.28067502,0.0003224532,0.00012415258,0.00006976613,0.00048122703,0.0033505345,0.0050544394],"genre_scores_gemma":[0.8609774,0.00042856619,0.13061175,0.00014745726,0.000026580721,0.00006257682,0.00094390515,0.00016280058,0.006638948],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9997625,0.000057779806,0.000013724639,0.000084969695,0.000050608935,0.000030397132],"domain_scores_gemma":[0.9998522,0.000054970755,0.000010759543,0.000020655536,0.000050548213,0.0000109031025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040240408,0.0004063528,0.0003973716,0.0004703218,0.00026830882,0.0005362432,0.00031179402,0.00036117475,0.001579512],"category_scores_gemma":[0.000590344,0.00018585769,0.00032483204,0.0003441328,0.00017397026,0.00047439034,0.00046365563,0.00043786544,0.001086098],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00082454574,0.00017525475,0.0068487036,0.0002802909,0.0001043324,0.0007483275,0.0004896987,0.030065233,0.42255065,0.0009760621,0.0024231917,0.5345137],"study_design_scores_gemma":[0.00007901638,0.000643391,0.066585906,0.000048614795,0.00019983682,0.0016717811,0.00040632067,0.70345294,0.21531278,0.0009775471,0.010524306,0.00009761866],"about_ca_topic_score_codex":0.0043366253,"about_ca_topic_score_gemma":0.009724664,"teacher_disagreement_score":0.0043366253,"about_ca_system_score_codex":0.00020580734,"about_ca_system_score_gemma":0.00036420586,"threshold_uncertainty_score":0.008622766},"labels":[],"label_agreement":null},{"id":"W4390912555","doi":"10.21437/speechprosody.2010-77","title":"Whispered speech prosody modeling for TTS synthesis","year":2010,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Prosody; Computer science; Speech synthesis; Speech recognition","score_opus":0.031759349840083335,"score_gpt":0.25995687634559256,"score_spread":0.22819752650550923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390912555","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035945382,0.00023880316,0.9597863,0.00005287235,0.000034793316,0.00003335769,0.00013439341,0.0007028769,0.0030711982],"genre_scores_gemma":[0.86484426,0.00055541674,0.12669964,0.00003060697,0.00004629888,0.00013542113,0.0003950223,0.0002213756,0.007071963],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999268,0.000024502922,0.000006000509,0.000014542583,0.00002299263,0.000005141428],"domain_scores_gemma":[0.9999186,0.000037776903,0.000009228523,0.000011776071,0.000018562898,0.000004076118],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017276435,0.0003691771,0.00022246006,0.00016213514,0.00016591075,0.00043214983,0.0002710197,0.00028249426,0.0024142654],"category_scores_gemma":[0.0003606911,0.00015321867,0.0005295552,0.00012938965,0.00014120426,0.00038188885,0.00019014807,0.00028912586,0.00076342723],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015495444,0.000034336448,0.0006985273,0.0001560453,0.000056465382,0.00019753685,0.00031940706,0.72936654,0.13886239,0.012539777,0.0008272674,0.11678674],"study_design_scores_gemma":[0.000002499751,0.000027394855,0.000207259,0.0000064723945,0.000009057302,0.00003360004,0.000019261624,0.9900018,0.0063011567,0.0013131667,0.0020729182,0.0000052744645],"about_ca_topic_score_codex":0.0022638869,"about_ca_topic_score_gemma":0.0016457574,"teacher_disagreement_score":0.0024142654,"about_ca_system_score_codex":0.00020126,"about_ca_system_score_gemma":0.0002499152,"threshold_uncertainty_score":0.008076489},"labels":[],"label_agreement":null},{"id":"W4390913029","doi":"10.21437/iscslp.2008-51","title":"Subword Latent Semantic Analysis for TextTiling-based Automatic Story Segmentation of Chinese Broadcast News","year":2008,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Science North","funders":"","keywords":"Bigram; Computer science; Artificial intelligence; Speech recognition; Latent semantic analysis; Natural language processing; Robustness (evolution); Mandarin Chinese; Sentence; Treebank; Hidden Markov model; Segmentation; Character (mathematics); Text segmentation; Trigram; Annotation; Linguistics","score_opus":0.03312502395368702,"score_gpt":0.27234236591370903,"score_spread":0.239217341960022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390913029","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16920504,0.00071323564,0.82318443,0.00020782983,0.00008574624,0.00014417824,0.00079677324,0.0033043495,0.0023585379],"genre_scores_gemma":[0.6523174,0.00035028675,0.34120974,0.00008306625,0.000116091665,0.00026579527,0.0029225494,0.00031916157,0.0024159532],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99946016,0.00016818801,0.000044890337,0.00014824065,0.00011870092,0.00005985655],"domain_scores_gemma":[0.9991366,0.00036189033,0.00014724009,0.00009089592,0.00021213027,0.00005125628],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056786375,0.00062710256,0.0005203714,0.0022654622,0.0004947454,0.00069280114,0.0004425704,0.00036030656,0.002144598],"category_scores_gemma":[0.001972425,0.00020679459,0.0007424265,0.0011544697,0.00039690654,0.0013332671,0.0005755238,0.00047053254,0.0011034575],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006807031,0.0001700283,0.0042718095,0.00034829465,0.000099233206,0.00017277588,0.0006271857,0.010727816,0.12238779,0.00485887,0.0026937455,0.8529617],"study_design_scores_gemma":[0.00006829746,0.00033096346,0.012608652,0.000043349,0.00014999333,0.00024622504,0.0006156108,0.87473506,0.09608804,0.007803967,0.0072215623,0.000088226756],"about_ca_topic_score_codex":0.002542903,"about_ca_topic_score_gemma":0.0038737073,"teacher_disagreement_score":0.002542903,"about_ca_system_score_codex":0.0004498801,"about_ca_system_score_gemma":0.00070442987,"threshold_uncertainty_score":0.0071744323},"labels":[],"label_agreement":null},{"id":"W4390917297","doi":"10.3389/fnins.2023.1351848","title":"Speaker-turn aware diarization for speech-based cognitive assessments","year":2024,"lang":"en","type":"article","venue":"Frontiers in Neuroscience","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Dalhousie University","funders":"Shenzhen University; National Natural Science Foundation of China","keywords":"Speaker diarisation; Computer science; Speech recognition; Cluster analysis; Channel (broadcasting); Microphone; Feature (linguistics); Similarity (geometry); Artificial intelligence; Speaker recognition; Telecommunications","score_opus":0.03173854922503484,"score_gpt":0.3128822342037598,"score_spread":0.281143684978725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390917297","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048137676,0.0025776427,0.93428016,0.00030644058,0.00046274633,0.00039981605,0.0022778595,0.0069788434,0.004578865],"genre_scores_gemma":[0.35082465,0.0015608703,0.63232476,0.00027346594,0.000409299,0.0005930611,0.006039925,0.0007595306,0.0072144354],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993088,0.00013454197,0.00004995726,0.00024279577,0.00020560053,0.00005832352],"domain_scores_gemma":[0.9987582,0.00027410281,0.00012634204,0.00018896983,0.00055591454,0.000096497206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009458097,0.0011573932,0.00048370077,0.001205456,0.00038186632,0.0007916586,0.0007675,0.0004990139,0.0037931383],"category_scores_gemma":[0.0034596995,0.00022107993,0.00050706713,0.00066613674,0.00028504062,0.0007143462,0.0011627576,0.00095652987,0.0030489203],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007877065,0.00009607955,0.0037633653,0.00027070066,0.00013698362,0.00011138356,0.00022464209,0.0056849355,0.09004464,0.001299305,0.0091910735,0.8883891],"study_design_scores_gemma":[0.00017413778,0.00084426533,0.07570238,0.00022324212,0.0004742249,0.0021105616,0.00071490643,0.49359515,0.33650553,0.012117188,0.077247255,0.00029121648],"about_ca_topic_score_codex":0.0031077792,"about_ca_topic_score_gemma":0.00737566,"teacher_disagreement_score":0.0037931383,"about_ca_system_score_codex":0.00039817323,"about_ca_system_score_gemma":0.0007717972,"threshold_uncertainty_score":0.012689352},"labels":[],"label_agreement":null},{"id":"W4390956048","doi":"10.1121/10.0024345","title":"Documenting and modeling the acoustic variability of intervocalic alveolar taps in conversational Peninsular Spanish","year":2024,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Social Sciences and Humanities Research Council; Social Sciences and Humanities Research Council of Canada","keywords":"Pronunciation; Categorical variable; Speech recognition; Computer science; Speech production; Linguistics","score_opus":0.017694126137270325,"score_gpt":0.2563845217135089,"score_spread":0.23869039557623856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390956048","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9694481,0.00030115168,0.02923471,0.000060447157,0.0000082633005,0.000012486379,0.00032307042,0.00013007346,0.0004816362],"genre_scores_gemma":[0.9949498,0.00011704213,0.004029477,0.00000748463,0.0000074547743,0.000020479612,0.00048479153,0.000051082694,0.00033231222],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9995433,0.00016879529,0.00001974391,0.00017533998,0.00004937072,0.00004344375],"domain_scores_gemma":[0.9983063,0.0012984492,0.00012575487,0.000107310356,0.00012749559,0.000034650435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013656066,0.0003561448,0.0003590567,0.000696755,0.00017403315,0.0011724231,0.00057624583,0.00043038806,0.0003601455],"category_scores_gemma":[0.0037304636,0.00027351116,0.00040624265,0.0005211438,0.00036742314,0.0004219442,0.0004158076,0.00036882533,0.0002453676],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010141572,0.00026458848,0.3571832,0.0003223432,0.00051701424,0.0007752785,0.005842735,0.3739481,0.058624323,0.002579111,0.00153089,0.19739826],"study_design_scores_gemma":[0.0000195293,0.00008010824,0.17259397,0.000025744575,0.000051569765,0.00019836171,0.0011010267,0.8204786,0.0020743192,0.0019321631,0.0014003987,0.00004414788],"about_ca_topic_score_codex":0.021766698,"about_ca_topic_score_gemma":0.021014746,"teacher_disagreement_score":0.021766698,"about_ca_system_score_codex":0.00040678732,"about_ca_system_score_gemma":0.00052994804,"threshold_uncertainty_score":0.043280005},"labels":[],"label_agreement":null},{"id":"W4391021767","doi":"10.1109/asru57964.2023.10389758","title":"CAMSAT: Augmentation Mix and Self-Augmented Training Clustering for Self-Supervised Speaker Recognition","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Computer science; Cluster analysis; Dependency (UML); Embedding; Representation (politics); Artificial intelligence; Variety (cybernetics); Pattern recognition (psychology); Speaker recognition; Speech recognition; Data mining; Machine learning","score_opus":0.06898587806828843,"score_gpt":0.27424666113269125,"score_spread":0.20526078306440282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391021767","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02905931,0.0002010145,0.9623724,0.0001432808,0.000087282126,0.00015620545,0.00015702753,0.0062939157,0.0015295608],"genre_scores_gemma":[0.2757554,0.00008532985,0.7168336,0.0002833612,0.00006847245,0.00032886653,0.0012995765,0.00072600815,0.0046194606],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989813,0.0003056439,0.00004072097,0.00032728008,0.0002603108,0.000084691026],"domain_scores_gemma":[0.9985903,0.00042033673,0.00010887063,0.0004398077,0.00036593538,0.00007469685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017529433,0.0012646924,0.0008350278,0.00096740155,0.000849497,0.00088541966,0.0021147614,0.0014757132,0.0028239123],"category_scores_gemma":[0.0037401454,0.00053193286,0.0008848926,0.0006537769,0.00088080263,0.0015294105,0.0022743358,0.001636254,0.0016114778],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00072336826,0.00036720472,0.0027797443,0.00019024096,0.00019479827,0.000111446665,0.0004366444,0.195277,0.04995589,0.00847895,0.011712456,0.72977227],"study_design_scores_gemma":[0.000025883764,0.00010616209,0.00052759814,0.000010212786,0.00001352871,0.000057784044,0.000037880527,0.9784936,0.01551368,0.0029552057,0.002238678,0.000019916035],"about_ca_topic_score_codex":0.0024842764,"about_ca_topic_score_gemma":0.0064304536,"teacher_disagreement_score":0.0028239123,"about_ca_system_score_codex":0.0006495394,"about_ca_system_score_gemma":0.0010613974,"threshold_uncertainty_score":0.009446979},"labels":[],"label_agreement":null},{"id":"W4391326347","doi":"10.1016/j.patrec.2024.01.024","title":"An analytic study on clustering driven self-supervised speaker verification","year":2024,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Computer science; Cluster analysis; Overfitting; Discriminative model; Artificial intelligence; Speaker verification; Noise (video); Pattern recognition (psychology); Embedding; Speaker recognition; Speech recognition; Machine learning; Artificial neural network","score_opus":0.041907874587752796,"score_gpt":0.27724486008457644,"score_spread":0.23533698549682364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391326347","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034508128,0.0010372559,0.9576839,0.00047630092,0.00006254786,0.00008434201,0.00008493951,0.00025584624,0.005806832],"genre_scores_gemma":[0.8815642,0.0011090626,0.1005353,0.00028988824,0.00029887073,0.0001269124,0.00034108778,0.00034403044,0.015390579],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982753,0.00055769924,0.000042448057,0.0003395378,0.0006090064,0.0001759319],"domain_scores_gemma":[0.98130196,0.01428163,0.0009414982,0.0009865387,0.0022839473,0.00020448302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031139173,0.000657653,0.0010404885,0.0011169108,0.0007005352,0.0012663184,0.002360925,0.0011788364,0.0044982303],"category_scores_gemma":[0.022297597,0.0006272736,0.00080626726,0.0011033067,0.0015608632,0.0030424197,0.0013958731,0.0013225614,0.0006360557],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021955105,0.00012228641,0.0023432751,0.0004295099,0.00013591208,0.00034272578,0.00059676834,0.63049555,0.012320001,0.24714246,0.005531918,0.100320004],"study_design_scores_gemma":[0.0000015048486,0.000020203897,0.00042032747,0.0000112781545,0.000009517568,0.00007444151,0.000026390759,0.9860771,0.0010273795,0.011828962,0.000494188,0.000008711285],"about_ca_topic_score_codex":0.004016131,"about_ca_topic_score_gemma":0.0031121091,"teacher_disagreement_score":0.0044982303,"about_ca_system_score_codex":0.0018595434,"about_ca_system_score_gemma":0.0012585759,"threshold_uncertainty_score":0.016468108},"labels":[],"label_agreement":null},{"id":"W4391331185","doi":"10.1109/smc53992.2023.10394252","title":"Assessing the Vulnerability of Self-Supervised Speech Representations for Keyword Spotting Under White-Box Adversarial Attacks","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Keyword spotting; Computer science; Adversarial system; Robustness (evolution); Speech recognition; Transferability; Artificial intelligence; Task (project management); White noise; Machine learning; Natural language processing; Telecommunications","score_opus":0.07714874044791163,"score_gpt":0.36170200470024877,"score_spread":0.2845532642523371,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391331185","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86820304,0.00060658465,0.12637903,0.00034272805,0.0001318167,0.000085995,0.00031790964,0.00072274695,0.003210143],"genre_scores_gemma":[0.99262285,0.000102893566,0.006280153,0.000042746517,0.000012568723,0.00002099358,0.00020078951,0.00003593327,0.0006810504],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99887604,0.00034015634,0.0000812198,0.00018977109,0.00035445424,0.0001583501],"domain_scores_gemma":[0.992303,0.0053279786,0.0006553391,0.000931677,0.0005180102,0.0002640194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016527757,0.00066134945,0.0004751384,0.0005516741,0.00024499543,0.0006455434,0.00041884658,0.0009861515,0.0010833085],"category_scores_gemma":[0.01102856,0.00019976054,0.0003639606,0.0002233116,0.00083063054,0.0012226048,0.0010442173,0.0010471392,0.00045830806],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015867942,0.00027736416,0.008357401,0.00026939774,0.00025755633,0.0003977027,0.00019582533,0.8507803,0.053043734,0.0045126975,0.0015456778,0.078775495],"study_design_scores_gemma":[0.000013902257,0.0006002399,0.0041085137,0.000026115002,0.000032478307,0.0003035407,0.00007374217,0.96135676,0.031239932,0.0017307514,0.00048011797,0.0000339565],"about_ca_topic_score_codex":0.0008833951,"about_ca_topic_score_gemma":0.00065561227,"teacher_disagreement_score":0.0016527757,"about_ca_system_score_codex":0.0004571281,"about_ca_system_score_gemma":0.0003693994,"threshold_uncertainty_score":0.008740842},"labels":[],"label_agreement":null},{"id":"W4391683008","doi":"10.3991/ijim.v18i03.43013","title":"Convolutional Neural Network Architectures for Gender, Emotional Detection from Speech and Speaker Diarization","year":2024,"lang":"en","type":"article","venue":"International Journal of Interactive Mobile Technologies (iJIM)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Speaker diarisation; Convolutional neural network; Speech recognition; Computer science; Speaker recognition; Artificial intelligence","score_opus":0.018665437822444866,"score_gpt":0.2789606270943671,"score_spread":0.26029518927192224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391683008","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13603461,0.0019755655,0.8470092,0.00045130946,0.00027140655,0.00009853139,0.0005326551,0.003220269,0.010406444],"genre_scores_gemma":[0.84352964,0.00091045594,0.13861649,0.00021023887,0.000064964705,0.0001280352,0.0011159737,0.00008525015,0.015338875],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9998235,0.000025262621,0.000008555413,0.00005106768,0.000046342044,0.0000452171],"domain_scores_gemma":[0.9998047,0.00005843995,0.000018365357,0.000024240768,0.00008061191,0.000013689661],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004909517,0.0006931244,0.00026095586,0.0003930233,0.0002488799,0.0004377275,0.00078866974,0.000603956,0.0022336715],"category_scores_gemma":[0.00096493965,0.00022288061,0.0003496722,0.00032706876,0.00021771561,0.0005146602,0.00053319585,0.000811221,0.00080387405],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040896272,0.0002368997,0.004504263,0.00013506893,0.0001802382,0.00016729509,0.00014926265,0.23145634,0.06797596,0.008539221,0.005485873,0.68076074],"study_design_scores_gemma":[0.0000047336616,0.000054814976,0.0018876771,0.000011429582,0.000031025713,0.000044927237,0.000016677923,0.98422354,0.010159203,0.0016754144,0.0018783184,0.000012233979],"about_ca_topic_score_codex":0.010291239,"about_ca_topic_score_gemma":0.01534282,"teacher_disagreement_score":0.010291239,"about_ca_system_score_codex":0.0007002074,"about_ca_system_score_gemma":0.0006035141,"threshold_uncertainty_score":0.020462692},"labels":[],"label_agreement":null},{"id":"W4391831786","doi":"10.4995/eurocall2023.2023.17007","title":"Evaluating the effectiveness of Microsoft Transcribe for automating the assessment of pronunciation in language proficiency tests","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Concordia University","funders":"Université du Québec à Montréal","keywords":"Computer science; Pronunciation; Natural language processing; Test (biology); Automation; Reliability (semiconductor); Artificial intelligence; Linguistics; Engineering","score_opus":0.0713846181357021,"score_gpt":0.4181764047821827,"score_spread":0.3467917866464806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391831786","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9892942,0.00013830756,0.008051844,0.000038643964,0.000027241022,0.00030030712,0.00015490864,0.0002428575,0.0017518053],"genre_scores_gemma":[0.9590955,0.00017921522,0.038242217,0.000047347847,0.000027715932,0.00030137238,0.00032114473,0.0000987649,0.0016867502],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99098164,0.0048761168,0.00095823914,0.000845086,0.0021180199,0.00022094721],"domain_scores_gemma":[0.9609774,0.026468998,0.0026069395,0.0018545132,0.007067108,0.0010249885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010037182,0.00077602704,0.0003566541,0.0012934924,0.00043685318,0.0010397517,0.00056660693,0.00075191126,0.0014710193],"category_scores_gemma":[0.040928535,0.00027316378,0.00036146306,0.00048994325,0.00048524718,0.0010104014,0.0010088177,0.0003413471,0.0008086744],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.013155586,0.0036167738,0.27621496,0.0009721927,0.00029527058,0.0010207943,0.01649211,0.009175276,0.15469056,0.0008761437,0.0022331364,0.5212572],"study_design_scores_gemma":[0.0007858482,0.03626252,0.73684245,0.00026412084,0.0006069744,0.0023119336,0.0094000185,0.05690725,0.14615738,0.0006448867,0.009458586,0.00035795732],"about_ca_topic_score_codex":0.004663447,"about_ca_topic_score_gemma":0.014811888,"teacher_disagreement_score":0.010037182,"about_ca_system_score_codex":0.000413181,"about_ca_system_score_gemma":0.0007028831,"threshold_uncertainty_score":0.053082347},"labels":[],"label_agreement":null},{"id":"W4391896879","doi":"10.2196/56245","title":"Investigation of Deepfake Voice Detection Using Speech Pause Patterns: Algorithm Development and Validation","year":2024,"lang":"en","type":"article","venue":"JMIR Biomedical Engineering","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Glycemic Index Laboratories","funders":"","keywords":"Preprint; Computer science; Speech recognition; World Wide Web","score_opus":0.024097442042768515,"score_gpt":0.2441410869546239,"score_spread":0.22004364491185538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391896879","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46388018,0.0031350367,0.5188582,0.0010284267,0.00029249454,0.0006574052,0.00055063254,0.008672647,0.002924916],"genre_scores_gemma":[0.8258276,0.00035915713,0.16987944,0.00032148432,0.00003597387,0.00046180704,0.0014071859,0.00012562617,0.0015817283],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987546,0.0004184216,0.00013110437,0.0003590107,0.00020111732,0.00013578318],"domain_scores_gemma":[0.9922105,0.0056128283,0.0002790533,0.0005011534,0.001209407,0.00018704405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056679705,0.0016475046,0.0010767068,0.00091376354,0.0005407064,0.0010724533,0.002141505,0.002225509,0.0018057147],"category_scores_gemma":[0.012532049,0.00051070726,0.0008943438,0.0004754553,0.00060583546,0.0011327557,0.0013166311,0.002665888,0.00084319286],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00079086475,0.00064814795,0.0112463655,0.0003071396,0.00027055,0.0002477399,0.00018373509,0.48037505,0.007828413,0.0015295409,0.0027096872,0.49386272],"study_design_scores_gemma":[0.00002398101,0.00010645909,0.00056962285,0.000014328321,0.000014772258,0.000033888802,0.000028381306,0.9959325,0.0026762115,0.00037276387,0.00022037893,0.000006682532],"about_ca_topic_score_codex":0.008025797,"about_ca_topic_score_gemma":0.005660099,"teacher_disagreement_score":0.008025797,"about_ca_system_score_codex":0.0011046233,"about_ca_system_score_gemma":0.0019252031,"threshold_uncertainty_score":0.029975474},"labels":[],"label_agreement":null},{"id":"W4392411857","doi":"10.1109/ijcb57857.2023.10449225","title":"Benchmark Dataset Dynamics, Bias and Privacy Challenges in Voice Biometrics Research","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; University of Toronto","funders":"","keywords":"Biometrics; Computer science; Benchmark (surveying); Information privacy; Dynamics (music); Internet privacy; Data science; Speech recognition; Data mining; Artificial intelligence; Psychology","score_opus":0.42622501651506584,"score_gpt":0.4011914368871123,"score_spread":0.02503357962795355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392411857","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77049,0.02732937,0.09501436,0.024799854,0.0028967147,0.0014185465,0.044386674,0.004839557,0.028824965],"genre_scores_gemma":[0.82024664,0.0031162915,0.08349178,0.0037509254,0.0007415551,0.0015462148,0.08228271,0.0011933838,0.0036304668],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9240955,0.037173625,0.0076987823,0.0074349516,0.022183726,0.0014133623],"domain_scores_gemma":[0.86692595,0.05541614,0.009968814,0.036807682,0.028820608,0.002060802],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.058161024,0.00072658894,0.00077359314,0.0034757985,0.0017632742,0.005562511,0.0029691404,0.0016360319,0.0014566247],"category_scores_gemma":[0.16124986,0.00025968757,0.00086209463,0.0052800192,0.0022588228,0.0052213245,0.0046197544,0.0020640995,0.0011730543],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019191845,0.00071258424,0.29988658,0.0026709514,0.0011703315,0.0004856997,0.0058354246,0.014505576,0.016621513,0.040277235,0.11961151,0.49630332],"study_design_scores_gemma":[0.00035100465,0.0014752074,0.33593747,0.002752277,0.00059893995,0.0037108343,0.0094720125,0.05695041,0.041843846,0.071115874,0.47523582,0.00055624545],"about_ca_topic_score_codex":0.0041685556,"about_ca_topic_score_gemma":0.0050475304,"teacher_disagreement_score":0.941839,"about_ca_system_score_codex":0.0023089687,"about_ca_system_score_gemma":0.0022567853,"threshold_uncertainty_score":0.30758858},"labels":[],"label_agreement":null},{"id":"W4392903183","doi":"10.1109/icassp48485.2024.10446486","title":"End-To-End Real Time Tracking of Children’s Reading with Pointer Network","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Science Foundation","keywords":"Computer science; Pointer (user interface); Ground truth; Speech recognition; BitTorrent tracker; TIMIT; Artificial neural network; End-to-end principle; Training set; Artificial intelligence; Reading (process); Eye tracking; Hidden Markov model","score_opus":0.011905208322205181,"score_gpt":0.2316135383811359,"score_spread":0.21970833005893073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392903183","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31584838,0.0017964495,0.61458945,0.00071167224,0.0006667714,0.00015409528,0.0066254064,0.048645463,0.0109623065],"genre_scores_gemma":[0.76922536,0.00036132114,0.20740713,0.00036268812,0.00011561762,0.00021279657,0.007220206,0.0007146242,0.01438017],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99949193,0.000083704654,0.000017754282,0.0002649679,0.000091103924,0.0000505009],"domain_scores_gemma":[0.9990393,0.00046265597,0.00006158142,0.00012038972,0.00025392274,0.00006226444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008152828,0.0011123297,0.00066961016,0.0007783712,0.00022726668,0.0006117836,0.0012110607,0.0010742674,0.0047441954],"category_scores_gemma":[0.0035578418,0.00033347867,0.0003386372,0.00052978133,0.0002619904,0.0014577653,0.0009780709,0.001367598,0.0035482545],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010418558,0.00029661076,0.021496933,0.0003856093,0.00018810085,0.0007457729,0.00058131834,0.06905906,0.07803319,0.0021031098,0.02386974,0.80219877],"study_design_scores_gemma":[0.000041706255,0.00037159937,0.014472683,0.00004504578,0.00007331342,0.00038231883,0.00015177818,0.94133085,0.03458612,0.002553813,0.005931335,0.000059333204],"about_ca_topic_score_codex":0.005659865,"about_ca_topic_score_gemma":0.013481581,"teacher_disagreement_score":0.005659865,"about_ca_system_score_codex":0.00046896088,"about_ca_system_score_gemma":0.00052213325,"threshold_uncertainty_score":0.015870929},"labels":[],"label_agreement":null},{"id":"W4392904518","doi":"10.1109/icassp48485.2024.10447101","title":"Self-Supervised Speaker Verification Employing A Novel Clustering Algorithm","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Cluster analysis; Computer science; Discriminative model; Artificial intelligence; Pattern recognition (psychology); Embedding; Correlation clustering; Speaker recognition; Representation (politics); Canopy clustering algorithm; Dependency (UML); Machine learning; Data mining","score_opus":0.03312310008655405,"score_gpt":0.25627538350246315,"score_spread":0.2231522834159091,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392904518","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009640223,0.00011728207,0.9876143,0.00006964529,0.000043227126,0.00006014579,0.00006449847,0.0015867794,0.0008039985],"genre_scores_gemma":[0.23786476,0.00010942485,0.7562657,0.00016903211,0.00009035134,0.00016660301,0.0008458121,0.0002603957,0.004227952],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9981061,0.00039420062,0.00009910623,0.0007502061,0.0005251707,0.00012519937],"domain_scores_gemma":[0.99828666,0.00036124847,0.00018113804,0.0004943489,0.0006102435,0.00006637717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015714078,0.0009703235,0.0012017883,0.0012468321,0.0008851848,0.0008528576,0.002069562,0.0014993058,0.0017230355],"category_scores_gemma":[0.0027815439,0.0005160686,0.0012141983,0.0007978608,0.000980798,0.0013119202,0.0017189581,0.0016711393,0.001738722],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005001772,0.00023369519,0.0020726777,0.00013867098,0.00026478985,0.00012317162,0.00029492265,0.1667727,0.081161074,0.011711808,0.0072034756,0.7295228],"study_design_scores_gemma":[0.000015221423,0.000053631502,0.00044261842,0.00000522339,0.00001571473,0.0001001167,0.00001777563,0.97767866,0.01782856,0.002457348,0.0013628778,0.000022219243],"about_ca_topic_score_codex":0.0027354509,"about_ca_topic_score_gemma":0.004841022,"teacher_disagreement_score":0.0027354509,"about_ca_system_score_codex":0.0006523501,"about_ca_system_score_gemma":0.0012644719,"threshold_uncertainty_score":0.008310497},"labels":[],"label_agreement":null},{"id":"W4392908955","doi":"10.1109/icassp48485.2024.10446327","title":"Unsupervised Speech Recognition with N-skipgram and Positional Unigram Matching","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada); Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Artificial intelligence; Speech recognition; Pattern recognition (psychology); Matching (statistics); Mathematics","score_opus":0.016749356415947825,"score_gpt":0.2276625302010225,"score_spread":0.21091317378507468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392908955","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03588976,0.0005353278,0.9396458,0.00015427441,0.000111800844,0.00009176495,0.0008851841,0.01934786,0.0033382422],"genre_scores_gemma":[0.44863284,0.00036438636,0.52828115,0.0003923714,0.00014428695,0.00031661347,0.0057482813,0.0013252478,0.014794886],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99948823,0.00011254191,0.000026432775,0.00023926036,0.000081501734,0.000052035895],"domain_scores_gemma":[0.99938107,0.00021602174,0.000041102612,0.00020377182,0.00012720498,0.0000307584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005876298,0.0010900825,0.0008785232,0.0007834828,0.00040729227,0.00065599795,0.0012693186,0.0008981525,0.004039359],"category_scores_gemma":[0.0016433414,0.00041745265,0.0007143568,0.0007113273,0.00041841101,0.0011685041,0.0011434965,0.0009227542,0.004512746],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055307115,0.00025195294,0.0014016159,0.00017753578,0.00014703812,0.00027400846,0.00015285957,0.07786069,0.092267446,0.0064501455,0.014365274,0.8060984],"study_design_scores_gemma":[0.000030121879,0.00012952439,0.0011019204,0.000016884635,0.000034922537,0.00019279853,0.000032315078,0.94159144,0.043620374,0.007341766,0.005880253,0.000027666236],"about_ca_topic_score_codex":0.0052273017,"about_ca_topic_score_gemma":0.014673427,"teacher_disagreement_score":0.0052273017,"about_ca_system_score_codex":0.00038447639,"about_ca_system_score_gemma":0.0009577346,"threshold_uncertainty_score":0.013512969},"labels":[],"label_agreement":null},{"id":"W4393043884","doi":"10.3390/s24061996","title":"Self-Supervised Open-Set Speaker Recognition with Laguerre–Voronoi Descriptors","year":2024,"lang":"en","type":"article","venue":"Sensors","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Speaker recognition; Pattern recognition (psychology); Speech recognition; Artificial intelligence; Open set; Feature extraction; Cluster analysis; Set (abstract data type); Feature (linguistics); Artificial neural network; Biometrics; Speaker diarisation; Voronoi diagram; Neural gas; Time delay neural network; Mathematics","score_opus":0.046830119155900594,"score_gpt":0.2578130349466004,"score_spread":0.2109829157906998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393043884","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03179589,0.00017852537,0.96581876,0.00007181874,0.000048504327,0.00005243733,0.000100445526,0.00084116723,0.001092472],"genre_scores_gemma":[0.7708655,0.00013837848,0.22405934,0.00012381734,0.00008693877,0.00010268167,0.00065410987,0.00015300488,0.003816186],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99895644,0.0002340913,0.000053049916,0.0003405117,0.00030809484,0.000107927866],"domain_scores_gemma":[0.99870384,0.00050998334,0.00017520909,0.00024914654,0.00029998834,0.0000617615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00088794157,0.0004978115,0.0011022178,0.0005785815,0.00042002692,0.0010263831,0.0017604153,0.00067886844,0.001749414],"category_scores_gemma":[0.002743699,0.00031352197,0.0006051052,0.00048787825,0.00072259223,0.0014015784,0.0016423551,0.0011349292,0.0008582515],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006165543,0.00021542373,0.002378254,0.0001356845,0.0001200612,0.00017275431,0.00035688083,0.17103182,0.05197056,0.018809171,0.00405945,0.7501334],"study_design_scores_gemma":[0.000007251569,0.00003318078,0.00037587222,0.0000050614167,0.000006701995,0.00008214005,0.00003113828,0.9812867,0.012641554,0.0047154585,0.0007995771,0.000015460928],"about_ca_topic_score_codex":0.0024241866,"about_ca_topic_score_gemma":0.0037678417,"teacher_disagreement_score":0.0024241866,"about_ca_system_score_codex":0.00061739626,"about_ca_system_score_gemma":0.0006808885,"threshold_uncertainty_score":0.0058524013},"labels":[],"label_agreement":null},{"id":"W4393068745","doi":"10.55041/ijsrem29567","title":"SPEECH RECOGNITION SYSTEM","year":2024,"lang":"en","type":"article","venue":"INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Robustness (evolution); Software deployment; Implementation; Adaptability; Field (mathematics); Data science; Artificial intelligence; Human–computer interaction; Software engineering","score_opus":0.06810367408651197,"score_gpt":0.3209838351931863,"score_spread":0.25288016110667433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393068745","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024033435,0.010375519,0.3641648,0.0069532404,0.009377757,0.0033872006,0.083903186,0.12789059,0.36991426],"genre_scores_gemma":[0.20026095,0.007487035,0.2285736,0.011371628,0.0033966657,0.0035325577,0.20909151,0.007230777,0.3290553],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99818724,0.0002123552,0.00023785149,0.00065891125,0.000526316,0.00017731979],"domain_scores_gemma":[0.9985044,0.00019268674,0.000070133116,0.00030596624,0.000844286,0.00008253879],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001256879,0.0018063094,0.0016862497,0.0017629629,0.0012905175,0.0036927843,0.0019446949,0.0023714777,0.11823322],"category_scores_gemma":[0.0034947612,0.000364213,0.0010244899,0.0010805298,0.00053236296,0.0029055248,0.0027794985,0.0015750771,0.22072017],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00094075396,0.00015602303,0.0021592157,0.0013883932,0.00012655354,0.0009359338,0.00033357905,0.0036914083,0.026551943,0.012994098,0.4280236,0.5226985],"study_design_scores_gemma":[0.00017596113,0.0002933918,0.0028033392,0.00041823977,0.00015473789,0.0017468465,0.00039027832,0.03647987,0.03193462,0.014165828,0.9112219,0.00021499215],"about_ca_topic_score_codex":0.003088203,"about_ca_topic_score_gemma":0.0020560394,"teacher_disagreement_score":0.11823322,"about_ca_system_score_codex":0.0010825967,"about_ca_system_score_gemma":0.0017475637,"threshold_uncertainty_score":0.3955295},"labels":[],"label_agreement":null},{"id":"W4393147067","doi":"10.1609/aaai.v38i16.29747","title":"UniCATS: A Unified Context-Aware Text-to-Speech Framework with Contextual VQ-Diffusion and Vocoding","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Context (archaeology); Computer science; Linguistics; Psychology; Speech recognition; Natural language processing; Biology; Paleontology","score_opus":0.06781807521491127,"score_gpt":0.29374818100819655,"score_spread":0.22593010579328526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393147067","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009660997,0.00097465044,0.98316795,0.0000983269,0.00018016949,0.000087270295,0.00026965875,0.0043469863,0.0012140154],"genre_scores_gemma":[0.32486624,0.001331736,0.658631,0.00045078606,0.0004182476,0.00037256876,0.0024373296,0.0009263879,0.010565682],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99959105,0.00007626681,0.000025386424,0.00012435518,0.00013487985,0.000048035276],"domain_scores_gemma":[0.9997291,0.00006657781,0.000023135352,0.00004391583,0.000105335945,0.00003191987],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046024055,0.0013566687,0.000806117,0.00054957217,0.00035957497,0.0007672657,0.0012465733,0.00073744263,0.0032282544],"category_scores_gemma":[0.0010152115,0.00033953367,0.0009121773,0.0004037199,0.0005042045,0.0011099334,0.001442497,0.0012037279,0.001568318],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006773459,0.00015080004,0.00074038113,0.0003144523,0.0001272486,0.0003885046,0.00022901317,0.15974927,0.12229075,0.012063101,0.009542239,0.693727],"study_design_scores_gemma":[0.000041963718,0.00019373094,0.00032424374,0.00002173404,0.000041917036,0.00017018223,0.00006219266,0.95137775,0.03206662,0.0044099144,0.011247298,0.000042466025],"about_ca_topic_score_codex":0.008996177,"about_ca_topic_score_gemma":0.014026484,"teacher_disagreement_score":0.008996177,"about_ca_system_score_codex":0.00043613958,"about_ca_system_score_gemma":0.0011936101,"threshold_uncertainty_score":0.017887652},"labels":[],"label_agreement":null},{"id":"W4393370699","doi":"","title":"Automatic Speech Recognition : from hybrid to end-to-end approach","year":2021,"lang":"fr","type":"preprint","venue":"theses.fr (ABES)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"End-to-end principle; Speech recognition; Computer science; Artificial intelligence","score_opus":0.07805801844596885,"score_gpt":0.2708289829992054,"score_spread":0.19277096455323653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393370699","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060798824,0.0007914536,0.98410827,0.0001891751,0.00010122357,0.00006960611,0.0001968371,0.0047986563,0.0036649532],"genre_scores_gemma":[0.18294011,0.0015493626,0.7873591,0.00043744937,0.00016680459,0.00025263432,0.0019438338,0.0007038287,0.024646915],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99879587,0.00026215345,0.00007875561,0.0003881855,0.00038837435,0.00008670863],"domain_scores_gemma":[0.9990144,0.00036141375,0.000032739375,0.00024536485,0.00030218955,0.000043959913],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095555437,0.0010500196,0.00091301464,0.00089174294,0.000405481,0.002483108,0.0018057894,0.0019512018,0.0069862576],"category_scores_gemma":[0.001747152,0.0005108601,0.0010525028,0.0005743702,0.00061180454,0.0023567777,0.0017233973,0.0014753838,0.008014454],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044248006,0.00015177476,0.00062038034,0.0004316768,0.00018325138,0.000357875,0.0005020794,0.035844415,0.092717946,0.010569331,0.00625354,0.85192525],"study_design_scores_gemma":[0.000045021046,0.0004459214,0.0018005422,0.00014769846,0.00016615166,0.0011471213,0.0005675738,0.7888416,0.12547927,0.029506244,0.05174616,0.00010680865],"about_ca_topic_score_codex":0.0017183503,"about_ca_topic_score_gemma":0.002674407,"teacher_disagreement_score":0.0069862576,"about_ca_system_score_codex":0.00048350304,"about_ca_system_score_gemma":0.0005930603,"threshold_uncertainty_score":0.023371398},"labels":[],"label_agreement":null},{"id":"W4393401667","doi":"10.5281/zenodo.1219621","title":"A Canadian French Emotional Speech Dataset","year":2018,"lang":"en","type":"dataset","venue":"Figshare","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Speech recognition; Computer science; Psychology","score_opus":0.04705013687903825,"score_gpt":0.26654014039925505,"score_spread":0.2194900035202168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393401667","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003512777,0.0007430105,0.0010293784,0.0003344829,0.00026510953,0.00021172687,0.9837731,0.0025872525,0.00754313],"genre_scores_gemma":[0.0028082742,0.00015332625,0.001225404,0.00011001418,0.00003158706,0.00023921204,0.9910561,0.00014590769,0.0042301244],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979327,0.00034016825,0.00011927205,0.0005015846,0.0007109075,0.00039535487],"domain_scores_gemma":[0.9972416,0.0003506255,0.00006054069,0.00042212792,0.0017133772,0.00021173946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013701636,0.004318192,0.0015856519,0.0041093654,0.003381803,0.0022011602,0.0036053925,0.0029150664,0.054232363],"category_scores_gemma":[0.0049598347,0.00051284785,0.0017222374,0.003814032,0.00079816265,0.0012008614,0.0020997708,0.0020671939,0.06595744],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020227523,0.000060981747,0.00084221415,0.00036868601,0.00005374819,0.00014037853,0.00007464902,0.000509989,0.000805693,0.00046939173,0.9773691,0.019102737],"study_design_scores_gemma":[0.00021753993,0.000088144385,0.021223556,0.00038494944,0.00010727963,0.00058288535,0.00048777077,0.0039820694,0.0022665607,0.0006811956,0.9698178,0.00016014953],"about_ca_topic_score_codex":0.58767796,"about_ca_topic_score_gemma":0.6865555,"teacher_disagreement_score":0.41232204,"about_ca_system_score_codex":0.0056138253,"about_ca_system_score_gemma":0.0076729553,"threshold_uncertainty_score":0.82950056},"labels":[],"label_agreement":null},{"id":"W4393475061","doi":"10.5281/zenodo.1478765","title":"A Canadian French Emotional Speech Dataset","year":2018,"lang":"en","type":"dataset","venue":"Figshare","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Speech recognition; Computer science; Psychology; Natural language processing","score_opus":0.04705013687903825,"score_gpt":0.26654014039925505,"score_spread":0.2194900035202168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393475061","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008278704,0.0011529143,0.0014023053,0.00044235485,0.00034498418,0.00035801026,0.97629637,0.0027108854,0.009013459],"genre_scores_gemma":[0.005315162,0.00021949447,0.0017005663,0.00012208532,0.000043199307,0.00033107292,0.98686475,0.0001428745,0.0052608736],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978783,0.00030683508,0.00012327817,0.000487729,0.0007874659,0.00041646315],"domain_scores_gemma":[0.9973979,0.00034034767,0.00006153456,0.000352445,0.0016083603,0.00023936688],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012862687,0.004358134,0.0014919172,0.004397152,0.0032746398,0.0019485349,0.003521181,0.003052324,0.037223592],"category_scores_gemma":[0.004376249,0.0004565637,0.0015193939,0.0035450223,0.00083900255,0.0010356057,0.0019627335,0.0020799125,0.04079878],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030862092,0.00013261422,0.0015845431,0.00058088807,0.00008548967,0.00031035344,0.00014455034,0.00076590985,0.0017775124,0.00069335906,0.9623495,0.03126669],"study_design_scores_gemma":[0.00025640067,0.00012631675,0.032774486,0.00042068135,0.00014373477,0.0010326032,0.0007404083,0.0056572245,0.0038408784,0.0006777798,0.95413303,0.00019638495],"about_ca_topic_score_codex":0.5791948,"about_ca_topic_score_gemma":0.7122421,"teacher_disagreement_score":0.42080522,"about_ca_system_score_codex":0.0057202415,"about_ca_system_score_gemma":0.00824149,"threshold_uncertainty_score":0.84656686},"labels":[],"label_agreement":null},{"id":"W4393644288","doi":"10.5281/zenodo.7803315","title":"SASS-E: The Steelpan Audio Sample Set for Evaluation","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Sass; Sample (material); Set (abstract data type); Computer science; World Wide Web; Chemistry; Programming language; Chromatography","score_opus":0.11111893059939838,"score_gpt":0.31064814488988435,"score_spread":0.19952921429048598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393644288","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051604804,0.002965749,0.025765384,0.0010235655,0.0027759057,0.0027676558,0.8491624,0.035101086,0.028833432],"genre_scores_gemma":[0.018170709,0.0003565615,0.013425202,0.0002326649,0.00014420738,0.001536419,0.9586444,0.00069360423,0.006796211],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961545,0.0006404916,0.00040996703,0.00073681684,0.0017328091,0.00032546566],"domain_scores_gemma":[0.99621516,0.00068974186,0.0001431663,0.00090447697,0.0016837056,0.00036364727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029336964,0.003813845,0.0018023074,0.0034240037,0.001346813,0.002147035,0.0034156456,0.0020910676,0.036644865],"category_scores_gemma":[0.0094003845,0.00049350265,0.0018863676,0.0026291558,0.0008936214,0.0022454786,0.0028001815,0.0020215837,0.057519145],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001576807,0.0005794156,0.004024731,0.001603863,0.00023175064,0.00034277272,0.00016227525,0.002837572,0.008206145,0.0006942535,0.84383917,0.13590121],"study_design_scores_gemma":[0.0018959871,0.0023563907,0.07843565,0.001178572,0.000439156,0.002515511,0.0021812129,0.05099946,0.023881605,0.0038781392,0.8317064,0.00053188653],"about_ca_topic_score_codex":0.019471377,"about_ca_topic_score_gemma":0.032502145,"teacher_disagreement_score":0.036644865,"about_ca_system_score_codex":0.0015156766,"about_ca_system_score_gemma":0.0023122896,"threshold_uncertainty_score":0.12258935},"labels":[],"label_agreement":null},{"id":"W4393657923","doi":"10.1109/o-cocosda60357.2023.10482992","title":"Fine-tuning the Wav2Vec2 Model for Automatic Speech Emotion Recognition System","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Speech recognition; Emotion recognition; Artificial intelligence","score_opus":0.08142040918939211,"score_gpt":0.2696513453232329,"score_spread":0.18823093613384081,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393657923","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26304567,0.00400844,0.68301874,0.0010477937,0.0019432848,0.00038030525,0.0030376017,0.029924843,0.013593316],"genre_scores_gemma":[0.7918674,0.00076937675,0.17533642,0.00079062633,0.0001754758,0.0004764239,0.010672886,0.0008006924,0.0191108],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99967885,0.00006500153,0.000019610827,0.00010160839,0.00007242577,0.000062417406],"domain_scores_gemma":[0.9997745,0.000040016166,0.0000079648125,0.00002225299,0.00014214823,0.000013050781],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000518236,0.0014315349,0.00048704166,0.00039316964,0.00029254664,0.00058918435,0.0008040484,0.00056610786,0.003389822],"category_scores_gemma":[0.0011018808,0.00028159824,0.00052551046,0.000235383,0.00019004385,0.00084474136,0.0006256239,0.0012164076,0.0028245973],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007978743,0.00048025418,0.0053024003,0.0002664252,0.0002781781,0.0002618563,0.00016533177,0.18912132,0.087607116,0.001611779,0.047048293,0.6670593],"study_design_scores_gemma":[0.00002601634,0.00010081754,0.0009747209,0.0000102798485,0.000024748471,0.000039248902,0.00003614761,0.9769766,0.018531255,0.00038907383,0.002874011,0.000017193619],"about_ca_topic_score_codex":0.014386345,"about_ca_topic_score_gemma":0.02074077,"teacher_disagreement_score":0.014386345,"about_ca_system_score_codex":0.00045278826,"about_ca_system_score_gemma":0.0006405501,"threshold_uncertainty_score":0.028605223},"labels":[],"label_agreement":null},{"id":"W4393770136","doi":"10.5281/zenodo.7356907","title":"LJ Speech - Aligned IPA transcriptions","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Speech recognition; Computer science; Natural language processing; Linguistics; Philosophy","score_opus":0.06039329554808336,"score_gpt":0.26344515785158457,"score_spread":0.2030518623035012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393770136","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040021916,0.00008111757,0.013302493,0.00023427667,0.000699587,0.00040123667,0.89359635,0.03785013,0.04983257],"genre_scores_gemma":[0.014587367,0.00012313157,0.018785303,0.00022618611,0.00034311615,0.00089397875,0.8935105,0.021962956,0.04956747],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99911433,0.000102609796,0.00009102756,0.00026720396,0.00033529912,0.000089519024],"domain_scores_gemma":[0.99593973,0.00089222036,0.000108737506,0.00081947,0.002078647,0.00016120893],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00059171906,0.0016827887,0.0008270332,0.0019320035,0.00088008575,0.0017436292,0.0011509367,0.00065043545,0.5184199],"category_scores_gemma":[0.0063656364,0.00062241405,0.0005585896,0.0025462273,0.0002889159,0.0012897386,0.0019123628,0.0012605422,0.46331996],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047577813,0.00005919594,0.000740787,0.0004278042,0.000015305945,0.00027915195,0.00021047895,0.00042353146,0.0053019044,0.00077977806,0.9203718,0.07091458],"study_design_scores_gemma":[0.00022332431,0.0001364156,0.011593628,0.00019509274,0.00003158306,0.00069243007,0.0006592036,0.002312592,0.018903162,0.0017166648,0.9634207,0.00011520192],"about_ca_topic_score_codex":0.0044196853,"about_ca_topic_score_gemma":0.00431712,"teacher_disagreement_score":0.5184199,"about_ca_system_score_codex":0.0005380082,"about_ca_system_score_gemma":0.0010526768,"threshold_uncertainty_score":0.6869155},"labels":[],"label_agreement":null},{"id":"W4393812211","doi":"10.5281/zenodo.7356908","title":"LJ Speech - Aligned IPA transcriptions","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Speech recognition; Computer science; Linguistics; Philosophy","score_opus":0.04805114250293462,"score_gpt":0.2514240244594909,"score_spread":0.20337288195655628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393812211","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0077128042,0.00015983245,0.03147472,0.00047648442,0.0020074847,0.0007781254,0.81277645,0.03658383,0.108030334],"genre_scores_gemma":[0.030300576,0.00025946816,0.053373344,0.00040410468,0.00065816264,0.0017678464,0.7859738,0.029752493,0.09751023],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990803,0.000110747234,0.000092977374,0.00027794208,0.0003551294,0.00008280825],"domain_scores_gemma":[0.9956691,0.0009941651,0.00010197628,0.00072271295,0.0023788335,0.00013316459],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005554879,0.0015691313,0.00066586316,0.0019033825,0.000852068,0.0016730536,0.0010772122,0.00070944155,0.45051062],"category_scores_gemma":[0.0078049507,0.0005305591,0.00051689765,0.0025826711,0.00035964028,0.0012283103,0.0019276197,0.0015507989,0.3515838],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00051430624,0.00006301463,0.0006552319,0.0007031214,0.000018059693,0.00046406305,0.00056053774,0.00048335386,0.009846515,0.0014652717,0.86581945,0.11940712],"study_design_scores_gemma":[0.00015157944,0.000117201016,0.010955285,0.00023990612,0.000029140076,0.0009010463,0.0011354659,0.002531835,0.019280443,0.0019309374,0.96260226,0.00012483909],"about_ca_topic_score_codex":0.0047509074,"about_ca_topic_score_gemma":0.0055961492,"teacher_disagreement_score":0.45051062,"about_ca_system_score_codex":0.0005116372,"about_ca_system_score_gemma":0.0010530655,"threshold_uncertainty_score":0.7837799},"labels":[],"label_agreement":null},{"id":"W4393818778","doi":"10.5281/zenodo.1219620","title":"A Canadian French Emotional Speech Dataset","year":2018,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Natural language processing; Speech recognition; Psychology; Computer science; Linguistics; Philosophy","score_opus":0.039420087785468606,"score_gpt":0.250193715978695,"score_spread":0.2107736281932264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393818778","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010716333,0.0014199822,0.001376947,0.0004709228,0.00034459232,0.00039198235,0.97305536,0.002555785,0.009668009],"genre_scores_gemma":[0.00564341,0.00023120145,0.0015165245,0.00011681374,0.000041430834,0.00030072563,0.98733497,0.00012253152,0.004692428],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99789786,0.00030751838,0.00011250941,0.00048205364,0.00077052007,0.00042946375],"domain_scores_gemma":[0.9977816,0.00026141136,0.0000583936,0.0003000614,0.0013773415,0.00022116912],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012325142,0.0046743425,0.0015869854,0.004484364,0.0033666412,0.0019936545,0.0036411951,0.0030269742,0.030304186],"category_scores_gemma":[0.0038741045,0.00045601086,0.0015514733,0.0036986577,0.0008842524,0.0010151312,0.0019758935,0.0020822375,0.033430424],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003703625,0.00015779107,0.0017871463,0.0006163227,0.0001065168,0.0003695542,0.00014731006,0.0009188428,0.0019925132,0.00073944934,0.96238285,0.030411404],"study_design_scores_gemma":[0.00028829658,0.00014369773,0.035322215,0.00043415438,0.00017477167,0.0011560111,0.00078904757,0.0065755406,0.004224601,0.0006714472,0.9500162,0.00020402581],"about_ca_topic_score_codex":0.60199136,"about_ca_topic_score_gemma":0.72408646,"teacher_disagreement_score":0.39800864,"about_ca_system_score_codex":0.0060471175,"about_ca_system_score_gemma":0.007859912,"threshold_uncertainty_score":0.8007052},"labels":[],"label_agreement":null},{"id":"W4393886693","doi":"10.5281/zenodo.7803316","title":"SASS-E: The Steelpan Audio Sample Set for Evaluation","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Sass; Sample (material); Set (abstract data type); Computer science; World Wide Web; Programming language; Physics","score_opus":0.11111893059939838,"score_gpt":0.31064814488988435,"score_spread":0.19952921429048598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393886693","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051604804,0.002965749,0.025765384,0.0010235655,0.0027759057,0.0027676558,0.8491624,0.035101086,0.028833432],"genre_scores_gemma":[0.018170709,0.0003565615,0.013425202,0.0002326649,0.00014420738,0.001536419,0.9586444,0.00069360423,0.006796211],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961545,0.0006404916,0.00040996703,0.00073681684,0.0017328091,0.00032546566],"domain_scores_gemma":[0.99621516,0.00068974186,0.0001431663,0.00090447697,0.0016837056,0.00036364727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029336964,0.003813845,0.0018023074,0.0034240037,0.001346813,0.002147035,0.0034156456,0.0020910676,0.036644865],"category_scores_gemma":[0.0094003845,0.00049350265,0.0018863676,0.0026291558,0.0008936214,0.0022454786,0.0028001815,0.0020215837,0.057519145],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001576807,0.0005794156,0.004024731,0.001603863,0.00023175064,0.00034277272,0.00016227525,0.002837572,0.008206145,0.0006942535,0.84383917,0.13590121],"study_design_scores_gemma":[0.0018959871,0.0023563907,0.07843565,0.001178572,0.000439156,0.002515511,0.0021812129,0.05099946,0.023881605,0.0038781392,0.8317064,0.00053188653],"about_ca_topic_score_codex":0.019471377,"about_ca_topic_score_gemma":0.032502145,"teacher_disagreement_score":0.036644865,"about_ca_system_score_codex":0.0015156766,"about_ca_system_score_gemma":0.0023122896,"threshold_uncertainty_score":0.12258935},"labels":[],"label_agreement":null},{"id":"W4394168003","doi":"10.6084/m9.figshare.21431332","title":"Creating a Large-Scale Audio-Aligned Parsed Corpus of Bilingual Russian Child and Child-Directed Speech (BiRCh): Challenges, Solutions, and Implications for Research","year":2022,"lang":"en","type":"dataset","venue":"Figshare","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Parsing; Scale (ratio); Linguistics; Computer science; Psychology; Natural language processing; Geography; Cartography","score_opus":0.12727723665928403,"score_gpt":0.3427014884403706,"score_spread":0.2154242517810866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394168003","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0975884,0.0010386409,0.009035536,0.0009542544,0.00041451756,0.0007687804,0.87722254,0.0045323065,0.008445012],"genre_scores_gemma":[0.023141634,0.00012527397,0.010512846,0.000107203305,0.00002935167,0.0011474618,0.96277064,0.00020075543,0.001964828],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974026,0.000948966,0.00025896667,0.0006629825,0.0004673463,0.00025906545],"domain_scores_gemma":[0.9956611,0.0017461983,0.00022493998,0.0010157261,0.0010290875,0.00032303805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003052681,0.0010957766,0.00092032546,0.0032043334,0.001556179,0.0013753788,0.0019984827,0.001879453,0.009849786],"category_scores_gemma":[0.005824489,0.00058414054,0.000696224,0.002821377,0.0009503714,0.0010774153,0.0031042134,0.0018337048,0.010745422],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016664588,0.0010125712,0.025585419,0.0042447266,0.00031988806,0.002568693,0.0036388566,0.005657091,0.031264342,0.0059327376,0.77524483,0.1428644],"study_design_scores_gemma":[0.00092670013,0.00035946185,0.16705255,0.00057537213,0.00020896805,0.0020565898,0.006260606,0.014077153,0.015790425,0.003288528,0.78908616,0.0003174373],"about_ca_topic_score_codex":0.030965133,"about_ca_topic_score_gemma":0.06513595,"teacher_disagreement_score":0.030965133,"about_ca_system_score_codex":0.0014806716,"about_ca_system_score_gemma":0.0022407894,"threshold_uncertainty_score":0.06156975},"labels":[],"label_agreement":null},{"id":"W4394938944","doi":"10.1109/tifs.2024.3390990","title":"On the Impact of Voice Anonymization on Speech Diagnostic Applications: A Case Study on COVID-19 Detection","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Information Forensics and Security","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Institut national de la recherche scientifique","keywords":"Computer science; Speech recognition; Coronavirus disease 2019 (COVID-19); Artificial intelligence; Medicine","score_opus":0.021931389801271156,"score_gpt":0.28886692742062026,"score_spread":0.2669355376193491,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394938944","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81162196,0.006858955,0.15962529,0.0060113287,0.0013188724,0.0008050254,0.0018948958,0.0043581296,0.0075055053],"genre_scores_gemma":[0.9504455,0.0010648385,0.04323019,0.0011464707,0.00023946888,0.00012875661,0.0019157876,0.00021067214,0.0016183192],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9858568,0.0071209017,0.0010579936,0.0018839255,0.003404009,0.00067641074],"domain_scores_gemma":[0.9651559,0.025011767,0.0019267913,0.0047076214,0.0026749354,0.0005229661],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008816604,0.0010667075,0.00085150555,0.0013145937,0.0014658651,0.0019603597,0.0014047794,0.002499821,0.0007859995],"category_scores_gemma":[0.04105953,0.00025641095,0.0005080161,0.0009283645,0.0018646572,0.0023554796,0.0026154872,0.0018209751,0.0008431214],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005224491,0.0013302405,0.1087086,0.002641526,0.0008077605,0.013773278,0.0055883704,0.11419209,0.073798515,0.015359335,0.04344323,0.6151326],"study_design_scores_gemma":[0.00039849532,0.0028368293,0.060148954,0.0010042026,0.00065064454,0.03403681,0.0061194464,0.48515156,0.29777926,0.026900096,0.08453027,0.00044336813],"about_ca_topic_score_codex":0.0021412107,"about_ca_topic_score_gemma":0.0021784946,"teacher_disagreement_score":0.008816604,"about_ca_system_score_codex":0.0010281933,"about_ca_system_score_gemma":0.00086618774,"threshold_uncertainty_score":0.046627223},"labels":[],"label_agreement":null},{"id":"W4394983439","doi":"10.4995/eurocall2023.2023.16987","title":"Assessing Google Translate ASR for feedback on L2 pronunciation errors in unpredictable sentence contexts","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Concordia University; Université du Québec à Trois-Rivières","funders":"","keywords":"Pronunciation; Sentence; Computer science; Speech recognition; Transcription (linguistics); Vowel; Context (archaeology); Natural language processing; Phonetic transcription; Corrective feedback; Word (group theory); Psychology; Artificial intelligence; Linguistics","score_opus":0.05796951542897077,"score_gpt":0.31790759372116867,"score_spread":0.2599380782921979,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394983439","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98993087,0.00015528133,0.003293343,0.00012089401,0.000046645036,0.00011957845,0.0014181373,0.00082874735,0.0040864972],"genre_scores_gemma":[0.9913054,0.00008859011,0.0039258082,0.000079914746,0.000021342417,0.00010494542,0.0013607778,0.00018654864,0.0029265366],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99717677,0.0010055377,0.00015949523,0.00045568598,0.0010124437,0.00019001352],"domain_scores_gemma":[0.985033,0.005381401,0.0011971203,0.0009524289,0.0069472273,0.0004888239],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031490957,0.0010759209,0.0004485073,0.00070206565,0.00042176383,0.00087607186,0.0005289544,0.00063997257,0.0042232033],"category_scores_gemma":[0.017364612,0.00021076245,0.00021637605,0.00037024735,0.00049079774,0.0004152004,0.00070875493,0.0003158748,0.0033077206],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004789054,0.00031261836,0.3176794,0.0011184169,0.00016695062,0.0022717458,0.02399433,0.003747807,0.30318692,0.00019682627,0.0074959174,0.33504006],"study_design_scores_gemma":[0.00007443921,0.001680112,0.91253215,0.00011841645,0.00010828857,0.0014089652,0.0070570945,0.008415598,0.05911884,0.00008204649,0.009250955,0.00015300584],"about_ca_topic_score_codex":0.04326699,"about_ca_topic_score_gemma":0.07569381,"teacher_disagreement_score":0.04326699,"about_ca_system_score_codex":0.00073461764,"about_ca_system_score_gemma":0.00092264556,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W4395110276","doi":"10.18280/ria.380218","title":"ASER: An Exhaustive Survey for Speech Recognition based on Methods, Datasets, Challenges, Future Scope","year":2024,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Scope (computer science); Computer science; Speech recognition; Artificial intelligence; Pattern recognition (psychology); Data science; Machine learning","score_opus":0.18043312639973536,"score_gpt":0.3757627437728945,"score_spread":0.19532961737315913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395110276","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019727621,0.47104633,0.41297317,0.0064655035,0.005984782,0.0016025731,0.030752318,0.028400844,0.023046803],"genre_scores_gemma":[0.06614328,0.32989004,0.39255446,0.006133882,0.0072064805,0.0035059557,0.1690294,0.0052215722,0.020314895],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9844164,0.004557722,0.002416336,0.0028472252,0.0052545876,0.00050770806],"domain_scores_gemma":[0.9684446,0.019542584,0.00083911885,0.004669875,0.005854328,0.0006495355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01646839,0.003954913,0.0059983935,0.011190555,0.0011370238,0.00650089,0.005366105,0.0034153068,0.010660415],"category_scores_gemma":[0.034268476,0.001199837,0.0029454457,0.0064510573,0.0012972954,0.011274979,0.004525316,0.0034818703,0.017432256],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000425159,0.00025377914,0.0025052098,0.00542078,0.00026519844,0.000067322166,0.00010860372,0.0021847484,0.0044982745,0.0020352337,0.056040958,0.92619485],"study_design_scores_gemma":[0.0001940122,0.001753637,0.018990822,0.0066513536,0.0013271401,0.002445401,0.0013342017,0.10404188,0.035568755,0.019059092,0.8079539,0.00067987974],"about_ca_topic_score_codex":0.0038879062,"about_ca_topic_score_gemma":0.0039642975,"teacher_disagreement_score":0.01646839,"about_ca_system_score_codex":0.0011499932,"about_ca_system_score_gemma":0.0042209597,"threshold_uncertainty_score":0.08709419},"labels":[],"label_agreement":null},{"id":"W4398228866","doi":"10.21437/odyssey.2024-9","title":"A Phonetic Analysis of Speaker Verification Systems through Phoneme selection and Integrated Gradients","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Grand Équipement National De Calcul Intensif; European Commission; Johns Hopkins University","keywords":"Computer science; Speaker verification; Selection (genetic algorithm); Speech recognition; Natural language processing; Artificial intelligence; Speaker recognition","score_opus":0.021236749597744672,"score_gpt":0.25224738282100323,"score_spread":0.23101063322325854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398228866","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5828171,0.0005812556,0.4112755,0.00015495521,0.00003142332,0.00012315452,0.00030770435,0.001975951,0.0027329605],"genre_scores_gemma":[0.91639876,0.00011305225,0.08092675,0.00002880547,0.000012895252,0.000043839987,0.00041709,0.00013441275,0.0019244036],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994691,0.000094588475,0.000032314507,0.000115543495,0.00022083693,0.00006776419],"domain_scores_gemma":[0.99905676,0.00042156887,0.000077585646,0.00009880615,0.0003130682,0.000032244512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075785967,0.00045004912,0.00038101504,0.00092299504,0.0003219997,0.00068654557,0.00030727955,0.00027706168,0.0017030817],"category_scores_gemma":[0.0024128465,0.00021876457,0.00032196715,0.00037402802,0.00033783593,0.00065287435,0.00041138195,0.00037003896,0.00045722115],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016646069,0.00018073134,0.016312664,0.00015081822,0.00014207923,0.0002695884,0.00037367758,0.06079682,0.40013397,0.003970442,0.00097298005,0.5150316],"study_design_scores_gemma":[0.00003665026,0.0007607679,0.06494395,0.000015945803,0.00006865288,0.00033627037,0.00015148765,0.7629711,0.16681184,0.0018812524,0.0019600024,0.00006206366],"about_ca_topic_score_codex":0.0069944467,"about_ca_topic_score_gemma":0.0069847098,"teacher_disagreement_score":0.0069944467,"about_ca_system_score_codex":0.00040040337,"about_ca_system_score_gemma":0.0005013812,"threshold_uncertainty_score":0.013907492},"labels":[],"label_agreement":null},{"id":"W4399527282","doi":"10.1109/taffc.2024.3412152","title":"Controllable Multi-Speaker Emotional Speech Synthesis With an Emotion Representation of High Generalization Capability","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Affective Computing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Science Foundation of Anhui Province; National Natural Science Foundation of China","keywords":"Generalization; Speech recognition; Emotion recognition; Representation (politics); Speaker recognition; Computer science; Emotion classification; Psychology; Artificial intelligence; Mathematics","score_opus":0.02894511557105801,"score_gpt":0.27953085991835863,"score_spread":0.25058574434730063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399527282","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028451826,0.000120187426,0.96906203,0.000046062774,0.000041858482,0.00003282913,0.000039504474,0.0007626686,0.0014430637],"genre_scores_gemma":[0.5592787,0.00019613128,0.4351215,0.0001304269,0.00006751691,0.0001717627,0.0002588511,0.00028461515,0.0044904323],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99981505,0.000038077786,0.000011305398,0.00006819562,0.000052983018,0.000014354386],"domain_scores_gemma":[0.9998596,0.00005225832,0.00001669343,0.000027943814,0.00003422279,0.000009269274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002670975,0.00045514383,0.00026390527,0.000121066834,0.00010941819,0.0002608842,0.00032795867,0.00024849366,0.0017562372],"category_scores_gemma":[0.00045860306,0.00012960154,0.00047414732,0.00008422615,0.00020597834,0.00036456765,0.00051848014,0.0004697411,0.0005529528],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024921008,0.00006928647,0.00028467603,0.00011885592,0.000044209864,0.00013051678,0.00015919218,0.03868915,0.7444557,0.0035448733,0.00077962223,0.21147476],"study_design_scores_gemma":[0.000029638764,0.00023167259,0.0009400129,0.000011432735,0.000043392796,0.00020820876,0.000038389884,0.7492401,0.2422705,0.0022271918,0.004733151,0.000026378868],"about_ca_topic_score_codex":0.0003149432,"about_ca_topic_score_gemma":0.0004133358,"teacher_disagreement_score":0.0017562372,"about_ca_system_score_codex":0.0001207864,"about_ca_system_score_gemma":0.0001222121,"threshold_uncertainty_score":0.00587523},"labels":[],"label_agreement":null},{"id":"W4400041227","doi":"10.18280/ts.410344","title":"Effect of Data Augmentation, Cross-Validation Methods in Robustness of Explainable Speech Based Emotion Recognition","year":2024,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Robustness (evolution); Speech recognition; Emotion recognition; Computer science; Artificial intelligence; Pattern recognition (psychology)","score_opus":0.07659052623993555,"score_gpt":0.3903428242834736,"score_spread":0.31375229804353805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400041227","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.434423,0.0055634235,0.54981154,0.00053799496,0.00093946094,0.0005234621,0.000796924,0.004289391,0.0031148212],"genre_scores_gemma":[0.88566566,0.00033019632,0.109296486,0.00024747715,0.00006749351,0.00038842126,0.0022609457,0.0003045804,0.0014388368],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.98886615,0.0062036403,0.0011840764,0.0019196277,0.0015302431,0.00029623896],"domain_scores_gemma":[0.9793825,0.012722366,0.0010562622,0.0033750208,0.0032308279,0.00023305326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021299107,0.0014927776,0.0009978281,0.0007914361,0.00072661805,0.001304419,0.0012604888,0.0013523548,0.0011254477],"category_scores_gemma":[0.03458504,0.00035001038,0.0010574647,0.0005463132,0.0008882318,0.0010490502,0.00127231,0.0013097584,0.00055564835],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0041795895,0.001605149,0.046390876,0.0009671903,0.0016825034,0.0006230282,0.0008046368,0.25092202,0.061832037,0.0028079816,0.005752128,0.6224329],"study_design_scores_gemma":[0.00011508254,0.00094648654,0.019692432,0.00017651316,0.00026576547,0.0003615722,0.000185665,0.9212129,0.051889542,0.0015899992,0.003478365,0.00008566386],"about_ca_topic_score_codex":0.0020471711,"about_ca_topic_score_gemma":0.001481793,"teacher_disagreement_score":0.021299107,"about_ca_system_score_codex":0.00046623126,"about_ca_system_score_gemma":0.00087694125,"threshold_uncertainty_score":0.11264181},"labels":[],"label_agreement":null},{"id":"W4400255094","doi":"10.20944/preprints202406.2082.v1","title":"TIPAA-SSL: Text Independent Phone-to-Audio Alignment based on Self-Supervised Learning and Knowledge Transfer","year":2024,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Phone; Speech recognition; Artificial intelligence; TIMIT; Classifier (UML); Transfer of learning; Natural language processing; Frame (networking); Hidden Markov model","score_opus":0.07535121666241719,"score_gpt":0.3170469676804163,"score_spread":0.24169575101799912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400255094","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012603478,0.00046174158,0.9499933,0.00019141952,0.00033669677,0.00015722631,0.00079727336,0.032116413,0.00334246],"genre_scores_gemma":[0.29223132,0.00033132086,0.66932464,0.0008709751,0.00045576002,0.000668421,0.008650369,0.0026616135,0.02480559],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984529,0.0003446806,0.000076032346,0.00061464094,0.00038121967,0.0001304347],"domain_scores_gemma":[0.99823856,0.00045526243,0.00011839663,0.0006400535,0.00044234988,0.00010536944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012968737,0.0015075218,0.0012360128,0.001271097,0.0006915478,0.0012865853,0.0032488713,0.0019726746,0.008280744],"category_scores_gemma":[0.0038390649,0.00061535835,0.00110913,0.0011715775,0.0007697128,0.0033132571,0.0026750024,0.0025471237,0.0114736045],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004087636,0.00048368363,0.0009661736,0.0001869232,0.00014936738,0.00018321375,0.00014062496,0.051371835,0.023076322,0.0033955744,0.028896974,0.89074045],"study_design_scores_gemma":[0.000044811015,0.00015331748,0.00052368856,0.000016702183,0.000030235611,0.00012011669,0.000043269065,0.9644867,0.020085994,0.007232197,0.0072295116,0.000033457432],"about_ca_topic_score_codex":0.0033752504,"about_ca_topic_score_gemma":0.0057852827,"teacher_disagreement_score":0.008280744,"about_ca_system_score_codex":0.00061236374,"about_ca_system_score_gemma":0.0013152988,"threshold_uncertainty_score":0.027701855},"labels":[],"label_agreement":null},{"id":"W4400285258","doi":"10.1121/10.0027483","title":"Perception of speaker identity for bilingual voices","year":2024,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Identity (music); Perception; Linguistics; Psychology; Communication; Speech recognition; Computer science; Art; Aesthetics","score_opus":0.022300024452987864,"score_gpt":0.2975020187165441,"score_spread":0.27520199426355624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400285258","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9981183,0.000048855367,0.00040909788,0.000021460506,0.000007528549,0.0000046952014,0.00002347305,0.0000058228234,0.0013607957],"genre_scores_gemma":[0.99909675,0.0000393303,0.00032961243,0.000025144689,0.0000055508244,0.0000048307456,0.000047152633,0.000004806542,0.00044690608],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9997818,0.000046506666,0.000015460742,0.000049558523,0.00008025553,0.000026495869],"domain_scores_gemma":[0.9993788,0.0002358817,0.00011054319,0.000036872458,0.00012780992,0.00011005722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041505537,0.0001934779,0.00021141012,0.0002133714,0.00030885646,0.00056991226,0.000069449015,0.00023215543,0.0028064675],"category_scores_gemma":[0.0022240789,0.00007570705,0.00014420705,0.00006474749,0.00023834778,0.00035612934,0.0005821926,0.00020135462,0.00032586086],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006102229,0.00015992811,0.06891783,0.00015478369,0.000047704365,0.00044029646,0.006400942,0.00015097047,0.8788179,0.00032457736,0.0002413491,0.038241517],"study_design_scores_gemma":[0.00017568328,0.0019067986,0.92209053,0.00003807063,0.00010759293,0.0018141875,0.01111917,0.0027830023,0.058022913,0.000700509,0.001182556,0.000058972037],"about_ca_topic_score_codex":0.0012432294,"about_ca_topic_score_gemma":0.0020320301,"teacher_disagreement_score":0.0028064675,"about_ca_system_score_codex":0.00017895407,"about_ca_system_score_gemma":0.00016054031,"threshold_uncertainty_score":0.009388506},"labels":[],"label_agreement":null},{"id":"W4400285553","doi":"10.1121/10.0027487","title":"Detecting ringed seal vocalizations in multiple environments using deep learning","year":2024,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Dalhousie University; Wildlife Conservation Society Canada; University of Victoria","funders":"","keywords":"Seal (emblem); Computer science; Deep learning; Artificial intelligence; Human–computer interaction; Geography; Archaeology","score_opus":0.025504177123565903,"score_gpt":0.2571948778182838,"score_spread":0.23169070069471792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400285553","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8258272,0.0009353122,0.16545041,0.00022671347,0.0001647544,0.00005523905,0.0007961086,0.0027207292,0.0038235944],"genre_scores_gemma":[0.93881136,0.00019997872,0.055694927,0.0000855701,0.000033912238,0.00003321289,0.0013282832,0.00007620756,0.003736663],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996356,0.00005702403,0.000013372536,0.00015590194,0.00007200715,0.000066208486],"domain_scores_gemma":[0.99963045,0.00013945706,0.000048288923,0.00004233694,0.000096413525,0.00004301911],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007437571,0.00074314,0.00048075456,0.0008895781,0.0003239861,0.00047271606,0.00047431278,0.00046619104,0.0009834559],"category_scores_gemma":[0.0010505589,0.00031146038,0.00040162992,0.00030767237,0.00027577375,0.0006043703,0.001058745,0.00053443096,0.000558744],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005800547,0.0003776724,0.09938657,0.00023912155,0.00038438378,0.00075302913,0.0007255505,0.11154031,0.13797362,0.001116709,0.0061316313,0.6407913],"study_design_scores_gemma":[0.000020975867,0.0001989687,0.059762027,0.000043424352,0.00007650317,0.00027608348,0.00037552882,0.89075434,0.043996904,0.0012795771,0.0031729243,0.000042723652],"about_ca_topic_score_codex":0.011205238,"about_ca_topic_score_gemma":0.027513465,"teacher_disagreement_score":0.011205238,"about_ca_system_score_codex":0.0004624953,"about_ca_system_score_gemma":0.00047059602,"threshold_uncertainty_score":0.022280037},"labels":[],"label_agreement":null},{"id":"W4400288586","doi":"10.1121/10.0027199","title":"Quantifying vowel category distinctness using Bayesian modelling","year":2024,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Bayesian probability; Vowel; Computer science; Bayesian inference; Artificial intelligence; Statistics; Natural language processing; Speech recognition; Mathematics","score_opus":0.05836696820019907,"score_gpt":0.2929317606397118,"score_spread":0.23456479243951275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400288586","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056391828,0.0002007883,0.9398688,0.00024619687,0.000021804834,0.00007214123,0.00028630893,0.00035838177,0.0025538085],"genre_scores_gemma":[0.56680644,0.00017347516,0.42838174,0.00018352969,0.00004805237,0.00031757227,0.0011479963,0.00030801728,0.002633251],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9946849,0.0024871696,0.00027004807,0.0014112688,0.00090884476,0.00023782412],"domain_scores_gemma":[0.9834298,0.013010112,0.0010021925,0.0013270831,0.0009477712,0.00028306257],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012047018,0.0009972682,0.0011810467,0.002743662,0.0013501967,0.0042594136,0.0026185464,0.0020959496,0.0044262027],"category_scores_gemma":[0.0440116,0.0010735737,0.0020009999,0.002280683,0.0017846981,0.004510142,0.0041692285,0.0028123653,0.0010023033],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005577356,0.0002841797,0.05774894,0.00037377072,0.000806501,0.00025890395,0.0060672257,0.36339846,0.0105218915,0.2642033,0.0040915497,0.2916876],"study_design_scores_gemma":[0.000027167662,0.000049808586,0.010857327,0.00007033817,0.00007011868,0.00013413646,0.00030010476,0.8225335,0.0009690628,0.1614019,0.0034847308,0.00010186819],"about_ca_topic_score_codex":0.015820857,"about_ca_topic_score_gemma":0.027403465,"teacher_disagreement_score":0.015820857,"about_ca_system_score_codex":0.0015917282,"about_ca_system_score_gemma":0.0015610965,"threshold_uncertainty_score":0.063711524},"labels":[],"label_agreement":null},{"id":"W4400292625","doi":"10.31234/osf.io/vufw4","title":"Establishing the reliability of metrics extracted from long-form recordings using LENA and the ACLEW pipeline","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada; Grand Équipement National De Calcul Intensif; European Commission; China Scholarship Council; National Institutes of Health; National Science Foundation; James S. McDonnell Foundation; Agence Nationale de la Recherche","keywords":"Pipeline (software); Reliability (semiconductor); Computer science; Reliability engineering; Statistics; Mathematics; Engineering; Physics; Programming language","score_opus":0.04114783272527828,"score_gpt":0.27198729144373485,"score_spread":0.23083945871845657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400292625","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.701572,0.0010482465,0.26629996,0.00041788563,0.00043128442,0.0007040709,0.0085778395,0.010073071,0.0108756805],"genre_scores_gemma":[0.7838874,0.00025650684,0.1892051,0.00017952344,0.0001110546,0.0016297409,0.01751013,0.0029012435,0.004319395],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.98790956,0.0030918813,0.0018310073,0.003798142,0.0027512312,0.00061812653],"domain_scores_gemma":[0.9512284,0.019674122,0.0036429286,0.0067181014,0.017963823,0.0007726246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016712246,0.0012853452,0.0008865517,0.004386604,0.0009630687,0.0029876444,0.0015264018,0.0011723768,0.00332024],"category_scores_gemma":[0.06458679,0.00054832635,0.0008204588,0.0023030885,0.0015207634,0.002702645,0.003622716,0.0012617373,0.0033662736],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017523214,0.00033334497,0.2632215,0.0017237536,0.0011423972,0.0007135204,0.01392407,0.00892969,0.10920168,0.0037033972,0.020542651,0.5748116],"study_design_scores_gemma":[0.00012649488,0.00074239814,0.7781866,0.00046478826,0.0003810017,0.0012061573,0.006334795,0.09633265,0.061454903,0.0056846724,0.048589554,0.00049607374],"about_ca_topic_score_codex":0.005015562,"about_ca_topic_score_gemma":0.010560116,"teacher_disagreement_score":0.016712246,"about_ca_system_score_codex":0.000675886,"about_ca_system_score_gemma":0.0011402387,"threshold_uncertainty_score":0.08838385},"labels":[],"label_agreement":null},{"id":"W4400527917","doi":"10.1109/fg59268.2024.10582047","title":"Distilling Privileged Multimodal Information for Expression Recognition using Optimal Transport","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; École de Technologie Supérieure","funders":"","keywords":"Computer science; Expression (computer science); Multimodal transport; Artificial intelligence; Human–computer interaction; Engineering; Transport engineering; Programming language","score_opus":0.040758615026911874,"score_gpt":0.2714358269321869,"score_spread":0.23067721190527501,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400527917","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03863863,0.00014712563,0.9583259,0.00021502655,0.00003167525,0.000033204684,0.00008110858,0.0014333345,0.0010940307],"genre_scores_gemma":[0.7937037,0.00022317802,0.20080338,0.00017975511,0.00004020192,0.00011247479,0.00039668262,0.00035909406,0.0041814987],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994978,0.000106185835,0.00003910749,0.00015382346,0.0001232159,0.00007986812],"domain_scores_gemma":[0.9992767,0.00028561207,0.00009440393,0.00018538735,0.00010938719,0.000048654332],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012629571,0.00090699946,0.0010263011,0.00080045534,0.00065565447,0.00129686,0.0016769392,0.0012152033,0.002755394],"category_scores_gemma":[0.0035508857,0.00043790112,0.001086689,0.0008553084,0.0013439404,0.004486082,0.0029072424,0.0020261672,0.00070841523],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005285413,0.0001745181,0.001476184,0.00012666023,0.00007512197,0.00015503116,0.00030823177,0.56362313,0.03369479,0.051422335,0.0026827515,0.34573275],"study_design_scores_gemma":[0.000007397858,0.000029002427,0.0000764142,0.0000043975097,0.0000060302273,0.000018017001,0.000018350169,0.98229873,0.0061700754,0.010836079,0.0005265111,0.000009027615],"about_ca_topic_score_codex":0.0049880766,"about_ca_topic_score_gemma":0.0033139705,"teacher_disagreement_score":0.0049880766,"about_ca_system_score_codex":0.0016017068,"about_ca_system_score_gemma":0.0012558228,"threshold_uncertainty_score":0.011621296},"labels":[],"label_agreement":null},{"id":"W4400910594","doi":"10.1109/ic3se62002.2024.10593399","title":"Exploring the Effectiveness of Advanced Machine Learning Models in Speech Emotion Recognition","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Speech recognition; Emotion recognition; Natural language processing; Artificial intelligence","score_opus":0.10295351290849031,"score_gpt":0.2651108309336718,"score_spread":0.16215731802518152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400910594","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8340685,0.0054067373,0.15025495,0.0008911155,0.00025690693,0.00014539322,0.00040850256,0.0009775847,0.0075902455],"genre_scores_gemma":[0.95883447,0.00088058977,0.03865342,0.00007303865,0.000042550448,0.00004281638,0.00032930443,0.000030332736,0.0011134739],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988072,0.000595088,0.00009394384,0.00017544629,0.00022945376,0.000098902885],"domain_scores_gemma":[0.99571204,0.0034304294,0.00013119601,0.00017634382,0.00049631053,0.000053811218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032603026,0.0011089784,0.0005658654,0.0008044615,0.0002326804,0.0013038862,0.0005893641,0.0009081396,0.0013072852],"category_scores_gemma":[0.0078416,0.00022885686,0.00059643056,0.0004440702,0.00023793225,0.0018439483,0.0004472336,0.00080463814,0.00053454505],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019940252,0.0007597694,0.019984934,0.00039835367,0.00050432555,0.00012488107,0.00022945192,0.4611535,0.015705483,0.002346898,0.001529638,0.49526873],"study_design_scores_gemma":[0.000014195478,0.00048209354,0.0025148499,0.000022929216,0.000050113253,0.000030017456,0.00006058439,0.99094814,0.0049059344,0.00057558843,0.00038046268,0.0000149753505],"about_ca_topic_score_codex":0.0051483274,"about_ca_topic_score_gemma":0.004440744,"teacher_disagreement_score":0.0051483274,"about_ca_system_score_codex":0.00060192886,"about_ca_system_score_gemma":0.00040459237,"threshold_uncertainty_score":0.017242312},"labels":[],"label_agreement":null},{"id":"W4400926002","doi":"10.1007/s11042-024-19892-4","title":"Deep normalization for light SpineNet speaker anti-spoofing systems","year":2024,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Normalization (sociology); Speaker verification; Speech recognition; Artificial intelligence; Spoofing attack; Computer security; Speaker recognition","score_opus":0.02683028761416486,"score_gpt":0.26277609325179724,"score_spread":0.23594580563763237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400926002","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055326313,0.0011081467,0.92581105,0.00052885123,0.00038688816,0.000105305255,0.0011971575,0.006791689,0.008744674],"genre_scores_gemma":[0.55904686,0.0009760457,0.39386043,0.0006011727,0.00024051538,0.00019803282,0.0047927424,0.00086456357,0.039419666],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99959284,0.000047731646,0.000019480882,0.00010093828,0.00014894412,0.000090095426],"domain_scores_gemma":[0.9996526,0.00006911254,0.00002316312,0.000057026962,0.00017594494,0.00002220614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066143606,0.0010330476,0.000681893,0.0009026002,0.00065850693,0.00094508985,0.0009127394,0.00073485577,0.008560459],"category_scores_gemma":[0.0011344807,0.00036256743,0.0005639338,0.0006349128,0.0003829218,0.00092588365,0.0011722646,0.0012019738,0.0040736473],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005452274,0.00018059116,0.00095897116,0.000114717615,0.00008340864,0.0001043996,0.00006930611,0.04548016,0.076522216,0.0054205726,0.010419838,0.86010057],"study_design_scores_gemma":[0.00001942022,0.00012902127,0.0019738297,0.000032724725,0.00006154189,0.0001131989,0.00005564323,0.90665686,0.07468625,0.00545734,0.010782238,0.000031879375],"about_ca_topic_score_codex":0.010134395,"about_ca_topic_score_gemma":0.026541157,"teacher_disagreement_score":0.010134395,"about_ca_system_score_codex":0.00084118627,"about_ca_system_score_gemma":0.0014556069,"threshold_uncertainty_score":0.028637528},"labels":[],"label_agreement":null},{"id":"W4401072402","doi":"10.1109/memea60663.2024.10596816","title":"Zero-Shot Multi-Task Cough Sound Analysis with Speech Foundation Model Embeddings","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; Carleton University","funders":"National Research Council Canada","keywords":"Zero (linguistics); Computer science; Task (project management); Speech recognition; Foundation (evidence); One shot; Shot (pellet); Acoustics; Physics; Engineering","score_opus":0.05202535987894881,"score_gpt":0.302398923194524,"score_spread":0.2503735633155752,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401072402","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23485494,0.0009647325,0.7556551,0.0005328135,0.00024844217,0.00012465383,0.0008162622,0.0038227336,0.0029804064],"genre_scores_gemma":[0.93113124,0.00019196028,0.06250256,0.00022005563,0.000082279534,0.000112302994,0.0016355244,0.00016343434,0.003960701],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996588,0.00007917746,0.000018571815,0.00012368764,0.000057269026,0.00006245993],"domain_scores_gemma":[0.99923575,0.00039071764,0.00006229634,0.00012622864,0.00012626476,0.00005875379],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070701947,0.0009911489,0.0006831335,0.000398927,0.0002843395,0.0006967796,0.00086309365,0.0010222698,0.0019950077],"category_scores_gemma":[0.0024717106,0.00031515164,0.0007821547,0.00031644112,0.0003746147,0.0014106528,0.0012110013,0.0015350787,0.0010718013],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011503189,0.00063008326,0.005730802,0.00037923057,0.00020502105,0.00032833428,0.00031997747,0.2779364,0.048874974,0.0036957604,0.0072559356,0.65349317],"study_design_scores_gemma":[0.000010841414,0.00011070196,0.0010251873,0.000010600367,0.000016007252,0.000052280637,0.000046781493,0.9905742,0.00522179,0.0024431841,0.00047441563,0.000014121649],"about_ca_topic_score_codex":0.002528635,"about_ca_topic_score_gemma":0.004302907,"teacher_disagreement_score":0.002528635,"about_ca_system_score_codex":0.00042929646,"about_ca_system_score_gemma":0.0006222652,"threshold_uncertainty_score":0.006673932},"labels":[],"label_agreement":null},{"id":"W4401110548","doi":"10.1109/cai59869.2024.00186","title":"On the influence of metric learning loss functions for robust self-supervised speaker verification to label noise","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Computer science; Metric (unit); Speech recognition; Noise (video); Speaker verification; Speaker recognition; Artificial intelligence; Robustness (evolution); Pattern recognition (psychology); Engineering","score_opus":0.035839557899245124,"score_gpt":0.2552282605859905,"score_spread":0.2193887026867454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401110548","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19358341,0.0019372829,0.79781085,0.00079016865,0.00014179474,0.0002042259,0.00013530457,0.0015247184,0.0038722255],"genre_scores_gemma":[0.8041386,0.00071268436,0.19135845,0.00044605773,0.00009408022,0.00020028665,0.0005014763,0.0004107878,0.0021376812],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9942807,0.0033825901,0.00024283066,0.00084503036,0.0010258869,0.00022294214],"domain_scores_gemma":[0.98260605,0.012453073,0.0008385846,0.0017878754,0.0019963325,0.00031808447],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0136994235,0.0019374627,0.001071471,0.0008253236,0.0007460276,0.0013853592,0.001615856,0.0016524334,0.0009584182],"category_scores_gemma":[0.03449799,0.00036254825,0.0006278289,0.0005440657,0.0019452058,0.0024880974,0.001877301,0.0023166058,0.00048771276],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010201449,0.00043037697,0.0044592107,0.00029457072,0.00026275154,0.00015568109,0.00018993668,0.7580623,0.02542807,0.008185147,0.0028242394,0.19868757],"study_design_scores_gemma":[0.000019996902,0.00030956295,0.0011039518,0.000036373942,0.000024161849,0.0000925504,0.000034370434,0.9833309,0.012927809,0.0015894251,0.00050700724,0.000024012352],"about_ca_topic_score_codex":0.0030011253,"about_ca_topic_score_gemma":0.0027889805,"teacher_disagreement_score":0.0136994235,"about_ca_system_score_codex":0.0010583542,"about_ca_system_score_gemma":0.001193601,"threshold_uncertainty_score":0.07245034},"labels":[],"label_agreement":null},{"id":"W4401281176","doi":"10.1016/j.csl.2024.101695","title":"Speech self-supervised representations benchmarking: A case for larger probing heads","year":2024,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Mila - Quebec Artificial Intelligence Institute","funders":"Agence de l'innovation de Défense","keywords":"Benchmarking; Computer science; Ranking (information retrieval); Inference; Task (project management); Downstream (manufacturing); Generalization; Feature (linguistics); Set (abstract data type); Artificial intelligence; Architecture; Machine learning; Benchmark (surveying); Data set; Natural language processing","score_opus":0.02313783000429004,"score_gpt":0.2944255563429296,"score_spread":0.27128772633863957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401281176","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28022808,0.0017372124,0.6750554,0.0030275262,0.0008945772,0.00056667026,0.0023794996,0.020586703,0.015524325],"genre_scores_gemma":[0.8184054,0.00016002155,0.16932388,0.00094455096,0.00013987883,0.00032672333,0.0040117335,0.0022525375,0.0044352217],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.98765045,0.0060689505,0.0006856744,0.0023268335,0.002479623,0.00078838604],"domain_scores_gemma":[0.9627472,0.017892353,0.0007019229,0.012053394,0.0056910906,0.0009140311],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014434551,0.0010577983,0.0018579422,0.0008149768,0.0012735862,0.0025173812,0.00396877,0.0032402987,0.010965627],"category_scores_gemma":[0.062120564,0.0004530371,0.00068642455,0.0012091451,0.0018207714,0.0050551924,0.0047403225,0.0025604141,0.002778806],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027788756,0.0010286814,0.012374251,0.0007342944,0.0003583696,0.0007450592,0.0014298514,0.11561867,0.046311706,0.016393734,0.030144945,0.7720816],"study_design_scores_gemma":[0.0002108743,0.0016536199,0.011882713,0.000217963,0.00018078592,0.0012409892,0.0019646664,0.8060158,0.087267615,0.046566244,0.042618815,0.00017983293],"about_ca_topic_score_codex":0.004018226,"about_ca_topic_score_gemma":0.006908358,"teacher_disagreement_score":0.014434551,"about_ca_system_score_codex":0.0010609829,"about_ca_system_score_gemma":0.0017797574,"threshold_uncertainty_score":0.07633811},"labels":[],"label_agreement":null},{"id":"W4401608508","doi":"10.1109/conit61985.2024.10626802","title":"Speaker Identification Using CNN-LSTM Model on RAVDESS Dataset: A Deep Learning Approach","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Identification (biology); Deep learning; Speaker identification; Speech recognition; Natural language processing; Pattern recognition (psychology); Speaker recognition","score_opus":0.07526706665184585,"score_gpt":0.3005111881364797,"score_spread":0.22524412148463385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401608508","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64111865,0.009616902,0.075973004,0.0013809698,0.0031134228,0.0010706214,0.20434691,0.043273915,0.020105625],"genre_scores_gemma":[0.44595817,0.0014786761,0.0877976,0.00035621756,0.00033622593,0.00073745684,0.44420058,0.0005054319,0.018629594],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99913186,0.0001399285,0.00008129579,0.00030170387,0.00021957085,0.0001256466],"domain_scores_gemma":[0.99950564,0.00008873624,0.0000374608,0.000107971144,0.00021536817,0.000044766944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009950958,0.0024402959,0.0011266341,0.0017189903,0.0005639177,0.00067957444,0.0014898251,0.0011850749,0.0035029673],"category_scores_gemma":[0.0016708107,0.00027547393,0.0011290197,0.0007965075,0.00024898956,0.0009083326,0.0010863794,0.0011719686,0.004292508],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023627144,0.0015229478,0.011945991,0.0013597512,0.0009075933,0.0014671197,0.00028536722,0.058297828,0.051366385,0.0010102473,0.22392169,0.64555246],"study_design_scores_gemma":[0.00033027984,0.0013526552,0.032687753,0.00022779085,0.00045546074,0.0014453104,0.0007704548,0.8133126,0.074992485,0.0022184886,0.07193486,0.00027189698],"about_ca_topic_score_codex":0.022041857,"about_ca_topic_score_gemma":0.033541918,"teacher_disagreement_score":0.022041857,"about_ca_system_score_codex":0.00094178424,"about_ca_system_score_gemma":0.0008562555,"threshold_uncertainty_score":0.043827116},"labels":[],"label_agreement":null},{"id":"W4401609584","doi":"10.1109/icasspw62465.2024.10626010","title":"Characterizing the Temporal Dynamics of Universal Speech Representations for Generalizable Deepfake Detection","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Dynamics (music); Computer science; Speech recognition; Artificial intelligence; Natural language processing; Acoustics; Physics","score_opus":0.028143047117421098,"score_gpt":0.2683847684010593,"score_spread":0.2402417212836382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401609584","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22590348,0.0014090375,0.76303023,0.00055200653,0.00018708997,0.0001235685,0.0009208548,0.0042373063,0.0036363476],"genre_scores_gemma":[0.9158699,0.00040935626,0.078697726,0.00016580083,0.00007148906,0.000083854706,0.0017381578,0.00029789438,0.002665812],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9992073,0.00017907903,0.000048686597,0.0002935321,0.00015332422,0.00011807269],"domain_scores_gemma":[0.99713093,0.0013991935,0.00026511835,0.0007633053,0.00030644768,0.00013504397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018078939,0.0012800272,0.00081764016,0.0011948785,0.00041283155,0.0009920318,0.0006959971,0.0009261867,0.001735873],"category_scores_gemma":[0.0071431333,0.00035203248,0.00053839065,0.0006111396,0.000762019,0.0020773702,0.0016760669,0.0020924262,0.0011310201],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007040378,0.00029532437,0.014348324,0.0002665706,0.00016343335,0.0003358491,0.00041332573,0.16467205,0.074156776,0.009072178,0.006515149,0.729057],"study_design_scores_gemma":[0.00001451622,0.00013682197,0.0048115705,0.00003274611,0.00003702088,0.00027330086,0.00009826912,0.96465635,0.018578779,0.009057631,0.0022746702,0.000028350805],"about_ca_topic_score_codex":0.0017268256,"about_ca_topic_score_gemma":0.003408534,"teacher_disagreement_score":0.0018078939,"about_ca_system_score_codex":0.0005446943,"about_ca_system_score_gemma":0.0007260588,"threshold_uncertainty_score":0.009561181},"labels":[],"label_agreement":null},{"id":"W4401994215","doi":"10.3390/acoustics6030042","title":"Text-Independent Phone-to-Audio Alignment Leveraging SSL (TIPAA-SSL) Pre-Trained Model Latent Representation and Knowledge Transfer","year":2024,"lang":"en","type":"article","venue":"Acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Phone; Speech recognition; Artificial intelligence; Classifier (UML); TIMIT; Transfer of learning; Hidden Markov model; Natural language processing; Frame (networking); Representation (politics)","score_opus":0.03828787458081839,"score_gpt":0.28654415752196705,"score_spread":0.24825628294114865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401994215","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022407472,0.00067928416,0.9533252,0.00027614748,0.0003723903,0.0001270554,0.0011266869,0.017592402,0.0040934216],"genre_scores_gemma":[0.50025207,0.0005255689,0.45922786,0.0008319007,0.0004752622,0.0004513058,0.010169547,0.0016091183,0.026457349],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989998,0.00018327039,0.000053651427,0.00042253514,0.00023668258,0.00010409313],"domain_scores_gemma":[0.9987972,0.00026778536,0.000097786,0.00044346694,0.00031828668,0.00007551945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008220381,0.0013108667,0.0009304295,0.0009020194,0.00055814977,0.0010692796,0.0018493341,0.0012426713,0.006201812],"category_scores_gemma":[0.0030221804,0.0004242694,0.00097587984,0.0009864997,0.0005772815,0.002627116,0.002057495,0.0023215804,0.010036751],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036085548,0.00039161937,0.0014671638,0.00018299007,0.00012295322,0.00021106565,0.00014935556,0.04761332,0.048691064,0.0038625745,0.02155696,0.87539005],"study_design_scores_gemma":[0.00003281519,0.00017173446,0.0011155941,0.000024706083,0.000042980028,0.00020869159,0.00007148669,0.94355255,0.038673446,0.007116787,0.008943954,0.00004513367],"about_ca_topic_score_codex":0.0043361066,"about_ca_topic_score_gemma":0.009221765,"teacher_disagreement_score":0.006201812,"about_ca_system_score_codex":0.00053730916,"about_ca_system_score_gemma":0.0013177351,"threshold_uncertainty_score":0.020747125},"labels":[],"label_agreement":null},{"id":"W4402112262","doi":"10.21437/interspeech.2024-552","title":"Quantifying the Role of Textual Predictability in Automatic Speech Recognition","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; University of Toronto","keywords":"Predictability; Computer science; Leverage (statistics); Lexicon; Speech recognition; Language model; Syntax; Natural language processing; Acoustic model; Semantics (computer science); Context (archaeology); Artificial intelligence; Hidden Markov model; Speech processing","score_opus":0.056951169292264014,"score_gpt":0.28977791828759497,"score_spread":0.23282674899533096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402112262","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6038793,0.0009979912,0.38783193,0.0009767722,0.00013995398,0.000054955304,0.000658137,0.0022182087,0.003242864],"genre_scores_gemma":[0.98161733,0.00016596264,0.017055906,0.000067832654,0.00007715176,0.000020677848,0.00037704327,0.00026092312,0.0003572803],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99571913,0.0015627904,0.00046594432,0.0008000506,0.0011922896,0.00025975832],"domain_scores_gemma":[0.91177183,0.07390558,0.005037868,0.0058948966,0.0027846808,0.0006051769],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005545248,0.0013801457,0.00078425335,0.0011878993,0.00063741265,0.0021849752,0.00073875475,0.0012124319,0.0010260874],"category_scores_gemma":[0.055009972,0.0007554877,0.00047486738,0.0011058178,0.0014037685,0.0043018707,0.0019039243,0.0016405422,0.00071485864],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019825285,0.0003561802,0.13880366,0.0005784908,0.0003948753,0.00083619414,0.0011597299,0.45753318,0.13579437,0.0069030845,0.0017910097,0.25386676],"study_design_scores_gemma":[0.00002055897,0.00039989685,0.042630512,0.000050223254,0.000101424346,0.00035917648,0.0002049825,0.884467,0.061698195,0.009311657,0.00065056287,0.00010587136],"about_ca_topic_score_codex":0.0032724908,"about_ca_topic_score_gemma":0.0050653447,"teacher_disagreement_score":0.005545248,"about_ca_system_score_codex":0.0006033562,"about_ca_system_score_gemma":0.0008238036,"threshold_uncertainty_score":0.02932638},"labels":[],"label_agreement":null},{"id":"W4402275989","doi":"10.1515/phon-2024-0015","title":"The Mason-Alberta Phonetic Segmenter: a forced alignment system based on deep neural networks and interpolation","year":2024,"lang":"en","type":"article","venue":"Phonetica","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"Social Sciences and Humanities Research Council of Canada; Nvidia","keywords":"Computer science; Interpolation (computer graphics); Speech recognition; Two-alternative forced choice; Artificial intelligence; Artificial neural network; Classifier (UML); Testbed; Task (project management); Similarity (geometry); Natural language processing; Mathematics","score_opus":0.007528713155730898,"score_gpt":0.21007607105451015,"score_spread":0.20254735789877926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402275989","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03662939,0.0005553592,0.86659324,0.00030040037,0.0005026282,0.00021710132,0.0021298842,0.08385815,0.009213806],"genre_scores_gemma":[0.19578515,0.00018407631,0.77689993,0.00037949672,0.00006341845,0.00025406576,0.0048362925,0.003116843,0.018480726],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993505,0.00010436211,0.000034524437,0.0002800647,0.00016835025,0.00006216087],"domain_scores_gemma":[0.99932575,0.00021840728,0.00004059478,0.00016116543,0.00019767805,0.000056404144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010513389,0.001109326,0.0005898218,0.0007871715,0.00084756734,0.0012003382,0.002064246,0.0011536891,0.015872473],"category_scores_gemma":[0.0025675052,0.0007917782,0.0006181467,0.00075860677,0.0005865512,0.0017206618,0.0017819325,0.0018277758,0.0062362715],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010474087,0.00012804776,0.002641823,0.00025329678,0.0001610473,0.00042076193,0.0006447608,0.036239706,0.10019623,0.007115284,0.029894102,0.82125753],"study_design_scores_gemma":[0.0001377712,0.0002976221,0.0034527802,0.00007754517,0.000120962504,0.0004067494,0.00025143955,0.8387129,0.095127925,0.008650422,0.052598428,0.00016554978],"about_ca_topic_score_codex":0.036460474,"about_ca_topic_score_gemma":0.08570433,"teacher_disagreement_score":0.036460474,"about_ca_system_score_codex":0.0011051354,"about_ca_system_score_gemma":0.0027150307,"threshold_uncertainty_score":0.072496474},"labels":[],"label_agreement":null},{"id":"W4402625500","doi":"10.1007/s00034-024-02854-4","title":"Attentive Context-Aware Deep Speaker Representations for Voice Biometrics in Adverse Conditions","year":2024,"lang":"en","type":"article","venue":"Circuits Systems and Signal Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Biometrics; Speech recognition; Speaker recognition; Context (archaeology); Computer science; Voice analysis; Psychology; Artificial intelligence; History","score_opus":0.047731877708680696,"score_gpt":0.30188998190649563,"score_spread":0.2541581041978149,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402625500","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23934895,0.0031000427,0.74870634,0.00051404285,0.00048880896,0.000076959026,0.0010962274,0.0021551822,0.004513451],"genre_scores_gemma":[0.9299481,0.00092078594,0.06372036,0.00023234545,0.00019110666,0.000050520626,0.00063096633,0.000102063714,0.0042037494],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99982303,0.00004112808,0.000007449674,0.000048368613,0.000038188788,0.000041794563],"domain_scores_gemma":[0.999833,0.00006996793,0.000016845168,0.00002474297,0.000040665615,0.000014858834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027899485,0.00056004047,0.0004205616,0.00024441848,0.00016313243,0.00035679562,0.00045235662,0.00044601294,0.0023400187],"category_scores_gemma":[0.0008564367,0.00017664506,0.00036765248,0.00020355698,0.00017270935,0.00061802,0.0009618748,0.00084860297,0.00095138873],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001179741,0.00027719646,0.0023231122,0.0001922484,0.00009400908,0.00021837014,0.00015207635,0.047529817,0.18940262,0.0020961883,0.005791069,0.7507435],"study_design_scores_gemma":[0.000027437905,0.0004631282,0.008135498,0.00006635159,0.00014741959,0.00039535403,0.00013881766,0.9049923,0.07624345,0.0051664524,0.0041796435,0.000044164888],"about_ca_topic_score_codex":0.0015938127,"about_ca_topic_score_gemma":0.004430733,"teacher_disagreement_score":0.0023400187,"about_ca_system_score_codex":0.0001703186,"about_ca_system_score_gemma":0.00035031687,"threshold_uncertainty_score":0.007828116},"labels":[],"label_agreement":null},{"id":"W4402671182","doi":"10.18653/v1/2024.acl-srw.34","title":"Homophone2Vec: Embedding Space Analysis for Empirical Evaluation of Phonological and Semantic Similarity","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"McGill University","keywords":"Computer science; Semantic similarity; Embedding; Similarity (geometry); Semantic space; Natural language processing; Space (punctuation); Artificial intelligence; Information retrieval","score_opus":0.11656631950415315,"score_gpt":0.38381896032013624,"score_spread":0.2672526408159831,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402671182","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22661345,0.0020146284,0.72423476,0.0004443071,0.00073032745,0.00024359122,0.015406783,0.026780512,0.0035315892],"genre_scores_gemma":[0.64462525,0.00053902477,0.30607256,0.00015225881,0.00020311041,0.00054368854,0.042700864,0.0017072342,0.0034560647],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99767905,0.0008495423,0.00020669133,0.0005785554,0.00049469265,0.00019148813],"domain_scores_gemma":[0.99635565,0.0018131412,0.00015191593,0.0008149504,0.00071772764,0.0001466503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025149707,0.0016573771,0.0010828869,0.0024478913,0.0007373488,0.0015379443,0.001357563,0.00094928587,0.005913695],"category_scores_gemma":[0.009568872,0.00029539163,0.0010816931,0.0027326595,0.00061362656,0.0024655683,0.0018551826,0.0015562597,0.0027189404],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013654521,0.00088840636,0.021906119,0.00082288845,0.0007862948,0.00027551918,0.0004325828,0.03940406,0.018235376,0.010312657,0.064938866,0.84063166],"study_design_scores_gemma":[0.00017040632,0.00061272865,0.0138473455,0.000083109466,0.0001487493,0.0006006517,0.0005665363,0.9313148,0.025122175,0.016221331,0.011205012,0.000107207765],"about_ca_topic_score_codex":0.0050227037,"about_ca_topic_score_gemma":0.0065327105,"teacher_disagreement_score":0.005913695,"about_ca_system_score_codex":0.00060133653,"about_ca_system_score_gemma":0.0012872099,"threshold_uncertainty_score":0.019783318},"labels":[],"label_agreement":null},{"id":"W4402980134","doi":"10.1109/otcon60325.2024.10687796","title":"Merging Speech Recognition Capabilities with Large Language Models for Enhanced Communication and Interaction","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Computer science; Speech recognition; Natural language processing; Language model; Human–computer interaction; Artificial intelligence","score_opus":0.027778326045515507,"score_gpt":0.2801247445404287,"score_spread":0.2523464184949132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402980134","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02080621,0.00055968,0.96706957,0.00062689435,0.00017066671,0.00006813312,0.00018601824,0.005272613,0.0052401596],"genre_scores_gemma":[0.5476178,0.0010516209,0.43756026,0.0004903236,0.00022081414,0.00019951463,0.0010271755,0.0008930121,0.010939429],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99876034,0.00042464596,0.00010217919,0.00026466185,0.00036196248,0.000086302716],"domain_scores_gemma":[0.99640286,0.0019065154,0.00012799604,0.0007656314,0.00070485595,0.00009213602],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020505395,0.0010782491,0.0010512513,0.0006337772,0.00035528094,0.002340904,0.0009766193,0.00084851525,0.0071510384],"category_scores_gemma":[0.004631182,0.00044513762,0.0013098582,0.0004145259,0.00071748294,0.0036817084,0.0019211464,0.0014559902,0.0030301549],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00066748046,0.00024453417,0.0024679063,0.0006009029,0.00031391502,0.00043478582,0.000696813,0.27060148,0.07970942,0.042782422,0.008339023,0.59314126],"study_design_scores_gemma":[0.000022956036,0.00020241553,0.00047944047,0.00003941139,0.00009931342,0.00021353521,0.00012039464,0.9372163,0.026009412,0.02190924,0.013637975,0.000049589813],"about_ca_topic_score_codex":0.0024864564,"about_ca_topic_score_gemma":0.0033238383,"teacher_disagreement_score":0.0071510384,"about_ca_system_score_codex":0.0007426363,"about_ca_system_score_gemma":0.0009245939,"threshold_uncertainty_score":0.023922622},"labels":[],"label_agreement":null},{"id":"W4403096752","doi":"10.1016/j.nlp.2024.100110","title":"Recent advancements in automatic disordered speech recognition: A survey paper","year":2024,"lang":"en","type":"article","venue":"Natural Language Processing Journal","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Speech recognition; Computer science","score_opus":0.024658999476806286,"score_gpt":0.301425732541467,"score_spread":0.2767667330646607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403096752","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0077905823,0.9386557,0.03591299,0.003732268,0.0016949193,0.00009040841,0.00064515806,0.0006535057,0.010824506],"genre_scores_gemma":[0.031233354,0.9278124,0.02765872,0.001957063,0.0040940666,0.00007614708,0.00242378,0.00018156241,0.004562975],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972996,0.0004466784,0.00046045662,0.00088046206,0.0007784324,0.0001343219],"domain_scores_gemma":[0.9850492,0.009653568,0.0006425501,0.0007679244,0.0035425667,0.0003442483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004810812,0.001306758,0.0014163757,0.0061961925,0.00052893243,0.0030908466,0.0017026422,0.0016703948,0.005452555],"category_scores_gemma":[0.010180478,0.0007780403,0.0012318727,0.007301997,0.0010345451,0.005653986,0.0016346594,0.0018982658,0.004427928],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009645336,0.00008642651,0.0024094605,0.004593588,0.00007939032,0.00011537957,0.00022273786,0.0013536902,0.0018006555,0.004003457,0.015961692,0.96927714],"study_design_scores_gemma":[0.000025812407,0.0005149083,0.010384143,0.004995996,0.00051116396,0.002681973,0.0013218423,0.013187612,0.00722524,0.009717094,0.9492203,0.00021393248],"about_ca_topic_score_codex":0.0025990708,"about_ca_topic_score_gemma":0.0019207625,"teacher_disagreement_score":0.0061961925,"about_ca_system_score_codex":0.00067871646,"about_ca_system_score_gemma":0.0019953002,"threshold_uncertainty_score":0.025442302},"labels":[],"label_agreement":null},{"id":"W4403863506","doi":"10.1109/taslp.2024.3487410","title":"CL-MASR: A Continual Learning Benchmark for Multilingual ASR","year":2024,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Benchmark (surveying); Computer science; Artificial intelligence; Geography","score_opus":0.017325009771891654,"score_gpt":0.2885879270057755,"score_spread":0.27126291723388385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403863506","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.335794,0.02181104,0.46363252,0.002733783,0.0037693756,0.0020238953,0.026850037,0.08368411,0.059701197],"genre_scores_gemma":[0.64257085,0.002152683,0.26771435,0.0012095795,0.0005550128,0.001408006,0.06278276,0.0038440982,0.017762631],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99363965,0.0018145322,0.0007187382,0.0017475018,0.0016141803,0.00046547412],"domain_scores_gemma":[0.99070555,0.0040474045,0.0004762645,0.0020088127,0.0022413665,0.0005206098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0060728663,0.0037413144,0.0017201059,0.0026472027,0.0013424718,0.0024636996,0.0049076034,0.0033926666,0.006848223],"category_scores_gemma":[0.02006544,0.0005583785,0.0013512914,0.0017658694,0.0015569392,0.0035982465,0.003878022,0.0028803085,0.0055800974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022478316,0.001441145,0.0063215955,0.0027008676,0.00057274324,0.00065435126,0.00034219483,0.20717508,0.018141927,0.005382375,0.0747027,0.6803172],"study_design_scores_gemma":[0.00037323177,0.0024266837,0.004617407,0.00027039566,0.00017886332,0.0013107372,0.00049077964,0.9011226,0.036577433,0.015128448,0.03727592,0.00022755576],"about_ca_topic_score_codex":0.00682539,"about_ca_topic_score_gemma":0.008465981,"teacher_disagreement_score":0.006848223,"about_ca_system_score_codex":0.0013216108,"about_ca_system_score_gemma":0.001967532,"threshold_uncertainty_score":0.03211677},"labels":[],"label_agreement":null},{"id":"W4404148262","doi":"10.37394/232025.2024.6.17","title":"Hubert-LSTM: A Hybrid Model for Artificial Intelligence and Human Speech","year":2024,"lang":"en","type":"article","venue":"Engineering World","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Speech recognition; Artificial intelligence","score_opus":0.0489171082153988,"score_gpt":0.26947782967047146,"score_spread":0.22056072145507266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404148262","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033555456,0.0028542257,0.9470544,0.0013049153,0.0004103327,0.00012166216,0.0011337597,0.007392986,0.00617231],"genre_scores_gemma":[0.72091144,0.0025472397,0.2506724,0.0011930274,0.0002539839,0.00042139404,0.002147955,0.00043794943,0.021414652],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99976796,0.000055415036,0.000013475938,0.00009518404,0.00004108642,0.000026915981],"domain_scores_gemma":[0.9996952,0.00015368096,0.000027783251,0.00003413926,0.00007136775,0.000017848082],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070685137,0.0012635153,0.00064900634,0.0006210403,0.0002804042,0.0011353716,0.001644913,0.0011825546,0.0031574864],"category_scores_gemma":[0.0015941375,0.00043013494,0.00078519026,0.0006267444,0.00041135508,0.0016764308,0.0007632425,0.0019470323,0.0014962116],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045326664,0.0002462202,0.0014589025,0.00033792102,0.000436127,0.00032556005,0.00022818407,0.41441768,0.026453817,0.016731402,0.015385447,0.5235255],"study_design_scores_gemma":[0.000006846025,0.000044999717,0.00020170858,0.000014860659,0.000036292433,0.000037976657,0.000011394855,0.9896423,0.0026430024,0.0054623582,0.0018862522,0.000012046481],"about_ca_topic_score_codex":0.007854499,"about_ca_topic_score_gemma":0.012487553,"teacher_disagreement_score":0.007854499,"about_ca_system_score_codex":0.0009182408,"about_ca_system_score_gemma":0.0009235334,"threshold_uncertainty_score":0.015617549},"labels":[],"label_agreement":null},{"id":"W4404238744","doi":"10.1109/ijcb62174.2024.10744521","title":"On the influence of regularization techniques on label noise robustness: Self-supervised speaker verification as a use case","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Robustness (evolution); Speaker verification; Computer science; Speech recognition; Regularization (linguistics); Speaker recognition; Artificial intelligence; Pattern recognition (psychology); Noise measurement; Noise reduction","score_opus":0.028424363915907774,"score_gpt":0.2556727641753869,"score_spread":0.22724840025947915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404238744","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3802366,0.002547021,0.6111616,0.0012634807,0.00010134519,0.00017786518,0.00010246523,0.0011974717,0.0032121947],"genre_scores_gemma":[0.8474125,0.0005041641,0.14996971,0.00024997687,0.000070265014,0.000075814125,0.00016024569,0.00025634433,0.001300972],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99250424,0.0047177966,0.0002523717,0.0009884767,0.0012766125,0.00026049835],"domain_scores_gemma":[0.95196295,0.036487583,0.0023281376,0.005534579,0.0032564981,0.00043032164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014710087,0.0013406569,0.0010837147,0.0009962184,0.000985602,0.0011671487,0.0011686917,0.0022589196,0.0007072446],"category_scores_gemma":[0.042173408,0.00044169396,0.0008631204,0.0006501566,0.002291145,0.002362318,0.0017821428,0.002106916,0.0003291141],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023329284,0.000613537,0.009739274,0.0005257686,0.0006883938,0.0003191525,0.00073562574,0.62321913,0.080979265,0.009244311,0.002224679,0.26937798],"study_design_scores_gemma":[0.000034205375,0.0005124393,0.0026595844,0.000043311993,0.00008989744,0.00025632855,0.00010998636,0.94096076,0.051286694,0.0033052315,0.00069116,0.000050435974],"about_ca_topic_score_codex":0.0029465365,"about_ca_topic_score_gemma":0.0029895497,"teacher_disagreement_score":0.014710087,"about_ca_system_score_codex":0.0008682109,"about_ca_system_score_gemma":0.0006221733,"threshold_uncertainty_score":0.07779527},"labels":[],"label_agreement":null},{"id":"W4404589970","doi":"10.1007/978-3-031-77961-9_5","title":"Advances in OpenASR21 Evaluation with Increased Temporal Resolution for Speech Self-supervised Learning Models","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Resolution (logic); Artificial intelligence; Speech recognition; Machine learning","score_opus":0.038711057289161604,"score_gpt":0.27545460294724594,"score_spread":0.23674354565808434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404589970","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10451028,0.016187713,0.76409674,0.0022183887,0.0046761683,0.00076280173,0.009086107,0.07190656,0.026555194],"genre_scores_gemma":[0.33612958,0.003495212,0.54462695,0.001260146,0.0011886304,0.0010284021,0.067381084,0.009069296,0.03582068],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9818557,0.0073000942,0.0013604253,0.003170061,0.00567025,0.00064350985],"domain_scores_gemma":[0.98322994,0.0063222954,0.000395822,0.0029760865,0.0065067923,0.0005690402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018445099,0.0031555146,0.0026411265,0.0025977804,0.0014130943,0.0040983525,0.0035636805,0.0038100483,0.012705398],"category_scores_gemma":[0.026703494,0.0008431166,0.0023418851,0.0016880713,0.00088941073,0.0045157545,0.0034961149,0.004215648,0.012842916],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017868325,0.0007690191,0.0027780891,0.0007927248,0.0008078528,0.00017349486,0.00015791133,0.057099257,0.02154908,0.0030623577,0.05023848,0.8607849],"study_design_scores_gemma":[0.00022335885,0.0012059573,0.0044368077,0.00021864196,0.00040523632,0.00048400124,0.00020065397,0.8745901,0.06465128,0.0055033304,0.047901005,0.00017975806],"about_ca_topic_score_codex":0.0107286675,"about_ca_topic_score_gemma":0.011891164,"teacher_disagreement_score":0.018445099,"about_ca_system_score_codex":0.0013732747,"about_ca_system_score_gemma":0.0019027239,"threshold_uncertainty_score":0.09754819},"labels":[],"label_agreement":null},{"id":"W4404591500","doi":"10.1007/978-3-031-78014-1_12","title":"On the Influence of CNN-Based Feature Learning Modules in Neural Speaker Verification Framework","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Speaker verification; Feature (linguistics); Speech recognition; Artificial intelligence; Artificial neural network; Speaker recognition; Pattern recognition (psychology)","score_opus":0.016975000110396377,"score_gpt":0.24203839625826967,"score_spread":0.2250633961478733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404591500","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06819785,0.0074082515,0.90774345,0.0006869803,0.00026158555,0.000046667254,0.00012565887,0.0007334774,0.014796072],"genre_scores_gemma":[0.867798,0.0034521606,0.116110474,0.00028733775,0.0003407789,0.000040604962,0.00025202878,0.0002306196,0.011488107],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995161,0.00016188907,0.000018880535,0.00011918081,0.000118758966,0.00006518915],"domain_scores_gemma":[0.99909425,0.00051813934,0.00004107185,0.00010363177,0.00020722627,0.000035643778],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013258057,0.0007469182,0.00065341097,0.00028999217,0.00024359721,0.0007683925,0.0009811663,0.0008667599,0.0030746125],"category_scores_gemma":[0.003010036,0.00027415104,0.00052973843,0.00029622868,0.0005166462,0.0015974606,0.00090401556,0.0009973191,0.00064179127],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006401426,0.00014028567,0.0019734055,0.0002589709,0.00024025286,0.00023293337,0.000092809525,0.28235978,0.061002202,0.05155812,0.0051367027,0.5963644],"study_design_scores_gemma":[0.0000061610713,0.00006127697,0.0005872668,0.000013672715,0.00005304188,0.000059833925,0.000010536656,0.98258233,0.009423752,0.005734555,0.0014594031,0.00000806885],"about_ca_topic_score_codex":0.0074774204,"about_ca_topic_score_gemma":0.007844265,"teacher_disagreement_score":0.0074774204,"about_ca_system_score_codex":0.00059337326,"about_ca_system_score_gemma":0.0005996736,"threshold_uncertainty_score":0.014867842},"labels":[],"label_agreement":null},{"id":"W4404782836","doi":"10.18653/v1/2024.emnlp-main.1231","title":"Is Child-Directed Speech Effective Training Data for Language Models?","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Training (meteorology); Speech recognition; Training set; Language model; Natural language processing; Artificial intelligence","score_opus":0.07857330905148112,"score_gpt":0.31690856967814024,"score_spread":0.2383352606266591,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404782836","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7037922,0.0032688384,0.24176767,0.0047013513,0.00065116177,0.00026154498,0.022012725,0.008444715,0.015099849],"genre_scores_gemma":[0.8632518,0.0008579337,0.09757648,0.0008516734,0.00006812854,0.00046395033,0.032209918,0.000669718,0.004050452],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967614,0.0020013964,0.00014179174,0.00064709113,0.0003247599,0.00012362353],"domain_scores_gemma":[0.9885689,0.0068330355,0.00034233736,0.0025899883,0.0013299087,0.00033580096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004327286,0.0010183195,0.00070330256,0.00048668246,0.00046396683,0.0012830897,0.0016103219,0.0014039763,0.004263906],"category_scores_gemma":[0.021788692,0.0005993853,0.0007762009,0.00056551385,0.0010162165,0.002840814,0.001578014,0.002151074,0.0042841397],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002529105,0.0010683031,0.14382817,0.0017033827,0.0007371112,0.0013345901,0.0048039015,0.10926706,0.076374106,0.011503431,0.056836966,0.5900139],"study_design_scores_gemma":[0.00048420645,0.0022555562,0.06276964,0.0011430422,0.0005597004,0.0022999595,0.0058351997,0.61729,0.14959978,0.02463344,0.13281904,0.00031046494],"about_ca_topic_score_codex":0.0064689456,"about_ca_topic_score_gemma":0.013154167,"teacher_disagreement_score":0.0064689456,"about_ca_system_score_codex":0.0006766736,"about_ca_system_score_gemma":0.0015593361,"threshold_uncertainty_score":0.022885144},"labels":[],"label_agreement":null},{"id":"W4404783544","doi":"10.18653/v1/2024.emnlp-main.302","title":"Improving Spoken Language Modeling with Phoneme Classification: A Simple Fine-tuning Approach","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Agence de l'innovation de Défense; Grand Équipement National De Calcul Intensif; Agence Nationale de la Recherche; École des Hautes Etudes en Sciences Sociales; Canadian Institute for Advanced Research","keywords":"Computer science; Simple (philosophy); Spoken language; Speech recognition; Natural language processing; Language model; Artificial intelligence; Fine-tuning","score_opus":0.03837804051959954,"score_gpt":0.25130765712570646,"score_spread":0.21292961660610693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404783544","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04282108,0.0008599543,0.94343585,0.00043007822,0.00021392648,0.00008034494,0.0004925955,0.009016357,0.0026498118],"genre_scores_gemma":[0.6531719,0.00053483056,0.3301113,0.00077687437,0.00031704834,0.00023248415,0.002141871,0.0010040174,0.0117096985],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996125,0.000078304685,0.000032826403,0.00016263046,0.00007396394,0.00003983018],"domain_scores_gemma":[0.9991124,0.00043601697,0.000049405524,0.00021525491,0.00014629091,0.000040574116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055642053,0.001134404,0.0007723766,0.0004330334,0.00033663734,0.0011442951,0.0013128732,0.0010289003,0.0066931425],"category_scores_gemma":[0.0024772803,0.00037628584,0.00082103495,0.0003820507,0.0003660167,0.0011906032,0.00092740264,0.001521008,0.0034688523],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003204511,0.00023663409,0.001977932,0.00014991556,0.00022909373,0.0001496466,0.000108970875,0.1773914,0.120385475,0.002336181,0.006253316,0.690461],"study_design_scores_gemma":[0.000013721197,0.000045066598,0.0011106872,0.000010363113,0.000037301572,0.000050318595,0.00002392524,0.97181827,0.021313943,0.0029886013,0.002565272,0.000022557455],"about_ca_topic_score_codex":0.0046694065,"about_ca_topic_score_gemma":0.009727947,"teacher_disagreement_score":0.0066931425,"about_ca_system_score_codex":0.00042664143,"about_ca_system_score_gemma":0.00060589437,"threshold_uncertainty_score":0.022390842},"labels":[],"label_agreement":null},{"id":"W4404903811","doi":"10.61618/ssov3472","title":"Voice Calling Detection Distance in Land Search and Rescue","year":2024,"lang":"en","type":"article","venue":"The Journal of Search and Rescue","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Search and rescue; Computer science; Speech recognition; Artificial intelligence","score_opus":0.029450898186600908,"score_gpt":0.28431550182374954,"score_spread":0.25486460363714863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404903811","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99239606,0.0002922647,0.0055587776,0.0000272963,0.0000044051303,0.000008200096,0.000049785,0.00004306943,0.0016200464],"genre_scores_gemma":[0.998021,0.000043071304,0.0014064267,0.000009929875,0.0000025146844,0.0000063603165,0.000048746453,0.000008320152,0.00045368756],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9995067,0.00013777138,0.000026458889,0.00010527836,0.00018317044,0.00004067798],"domain_scores_gemma":[0.99814546,0.0010924508,0.00025877872,0.000069005786,0.00027218758,0.0001620879],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006138559,0.00025752423,0.0002706115,0.0008434151,0.0002619492,0.00047296737,0.00038056128,0.0005155246,0.0009970047],"category_scores_gemma":[0.0040776557,0.00019760361,0.00016781205,0.00033875895,0.00045315654,0.0005882944,0.00050847605,0.00027793553,0.00041779163],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015067977,0.000259784,0.70807225,0.0003487241,0.00012252008,0.0014371317,0.0053424393,0.043753073,0.09603617,0.0010003818,0.00062223914,0.14149842],"study_design_scores_gemma":[0.000021961538,0.0005595225,0.9356734,0.000047851172,0.00004572204,0.0017292987,0.002224061,0.044354435,0.013646905,0.0007651472,0.00085800525,0.00007372112],"about_ca_topic_score_codex":0.0053490954,"about_ca_topic_score_gemma":0.007665385,"teacher_disagreement_score":0.0053490954,"about_ca_system_score_codex":0.00039298568,"about_ca_system_score_gemma":0.0002111128,"threshold_uncertainty_score":0.010635912},"labels":[],"label_agreement":null},{"id":"W4405013581","doi":"10.1007/978-3-031-78122-3_7","title":"CAB-KWS : Contrastive Augmentation: An Unsupervised Learning Approach for Keyword Spotting in Speech Technology","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Keyword spotting; Computer science; Spotting; Speech recognition; Artificial intelligence; Natural language processing","score_opus":0.024741399971856606,"score_gpt":0.26446691578312764,"score_spread":0.23972551581127105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405013581","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0057129483,0.00032348017,0.97769576,0.00007722225,0.00013001023,0.00008368242,0.0005737674,0.012278755,0.0031243856],"genre_scores_gemma":[0.07313259,0.00038959007,0.90891653,0.00014499974,0.00013230332,0.00021121836,0.0025986065,0.0018044158,0.012669755],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99932647,0.00013657048,0.00003122764,0.0002106952,0.00023842562,0.00005673592],"domain_scores_gemma":[0.99914145,0.00036081637,0.000041995932,0.00019939907,0.0002097249,0.00004650428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007810277,0.0011765374,0.0009679138,0.0010321017,0.0005148803,0.0010112879,0.0021698517,0.0011118869,0.010324171],"category_scores_gemma":[0.0017572432,0.0005955748,0.00080118905,0.0013098808,0.0006856188,0.0017937827,0.0016449232,0.0018224629,0.006563363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040107412,0.00017644234,0.00028595806,0.00024585763,0.000055442742,0.00009915374,0.00008627765,0.015650617,0.08031749,0.005422348,0.016206501,0.88105285],"study_design_scores_gemma":[0.000045511988,0.00015635254,0.0008889582,0.000029375165,0.000045483917,0.00029247376,0.000052037773,0.86197746,0.09926052,0.010936319,0.026267033,0.00004846736],"about_ca_topic_score_codex":0.0030104208,"about_ca_topic_score_gemma":0.0065952833,"teacher_disagreement_score":0.010324171,"about_ca_system_score_codex":0.00041409303,"about_ca_system_score_gemma":0.00085238717,"threshold_uncertainty_score":0.03453785},"labels":[],"label_agreement":null},{"id":"W4405365437","doi":"10.1016/j.specom.2024.103167","title":"Spoken language identification: An overview of past and present research trends","year":2024,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Spoken language; Computer science; Identification (biology); Natural language processing; Language identification; Speech recognition; Linguistics; Artificial intelligence; Natural language","score_opus":0.19144291836526953,"score_gpt":0.4379504369399535,"score_spread":0.24650751857468398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405365437","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015055112,0.9805234,0.006670725,0.002015452,0.00093985186,0.000024257688,0.00011395179,0.00014957397,0.00805722],"genre_scores_gemma":[0.008353126,0.9738401,0.01033016,0.000999273,0.0017960938,0.000046428144,0.00033887848,0.000047145113,0.004248784],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995172,0.0000754498,0.00007956451,0.00011824185,0.00017728447,0.00003218163],"domain_scores_gemma":[0.99821544,0.0010664172,0.00014115282,0.000048071157,0.0004387358,0.00009017865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010892822,0.00074226665,0.00064795255,0.0048135864,0.00044289557,0.0022747274,0.0008190274,0.0014080663,0.004863557],"category_scores_gemma":[0.0019643137,0.0004776487,0.00050171727,0.004244186,0.0007342663,0.0035852662,0.00085796363,0.0013842296,0.0033121],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007042496,0.00007722993,0.0016008267,0.006040354,0.000045975492,0.00014351738,0.00024780436,0.0009618174,0.0023628909,0.008581885,0.019751158,0.96011615],"study_design_scores_gemma":[0.000008153355,0.0002312158,0.005937958,0.0051896065,0.0001026195,0.0017655828,0.0006265095,0.0024959727,0.0015680552,0.010133582,0.97183603,0.00010467564],"about_ca_topic_score_codex":0.0015934547,"about_ca_topic_score_gemma":0.0022303022,"teacher_disagreement_score":0.004863557,"about_ca_system_score_codex":0.0010046355,"about_ca_system_score_gemma":0.0010565434,"threshold_uncertainty_score":0.01627022},"labels":[],"label_agreement":null},{"id":"W4406080107","doi":"10.1016/j.rineng.2025.103943","title":"Automated speech therapy through personalized pronunciation correction using reinforcement learning and large language models","year":2025,"lang":"en","type":"article","venue":"Results in Engineering","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Pronunciation; Computer science; Reinforcement learning; Natural language processing; Reinforcement; Speech therapy; Speech recognition; Artificial intelligence; Linguistics; Psychology; Audiology; Medicine; Social psychology","score_opus":0.018812858151487085,"score_gpt":0.27529237021562325,"score_spread":0.25647951206413616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406080107","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023754667,0.00032419577,0.9557244,0.000301335,0.00011695269,0.00020386702,0.00023407173,0.01672679,0.002613581],"genre_scores_gemma":[0.5421859,0.0002853199,0.4472641,0.0003424064,0.000068481735,0.0005093085,0.0007219429,0.00068851566,0.007933928],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99903584,0.00026726045,0.00006324764,0.00033028584,0.000247489,0.0000559566],"domain_scores_gemma":[0.9992173,0.000386552,0.00007230063,0.00013552181,0.00013534939,0.00005299226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000995112,0.0010631938,0.0007460542,0.0003946373,0.00033147956,0.0010530204,0.001287409,0.0007407431,0.0039976155],"category_scores_gemma":[0.0034253756,0.00034241175,0.0006286255,0.0002547877,0.00043545556,0.0009469719,0.0014363185,0.0012926544,0.0026985006],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004653204,0.00036464998,0.0027191057,0.0002673137,0.00013303508,0.00038094312,0.00044301423,0.11706011,0.05434746,0.002611995,0.006342474,0.8148646],"study_design_scores_gemma":[0.00006420612,0.00019217718,0.00094948115,0.000030559117,0.00004413828,0.00030209907,0.00008652841,0.9615126,0.025588404,0.004144338,0.0070367125,0.000048783106],"about_ca_topic_score_codex":0.003175842,"about_ca_topic_score_gemma":0.0032123025,"teacher_disagreement_score":0.0039976155,"about_ca_system_score_codex":0.0005261144,"about_ca_system_score_gemma":0.0011072747,"threshold_uncertainty_score":0.013373375},"labels":[],"label_agreement":null},{"id":"W4406201495","doi":"10.1002/alz.089917","title":"Transformer‐based Deep Learning Architecture Improves Detection of Associations between Spontaneous Speech Language Markers and Cognition","year":2024,"lang":"en","type":"article","venue":"Alzheimer s & Dementia","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Cognition; Transformer; Natural language processing; Language model; Speech recognition; Artificial intelligence; Psychology","score_opus":0.012782707561069891,"score_gpt":0.24264903214625397,"score_spread":0.22986632458518408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406201495","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57153827,0.0005147035,0.4205518,0.0003456698,0.00009536357,0.000076040466,0.0007923924,0.0032228623,0.0028628341],"genre_scores_gemma":[0.96959543,0.00011118414,0.027064413,0.00008556273,0.000017296108,0.00004272744,0.0008575507,0.000059498856,0.002166321],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997267,0.00007598072,0.000013275934,0.00010269717,0.000041014922,0.00004033417],"domain_scores_gemma":[0.9993291,0.0003743376,0.000051327745,0.00007317029,0.00013300829,0.000038985505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009483262,0.0007520768,0.0003942449,0.00046308382,0.00016623664,0.00055914547,0.0006439157,0.00041243603,0.0019022558],"category_scores_gemma":[0.0026090604,0.00024108103,0.0005458957,0.00031273684,0.00027025104,0.0006894765,0.00070161256,0.00090792205,0.00078104],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014114551,0.00093840255,0.037485536,0.0002211495,0.0005231486,0.00045123827,0.00033084687,0.24800482,0.089933164,0.0028636288,0.0065120626,0.61132455],"study_design_scores_gemma":[0.000018095649,0.00017613704,0.006178203,0.000009702904,0.000050566578,0.00009144747,0.000035682857,0.9827375,0.00878033,0.001426455,0.00048149447,0.000014395964],"about_ca_topic_score_codex":0.0043608644,"about_ca_topic_score_gemma":0.0055852565,"teacher_disagreement_score":0.0043608644,"about_ca_system_score_codex":0.00045267798,"about_ca_system_score_gemma":0.00065343,"threshold_uncertainty_score":0.008670926},"labels":[],"label_agreement":null},{"id":"W4406344031","doi":"10.1121/10.0035261","title":"Three-dimensional finite element acoustic analysis of bent vocal tracts","year":2024,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Bent molecular geometry; Finite element method; Acoustics; Element (criminal law); Structural engineering; Geology; Computer science; Physics; Engineering; Political science","score_opus":0.01954315128730221,"score_gpt":0.26168890968996733,"score_spread":0.2421457584026651,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406344031","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4465722,0.00025441285,0.5416492,0.0002244875,0.000055253764,0.000093010756,0.000508685,0.00080055476,0.009842114],"genre_scores_gemma":[0.90128887,0.00017626697,0.09282811,0.00006412192,0.000011934049,0.00013157555,0.00045413637,0.00012513537,0.004919919],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99988747,0.000019119268,0.000008343904,0.000015727486,0.000055992925,0.0000132653595],"domain_scores_gemma":[0.99967396,0.00016126956,0.00003772936,0.000031405532,0.0000764684,0.000019103287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025160817,0.0003354964,0.00029399106,0.00041383514,0.00021594098,0.0005152291,0.0004788764,0.00092498603,0.0017828142],"category_scores_gemma":[0.00075746723,0.00026679743,0.0005279311,0.00018575935,0.00038944808,0.00028198783,0.0003795079,0.000313997,0.0004238922],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039146522,0.00004331241,0.001823486,0.000076284356,0.000017840746,0.00011339451,0.0001431119,0.95449173,0.03207024,0.001354068,0.00020104057,0.009626257],"study_design_scores_gemma":[0.0000022409592,0.000014860276,0.0005608862,0.000006453061,0.0000025515865,0.000024337045,0.000024099776,0.99610186,0.0025605892,0.00021195601,0.0004836285,0.0000066108055],"about_ca_topic_score_codex":0.0029963267,"about_ca_topic_score_gemma":0.0029629376,"teacher_disagreement_score":0.0029963267,"about_ca_system_score_codex":0.00026821546,"about_ca_system_score_gemma":0.00046470025,"threshold_uncertainty_score":0.0059641004},"labels":[],"label_agreement":null},{"id":"W4406453155","doi":"10.1016/s0967-0653(98)82019-x","title":"10.1016/s0967-0653(98)82019-x","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Track (disk drive); Matching (statistics); Multipath propagation; Correlation; Computer science; Statistics; Telecommunications; Mathematics; Geometry","score_opus":0.010475086020867306,"score_gpt":0.1818329516253262,"score_spread":0.1713578656044589,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406453155","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005577929,0.00051078113,0.0009243563,0.00038128262,0.0003872631,0.0001344227,0.0007635683,0.001031066,0.99530953],"genre_scores_gemma":[0.0005410812,0.0002214182,0.00039146666,0.00021940637,0.00006286794,0.00006129335,0.00033652433,0.0001729392,0.9979931],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992207,0.000052950712,0.00006927646,0.00030966825,0.0001742974,0.00017305321],"domain_scores_gemma":[0.9975311,0.00064741244,0.00015656679,0.00029211334,0.0005796954,0.00079300697],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0011856712,0.0034940392,0.0020309011,0.0032723323,0.0029404045,0.00417405,0.004000324,0.006431923,0.9893736],"category_scores_gemma":[0.0016870648,0.0011202503,0.0016635987,0.0027061806,0.0025738042,0.006740314,0.0032896947,0.003046049,0.992766],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005029662,0.00023567621,0.00087816216,0.0008637469,0.00004986399,0.00039850865,0.00017983088,0.0005078052,0.0030309367,0.0070638666,0.40140092,0.5848877],"study_design_scores_gemma":[0.000059844355,0.00014526924,0.00064063654,0.00039912734,0.000019092486,0.00044826118,0.00018402464,0.0002558855,0.000434188,0.00069422985,0.99669063,0.000028722536],"about_ca_topic_score_codex":0.004690701,"about_ca_topic_score_gemma":0.0039525847,"teacher_disagreement_score":0.010626376,"about_ca_system_score_codex":0.0012741418,"about_ca_system_score_gemma":0.0010517691,"threshold_uncertainty_score":0.015157223},"labels":[],"label_agreement":null},{"id":"W4406565803","doi":"10.1016/j.endend.2012.08.088","title":"10.1016/j.endend.2012.08.088","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"End-to-end principle; Test (biology); Computer science; Biology; Artificial intelligence","score_opus":0.010125527640857635,"score_gpt":0.17918364752398241,"score_spread":0.16905811988312477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406565803","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029261822,0.0064586136,0.0068178996,0.0029111363,0.0016515809,0.00009451116,0.0020101722,0.002956705,0.9741732],"genre_scores_gemma":[0.008566286,0.0023286936,0.003051907,0.001180974,0.00031125054,0.00007167526,0.0014056416,0.00036019407,0.98272336],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99968946,0.000020530579,0.000025131309,0.000114720904,0.00008560619,0.00006461155],"domain_scores_gemma":[0.99905914,0.00026878194,0.00009968585,0.00009374448,0.00018161874,0.0002970365],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007547174,0.0014734946,0.00069626916,0.0019543215,0.0010526286,0.0042991308,0.0013501502,0.0052310545,0.9393288],"category_scores_gemma":[0.0016235141,0.00048614186,0.00062297727,0.0009991579,0.0010846447,0.0031507113,0.0015063055,0.0012867312,0.9262221],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017181186,0.00021741063,0.0025020016,0.00048730077,0.00003220491,0.0004022939,0.00013131842,0.00041661825,0.001429834,0.006163564,0.2525692,0.73547643],"study_design_scores_gemma":[0.0000503224,0.00010592761,0.0027550627,0.000859685,0.000050852792,0.0024582283,0.00034085775,0.0005600712,0.0006790982,0.0056280917,0.98647505,0.000036728878],"about_ca_topic_score_codex":0.0015838395,"about_ca_topic_score_gemma":0.0017229394,"teacher_disagreement_score":0.06067121,"about_ca_system_score_codex":0.00060424843,"about_ca_system_score_gemma":0.00093179883,"threshold_uncertainty_score":0.08654004},"labels":[],"label_agreement":null},{"id":"W4407130456","doi":"10.1109/icit63607.2024.10860229","title":"Streamlining Attendance with Voice Recognition via Gaussian Mixture Model","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Speech recognition; Mixture model; Gaussian; Attendance; Gaussian process; Artificial intelligence; Pattern recognition (psychology); Physics","score_opus":0.025188535148869814,"score_gpt":0.24478488790510933,"score_spread":0.2195963527562395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407130456","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024199672,0.00014288125,0.96977127,0.00012197528,0.000084764855,0.000060963353,0.00010889587,0.0044965628,0.0010130227],"genre_scores_gemma":[0.54816103,0.0002992085,0.44365454,0.00015967757,0.00009997867,0.00014033668,0.00056049594,0.00043139927,0.0064933677],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916863,0.00019126809,0.00004299764,0.00023237277,0.00025710848,0.00010762863],"domain_scores_gemma":[0.99905485,0.00044833447,0.000078030265,0.0001118711,0.0002551443,0.00005185687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011264586,0.0006943945,0.0007615486,0.00090244703,0.00030192063,0.00088961073,0.0011370318,0.0008304038,0.0015411606],"category_scores_gemma":[0.0031890753,0.00036587156,0.0008056071,0.0008504385,0.00033241723,0.0009519518,0.0010531268,0.0017392178,0.0019021925],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039421592,0.0002979134,0.00502837,0.00014104851,0.00012016488,0.00009030256,0.00035037522,0.106495984,0.050537936,0.0027139024,0.0033058394,0.8305239],"study_design_scores_gemma":[0.000010049811,0.00008469447,0.0025694363,0.000011528913,0.0000361938,0.00007253074,0.000041266434,0.9758228,0.01824596,0.0009880307,0.0020749464,0.000042548003],"about_ca_topic_score_codex":0.0064760167,"about_ca_topic_score_gemma":0.006589538,"teacher_disagreement_score":0.0064760167,"about_ca_system_score_codex":0.0005167003,"about_ca_system_score_gemma":0.0005813158,"threshold_uncertainty_score":0.01287663},"labels":[],"label_agreement":null},{"id":"W4407561023","doi":"10.3390/app15042002","title":"Speaker Diarization: A Review of Objectives and Methods","year":2025,"lang":"en","type":"review","venue":"Applied Sciences","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Speaker diarisation; Computer science; Speech recognition; Speaker recognition","score_opus":0.05587897824479983,"score_gpt":0.4048335960937901,"score_spread":0.3489546178489903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407561023","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008817556,0.9960368,0.002110871,0.00029150778,0.00023231232,0.000021519407,0.00005858738,0.000027045597,0.0011331834],"genre_scores_gemma":[0.0010119986,0.9939078,0.0031413736,0.0002836842,0.00048910064,0.00004648118,0.00013978007,0.000020799587,0.0009589451],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987631,0.00021721401,0.00021275853,0.00028359835,0.00046840482,0.000054953416],"domain_scores_gemma":[0.99684393,0.0018122167,0.000253832,0.00010357215,0.0008868535,0.000099653196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034360737,0.0018150936,0.0025582376,0.004316811,0.00048380689,0.0017386674,0.0026851797,0.0017922147,0.0062352465],"category_scores_gemma":[0.0052543557,0.0009307368,0.0009954248,0.0035893691,0.0011073131,0.003025701,0.00114224,0.0019481657,0.0066856113],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007341655,0.000051311017,0.0002299223,0.014686553,0.0000754259,0.00006437936,0.00006323647,0.0004262578,0.00081652985,0.003655877,0.016872978,0.96298414],"study_design_scores_gemma":[0.000021631531,0.00014835784,0.0013931759,0.0095394375,0.00024259562,0.0010304175,0.00011517605,0.00050350506,0.0013960546,0.005715958,0.97980875,0.00008492177],"about_ca_topic_score_codex":0.0024358437,"about_ca_topic_score_gemma":0.002234827,"teacher_disagreement_score":0.0062352465,"about_ca_system_score_codex":0.0010156188,"about_ca_system_score_gemma":0.0020754228,"threshold_uncertainty_score":0.020858943},"labels":[],"label_agreement":null},{"id":"W4407735899","doi":"10.1109/twc.2025.3535714","title":"Latent Diffusion Model-Enabled Low-Latency Semantic Communication in the Presence of Semantic Ambiguities and Wireless Channel Noises","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Wireless Communications","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Wireless; Channel (broadcasting); Latency (audio); Computer network; Telecommunications","score_opus":0.030945437271525045,"score_gpt":0.26260520276381677,"score_spread":0.23165976549229172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407735899","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018850422,0.00022511801,0.97825396,0.00018903472,0.00005464267,0.000020065105,0.00007847427,0.0012128917,0.0011153587],"genre_scores_gemma":[0.7416037,0.0005791126,0.25017673,0.0005039063,0.00009661483,0.00010846383,0.00060749083,0.00031666717,0.0060072467],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995658,0.00010452475,0.000023254726,0.00010360546,0.00013363146,0.00006930355],"domain_scores_gemma":[0.99921787,0.00030665623,0.000084974214,0.00015297647,0.00019154328,0.000046010297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00090716407,0.0008190126,0.00078208867,0.0003570726,0.00034540595,0.0010418206,0.0012637826,0.0009340139,0.0011407238],"category_scores_gemma":[0.0031389259,0.00030767385,0.00046915244,0.0005462028,0.00066714117,0.0023952147,0.0020262434,0.0020102914,0.00056535436],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061389006,0.0002292891,0.002156361,0.0003073566,0.0001392007,0.00052268984,0.00047830082,0.497637,0.05511744,0.034325924,0.008045156,0.40042743],"study_design_scores_gemma":[0.000009491972,0.000032843334,0.00010831363,0.000008187875,0.0000113573915,0.000057353147,0.000026596304,0.9821907,0.009115018,0.00745376,0.0009750445,0.00001120627],"about_ca_topic_score_codex":0.0026667845,"about_ca_topic_score_gemma":0.00417804,"teacher_disagreement_score":0.0026667845,"about_ca_system_score_codex":0.0004987027,"about_ca_system_score_gemma":0.0010415983,"threshold_uncertainty_score":0.005302489},"labels":[],"label_agreement":null},{"id":"W4407901436","doi":"10.1109/ictis62692.2024.10894357","title":"Transformer-Based Multi-Head Attention for Noisy Speech Recognition","year":2024,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Speech recognition; Transformer; Artificial intelligence; Engineering; Electrical engineering; Voltage","score_opus":0.08409056606303837,"score_gpt":0.31579167348323833,"score_spread":0.23170110742019995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407901436","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06257996,0.002871802,0.9226044,0.000341243,0.0004040606,0.0001376581,0.00046546894,0.0053753224,0.0052200863],"genre_scores_gemma":[0.867069,0.0013414533,0.11708501,0.0006762232,0.0003685378,0.00014932224,0.0014695023,0.00031709118,0.011523955],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994017,0.00012459453,0.0000308434,0.00019816628,0.00014390201,0.00010071784],"domain_scores_gemma":[0.99950457,0.00018285224,0.000030225063,0.00006424008,0.00018534582,0.000032624408],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093043444,0.0013145024,0.0010033753,0.0009994607,0.00036487292,0.00070627435,0.001526436,0.0007115195,0.002680328],"category_scores_gemma":[0.0016264074,0.00033288755,0.0011303433,0.0006664723,0.00038730496,0.0010310968,0.0014737851,0.0011095733,0.0018077235],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00094316225,0.00028016098,0.0029301893,0.00018680036,0.00021902267,0.0002631076,0.00017938495,0.09666638,0.055351883,0.0029731982,0.0067988387,0.8332079],"study_design_scores_gemma":[0.000025258205,0.00024747956,0.0022538365,0.000017783284,0.0001519049,0.0002680162,0.000056861103,0.9662352,0.024836158,0.0025573326,0.003312773,0.00003725246],"about_ca_topic_score_codex":0.009883271,"about_ca_topic_score_gemma":0.015209547,"teacher_disagreement_score":0.009883271,"about_ca_system_score_codex":0.0006732226,"about_ca_system_score_gemma":0.0009250305,"threshold_uncertainty_score":0.019651532},"labels":[],"label_agreement":null},{"id":"W4408132766","doi":"10.1007/978-3-031-82156-1_12","title":"An RNN-LSTM Approach for Algerian Accent Identification","year":2025,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Stress (linguistics); Identification (biology); Computer science; Natural language processing; Artificial intelligence; Speech recognition; Botany; Biology","score_opus":0.05676930210946809,"score_gpt":0.31504300315739775,"score_spread":0.2582737010479297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408132766","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012140607,0.0030381447,0.9634809,0.0003576124,0.0009035216,0.000046745674,0.00046763892,0.004336453,0.0152282845],"genre_scores_gemma":[0.2405308,0.0032559705,0.6716463,0.0005040737,0.0005424184,0.00010176869,0.0021585913,0.00075349497,0.08050663],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99986494,0.000033519165,0.000009271295,0.00004029837,0.000029554789,0.000022331285],"domain_scores_gemma":[0.99991333,0.000022021535,0.0000046137247,0.000011956641,0.00004280625,0.0000052664764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032298075,0.0007521882,0.00036549853,0.0003623344,0.0003690483,0.00073178054,0.00065742305,0.00078433927,0.007856246],"category_scores_gemma":[0.00049059966,0.00022243141,0.0005018552,0.00055678206,0.0001869315,0.00076307124,0.0005815399,0.0007843946,0.0053062323],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001361478,0.00005329093,0.0002577663,0.00013084842,0.00008377629,0.0001805815,0.00007177591,0.049525797,0.036745377,0.0067639416,0.014508202,0.8915425],"study_design_scores_gemma":[0.000010772882,0.000078634665,0.0010959497,0.000049478567,0.00007325825,0.00031061546,0.00009380691,0.93462425,0.026518665,0.010274739,0.026837511,0.00003224791],"about_ca_topic_score_codex":0.005305711,"about_ca_topic_score_gemma":0.010204026,"teacher_disagreement_score":0.007856246,"about_ca_system_score_codex":0.00025191638,"about_ca_system_score_gemma":0.00047696533,"threshold_uncertainty_score":0.026281774},"labels":[],"label_agreement":null},{"id":"W4408267680","doi":"10.20865/202510701","title":"A Study on Final Devoicing in Russian through Quantitative Analysis","year":2025,"lang":"en","type":"article","venue":"Language and Linguistics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Linguistics; History; Computer science; Philosophy","score_opus":0.0490464943126742,"score_gpt":0.3590970564083973,"score_spread":0.31005056209572307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408267680","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9804602,0.0002640868,0.011130133,0.000026759079,0.00002013709,0.000052707856,0.000557751,0.00008545675,0.007402743],"genre_scores_gemma":[0.9922839,0.00014090152,0.0055226595,0.000008830903,0.000012889169,0.000054014803,0.00047995718,0.000037603404,0.0014593662],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99857354,0.00047491616,0.00016853618,0.0002914464,0.0004083108,0.00008316859],"domain_scores_gemma":[0.99426454,0.0031834047,0.00075763924,0.00032213551,0.0013133055,0.00015900274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018607465,0.0003471907,0.0002486003,0.0023735825,0.00054540974,0.0009956567,0.00024672635,0.0002343147,0.0018436786],"category_scores_gemma":[0.0072060376,0.00015066075,0.00020896515,0.001697942,0.0008108894,0.0008377898,0.0005425913,0.00036377314,0.000516543],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016884147,0.00049972674,0.3441295,0.0016298849,0.0002007024,0.001203015,0.078690015,0.0031462112,0.34055662,0.014423569,0.0012461987,0.21258613],"study_design_scores_gemma":[0.000026239395,0.0013365307,0.8562371,0.00018056521,0.00013560388,0.0014386204,0.042282026,0.011299111,0.06542224,0.0023949286,0.019063665,0.00018340013],"about_ca_topic_score_codex":0.0026621735,"about_ca_topic_score_gemma":0.002329157,"teacher_disagreement_score":0.0026621735,"about_ca_system_score_codex":0.00054805883,"about_ca_system_score_gemma":0.00038832164,"threshold_uncertainty_score":0.009840727},"labels":[],"label_agreement":null},{"id":"W4408352315","doi":"10.1109/icassp49660.2025.10888434","title":"Large-Scale Recurrent Neural Networks with Fully Homomorphic Encryption for Privacy-Enhanced Speaker Identification","year":2025,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Homomorphic encryption; Computer science; Encryption; Identification (biology); Speaker identification; Artificial neural network; Scale (ratio); Speech recognition; Computer security; Computer network; Speaker recognition; Artificial intelligence","score_opus":0.014548531761685038,"score_gpt":0.2527619497386806,"score_spread":0.23821341797699558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408352315","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0404558,0.00038029975,0.9553823,0.000310362,0.00006367215,0.000028255155,0.00009123599,0.0011542328,0.002133908],"genre_scores_gemma":[0.7739507,0.00034832972,0.2195035,0.00021021269,0.000071652204,0.000055755245,0.0002876376,0.000118145676,0.0054539437],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996214,0.000089811474,0.00002603451,0.00007289084,0.00014363717,0.000046282905],"domain_scores_gemma":[0.9995654,0.00015233587,0.000048449347,0.0001356028,0.000080624675,0.000017467182],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005957894,0.0003323057,0.0002939227,0.00016038363,0.00020228676,0.00044064445,0.00062115566,0.00042452264,0.0016786325],"category_scores_gemma":[0.0015368953,0.00018737908,0.00032906863,0.0002239316,0.00041032993,0.001182178,0.0007736333,0.0010380978,0.00060778303],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049385306,0.00016112514,0.0010017869,0.00015277603,0.00011793812,0.0004615712,0.00019603179,0.37368423,0.13768542,0.05095321,0.0069337413,0.42815837],"study_design_scores_gemma":[0.000005847479,0.000041515224,0.00017583507,0.0000050948847,0.000010043571,0.000058380927,0.0000114332925,0.9724215,0.020201119,0.0056218817,0.0014398674,0.0000073908627],"about_ca_topic_score_codex":0.0015870611,"about_ca_topic_score_gemma":0.0032668684,"teacher_disagreement_score":0.0016786325,"about_ca_system_score_codex":0.0004624063,"about_ca_system_score_gemma":0.00053756504,"threshold_uncertainty_score":0.0056156516},"labels":[],"label_agreement":null},{"id":"W4408352429","doi":"10.1109/icassp49660.2025.10889032","title":"Phone-purity Guided Discrete Tokens for Dysarthric Speech Recognition","year":2025,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"Youth Innovation Promotion Association","keywords":"Speech recognition; Phone; Computer science; Linguistics","score_opus":0.04100966815545745,"score_gpt":0.29886033453776717,"score_spread":0.2578506663823097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408352429","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10245992,0.00069449184,0.8914962,0.000107897766,0.00009875624,0.00008247923,0.0006197366,0.0027195239,0.0017210703],"genre_scores_gemma":[0.673942,0.00030964037,0.31990215,0.00007149697,0.000029875859,0.00010820035,0.001632617,0.00039889125,0.0036050263],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995628,0.00010598493,0.000037266174,0.00012992989,0.000117926174,0.000046010737],"domain_scores_gemma":[0.99953437,0.00018228556,0.000058657904,0.00010470224,0.00008984169,0.000030165662],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047664053,0.0004572586,0.000381263,0.00048895465,0.00030963394,0.0007625013,0.00057729665,0.00040254125,0.001982516],"category_scores_gemma":[0.0016172249,0.00022371564,0.00026951975,0.00046211632,0.00049693155,0.0007812607,0.00094729144,0.0006196195,0.0015664225],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001032187,0.00011273604,0.002889649,0.0002637274,0.000056455414,0.00032073885,0.0003300764,0.028306061,0.33150694,0.00812517,0.0026854544,0.6243709],"study_design_scores_gemma":[0.00008519249,0.0005951943,0.0130149815,0.00007875396,0.00009236003,0.001099656,0.0004661762,0.5501612,0.4021578,0.012691853,0.01942499,0.00013174817],"about_ca_topic_score_codex":0.0020404097,"about_ca_topic_score_gemma":0.0045898096,"teacher_disagreement_score":0.0020404097,"about_ca_system_score_codex":0.00035803535,"about_ca_system_score_gemma":0.00072328973,"threshold_uncertainty_score":0.006632149},"labels":[],"label_agreement":null},{"id":"W4408353132","doi":"10.1109/icassp49660.2025.10888478","title":"Text-dependent Speaker Verification Challenge 2024: Exploring Shared and User-defined Passphrases","year":2025,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Speaker verification; Human–computer interaction; Natural language processing; Speech recognition; Speaker recognition","score_opus":0.06496050737107423,"score_gpt":0.26082747468268785,"score_spread":0.19586696731161363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408353132","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48109394,0.00506087,0.455743,0.002410003,0.0016490985,0.002161099,0.017545005,0.014684069,0.019652804],"genre_scores_gemma":[0.72511727,0.0006762097,0.21194312,0.0008148611,0.0004009789,0.0010366037,0.044840783,0.00086710654,0.01430311],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98643154,0.0056543057,0.0006947282,0.0021801528,0.004308933,0.0007302921],"domain_scores_gemma":[0.98645335,0.0065585324,0.00047483828,0.0027805052,0.003059946,0.0006727851],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009697049,0.0019549718,0.0022985842,0.0010900955,0.0010990085,0.0020063932,0.0015899718,0.0029559503,0.002688544],"category_scores_gemma":[0.019316737,0.00033285771,0.001209596,0.00065787183,0.0010851554,0.0026982594,0.0045125014,0.0022539953,0.002668176],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004462576,0.0020168747,0.01146286,0.0022910102,0.0008237611,0.0009956907,0.00093797455,0.0473849,0.10814125,0.007243297,0.080326356,0.73391354],"study_design_scores_gemma":[0.00068700325,0.00396628,0.030015599,0.00021604131,0.00032704778,0.0037524595,0.0019673402,0.66933894,0.2012593,0.016650805,0.0714629,0.00035630606],"about_ca_topic_score_codex":0.004458891,"about_ca_topic_score_gemma":0.0060147005,"teacher_disagreement_score":0.009697049,"about_ca_system_score_codex":0.0008237479,"about_ca_system_score_gemma":0.0018206544,"threshold_uncertainty_score":0.05128354},"labels":[],"label_agreement":null},{"id":"W4408353590","doi":"10.1109/icassp49660.2025.10890553","title":"Stable-TTS: Stable Speaker-Adaptive Text-to-Speech Synthesis via Prosody Prompting","year":2025,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Prosody; Speech synthesis; Speech recognition; Computer science","score_opus":0.02149870901442346,"score_gpt":0.25179105564420484,"score_spread":0.23029234662978137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408353590","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012187694,0.00030410523,0.9782009,0.00009644606,0.00019272084,0.00008810916,0.0004392688,0.0060837055,0.002406999],"genre_scores_gemma":[0.28028384,0.00049238064,0.700816,0.0003438176,0.00024579573,0.00035806687,0.0035924567,0.0017072358,0.012160475],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99939966,0.00012250434,0.0000359872,0.00019237695,0.00020737328,0.00004211336],"domain_scores_gemma":[0.9993692,0.00023025429,0.000046167956,0.00013788004,0.00016919438,0.000047340927],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009874043,0.0010154379,0.00070737774,0.0005616216,0.0003449025,0.0007700602,0.0011924901,0.00077555026,0.0060109184],"category_scores_gemma":[0.0020839523,0.00031675084,0.00073272747,0.0005292973,0.0005235775,0.000961163,0.0015962952,0.000994921,0.004086486],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010609832,0.00015277267,0.00096357614,0.0002486869,0.0001258858,0.0002710341,0.00021007344,0.04939634,0.19331887,0.0056485264,0.010746066,0.73785716],"study_design_scores_gemma":[0.00009828322,0.0003884675,0.0013578103,0.000028716186,0.000062844774,0.00048217835,0.000079392266,0.8353816,0.1338441,0.0067021386,0.021499904,0.000074588395],"about_ca_topic_score_codex":0.0014172562,"about_ca_topic_score_gemma":0.0024116682,"teacher_disagreement_score":0.0060109184,"about_ca_system_score_codex":0.00028322617,"about_ca_system_score_gemma":0.0006146814,"threshold_uncertainty_score":0.020108521},"labels":[],"label_agreement":null},{"id":"W4408354505","doi":"10.1109/icassp49660.2025.10888920","title":"Effective and Efficient Mixed Precision Quantization of Speech Foundation Models","year":2025,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Quantization (signal processing); Foundation (evidence); Speech recognition; Artificial intelligence; Algorithm","score_opus":0.014984164037450507,"score_gpt":0.2609719196665165,"score_spread":0.245987755629066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408354505","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042523883,0.0015403767,0.9362914,0.0004477415,0.00023641394,0.00010358304,0.0011686147,0.0152117545,0.0024761974],"genre_scores_gemma":[0.5931292,0.0007175593,0.3939292,0.0004319419,0.00012235295,0.00021597785,0.004622381,0.000902697,0.0059287436],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987129,0.00024791586,0.00008898301,0.00033108718,0.00050128304,0.000117928204],"domain_scores_gemma":[0.9989442,0.00032663153,0.00006855794,0.00034541107,0.00027711186,0.00003803254],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001075299,0.0018166404,0.0009867671,0.00087875046,0.0004967632,0.0018473205,0.0019768756,0.00093699584,0.004359347],"category_scores_gemma":[0.0056029493,0.0006540764,0.00077491894,0.00078910124,0.00063365605,0.002987545,0.0025683567,0.0023616753,0.002931492],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00078854157,0.0001479725,0.0016280136,0.00022841623,0.00012396423,0.00019372812,0.00021851929,0.13355638,0.04446484,0.0095419455,0.011776989,0.7973306],"study_design_scores_gemma":[0.000091545044,0.00020130319,0.00064811204,0.000046352703,0.000063256535,0.00016689034,0.00011182721,0.9399956,0.039737314,0.012610147,0.0062697805,0.000057851485],"about_ca_topic_score_codex":0.007245011,"about_ca_topic_score_gemma":0.014135154,"teacher_disagreement_score":0.007245011,"about_ca_system_score_codex":0.0008253299,"about_ca_system_score_gemma":0.0014346944,"threshold_uncertainty_score":0.014583409},"labels":[],"label_agreement":null},{"id":"W4408355320","doi":"10.1109/icassp49660.2025.10888977","title":"LAVViT: Latent Audio-Visual Vision Transformers for Speaker Verification","year":2025,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Audio visual; Transformer; Speech recognition; Speaker verification; Computer vision; Artificial intelligence; Speaker recognition; Multimedia; Engineering; Electrical engineering","score_opus":0.014257599488651186,"score_gpt":0.30255972333916004,"score_spread":0.28830212385050885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408355320","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020683061,0.0008450643,0.921994,0.0002469615,0.0003081307,0.00023035068,0.0017316681,0.049584035,0.0043768166],"genre_scores_gemma":[0.5247533,0.0004900699,0.44414994,0.00063468044,0.00016669784,0.00039929664,0.012107822,0.0018845985,0.015413657],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993773,0.00013075718,0.00002575975,0.00022337951,0.00015423985,0.0000885166],"domain_scores_gemma":[0.9994042,0.0001905466,0.000036477813,0.00018885147,0.00012211321,0.000057864738],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014885335,0.00138523,0.00073985214,0.0008062372,0.00039688926,0.0010634101,0.002557722,0.001082358,0.01547162],"category_scores_gemma":[0.00400746,0.00062807277,0.0009440108,0.00044211457,0.00063483237,0.0023865574,0.0027716588,0.0021522166,0.008137542],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010980077,0.00026234332,0.0024295195,0.00037202466,0.00023506078,0.00019145329,0.00017202582,0.050386135,0.0633001,0.012562511,0.040733077,0.8282577],"study_design_scores_gemma":[0.00012912808,0.00027798588,0.0011572611,0.00005430549,0.00006615249,0.00028805513,0.000063584135,0.90760654,0.056948826,0.016670996,0.016687429,0.00004976129],"about_ca_topic_score_codex":0.0052368315,"about_ca_topic_score_gemma":0.009830005,"teacher_disagreement_score":0.01547162,"about_ca_system_score_codex":0.00077286555,"about_ca_system_score_gemma":0.0011353743,"threshold_uncertainty_score":0.051757693},"labels":[],"label_agreement":null},{"id":"W4408498124","doi":"10.1007/978-981-97-8695-4_40","title":"Artificial Neural Networks for Speaker Verification","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BP (Canada)","funders":"","keywords":"Speaker verification; Artificial neural network; Computer science; Speech recognition; Speaker recognition; Artificial intelligence","score_opus":0.027368379244865786,"score_gpt":0.24192020371765405,"score_spread":0.21455182447278826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408498124","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004488341,0.029416917,0.9435887,0.0004008758,0.0009851503,0.000042569984,0.0004663444,0.0028997543,0.017711407],"genre_scores_gemma":[0.18744367,0.02409041,0.6142377,0.0004241778,0.0013050756,0.00020379481,0.0022193808,0.00077144156,0.1693043],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997707,0.00005144861,0.000014811294,0.000053182142,0.00009038232,0.000019509615],"domain_scores_gemma":[0.999746,0.00012772951,0.00001286056,0.000042027394,0.00006722213,0.000004141551],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003958292,0.0006809053,0.0006966873,0.0004549053,0.00021306278,0.00066644436,0.00083193,0.00096504163,0.011437231],"category_scores_gemma":[0.00077770196,0.00036652808,0.00039920112,0.00066945894,0.00023430285,0.0007241985,0.0005422263,0.0009927063,0.0056660543],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008288356,0.00002979881,0.00013167187,0.00019742931,0.00007417344,0.000063739986,0.000020191863,0.055622794,0.0116495015,0.010022445,0.020643398,0.901462],"study_design_scores_gemma":[0.000014317301,0.000048439426,0.00074499875,0.00008078209,0.00005209202,0.00017010952,0.000023867984,0.9179146,0.015786286,0.019920502,0.04520989,0.000034103534],"about_ca_topic_score_codex":0.0027910238,"about_ca_topic_score_gemma":0.003923127,"teacher_disagreement_score":0.011437231,"about_ca_system_score_codex":0.00030978036,"about_ca_system_score_gemma":0.00023945386,"threshold_uncertainty_score":0.038261354},"labels":[],"label_agreement":null},{"id":"W4408678082","doi":"10.1016/j.wocn.2025.101402","title":"Processing pronunciation variation with independently mappable allophones","year":2025,"lang":"en","type":"article","venue":"Journal of Phonetics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Pronunciation; Variation (astronomy); Speech recognition; Computer science; Linguistics; Philosophy","score_opus":0.006363307138592676,"score_gpt":0.21844346278485252,"score_spread":0.21208015564625984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408678082","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9158256,0.00017512847,0.0741925,0.00024202811,0.00004255013,0.00010176648,0.00046525468,0.0005635431,0.008391641],"genre_scores_gemma":[0.97985256,0.00006504208,0.01718623,0.00007899832,0.000011439351,0.00006434552,0.0005409945,0.0001175037,0.0020828615],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9991406,0.00016466317,0.00005090588,0.00028359602,0.00024685395,0.00011336633],"domain_scores_gemma":[0.9966678,0.0016662502,0.00028048633,0.0005074371,0.0007229689,0.00015497816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010223332,0.0007107283,0.00046635483,0.00046481035,0.00058417366,0.0016310852,0.00047199544,0.0006575709,0.003084456],"category_scores_gemma":[0.006633542,0.00039260183,0.00040991392,0.00037094968,0.000785651,0.0013854872,0.0014052611,0.00087150594,0.00052437815],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00065620884,0.0001494997,0.03799001,0.00026783595,0.00017226422,0.00027293136,0.002808928,0.007835697,0.7747029,0.004073961,0.00085860037,0.17021108],"study_design_scores_gemma":[0.00011761629,0.0006661638,0.6481838,0.00009551219,0.00038845427,0.00068195164,0.0014597764,0.15533721,0.15864043,0.02770733,0.006363266,0.00035837558],"about_ca_topic_score_codex":0.026985753,"about_ca_topic_score_gemma":0.043397054,"teacher_disagreement_score":0.026985753,"about_ca_system_score_codex":0.0010481472,"about_ca_system_score_gemma":0.00093941344,"threshold_uncertainty_score":0.053657353},"labels":[],"label_agreement":null},{"id":"W4408691358","doi":"10.5753/eniac.2024.245057","title":"Phonetic segmentation for Brazilian Portuguese based on a self-supervised model and forced-alignment","year":2024,"lang":"pt","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Segmentation; Portuguese; Brazilian Portuguese; Artificial intelligence; Natural language processing; Image segmentation; Speech recognition; Computer vision; Pattern recognition (psychology); Linguistics","score_opus":0.030129838190083653,"score_gpt":0.27693819479266324,"score_spread":0.24680835660257958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408691358","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32282308,0.00069808785,0.6635369,0.00032437287,0.00018358669,0.00012284228,0.00079110474,0.0059655383,0.005554478],"genre_scores_gemma":[0.8148858,0.00021839437,0.17780024,0.00006609903,0.00003200437,0.00009848313,0.0013566503,0.00050190295,0.005040483],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996271,0.00007873205,0.000022924662,0.00017420755,0.000052760497,0.000044254568],"domain_scores_gemma":[0.99954116,0.00020541507,0.00003352404,0.0000672304,0.00012212714,0.00003060172],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061961985,0.0006750871,0.00072031445,0.000726867,0.00051958166,0.0012784919,0.00066073425,0.0007368722,0.0027605705],"category_scores_gemma":[0.0016137417,0.0004116736,0.0009862948,0.0006184726,0.00032927952,0.0007234649,0.00047834855,0.00066677,0.0012297988],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013603256,0.0001960059,0.0073606116,0.00032536712,0.00018336509,0.00044615119,0.001010288,0.23737985,0.08353826,0.0030788556,0.0029105549,0.66221035],"study_design_scores_gemma":[0.000013161178,0.00005564596,0.0029680887,0.000014753546,0.000026974893,0.000063020685,0.00006747097,0.987971,0.007102886,0.00073417654,0.00096592796,0.000016911023],"about_ca_topic_score_codex":0.030914709,"about_ca_topic_score_gemma":0.0481708,"teacher_disagreement_score":0.030914709,"about_ca_system_score_codex":0.0007600014,"about_ca_system_score_gemma":0.0015206952,"threshold_uncertainty_score":0.061469555},"labels":[],"label_agreement":null},{"id":"W4409036126","doi":"10.1075/jslp.24035.joh","title":"Exploring automatic speech recognition for corrective and confirmative pronunciation feedback","year":2025,"lang":"en","type":"article","venue":"Journal of Second Language Pronunciation","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université du Québec à Trois-Rivières; Concordia University; University of Calgary","funders":"","keywords":"Pronunciation; Speech recognition; Corrective feedback; Computer science; Natural language processing; Artificial intelligence; Psychology; Linguistics","score_opus":0.05225835841736854,"score_gpt":0.27115238157028987,"score_spread":0.21889402315292134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409036126","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9786831,0.00019323059,0.015640339,0.0001209017,0.000038365484,0.000095948075,0.00091106776,0.0010133199,0.0033037593],"genre_scores_gemma":[0.9903037,0.00006569959,0.0072919503,0.00003883443,0.000008583192,0.00003596211,0.000456867,0.000065716886,0.0017326119],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982115,0.0006466593,0.00007602136,0.00037465084,0.000534206,0.00015698437],"domain_scores_gemma":[0.9916638,0.0037834619,0.00042779546,0.00039456508,0.0035511705,0.00017912187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015262397,0.0005656907,0.00034695957,0.00053292804,0.0002507929,0.00093467627,0.0004517908,0.0005121434,0.002983558],"category_scores_gemma":[0.007134083,0.00013321255,0.00016964416,0.00031104434,0.0003225315,0.00032483108,0.00028646927,0.00029410823,0.0019308719],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018949598,0.00012376557,0.07799764,0.00045505128,0.00005530922,0.0006812256,0.0038621456,0.0033199543,0.6246604,0.00031076168,0.0016215044,0.2850172],"study_design_scores_gemma":[0.00010542658,0.001799807,0.44531164,0.00014245359,0.00014028385,0.001956093,0.004392509,0.080732085,0.45625585,0.0003740758,0.008630485,0.0001593988],"about_ca_topic_score_codex":0.04076062,"about_ca_topic_score_gemma":0.046357702,"teacher_disagreement_score":0.04076062,"about_ca_system_score_codex":0.0007268729,"about_ca_system_score_gemma":0.0009850144,"threshold_uncertainty_score":0.08104676},"labels":[],"label_agreement":null},{"id":"W4409450725","doi":"10.1016/j.specom.2025.103230","title":"Neural Chinese silent speech recognition with facial electromyography","year":2025,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Natural Science Foundation of China","keywords":"Speech recognition; Electromyography; Facial electromyography; Computer science; Hidden Markov model; Artificial intelligence; Pattern recognition (psychology); Physical medicine and rehabilitation; Facial expression; Medicine","score_opus":0.012525358833797075,"score_gpt":0.2535649671924412,"score_spread":0.24103960835864413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409450725","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39850304,0.0019836384,0.58070326,0.00031824686,0.0004428568,0.00022984411,0.0013003072,0.002139042,0.01437975],"genre_scores_gemma":[0.88773644,0.00065957365,0.09926107,0.00009521968,0.00011148713,0.000104613864,0.0010265294,0.00009555972,0.010909528],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999093,0.000016015076,0.0000065323566,0.00003115997,0.0000224314,0.0000146094535],"domain_scores_gemma":[0.99991274,0.000032024018,0.000005838045,0.000009563938,0.00003124527,0.000008596761],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018946108,0.00046607107,0.00024333633,0.00033829405,0.00016436355,0.00029706894,0.00020802763,0.00029875292,0.0032562746],"category_scores_gemma":[0.0004213925,0.00011890991,0.00028690798,0.00035845593,0.00014247654,0.00035818794,0.0002509357,0.00023171182,0.00090699515],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040184744,0.000074891745,0.0032291214,0.00014300874,0.0000530312,0.000249642,0.00007409042,0.003583329,0.32929337,0.00077811803,0.001629359,0.6604903],"study_design_scores_gemma":[0.00009628507,0.00070283655,0.10309669,0.000059695707,0.0003265839,0.0013443448,0.00029208724,0.5053349,0.37926766,0.0021785512,0.0072343536,0.000065965745],"about_ca_topic_score_codex":0.002666323,"about_ca_topic_score_gemma":0.0048559816,"teacher_disagreement_score":0.0032562746,"about_ca_system_score_codex":0.00012127319,"about_ca_system_score_gemma":0.0003064265,"threshold_uncertainty_score":0.010893285},"labels":[],"label_agreement":null},{"id":"W4409787672","doi":"10.61091/jcmcc127a-300","title":"Artificial Intelligence-driven Speech Signal Extraction and Generation Based on Wave RNN Models","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Recurrent neural network; Speech recognition; SIGNAL (programming language); Artificial intelligence; Extraction (chemistry); Natural language processing; Artificial neural network; Chemistry","score_opus":0.05272196945616726,"score_gpt":0.28455377712720986,"score_spread":0.2318318076710426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409787672","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02356298,0.00028630972,0.9727581,0.00009589818,0.000044683005,0.000040708168,0.000039309834,0.00047995916,0.0026920317],"genre_scores_gemma":[0.76786923,0.0007231878,0.22304025,0.00011689884,0.000042144664,0.00018615556,0.00028941708,0.00011252219,0.007620298],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9998392,0.00003250289,0.000010429088,0.000047936486,0.000054888635,0.000015070009],"domain_scores_gemma":[0.9998084,0.00008581174,0.00002152846,0.000017390936,0.000059252943,0.000007635912],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031903747,0.000611308,0.000300309,0.00027481993,0.00019902556,0.00038696174,0.00064759667,0.0004133563,0.0013587498],"category_scores_gemma":[0.0006855074,0.00025144508,0.0005727191,0.00024020068,0.00029530548,0.0007951675,0.00028530107,0.00064914644,0.0004576325],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014299186,0.000090938505,0.0011989656,0.00015725671,0.00007208909,0.00024980787,0.00014367438,0.70487297,0.056623653,0.014288552,0.0012190609,0.22094002],"study_design_scores_gemma":[0.0000023914688,0.000015082064,0.000118312375,0.0000021697936,0.0000058542873,0.000019014655,0.0000029824394,0.99593025,0.0029319716,0.00067582814,0.00029246896,0.000003612512],"about_ca_topic_score_codex":0.0038388697,"about_ca_topic_score_gemma":0.0036158073,"teacher_disagreement_score":0.0038388697,"about_ca_system_score_codex":0.00038256732,"about_ca_system_score_gemma":0.00040636348,"threshold_uncertainty_score":0.0076330304},"labels":[],"label_agreement":null},{"id":"W4410291915","doi":"10.1016/j.specom.2025.103253","title":"Human and automatic voice comparison with regionally variable speech samples","year":2025,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Arts and Humanities Research Council; Arts and Humanities Research Board","keywords":"Speech recognition; Computer science; Variable (mathematics); Voice activity detection; Speech processing; Natural language processing; Artificial intelligence; Mathematics","score_opus":0.03229459497336561,"score_gpt":0.29117057046485045,"score_spread":0.25887597549148483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410291915","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91425514,0.0011301967,0.07640118,0.0000805869,0.00029796816,0.00009016684,0.0009224908,0.0012128445,0.005609506],"genre_scores_gemma":[0.98140496,0.00017351999,0.015162933,0.000038179205,0.00004815747,0.000028873645,0.0006920042,0.00025621636,0.0021951431],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991032,0.00034861147,0.00005911061,0.0002466315,0.00015438178,0.000088110675],"domain_scores_gemma":[0.9983589,0.00093331136,0.000047590638,0.00016597447,0.00043634805,0.000057885027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010982524,0.0004149877,0.00043813203,0.0007192447,0.00034793938,0.00082184974,0.00035518507,0.0008635613,0.006349981],"category_scores_gemma":[0.003631914,0.00017785515,0.0004409571,0.00030179057,0.0004475479,0.00060866156,0.00047118354,0.0002490463,0.0015283143],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008967731,0.00015744443,0.008196811,0.00051025185,0.0002413486,0.00079373206,0.0007514661,0.0058527724,0.76388556,0.0008251068,0.0010293814,0.2087883],"study_design_scores_gemma":[0.00045436822,0.0024231295,0.18726987,0.00008252404,0.0007631492,0.005862872,0.0016318202,0.12037203,0.6705999,0.0012536807,0.009119364,0.00016740031],"about_ca_topic_score_codex":0.0017015825,"about_ca_topic_score_gemma":0.002675948,"teacher_disagreement_score":0.006349981,"about_ca_system_score_codex":0.0002146324,"about_ca_system_score_gemma":0.0002514681,"threshold_uncertainty_score":0.021242797},"labels":[],"label_agreement":null},{"id":"W4410431605","doi":"10.1016/j.csl.2025.101815","title":"BERSting at the screams: A benchmark for distanced, emotional and shouted speech recognition","year":2025,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Computer science; Benchmark (surveying); Speech recognition; Emotion recognition; Natural language processing","score_opus":0.01565752871258395,"score_gpt":0.2604487816432463,"score_spread":0.24479125293066237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410431605","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36261338,0.026697999,0.04577526,0.003958049,0.007957797,0.0029523156,0.44590357,0.04962753,0.05451411],"genre_scores_gemma":[0.113848,0.0019041498,0.038661715,0.0009613886,0.00050866744,0.001184652,0.82801414,0.001057448,0.013859823],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99349535,0.0014371929,0.00084564066,0.0014812791,0.0021413222,0.00059928227],"domain_scores_gemma":[0.99509686,0.0012965263,0.0003247551,0.001179124,0.0015696748,0.0005329923],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034898524,0.0051511494,0.0025513822,0.00336269,0.0017956507,0.0028002532,0.004288053,0.004305886,0.0066460217],"category_scores_gemma":[0.008632181,0.00050602684,0.0017593572,0.0024276322,0.0012889127,0.0030892014,0.004704046,0.0027391673,0.016798126],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034471988,0.002146336,0.008837781,0.005208268,0.00073471986,0.0018943951,0.0009301549,0.01627897,0.031835083,0.0017994675,0.56688875,0.35999885],"study_design_scores_gemma":[0.0014899498,0.004714636,0.10420149,0.0019611141,0.0007180106,0.009171566,0.006402718,0.21858467,0.08512628,0.006732907,0.5599101,0.0009865361],"about_ca_topic_score_codex":0.018667305,"about_ca_topic_score_gemma":0.029806416,"teacher_disagreement_score":0.018667305,"about_ca_system_score_codex":0.0016036388,"about_ca_system_score_gemma":0.001604863,"threshold_uncertainty_score":0.037117302},"labels":[],"label_agreement":null},{"id":"W4410617847","doi":"10.54254/2755-2721/2025.tj23214","title":"Study for Automatic Speech Recognition for Wav2Vec2.0","year":2025,"lang":"en","type":"article","venue":"Applied and Computational Engineering","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Speech recognition; Computer science; Natural language processing","score_opus":0.019156557871145046,"score_gpt":0.24763702891965278,"score_spread":0.22848047104850774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410617847","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23502444,0.0042861337,0.7125656,0.0024295885,0.001874535,0.00085888343,0.007411258,0.02148932,0.014060288],"genre_scores_gemma":[0.61412233,0.0012713998,0.31197765,0.0010136038,0.00036815563,0.001081036,0.045388885,0.001808687,0.022968147],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99844956,0.00048393852,0.000107843276,0.00034484908,0.00047374945,0.00014012677],"domain_scores_gemma":[0.99766564,0.00071410416,0.000055841072,0.00034536264,0.0011556055,0.00006335068],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016716875,0.0010733457,0.00050516706,0.0006956874,0.000554759,0.0010762454,0.00088019355,0.0007411802,0.006066736],"category_scores_gemma":[0.0048794863,0.00032397997,0.0008971192,0.0006884493,0.0003099473,0.001800782,0.0005798554,0.0013113106,0.004844561],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00076308387,0.0007257844,0.009111036,0.0006457707,0.0003307538,0.0005815821,0.00033716124,0.08944024,0.07140314,0.011148117,0.082508616,0.7330048],"study_design_scores_gemma":[0.000049824495,0.00039667543,0.004292229,0.000040408333,0.00004979419,0.0002997086,0.0002025452,0.9225529,0.04666231,0.001985528,0.023432178,0.000035891826],"about_ca_topic_score_codex":0.015615127,"about_ca_topic_score_gemma":0.013448612,"teacher_disagreement_score":0.015615127,"about_ca_system_score_codex":0.0007314947,"about_ca_system_score_gemma":0.0013008298,"threshold_uncertainty_score":0.031048477},"labels":[],"label_agreement":null},{"id":"W4411272738","doi":"10.1007/978-981-96-1758-6_16","title":"An Efficient Voice Replay Antispoofing Method","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hamilton Health Sciences","funders":"","keywords":"Computer science; Speech recognition","score_opus":0.016423412517061097,"score_gpt":0.26617372554144547,"score_spread":0.24975031302438438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411272738","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006166455,0.00024764356,0.9886684,0.000039372135,0.00010161836,0.00006557458,0.00005407523,0.0019058331,0.0027509942],"genre_scores_gemma":[0.09410835,0.00036008775,0.88732517,0.00008484729,0.00013696826,0.00014021731,0.00041884635,0.00036294223,0.017062506],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995197,0.00007898454,0.000028217382,0.00010234234,0.000229709,0.000040985353],"domain_scores_gemma":[0.9996376,0.00008762739,0.000024872503,0.00011967927,0.00011369345,0.00001643364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003118392,0.0011899784,0.0008092722,0.0008004332,0.0005597619,0.0006422716,0.0010200056,0.00070837105,0.009805408],"category_scores_gemma":[0.0006101938,0.00040387886,0.0006192786,0.000536655,0.0003240448,0.00075441,0.0009103006,0.0007841188,0.004777423],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004239701,0.00009405676,0.00015325446,0.00012424223,0.000046183275,0.0001446004,0.00005761238,0.004933628,0.21985562,0.0048908195,0.0038562885,0.7654197],"study_design_scores_gemma":[0.0001491482,0.0005333634,0.000869885,0.000037452985,0.00015620852,0.0017394357,0.000098949036,0.6382201,0.30657035,0.006177457,0.04536964,0.00007807041],"about_ca_topic_score_codex":0.0006366989,"about_ca_topic_score_gemma":0.00096506457,"teacher_disagreement_score":0.009805408,"about_ca_system_score_codex":0.00018539236,"about_ca_system_score_gemma":0.00036827425,"threshold_uncertainty_score":0.032802343},"labels":[],"label_agreement":null},{"id":"W4411757453","doi":"10.1145/3746638","title":"Latency-Aware Pruning and Quantization of Self-Supervised Speech Transformers for Edge Devices","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Embedded Computing Systems","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Quantization (signal processing); Transformer; Speech recognition; Artificial intelligence; Algorithm; Engineering; Electrical engineering","score_opus":0.022925303094301124,"score_gpt":0.2754509292688123,"score_spread":0.2525256261745112,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411757453","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05160585,0.000432548,0.9366417,0.00020884047,0.00013577576,0.00012617503,0.00021005831,0.0074801845,0.003158973],"genre_scores_gemma":[0.46892673,0.00033740734,0.5193319,0.00035450087,0.000095603755,0.00024622108,0.0011454544,0.00087027333,0.008692018],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99946827,0.00007171817,0.00004322959,0.00010336245,0.00025049894,0.00006296596],"domain_scores_gemma":[0.9986786,0.0005039169,0.00008612529,0.00027699562,0.0003901008,0.000064295375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005621382,0.00088757236,0.0006211222,0.00067685964,0.00045095352,0.00089526456,0.0014455657,0.00055887026,0.0038854196],"category_scores_gemma":[0.0036298647,0.00029432788,0.0004221063,0.0005273615,0.00056861085,0.0014299258,0.0012104454,0.0011472136,0.001655587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005096074,0.00019299665,0.001730453,0.00017103872,0.000039152106,0.00024012315,0.00025235614,0.064723454,0.072625905,0.0055386536,0.009571158,0.84440506],"study_design_scores_gemma":[0.00004227296,0.00014448482,0.0007599499,0.000022242595,0.000023313509,0.00019842673,0.00010171741,0.9164304,0.07167791,0.0052026473,0.005376042,0.000020584617],"about_ca_topic_score_codex":0.00327791,"about_ca_topic_score_gemma":0.009400979,"teacher_disagreement_score":0.0038854196,"about_ca_system_score_codex":0.0005061296,"about_ca_system_score_gemma":0.0014066008,"threshold_uncertainty_score":0.0129980445},"labels":[],"label_agreement":null},{"id":"W4411792967","doi":"10.18280/ts.420312","title":"Mel-Spectrograms Based LSTM Model for Speech Emotion Recognition","year":2025,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Spectrogram; Speech recognition; Computer science; Emotion recognition; Artificial intelligence","score_opus":0.03934978002030785,"score_gpt":0.26331803997867764,"score_spread":0.2239682599583698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411792967","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05611865,0.0015301392,0.9343374,0.0005622228,0.0002569904,0.00004544,0.00060263183,0.002614885,0.0039316323],"genre_scores_gemma":[0.86814004,0.0008702682,0.1193872,0.00031208553,0.00010775868,0.0001384092,0.0010415047,0.000115829665,0.009886979],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999138,0.000017393368,0.0000057209845,0.000029793926,0.000019503126,0.000013737993],"domain_scores_gemma":[0.99988806,0.00004758355,0.000010445345,0.000010256275,0.00003840369,0.0000052032615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022360774,0.0005928212,0.00027839674,0.0002197002,0.00013115893,0.0003179183,0.0005382559,0.00050279585,0.0024765015],"category_scores_gemma":[0.00058974954,0.00017554227,0.00035698203,0.00027836623,0.00018380175,0.00059447315,0.00031896116,0.0009366103,0.0010246406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002735388,0.00015525371,0.0012692931,0.00021072982,0.00013088131,0.00016328103,0.0001262454,0.5374265,0.076213524,0.0073953127,0.007017769,0.3696177],"study_design_scores_gemma":[0.0000022255529,0.000022048764,0.00020336725,0.000005129599,0.000007852528,0.000014253968,0.000005383079,0.99476457,0.002876329,0.0014588841,0.0006361684,0.0000037569625],"about_ca_topic_score_codex":0.0037818411,"about_ca_topic_score_gemma":0.007203087,"teacher_disagreement_score":0.0037818411,"about_ca_system_score_codex":0.00044593666,"about_ca_system_score_gemma":0.00040313706,"threshold_uncertainty_score":0.008284748},"labels":[],"label_agreement":null},{"id":"W4411859426","doi":"10.1007/978-981-96-6599-0_22","title":"Optimizing Learnable Frequency-Domain Filterbanks for Depression Detection via Speech Representation Disentanglement","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Representation (politics); Speech recognition; Frequency domain; Domain (mathematical analysis); Algorithm; Artificial intelligence; Mathematics; Computer vision","score_opus":0.021331876213969064,"score_gpt":0.26678365580849234,"score_spread":0.24545177959452327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411859426","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024907025,0.0005540748,0.9712812,0.00024199621,0.000066976245,0.000046327656,0.00027595647,0.0014169079,0.0012095664],"genre_scores_gemma":[0.46981457,0.0007173243,0.5177398,0.00029734534,0.00013935458,0.00028707946,0.0017166943,0.00028453642,0.009003323],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997429,0.00006019576,0.000017246506,0.000082516504,0.00004694798,0.000050104707],"domain_scores_gemma":[0.99934,0.0004850753,0.000035452198,0.000034481036,0.00008013496,0.000024694478],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007304863,0.0010688097,0.0008621661,0.00043205635,0.00021439676,0.0008899269,0.00071995653,0.0012707441,0.0039463965],"category_scores_gemma":[0.0020609589,0.00054213125,0.00074459537,0.00040504427,0.0003270769,0.0009385904,0.0008509106,0.0011472338,0.0018591796],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005988422,0.00021793273,0.0010377226,0.00015559894,0.00015804941,0.00014282281,0.00007631351,0.24718846,0.047267865,0.0044776914,0.0052554104,0.6934233],"study_design_scores_gemma":[0.000030717398,0.00006486911,0.00060042203,0.000011459922,0.00003347073,0.000045205466,0.000018736706,0.99094415,0.0052436455,0.0022567366,0.00074088044,0.000009653691],"about_ca_topic_score_codex":0.0045500407,"about_ca_topic_score_gemma":0.0081703365,"teacher_disagreement_score":0.0045500407,"about_ca_system_score_codex":0.0004406504,"about_ca_system_score_gemma":0.0010501891,"threshold_uncertainty_score":0.013202012},"labels":[],"label_agreement":null},{"id":"W4411934141","doi":"10.1162/tacl_a_00759","title":"A Comparative Approach for Auditing Multilingual Phonetic Transcript Archives","year":2025,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Audit; Natural language processing; Linguistics; Speech recognition; Data science; Artificial intelligence; World Wide Web; Accounting; Business","score_opus":0.030497832723930175,"score_gpt":0.29480967779670436,"score_spread":0.26431184507277417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411934141","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17001481,0.0015858165,0.7810168,0.0013300374,0.000449969,0.0011102752,0.0052370913,0.014668073,0.024587087],"genre_scores_gemma":[0.35515332,0.00037896936,0.63463527,0.00022739288,0.00014617621,0.00050430093,0.003885173,0.00095039525,0.0041190768],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.98816663,0.0046687634,0.0009603114,0.0019515596,0.0038116872,0.00044094372],"domain_scores_gemma":[0.96839005,0.0077804155,0.0018230262,0.007962522,0.013064839,0.0009791758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008241626,0.00089352095,0.0007599272,0.0074893553,0.0020163292,0.0033961122,0.0025237398,0.0013337313,0.007476762],"category_scores_gemma":[0.0327965,0.0006214657,0.000655517,0.00462818,0.0011086151,0.0033203252,0.0049565765,0.0012551263,0.0032990512],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012321378,0.00041866102,0.032647017,0.0009832545,0.00028722032,0.0013555823,0.0070505654,0.009237997,0.10908742,0.009038255,0.011176769,0.81748503],"study_design_scores_gemma":[0.00030463006,0.0016339,0.12670118,0.00090566685,0.0007534023,0.005274907,0.019650964,0.36817104,0.2681974,0.030186707,0.17757004,0.0006501582],"about_ca_topic_score_codex":0.0059289606,"about_ca_topic_score_gemma":0.015480884,"teacher_disagreement_score":0.008241626,"about_ca_system_score_codex":0.001287349,"about_ca_system_score_gemma":0.0030373689,"threshold_uncertainty_score":0.043586373},"labels":[],"label_agreement":null},{"id":"W4411990369","doi":"10.1007/978-3-031-85747-8_10","title":"An Efficient Clustering Algorithm for Self-Supervised Speaker Recognition","year":2025,"lang":"en","type":"book-chapter","venue":"Machine translation","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Cluster analysis; Pattern recognition (psychology); Artificial intelligence; Speaker recognition; Speech recognition","score_opus":0.0329297984314789,"score_gpt":0.2570398133233841,"score_spread":0.2241100148919052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411990369","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011300332,0.00016069076,0.995447,0.000028907307,0.00007427902,0.000044160508,0.0001070128,0.0020326315,0.00097523094],"genre_scores_gemma":[0.012227922,0.00012372893,0.9801777,0.00006339417,0.000057631005,0.00016467928,0.0007230958,0.00046384125,0.0059981397],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988575,0.00019508952,0.00006882804,0.00031209184,0.0004782856,0.00008820762],"domain_scores_gemma":[0.999022,0.0002567459,0.00004048634,0.00021068045,0.00043951554,0.000030484021],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008103116,0.0013402521,0.0016188511,0.0015196609,0.00118338,0.0009813453,0.0028377655,0.001444564,0.008766781],"category_scores_gemma":[0.0018346894,0.0008105568,0.0013764041,0.0022066263,0.0005232378,0.0012648194,0.0016266265,0.0016380316,0.010937555],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011030782,0.00007746631,0.00017321829,0.00008465502,0.00009335233,0.000042011317,0.00007247905,0.036212903,0.022826955,0.004921495,0.015809504,0.91957575],"study_design_scores_gemma":[0.00002559942,0.000049253576,0.00073285325,0.000017640292,0.000040853993,0.00023362137,0.000043583306,0.9567262,0.018842356,0.0096570635,0.01358509,0.000045812285],"about_ca_topic_score_codex":0.006942931,"about_ca_topic_score_gemma":0.013284141,"teacher_disagreement_score":0.008766781,"about_ca_system_score_codex":0.00068886636,"about_ca_system_score_gemma":0.0011299999,"threshold_uncertainty_score":0.02932775},"labels":[],"label_agreement":null},{"id":"W4412020141","doi":"10.19139/soic-2310-5070-2521","title":"A Hybrid Approach of Long Short Term Memory and Transformer Models for Speech Emotion Recognition","year":2025,"lang":"en","type":"article","venue":"Statistics Optimization & Information Computing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Speech recognition; Term (time); Transformer; Long short term memory; Computer science; Short-term memory; Cognitive psychology; Natural language processing; Psychology; Artificial intelligence; Cognition; Engineering; Artificial neural network; Working memory; Electrical engineering; Recurrent neural network; Neuroscience","score_opus":0.02329019575944726,"score_gpt":0.2514189199685227,"score_spread":0.22812872420907546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412020141","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046435997,0.0015482644,0.94178796,0.0003979523,0.0002997806,0.00009752975,0.00034462442,0.0041735508,0.0049143317],"genre_scores_gemma":[0.8234814,0.0012253037,0.16361667,0.00048571426,0.00012288711,0.0001439458,0.0010195232,0.00020053319,0.009704035],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99974924,0.000047649417,0.000019098476,0.00008564414,0.000059276226,0.000039215305],"domain_scores_gemma":[0.99973303,0.000093073344,0.00001861078,0.000038005768,0.00009989418,0.000017402466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005917244,0.0009953594,0.0005656333,0.0005566019,0.00020015445,0.0007897,0.0011334049,0.00061631063,0.002613223],"category_scores_gemma":[0.0010504213,0.0002656061,0.000957247,0.00050786114,0.00024531264,0.0016821377,0.00076853234,0.0012340295,0.0014799181],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000589583,0.00033288985,0.0021745085,0.0002642629,0.00039004415,0.0002706053,0.0001700947,0.1095457,0.06660797,0.0064620795,0.0059143384,0.807278],"study_design_scores_gemma":[0.000016231248,0.00019819265,0.00056510145,0.00001769063,0.00010706802,0.00014497235,0.000043455428,0.9781279,0.015337447,0.0035956278,0.0018240706,0.000022198099],"about_ca_topic_score_codex":0.0039461376,"about_ca_topic_score_gemma":0.006255255,"teacher_disagreement_score":0.0039461376,"about_ca_system_score_codex":0.00041448974,"about_ca_system_score_gemma":0.0006028156,"threshold_uncertainty_score":0.008742094},"labels":[],"label_agreement":null},{"id":"W4412195314","doi":"10.3390/s25144288","title":"Phoneme-Aware Hierarchical Augmentation and Semantic-Aware SpecAugment for Low-Resource Cantonese Speech Recognition","year":2025,"lang":"en","type":"article","venue":"Sensors","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Natural Science Foundation of Shandong Province; National Natural Science Foundation of China","keywords":"Computer science; Speech recognition; Pronunciation; Word error rate; Context (archaeology); Masking (illustration); Artificial intelligence","score_opus":0.016940222352218908,"score_gpt":0.2642564729911856,"score_spread":0.2473162506389667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412195314","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.100218594,0.00053140736,0.8894449,0.00021447241,0.0001266335,0.000051525833,0.00026197615,0.0056714294,0.0034790987],"genre_scores_gemma":[0.82823396,0.00020664131,0.16427699,0.00019497967,0.00005892266,0.00010757085,0.0009586762,0.00031418,0.0056479964],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9997284,0.00006871804,0.000009458193,0.00008030904,0.00007006136,0.000043103697],"domain_scores_gemma":[0.999739,0.0000963489,0.000020665277,0.000068458176,0.000055123586,0.00002038414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003634873,0.00087257376,0.00045277335,0.00024358957,0.0002697807,0.00038229465,0.0007378985,0.00036208867,0.0016383225],"category_scores_gemma":[0.000936108,0.00021703643,0.0004368263,0.00019629979,0.0004293967,0.0005819338,0.0009673855,0.0008105267,0.0008598714],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00056802697,0.00014677823,0.0016440293,0.000107489635,0.00006292038,0.00021913754,0.00025375313,0.2581974,0.18546501,0.0049353205,0.0047645685,0.54363555],"study_design_scores_gemma":[0.000009465203,0.00011053841,0.0006230129,0.0000069751177,0.000015900105,0.00006095564,0.000032455213,0.96149075,0.033313315,0.001851924,0.0024670053,0.00001783571],"about_ca_topic_score_codex":0.005847094,"about_ca_topic_score_gemma":0.0123421615,"teacher_disagreement_score":0.005847094,"about_ca_system_score_codex":0.00028738953,"about_ca_system_score_gemma":0.00072746543,"threshold_uncertainty_score":0.011626124},"labels":[],"label_agreement":null},{"id":"W4412222534","doi":"","title":"D7.6 – Demo site report #6 N. Denmark","year":2023,"lang":"en","type":"report","venue":"VBN Forskningsportal (Aalborg Universitet)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Semtech (Canada)","funders":"","keywords":"Geography","score_opus":0.06467585731613737,"score_gpt":0.29003145903714206,"score_spread":0.2253556017210047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412222534","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035675627,0.0006843719,0.010285379,0.00079634786,0.0010567643,0.0008102787,0.4048407,0.009227183,0.5687314],"genre_scores_gemma":[0.021119023,0.0021587578,0.021499526,0.0003443947,0.00011998412,0.0014670091,0.54559964,0.013639697,0.39405188],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99767333,0.0003814884,0.00017628369,0.00034022046,0.0011825542,0.00024614704],"domain_scores_gemma":[0.99811506,0.00031637668,0.00011978452,0.00040219963,0.0007665314,0.00028004174],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0033627606,0.0008772697,0.00065023033,0.0016966931,0.00083340897,0.004044574,0.001354859,0.00114576,0.36111814],"category_scores_gemma":[0.004447569,0.0009643725,0.0006742088,0.00217782,0.0002939975,0.0020993394,0.0019266567,0.0013517167,0.3620474],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020991865,0.00006550312,0.00097048323,0.00057133683,0.000012587627,0.00013780319,0.0004276751,0.00118802,0.0011331582,0.0057171434,0.9478766,0.041689783],"study_design_scores_gemma":[0.000013496099,0.000014272175,0.0010114033,0.00007020516,0.0000021984447,0.000026789206,0.00015043264,0.0001309318,0.00046431043,0.00036064413,0.9977435,0.000011854163],"about_ca_topic_score_codex":0.030854207,"about_ca_topic_score_gemma":0.022284247,"teacher_disagreement_score":0.36111814,"about_ca_system_score_codex":0.0016053115,"about_ca_system_score_gemma":0.0030009586,"threshold_uncertainty_score":0.9112874},"labels":[],"label_agreement":null},{"id":"W4412566360","doi":"10.36227/techrxiv.175321809.95815200/v1","title":"A Survey on Speech Large Language Models for Understanding","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Optech (Canada)","funders":"","keywords":"Linguistics; Computer science; Indirect speech; Natural language processing; Philosophy","score_opus":0.15512074020316538,"score_gpt":0.33272328338252016,"score_spread":0.17760254317935478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412566360","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060609947,0.47874457,0.47561264,0.008235142,0.0012125712,0.0002600099,0.0030381004,0.0034269823,0.023409104],"genre_scores_gemma":[0.07057094,0.63138634,0.26702428,0.0031619465,0.002640734,0.00076423027,0.012608261,0.001525155,0.010318084],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.997928,0.00083008205,0.0002630564,0.0003922741,0.00052411796,0.000062478866],"domain_scores_gemma":[0.9909725,0.0070581967,0.0002454306,0.000706385,0.00090195076,0.00011551648],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036316914,0.0019264193,0.0013817989,0.0039529228,0.00062719913,0.003979079,0.0027662723,0.00197482,0.011716993],"category_scores_gemma":[0.01580172,0.00091380667,0.0014848489,0.0037523538,0.0009831851,0.008714201,0.0020438724,0.002569147,0.0053888904],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010444284,0.0000927055,0.0015815251,0.006025023,0.00016582699,0.0001588251,0.0007384128,0.01344438,0.0016867332,0.061412267,0.042656623,0.8719332],"study_design_scores_gemma":[0.000030325526,0.00018279113,0.0023432297,0.004926945,0.0002777189,0.00079347554,0.0008635932,0.09557939,0.0034614946,0.13528576,0.7561047,0.00015059336],"about_ca_topic_score_codex":0.004793379,"about_ca_topic_score_gemma":0.0044841613,"teacher_disagreement_score":0.011716993,"about_ca_system_score_codex":0.0016371547,"about_ca_system_score_gemma":0.0031808624,"threshold_uncertainty_score":0.039197266},"labels":[],"label_agreement":null},{"id":"W4412672023","doi":"10.1101/2025.07.25.25332211","title":"Performance Analysis of Speech Recognition Models in Automated Scoring of the QuickSIN Test","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Test (biology); Speech recognition; Computer science; Natural language processing; Artificial intelligence; Pattern recognition (psychology); Biology","score_opus":0.046860780830607664,"score_gpt":0.2710023107536934,"score_spread":0.22414152992308575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412672023","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93429285,0.00051641464,0.059054565,0.000083138126,0.000107331,0.00032069747,0.00057260285,0.0015126724,0.0035398076],"genre_scores_gemma":[0.9731041,0.00010537206,0.024954623,0.000038633792,0.000021842854,0.00019264959,0.00048932066,0.0001442048,0.0009493005],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99195063,0.004226014,0.00064906053,0.0013141347,0.0016438351,0.00021639097],"domain_scores_gemma":[0.9675565,0.02261754,0.0020896557,0.0018373893,0.0053153033,0.00058370346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008740417,0.0010533364,0.0006652251,0.0011686338,0.00028532144,0.0016275978,0.00084542664,0.00060556177,0.0027490936],"category_scores_gemma":[0.036560923,0.00032043786,0.00061317225,0.00055048254,0.00034974655,0.0010079474,0.0010459054,0.00035288156,0.002091746],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.014540186,0.00080158614,0.31489196,0.00059403,0.00068582257,0.00027413355,0.0023988269,0.024689315,0.06384716,0.0009373136,0.0036496522,0.57269007],"study_design_scores_gemma":[0.00034360916,0.0067646024,0.38362056,0.00016722077,0.00052117987,0.0012714312,0.0013609125,0.50516224,0.09550489,0.00079971796,0.004189847,0.00029383303],"about_ca_topic_score_codex":0.0026974112,"about_ca_topic_score_gemma":0.0025725646,"teacher_disagreement_score":0.008740417,"about_ca_system_score_codex":0.0005199859,"about_ca_system_score_gemma":0.00045163877,"threshold_uncertainty_score":0.046224236},"labels":[],"label_agreement":null},{"id":"W4412754181","doi":"10.2139/ssrn.5372225","title":"Stacked One-vs-One (Sovo): A New Approach for Multi-Class Classification for Semg Recognition","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Class (philosophy); Pattern recognition (psychology); Artificial intelligence; Computer science; Speech recognition","score_opus":0.14259113620166353,"score_gpt":0.3227645324264219,"score_spread":0.18017339622475836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412754181","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011846619,0.0006318913,0.9766549,0.00015497499,0.00041843808,0.00014561607,0.0004107449,0.007587673,0.0021491363],"genre_scores_gemma":[0.2287327,0.0006295888,0.75760084,0.000516282,0.00038405985,0.00034568668,0.001958654,0.0017069401,0.0081252735],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981614,0.00034580458,0.00011320058,0.00044635145,0.0006541935,0.00027910256],"domain_scores_gemma":[0.99837315,0.0005008493,0.00009386147,0.00045604628,0.00044691472,0.0001290743],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017845756,0.0021110103,0.002936588,0.0028536224,0.0010866609,0.0025613033,0.0029198604,0.0024150822,0.008806184],"category_scores_gemma":[0.0033236106,0.0007462185,0.0020730244,0.0022314726,0.0007117541,0.0022320896,0.0030445217,0.0023581323,0.0046959827],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045533184,0.00020520996,0.00079526514,0.00011137416,0.0001535642,0.00006900029,0.00008162369,0.00923725,0.026251694,0.0027393785,0.0063182935,0.9535819],"study_design_scores_gemma":[0.000040420742,0.0002452249,0.0018002634,0.00004357726,0.00011312162,0.00031951146,0.0001333655,0.9352739,0.035442412,0.016044617,0.010466126,0.00007748945],"about_ca_topic_score_codex":0.0046514925,"about_ca_topic_score_gemma":0.010285694,"teacher_disagreement_score":0.008806184,"about_ca_system_score_codex":0.0004939655,"about_ca_system_score_gemma":0.0012922316,"threshold_uncertainty_score":0.029459655},"labels":[],"label_agreement":null},{"id":"W4412871783","doi":"10.1121/10.0037268","title":"Transforming child speech data into clinical-grade artificial intelligence pipelines for speech-language impairment detection","year":2025,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Language impairment; Speech recognition; Computer science; Psychology; Audiology; Natural language processing; Medicine; Developmental psychology","score_opus":0.04871944744811161,"score_gpt":0.3495868000122566,"score_spread":0.300867352564145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412871783","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051862635,0.00044938485,0.881746,0.0014283479,0.00021936515,0.00092901033,0.019600049,0.03573882,0.008026332],"genre_scores_gemma":[0.26950535,0.00050978013,0.68788904,0.00067339645,0.00014060421,0.0018066021,0.03182923,0.0026428476,0.0050031766],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976178,0.00070986967,0.00025424402,0.0007025358,0.0005750559,0.00014053349],"domain_scores_gemma":[0.9937866,0.0024343645,0.0003976038,0.0015044794,0.0016447492,0.00023232502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033147486,0.0013043626,0.0005572012,0.0023976385,0.0005468217,0.0020213828,0.0014014002,0.0007773119,0.008804719],"category_scores_gemma":[0.021347988,0.00045481508,0.000839346,0.0010879573,0.00059257325,0.0015888308,0.002937075,0.0016029167,0.007721825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008914676,0.00033473183,0.034205843,0.00062292186,0.00030170358,0.0007879668,0.0022130394,0.014688289,0.045763057,0.009853593,0.039390653,0.8509467],"study_design_scores_gemma":[0.00023600445,0.0012002612,0.12388622,0.0007136205,0.00044490932,0.0024860862,0.004097909,0.36343646,0.18776657,0.09002647,0.22524446,0.0004610522],"about_ca_topic_score_codex":0.006172978,"about_ca_topic_score_gemma":0.012516893,"teacher_disagreement_score":0.008804719,"about_ca_system_score_codex":0.0009657793,"about_ca_system_score_gemma":0.0022207217,"threshold_uncertainty_score":0.029454708},"labels":[],"label_agreement":null},{"id":"W4412944958","doi":"10.18653/v1/2025.acl-long.961","title":"ZIPA: A family of efficient models for multilingual phone recognition","year":2025,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Phone; Computer science; Speech recognition; Artificial intelligence; Pattern recognition (psychology); Linguistics","score_opus":0.05388308592547792,"score_gpt":0.2870036363835925,"score_spread":0.23312055045811458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412944958","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008021986,0.0007612257,0.9732175,0.00026113016,0.0002031999,0.00010673279,0.0018753129,0.013517604,0.0020352826],"genre_scores_gemma":[0.2820615,0.0015869114,0.6769593,0.0008202369,0.00041451177,0.0010759572,0.016639303,0.0036435893,0.016798707],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989484,0.00027270283,0.0000615298,0.00034753446,0.00027227483,0.00009759294],"domain_scores_gemma":[0.9981735,0.0007937636,0.00008345731,0.00041432044,0.00043050674,0.00010448353],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016292545,0.0020295416,0.0013118627,0.0012117934,0.0007167821,0.0016054116,0.0030261225,0.0013352869,0.00810727],"category_scores_gemma":[0.0067633484,0.0009582115,0.0015648172,0.0010339391,0.0005433446,0.0025969432,0.0029568358,0.0032477814,0.011302676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006324069,0.00020766238,0.0029172034,0.0003344563,0.0002984091,0.00022265625,0.00019771367,0.3291301,0.015227287,0.0105052665,0.030360553,0.6099663],"study_design_scores_gemma":[0.000016697932,0.000057358186,0.00022703738,0.000013881118,0.000023746581,0.00008020397,0.000021060067,0.9843137,0.0031638038,0.005805053,0.006257143,0.000020273133],"about_ca_topic_score_codex":0.006638352,"about_ca_topic_score_gemma":0.010394056,"teacher_disagreement_score":0.00810727,"about_ca_system_score_codex":0.0007766408,"about_ca_system_score_gemma":0.0015290807,"threshold_uncertainty_score":0.027121544},"labels":[],"label_agreement":null},{"id":"W4412967876","doi":"10.1101/2025.07.14.25331543","title":"CharMark: A Markov Approach to Linguistic Biomarkers in Dementia","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Science Foundation","keywords":"Dementia; Discriminative model; Character (mathematics); Cognition; Cognitive decline; Psychology; Computer science; Cognitive psychology; Artificial intelligence; Linguistics; Medicine; Disease; Mathematics; Psychiatry","score_opus":0.033594758036118215,"score_gpt":0.27707004961444714,"score_spread":0.24347529157832892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412967876","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05061666,0.00065638765,0.9430784,0.0009163609,0.0000708973,0.00008001999,0.0009497898,0.00095773995,0.0026738443],"genre_scores_gemma":[0.7210684,0.00076958846,0.2682923,0.00034676213,0.00023906652,0.00034144858,0.0018045816,0.00017713908,0.00696082],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992874,0.0003613838,0.000031131385,0.00016929045,0.00008825005,0.000062611856],"domain_scores_gemma":[0.99752253,0.0018328897,0.000231621,0.00016158623,0.00015625264,0.000095048184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017742087,0.0005974521,0.000529426,0.0019162694,0.0004579862,0.0012930675,0.0008009406,0.0007719962,0.003152479],"category_scores_gemma":[0.0053364076,0.00040580097,0.0009508133,0.0008779215,0.00072036765,0.00093626324,0.0012671768,0.0011059891,0.0005971822],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047914503,0.00023226455,0.01710856,0.00020494011,0.00023540528,0.00055524823,0.00074065325,0.5724863,0.0069248048,0.15206258,0.005234812,0.24373534],"study_design_scores_gemma":[0.0000056674603,0.000026458853,0.0010921473,0.000014923854,0.0000108997665,0.000036920625,0.000029737283,0.93953687,0.0003116647,0.058060803,0.0008605371,0.000013272575],"about_ca_topic_score_codex":0.008726955,"about_ca_topic_score_gemma":0.008738868,"teacher_disagreement_score":0.008726955,"about_ca_system_score_codex":0.0009979741,"about_ca_system_score_gemma":0.0011817787,"threshold_uncertainty_score":0.017352343},"labels":[],"label_agreement":null},{"id":"W4412973321","doi":"10.1121/10.0038240","title":"Exploring the perception–production link in bilingual voices","year":2025,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Perception; Psychology; Production (economics); Quality (philosophy); Identification (biology); Identity (music); Cognitive psychology; Speech recognition; Acoustics; Computer science","score_opus":0.04558349218917922,"score_gpt":0.27866690866120813,"score_spread":0.2330834164720289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412973321","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9947173,0.00016730913,0.0026707395,0.000038913207,0.0000042449615,0.000009205162,0.00006817728,0.000010621249,0.002313476],"genre_scores_gemma":[0.99871933,0.000059849728,0.0008881504,0.000015734722,0.000005205185,0.000007095929,0.0000462846,0.000009570889,0.00024867046],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99960524,0.0001232972,0.000025184803,0.0000991166,0.00010777922,0.000039475337],"domain_scores_gemma":[0.99781066,0.0015610593,0.00026625895,0.000106300075,0.00017994622,0.00007584791],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009597469,0.00020210535,0.00018812522,0.0003959823,0.0002616901,0.000962821,0.000107788284,0.00024364135,0.0018833957],"category_scores_gemma":[0.0044824528,0.0001738323,0.00014216374,0.00021391507,0.00047850545,0.0005472489,0.0007494075,0.0003008612,0.00018112946],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029091837,0.00021815673,0.31881997,0.00038843253,0.00015741843,0.0014114416,0.012549599,0.0010383832,0.5896002,0.001317934,0.00016943253,0.07141982],"study_design_scores_gemma":[0.000024393119,0.00043161662,0.97400224,0.000019112447,0.000037789232,0.0008955924,0.0025705097,0.0014929799,0.018981183,0.0010242901,0.00049746427,0.000022890577],"about_ca_topic_score_codex":0.0016362049,"about_ca_topic_score_gemma":0.002736013,"teacher_disagreement_score":0.0018833957,"about_ca_system_score_codex":0.00020837165,"about_ca_system_score_gemma":0.00025253536,"threshold_uncertainty_score":0.0063005686},"labels":[],"label_agreement":null},{"id":"W4412974457","doi":"10.1121/10.0037796","title":"Utilizing extended high frequencies for fricative identification","year":2025,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Intelligibility (philosophy); CLARITY; Identification (biology); Speech recognition; Random forest; Computer science; Acoustics; Artificial intelligence; Physics","score_opus":0.02347862433249369,"score_gpt":0.280669455454313,"score_spread":0.2571908311218193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412974457","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25807545,0.0006286829,0.73813117,0.00007392412,0.000046031426,0.00007331625,0.0002710073,0.000735248,0.001965231],"genre_scores_gemma":[0.86212665,0.00032575557,0.13542663,0.000029914185,0.000051446157,0.000062428975,0.0006164164,0.00009574438,0.0012648943],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9994954,0.00013325516,0.00002207841,0.00012873145,0.00011184595,0.00010863239],"domain_scores_gemma":[0.9987987,0.0006752762,0.00012168013,0.00011291532,0.00024039124,0.000050951257],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014383175,0.0008989735,0.00050128606,0.0012400256,0.0005949657,0.0006690552,0.0005284333,0.00061983423,0.0013078052],"category_scores_gemma":[0.0031021808,0.0002584964,0.0007392981,0.000611116,0.00043000723,0.0010796249,0.0005489411,0.00054820924,0.0011341015],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014126106,0.0003576196,0.044559512,0.00036416802,0.0002728546,0.00079595676,0.001067994,0.23399551,0.16588786,0.004396232,0.0013661636,0.5455236],"study_design_scores_gemma":[0.000021261036,0.0002461397,0.036687184,0.00007632379,0.00013609225,0.0005467201,0.00036933657,0.92339134,0.031193743,0.0039816042,0.003233504,0.000116713105],"about_ca_topic_score_codex":0.008433792,"about_ca_topic_score_gemma":0.0111075165,"teacher_disagreement_score":0.008433792,"about_ca_system_score_codex":0.00020436032,"about_ca_system_score_gemma":0.00073724904,"threshold_uncertainty_score":0.01676941},"labels":[],"label_agreement":null},{"id":"W4413051886","doi":"10.3233/shti250991","title":"A Proof-of-Concept Development on Speech Analysis for Concussion Detection","year":2025,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Proof of concept; Computer science; Speech recognition; Natural language processing; Concussion; Medicine; Medical emergency; Injury prevention; Poison control; Operating system","score_opus":0.04934642542530765,"score_gpt":0.35157778503627135,"score_spread":0.3022313596109637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413051886","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0852313,0.003966784,0.8862889,0.0023866699,0.0023961847,0.003401676,0.0018485421,0.0063102436,0.008169687],"genre_scores_gemma":[0.20236821,0.0029725444,0.78003395,0.0012991627,0.00047225563,0.0025685404,0.0019467956,0.00036413755,0.007974466],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9979621,0.00028458153,0.000117888,0.00038095508,0.0011254441,0.00012899667],"domain_scores_gemma":[0.99667716,0.0006991441,0.0002575505,0.00026710387,0.0018256179,0.00027344716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040366375,0.0011721969,0.00090480054,0.0008390049,0.0004944142,0.0011967118,0.0016178286,0.0018140881,0.004993643],"category_scores_gemma":[0.006216975,0.00051410473,0.0007851615,0.00035918746,0.0007117928,0.0015684278,0.0011864145,0.0016682325,0.0038535895],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00059460796,0.0006458069,0.00153281,0.0011811327,0.00015191876,0.00088124257,0.00021035525,0.0024753604,0.7960511,0.0038328748,0.00905308,0.18338975],"study_design_scores_gemma":[0.00028808112,0.004609111,0.0032887901,0.0002439968,0.00015470556,0.0028963194,0.00016818872,0.035129357,0.8758398,0.0013978077,0.07584474,0.00013906762],"about_ca_topic_score_codex":0.0007964297,"about_ca_topic_score_gemma":0.00071044423,"teacher_disagreement_score":0.004993643,"about_ca_system_score_codex":0.00041809442,"about_ca_system_score_gemma":0.0017392857,"threshold_uncertainty_score":0.021348},"labels":[],"label_agreement":null},{"id":"W4413096419","doi":"10.1109/icc-robins64345.2025.11086131","title":"Optimized Efficientnet-B0 Framework for Speech Pathology Classification","year":2025,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Speech recognition; Artificial intelligence; Natural language processing","score_opus":0.037262661558918414,"score_gpt":0.3138960212722057,"score_spread":0.2766333597132873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413096419","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02169406,0.00035993432,0.96581084,0.000115944364,0.000052175117,0.000157134,0.0010554042,0.008353263,0.0024012],"genre_scores_gemma":[0.21239454,0.00033907968,0.7725645,0.00022029286,0.000097189935,0.0005764393,0.0066312235,0.0006588752,0.0065178187],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99951303,0.000089181274,0.00003224896,0.00013912692,0.0001467903,0.00007960152],"domain_scores_gemma":[0.9996799,0.00009039954,0.00003229701,0.00005275453,0.00012600407,0.000018646853],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010409971,0.0013804534,0.0008367108,0.0013900687,0.00043037406,0.001195401,0.0016214541,0.00087930996,0.0048250393],"category_scores_gemma":[0.0018484453,0.00041181096,0.00072112976,0.0008410267,0.00035357306,0.0013988934,0.0008466008,0.0008050803,0.002876705],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006204593,0.00031060993,0.0020933077,0.00015772937,0.00012021364,0.00017976432,0.00007205568,0.2423999,0.016964074,0.013625927,0.01549351,0.70796245],"study_design_scores_gemma":[0.000026129826,0.0000734825,0.00056125,0.000009661722,0.000014728771,0.00006861129,0.000017963683,0.9848739,0.004509274,0.006607364,0.003225729,0.000011942883],"about_ca_topic_score_codex":0.011818706,"about_ca_topic_score_gemma":0.01646351,"teacher_disagreement_score":0.011818706,"about_ca_system_score_codex":0.00095389923,"about_ca_system_score_gemma":0.001568929,"threshold_uncertainty_score":0.023499846},"labels":[],"label_agreement":null},{"id":"W4413205493","doi":"10.1109/eaic66483.2025.11101389","title":"DeepVoice: An End-to-End Speaker Recognition System Leveraging Convolutional and Recurrent Neural Networks for Robust Voice Identification","year":2025,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Speech recognition; Speaker recognition; End-to-end principle; Speaker identification; Convolutional neural network; Identification (biology); Speaker diarisation; Artificial intelligence","score_opus":0.04841114124058102,"score_gpt":0.27203916024032376,"score_spread":0.22362801899974274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413205493","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054731086,0.0009771493,0.9140253,0.00017904039,0.00042722994,0.00017697796,0.0006999354,0.025038952,0.0037443698],"genre_scores_gemma":[0.53350234,0.00043698624,0.4440373,0.00074038905,0.00019838994,0.00022639261,0.0033133584,0.00087847526,0.016666414],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995988,0.000051530256,0.000019313014,0.00012899474,0.00014764673,0.000053688054],"domain_scores_gemma":[0.99968743,0.000087616216,0.000026436834,0.00005448995,0.000111344205,0.00003274903],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000684684,0.0006694232,0.00062350626,0.0004460276,0.00029547446,0.0005064409,0.0012996366,0.00084930187,0.002956996],"category_scores_gemma":[0.001079717,0.00031842457,0.0003965508,0.00014439886,0.00024571503,0.000979696,0.0012255237,0.0009320888,0.0014373364],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00086726533,0.00027572125,0.002961813,0.00024294289,0.00027123024,0.00044277782,0.00020479549,0.034137484,0.2136649,0.0027192591,0.016627558,0.7275843],"study_design_scores_gemma":[0.000102642574,0.0005650206,0.0036543917,0.000048881368,0.00012221816,0.00097171566,0.00006486687,0.82472974,0.14362668,0.0034863597,0.022477841,0.00014962991],"about_ca_topic_score_codex":0.0026582503,"about_ca_topic_score_gemma":0.0062085046,"teacher_disagreement_score":0.002956996,"about_ca_system_score_codex":0.00028717314,"about_ca_system_score_gemma":0.0006271964,"threshold_uncertainty_score":0.009892106},"labels":[],"label_agreement":null},{"id":"W4413441258","doi":"10.1613/jair.1.19171","title":"An MRP Formulation for Supervised Learning: Generalized Temporal Difference Learning Models","year":2025,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Royal Academy of Engineering; UK Research and Innovation","keywords":"Computer science; Artificial intelligence; Supervised learning; Temporal difference learning; Machine learning; Artificial neural network","score_opus":0.30398104370192736,"score_gpt":0.4386553844920129,"score_spread":0.13467434079008556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413441258","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037791415,0.00037132046,0.99361765,0.0006933476,0.00004477389,0.00004401664,0.000103101745,0.00009839304,0.001248341],"genre_scores_gemma":[0.53499955,0.0015126272,0.45015228,0.0011546232,0.00042622464,0.0010476174,0.0008838505,0.00024830483,0.009574862],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9965959,0.0016394975,0.0001829515,0.00084472564,0.00056527695,0.00017166506],"domain_scores_gemma":[0.98343843,0.012731031,0.0011089097,0.00076316576,0.0016510749,0.00030739052],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007375999,0.0012500981,0.0014129147,0.0009888578,0.0004764364,0.0018148981,0.0040231007,0.002779751,0.0043208646],"category_scores_gemma":[0.018940087,0.0007757232,0.0013488599,0.0016076326,0.0021676258,0.003425047,0.0022359118,0.0044326773,0.00081470277],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056383455,0.000058883918,0.0010001329,0.00018729355,0.000074650794,0.00011101741,0.00012806963,0.8040009,0.0004347867,0.15511242,0.0026605316,0.036174934],"study_design_scores_gemma":[0.0000055954165,0.000016406007,0.00005148743,0.000008208845,0.0000053337485,0.000011924953,0.000004200881,0.9711322,0.00007025816,0.028236447,0.00045308465,0.0000048534885],"about_ca_topic_score_codex":0.004817617,"about_ca_topic_score_gemma":0.004132867,"teacher_disagreement_score":0.007375999,"about_ca_system_score_codex":0.0023951342,"about_ca_system_score_gemma":0.002222806,"threshold_uncertainty_score":0.0390085},"labels":[],"label_agreement":null},{"id":"W4413458003","doi":"10.1109/iwbf63717.2025.11113424","title":"A Novel Hybrid Neural Embedding Extractor for Text Independent Speaker Verification","year":2025,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Extractor; Speaker verification; Speech recognition; Embedding; Speaker recognition; Artificial intelligence; Natural language processing; Pattern recognition (psychology); Engineering","score_opus":0.0323791740611883,"score_gpt":0.29495054214609395,"score_spread":0.26257136808490567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413458003","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0154467765,0.00050731,0.97673756,0.00008705727,0.00013535138,0.00007822973,0.00031866584,0.0056166337,0.0010724369],"genre_scores_gemma":[0.32803658,0.0005161076,0.64870024,0.00032948106,0.0001498209,0.00024991558,0.0027390998,0.00053589826,0.018742945],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993605,0.00009051055,0.000035068137,0.00020657147,0.00022909949,0.00007825822],"domain_scores_gemma":[0.99959236,0.00008385585,0.000041761657,0.000093103576,0.0001616125,0.000027406828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009352606,0.0011960047,0.0008609954,0.0008201333,0.00027998158,0.0005137341,0.001445784,0.0009361512,0.005014394],"category_scores_gemma":[0.00132699,0.00043795604,0.0007578857,0.0005041737,0.0002888206,0.0018212455,0.0015398037,0.0012424433,0.0037696874],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003871388,0.00013705845,0.0007648896,0.00010973724,0.00013990543,0.00012226625,0.000052576037,0.01684113,0.10435295,0.0022256724,0.005197401,0.86966926],"study_design_scores_gemma":[0.000028757511,0.0001790264,0.0015070374,0.000019041954,0.000072818395,0.00030490267,0.000026319405,0.88958824,0.099228896,0.00234073,0.006662116,0.000042188243],"about_ca_topic_score_codex":0.002489224,"about_ca_topic_score_gemma":0.0051021725,"teacher_disagreement_score":0.005014394,"about_ca_system_score_codex":0.0004390742,"about_ca_system_score_gemma":0.000628068,"threshold_uncertainty_score":0.016774833},"labels":[],"label_agreement":null},{"id":"W4413979917","doi":"10.1109/taslpro.2025.3606235","title":"Exploring Cross-Utterance Speech Contexts for Conformer-Transducer Speech Recognition Systems","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"National Natural Science Foundation of China","keywords":"Utterance; Speech recognition; Computer science; Speech processing; Natural language processing; Artificial intelligence","score_opus":0.05215438308880152,"score_gpt":0.2992675605736401,"score_spread":0.2471131774848386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413979917","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16572604,0.0008635608,0.82787377,0.00018204928,0.000076292825,0.00010331607,0.0002137668,0.002780879,0.00218031],"genre_scores_gemma":[0.8790269,0.00033080493,0.11787231,0.00010319703,0.000050250826,0.00012072218,0.0007317804,0.00026432023,0.0014996927],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99854314,0.00052671356,0.000076993456,0.00055309426,0.00019686276,0.00010321971],"domain_scores_gemma":[0.9986796,0.00070234283,0.00009623992,0.00023127017,0.0002242411,0.000066298184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001356232,0.0011754557,0.00071962073,0.0005259602,0.00043566918,0.00091906806,0.0009970968,0.0006716285,0.001954491],"category_scores_gemma":[0.0038771422,0.0005913433,0.0007925704,0.00037880812,0.0004973396,0.0022418033,0.0018877777,0.0010708093,0.000995011],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018446365,0.0003065048,0.006118167,0.00026477332,0.00020616622,0.0006579557,0.0010930308,0.3053651,0.112363786,0.0099202255,0.0020358807,0.55982375],"study_design_scores_gemma":[0.000022032595,0.00031422553,0.0016496208,0.000013611181,0.000053801705,0.00016739144,0.000258625,0.9662417,0.024967618,0.0040967963,0.0021814757,0.00003321028],"about_ca_topic_score_codex":0.005026942,"about_ca_topic_score_gemma":0.0075629586,"teacher_disagreement_score":0.005026942,"about_ca_system_score_codex":0.0004491371,"about_ca_system_score_gemma":0.0009141662,"threshold_uncertainty_score":0.009995341},"labels":[],"label_agreement":null},{"id":"W4414039198","doi":"10.31234/osf.io/39fqa_v3","title":"A review of computational models of word recognition and pronunciation","year":2025,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Pronunciation; Computer science; Word (group theory); Natural language processing; Speech recognition; Artificial intelligence; Linguistics; Philosophy","score_opus":0.05549418121023892,"score_gpt":0.2737425653071686,"score_spread":0.2182483840969297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414039198","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0049918713,0.7453823,0.20588116,0.008976196,0.0016001699,0.00006609692,0.0011473439,0.0010436095,0.030911205],"genre_scores_gemma":[0.052007444,0.85736996,0.07250269,0.0025028707,0.0026717677,0.00020266701,0.001989774,0.00031092193,0.010441979],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994863,0.0001199992,0.000065129105,0.00013787976,0.00015840484,0.00003221792],"domain_scores_gemma":[0.998114,0.0013984428,0.00010245604,0.00011607698,0.00023421955,0.00003488675],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092734786,0.0014346814,0.0013718166,0.0019239766,0.0004926184,0.0023489424,0.0026023423,0.0015379245,0.005618683],"category_scores_gemma":[0.004781245,0.0008550851,0.0010302009,0.002779073,0.0012947305,0.0056639914,0.0008483176,0.001829771,0.004519636],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013760297,0.00007912363,0.0016627858,0.0075169853,0.00022698645,0.0002849615,0.00034660188,0.026547737,0.0018580211,0.21277443,0.051822305,0.6967425],"study_design_scores_gemma":[0.000023204695,0.00010118619,0.0021804597,0.003185418,0.0002498335,0.0012594141,0.00016172916,0.03833929,0.0015030651,0.4268818,0.52597594,0.0001387383],"about_ca_topic_score_codex":0.0036014102,"about_ca_topic_score_gemma":0.0027031472,"teacher_disagreement_score":0.005618683,"about_ca_system_score_codex":0.0013514671,"about_ca_system_score_gemma":0.00203283,"threshold_uncertainty_score":0.018796384},"labels":[],"label_agreement":null},{"id":"W4414069553","doi":"10.3390/sym17091478","title":"Phoneme-Aware Augmentation for Robust Cantonese ASR Under Low-Resource Conditions","year":2025,"lang":"en","type":"article","venue":"Symmetry","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Natural Science Foundation of China; Natural Science Foundation of Shandong Province; Texas Space Grant Consortium","keywords":"Dropout (neural networks); Connectionism; Formant; Lexicon; Word error rate; Field (mathematics); Speech processing; Conjunction (astronomy)","score_opus":0.02059244963797242,"score_gpt":0.28637632700530685,"score_spread":0.26578387736733444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414069553","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1320193,0.0012310743,0.8423135,0.00044812236,0.00036557802,0.00012510615,0.001263396,0.0149906855,0.0072432337],"genre_scores_gemma":[0.75578797,0.0004961827,0.22814608,0.0003423246,0.0001595307,0.00031541896,0.0041514277,0.00075259473,0.009848415],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99947196,0.00011902743,0.00002386065,0.00016491237,0.00015097519,0.0000693022],"domain_scores_gemma":[0.9994691,0.00018101392,0.000029045761,0.00014446092,0.00014743692,0.00002899785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006365906,0.0011341474,0.00069450634,0.00039167603,0.00040224876,0.0005240706,0.000982482,0.00046397926,0.003584207],"category_scores_gemma":[0.0017504417,0.00029876147,0.00038618452,0.00034294018,0.00042935784,0.0008973282,0.0012254489,0.0010953398,0.0022285252],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007347863,0.00018139706,0.0017207756,0.0001933488,0.000060403065,0.00027340473,0.0002931183,0.071375415,0.2081967,0.0024064975,0.010282642,0.7042815],"study_design_scores_gemma":[0.00005305462,0.00033071122,0.004014013,0.00003895599,0.000064632055,0.0002903622,0.00015558088,0.8638201,0.11051473,0.0043663713,0.016281659,0.000069934926],"about_ca_topic_score_codex":0.0063498933,"about_ca_topic_score_gemma":0.015303702,"teacher_disagreement_score":0.0063498933,"about_ca_system_score_codex":0.00030569787,"about_ca_system_score_gemma":0.0010662463,"threshold_uncertainty_score":0.012625873},"labels":[],"label_agreement":null},{"id":"W4414371545","doi":"10.1145/3769089","title":"A Systematic Literature Review on Bias Evaluation and Mitigation in Automatic Speech Recognition Models for Low-Resource African Languages","year":2025,"lang":"en","type":"article","venue":"ACM Computing Surveys","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Systematic review; Adversarial system; Diversity (politics); Languages of Africa; Linguistic diversity","score_opus":0.05212062967271452,"score_gpt":0.32011294596393874,"score_spread":0.2679923162912242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414371545","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00072402874,0.9925768,0.00323421,0.0013444425,0.00029966756,0.00035906682,0.00061071554,0.000057858335,0.00079320825],"genre_scores_gemma":[0.011174512,0.9774989,0.0071285116,0.0017153264,0.00031283416,0.0011079994,0.0007293993,0.000042671676,0.0002897454],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9783678,0.010182879,0.0060517597,0.0015897657,0.0035018853,0.00030594945],"domain_scores_gemma":[0.86286175,0.11714656,0.008668648,0.0023933111,0.008407757,0.0005220363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.031064585,0.0021120834,0.0049333344,0.009659267,0.0009253871,0.0039361194,0.0026880852,0.0026095342,0.0070691253],"category_scores_gemma":[0.14468373,0.0015352827,0.0081930505,0.0052759834,0.0014355199,0.0042774263,0.0023680495,0.0021370945,0.0012527352],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002715253,0.000075439115,0.0013501532,0.6274041,0.004517429,0.00009436656,0.00047125516,0.0012684985,0.00041043537,0.0024616867,0.010260205,0.3514149],"study_design_scores_gemma":[0.0001604077,0.0004868234,0.0034416926,0.86039174,0.022419997,0.000347213,0.0004439787,0.000742321,0.00071172783,0.0042739827,0.10647898,0.00010115889],"about_ca_topic_score_codex":0.007867806,"about_ca_topic_score_gemma":0.019077964,"teacher_disagreement_score":0.031064585,"about_ca_system_score_codex":0.0030791892,"about_ca_system_score_gemma":0.01866383,"threshold_uncertainty_score":0.16428721},"labels":[],"label_agreement":null},{"id":"W4414537366","doi":"10.47392/irjaeh.2025.0550","title":"Machine Learning Methods for Speech Emotion Recognition","year":2025,"lang":"en","type":"article","venue":"International Research Journal on Advanced Engineering Hub (IRJAEH)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Semtech (Canada)","funders":"","keywords":"Convolutional neural network; Support vector machine; Robustness (evolution); Feature extraction; Emotion classification; Mel-frequency cepstrum; Random forest; Generalization; Feature (linguistics); Benchmark (surveying)","score_opus":0.07098266512585713,"score_gpt":0.43011916330131245,"score_spread":0.35913649817545534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414537366","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027324257,0.0065766517,0.98551196,0.0005277017,0.00035005648,0.000104400766,0.00038213166,0.0014113258,0.002403213],"genre_scores_gemma":[0.21502307,0.015071871,0.7518299,0.0006995905,0.0012963159,0.00077698444,0.0029011436,0.00032612882,0.012074842],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990864,0.00023450343,0.000105611216,0.00021775979,0.00030876117,0.000047015234],"domain_scores_gemma":[0.99890995,0.0005902987,0.00009258373,0.00012505095,0.00026746845,0.000014774541],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015617998,0.001107425,0.0009755591,0.0013030613,0.00027423966,0.0011625444,0.0013096681,0.0009815613,0.0041346415],"category_scores_gemma":[0.0035362493,0.0003588926,0.0012023768,0.0014631811,0.00035733767,0.0011322465,0.0006778047,0.0018780705,0.0026344315],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006660455,0.00008864982,0.0009510252,0.00045971753,0.00016215627,0.000079735204,0.000060805996,0.07555005,0.005679538,0.013656738,0.011264946,0.8919801],"study_design_scores_gemma":[0.00001297476,0.000045867833,0.0009467322,0.000072446666,0.000025591844,0.000074799995,0.000030318926,0.9641349,0.0030239604,0.02017774,0.011425779,0.000028818722],"about_ca_topic_score_codex":0.002532648,"about_ca_topic_score_gemma":0.0021412952,"teacher_disagreement_score":0.0041346415,"about_ca_system_score_codex":0.0006173407,"about_ca_system_score_gemma":0.0005837807,"threshold_uncertainty_score":0.013831794},"labels":[],"label_agreement":null},{"id":"W4414774870","doi":"10.64701/ijrc/345/8907","title":"Speech Emotion Recognition with Hybrid CNN- LSTM and Transformers Models: Evaluating the Hybrid Model Using Grad-CAM","year":2024,"lang":"en","type":"article","venue":"International Journal of Research in Computing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Transformer; Convolutional neural network; Encoder; Feature extraction; Pattern recognition (psychology); Artificial neural network; Mel-frequency cepstrum; Hybrid neural network; Spectrogram","score_opus":0.2764907419420464,"score_gpt":0.43994649405967867,"score_spread":0.16345575211763225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414774870","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8311326,0.0057003177,0.14403129,0.0010341943,0.0010159898,0.00031131238,0.0011792384,0.004564814,0.011030223],"genre_scores_gemma":[0.97259164,0.0005131846,0.021941498,0.0001562908,0.000048998147,0.000098373326,0.0011183575,0.000052274783,0.0034793038],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999663,0.000077658275,0.000030121248,0.00009719271,0.000074227304,0.00005776353],"domain_scores_gemma":[0.99952364,0.00017449513,0.00002703694,0.000036278583,0.00020921709,0.000029327253],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012175791,0.001345997,0.00076095626,0.000684764,0.00024517678,0.00082428893,0.0010366011,0.0008428788,0.002103517],"category_scores_gemma":[0.001677268,0.00022790526,0.0008368679,0.00039219225,0.00021939038,0.00082960894,0.00057344855,0.0009014725,0.00068692316],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018247465,0.0007343094,0.010212694,0.00052323507,0.0006172564,0.0003343691,0.0001645164,0.4915384,0.022088444,0.0014453832,0.007842923,0.46267366],"study_design_scores_gemma":[0.000009902593,0.0001354665,0.00078507717,0.000010181258,0.000046963447,0.00001718901,0.000029008655,0.99585235,0.0027276685,0.00012278593,0.00025638202,0.0000070158917],"about_ca_topic_score_codex":0.016907081,"about_ca_topic_score_gemma":0.012475839,"teacher_disagreement_score":0.016907081,"about_ca_system_score_codex":0.0009798878,"about_ca_system_score_gemma":0.0006051245,"threshold_uncertainty_score":0.033617377},"labels":[],"label_agreement":null},{"id":"W4414789198","doi":"10.48550/arxiv.2509.20786","title":"LiLAW: Lightweight Learnable Adaptive Weighting to Learn Sample Difficulty & Improve Noisy Training","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; University of Toronto","keywords":"Robustness (evolution); Weighting; Hyperparameter; Artificial neural network; Training set; Stochastic gradient descent; Gradient descent; Generalization; Noisy data","score_opus":0.09525507824844402,"score_gpt":0.2889259135805544,"score_spread":0.19367083533211038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414789198","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030216,0.00089311466,0.9591387,0.000491743,0.0001571689,0.00013805009,0.0002415564,0.0069083036,0.0018153085],"genre_scores_gemma":[0.56910473,0.00053057086,0.4177269,0.0015435214,0.00021356357,0.0007285633,0.0017999291,0.0018639858,0.0064882683],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984396,0.00038357516,0.00011606337,0.00046559182,0.00043022525,0.00016493665],"domain_scores_gemma":[0.99706954,0.0012750638,0.0002755597,0.0007368645,0.00047854672,0.00016447519],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034787399,0.0025789668,0.0015816332,0.0008617821,0.0006254349,0.0014925608,0.0043499814,0.0019012737,0.0027244603],"category_scores_gemma":[0.015994169,0.0009677791,0.0008918573,0.00073687296,0.00124609,0.0038399713,0.004227778,0.004113747,0.0016064415],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005909769,0.0005050419,0.0064006303,0.0003476749,0.00026452815,0.00019790734,0.00027696893,0.39718464,0.024053428,0.01065069,0.0163435,0.5431839],"study_design_scores_gemma":[0.000053456024,0.0001215528,0.00034702846,0.000029684512,0.00002291974,0.000052464657,0.000025117639,0.9840851,0.005264218,0.008241595,0.0017350173,0.000021783597],"about_ca_topic_score_codex":0.0038143147,"about_ca_topic_score_gemma":0.0072722486,"teacher_disagreement_score":0.0043499814,"about_ca_system_score_codex":0.0013445958,"about_ca_system_score_gemma":0.0016107698,"threshold_uncertainty_score":0.01839751},"labels":[],"label_agreement":null},{"id":"W4414870063","doi":"10.1101/2025.10.05.680511","title":"Mixture Models for Domain-Adaptive Brain Decoding","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Decoding methods; Mixture model; Weighting; Scalability; Selection (genetic algorithm); Generalization; Inference; Model selection","score_opus":0.027392009061669487,"score_gpt":0.23934329152199169,"score_spread":0.2119512824603222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414870063","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021189693,0.00008429509,0.99706763,0.00008125744,0.000011721192,0.000013322623,0.000028423032,0.00031891008,0.0002754512],"genre_scores_gemma":[0.24144347,0.00038249997,0.7510784,0.0003045196,0.00011247912,0.0002862115,0.0005478046,0.00071445067,0.0051301243],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990017,0.00045443684,0.00004715372,0.00020347469,0.00021694168,0.000076309996],"domain_scores_gemma":[0.9981365,0.0011840141,0.00011388404,0.00022984747,0.0002763623,0.00005926646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023110139,0.0010690688,0.0010303176,0.0010032629,0.00035424565,0.001028134,0.0018909663,0.0012080302,0.0028952856],"category_scores_gemma":[0.009064263,0.00065993593,0.0011899468,0.00092151127,0.0009858368,0.0015019879,0.0022831475,0.0026637071,0.0017116341],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016104447,0.00007681056,0.00062681665,0.00010281585,0.00014887603,0.000067604,0.00014020063,0.68021464,0.011814761,0.055986468,0.003798017,0.24686193],"study_design_scores_gemma":[0.000006033227,0.000008613787,0.00006933386,0.000004433925,0.0000051298102,0.000013627605,0.00000390611,0.97974783,0.0014461598,0.018040773,0.0006479974,0.0000060772995],"about_ca_topic_score_codex":0.0035704616,"about_ca_topic_score_gemma":0.0039135353,"teacher_disagreement_score":0.0035704616,"about_ca_system_score_codex":0.0010494431,"about_ca_system_score_gemma":0.0009878526,"threshold_uncertainty_score":0.012221992},"labels":[],"label_agreement":null},{"id":"W4414995823","doi":"10.21203/rs.3.rs-7808032/v1","title":"Mixed Signal Design Using C++ and DSP Acceleration for Low Latency and Secure Speech Systems","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Latency (audio); Digital signal processing; Low latency (capital markets); Voice activity detection; Novelty; Speech processing; Signal processing; Digital signal processor","score_opus":0.24811628790915286,"score_gpt":0.39797848103519823,"score_spread":0.14986219312604537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414995823","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019748783,0.00030790715,0.96621376,0.00013475015,0.0001291475,0.00018912798,0.000084336636,0.004628021,0.008564188],"genre_scores_gemma":[0.4287445,0.00023596849,0.55122805,0.00027474324,0.00011847578,0.00029695922,0.00027212518,0.0007067516,0.01812234],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995072,0.0000938087,0.00004050361,0.00006977224,0.00022050188,0.000068165136],"domain_scores_gemma":[0.99933285,0.00017687521,0.000057385856,0.00007507067,0.00032783955,0.000029952344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046215445,0.00090575113,0.0003231671,0.00066485145,0.00048120783,0.0013192042,0.0011376803,0.0005604663,0.016206147],"category_scores_gemma":[0.0010586708,0.0003459204,0.00030786043,0.00036058883,0.00020226729,0.0005521788,0.00037757095,0.0006423395,0.0038198684],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015859624,0.00026299513,0.000777483,0.00054659584,0.00013966288,0.0002868097,0.00018467932,0.044275824,0.35759908,0.017334439,0.008180814,0.5688256],"study_design_scores_gemma":[0.00027772787,0.0023276922,0.00094137096,0.0000928099,0.00015163947,0.0005473307,0.0000775285,0.5851333,0.35812137,0.005288013,0.046980876,0.00006041877],"about_ca_topic_score_codex":0.0013013794,"about_ca_topic_score_gemma":0.002786384,"teacher_disagreement_score":0.016206147,"about_ca_system_score_codex":0.00053381873,"about_ca_system_score_gemma":0.00075451954,"threshold_uncertainty_score":0.054214954},"labels":[],"label_agreement":null},{"id":"W4415003378","doi":"10.1109/ciacon65473.2025.11189784","title":"VoiceIDE: Real-Time Code Editing Through Speech Recognition","year":2025,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Code (set theory); Java; Coding (social sciences); Speaker recognition; Speech technology; Speech processing; Acoustic model; Speech analytics","score_opus":0.03095695232509905,"score_gpt":0.2807548199204027,"score_spread":0.24979786759530365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415003378","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018929085,0.00031407294,0.7496502,0.000120636956,0.0003155341,0.00025660143,0.0005417479,0.22230189,0.007570273],"genre_scores_gemma":[0.30054682,0.00043774938,0.62752664,0.00090572133,0.00028967828,0.0004604122,0.0033621476,0.027206607,0.039264284],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99873334,0.00015378559,0.00009135291,0.00036595832,0.0005672618,0.00008827407],"domain_scores_gemma":[0.99761707,0.00095565704,0.00018607176,0.0004965128,0.00057227677,0.00017233001],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008572568,0.0010654959,0.0005684133,0.00074390275,0.00024613168,0.0014165511,0.0017648294,0.00080813596,0.009575064],"category_scores_gemma":[0.0035376255,0.00043061926,0.00044254362,0.00023285304,0.0004566076,0.0012113769,0.0011627265,0.0009548927,0.005862806],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013766655,0.00029654414,0.0022257469,0.00050553825,0.00013923686,0.0011133378,0.0005278084,0.0043051457,0.3101772,0.003840805,0.04016509,0.63532686],"study_design_scores_gemma":[0.00022580783,0.0005628617,0.0026853988,0.000104242245,0.00012459053,0.0019022328,0.00015411281,0.2704361,0.59923327,0.003190246,0.121146314,0.00023489952],"about_ca_topic_score_codex":0.0009655388,"about_ca_topic_score_gemma":0.0010277565,"teacher_disagreement_score":0.009575064,"about_ca_system_score_codex":0.00021390998,"about_ca_system_score_gemma":0.0005846875,"threshold_uncertainty_score":0.032031775},"labels":[],"label_agreement":null},{"id":"W4415540898","doi":"10.1145/3746027.3754745","title":"Pseudo-Autoregressive Neural Codec Language Models for Efficient Zero-Shot Text-to-Speech Synthesis","year":2025,"lang":"","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Microsoft (Canada)","funders":"National Natural Science Foundation of China","keywords":"Autoregressive model; Language model; Set (abstract data type); Inference; Codec; Face (sociological concept); Speech processing; Speech synthesis","score_opus":0.03375509139618933,"score_gpt":0.2939912735728801,"score_spread":0.26023618217669076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415540898","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008136044,0.00033254625,0.98578864,0.000100471385,0.00008162457,0.000040637413,0.00024020692,0.004051977,0.0012278853],"genre_scores_gemma":[0.38888755,0.0005873837,0.59605676,0.00035557087,0.000120505545,0.00039764098,0.002633689,0.0011841838,0.009776783],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995247,0.000112444635,0.00003117824,0.00012044753,0.00016781369,0.00004341337],"domain_scores_gemma":[0.9991233,0.0004424916,0.00005241532,0.00009691335,0.0002543387,0.00003063885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071248267,0.0008040779,0.00056230376,0.00046294346,0.0002711205,0.0006175387,0.0012908803,0.0007040405,0.004240506],"category_scores_gemma":[0.0025935364,0.00038359704,0.0006622842,0.0004058122,0.00036071142,0.0010011967,0.0007822511,0.0015272471,0.0028637757],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004408282,0.0001549043,0.0006718293,0.00024009874,0.00010243705,0.00027000354,0.00017976908,0.39820656,0.05149132,0.013366201,0.008435472,0.5264406],"study_design_scores_gemma":[0.000008703718,0.000029068058,0.0000782229,0.0000071204254,0.000008569874,0.000034509532,0.00000788048,0.9906143,0.0060568685,0.0016876557,0.001458316,0.000008663024],"about_ca_topic_score_codex":0.0061102123,"about_ca_topic_score_gemma":0.00963534,"teacher_disagreement_score":0.0061102123,"about_ca_system_score_codex":0.00046780228,"about_ca_system_score_gemma":0.0009970195,"threshold_uncertainty_score":0.014185905},"labels":[],"label_agreement":null},{"id":"W4415898436","doi":"10.48550/arxiv.2503.06211","title":"Late Fusion and Multi-Level Fission Amplify Cross-Modal Transfer in Text-Speech LMs","year":2025,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Principle of compositionality; Feature (linguistics); Representation (politics); Process (computing); Hierarchy; Modality (human–computer interaction); Transfer (computing)","score_opus":0.1290470316641667,"score_gpt":0.23679426623934757,"score_spread":0.10774723457518087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415898436","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1093162,0.00042897512,0.87826926,0.0004872065,0.0001630574,0.00007047768,0.00014329399,0.0056993365,0.0054221796],"genre_scores_gemma":[0.860638,0.00015468687,0.12777193,0.00031709945,0.000068393514,0.00011617299,0.0004439929,0.000470296,0.010019351],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994822,0.00014171324,0.000029155875,0.00016158744,0.00010935075,0.00007595548],"domain_scores_gemma":[0.9987845,0.000703005,0.00006026712,0.00018980962,0.00017801994,0.000084462314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017881809,0.00095933775,0.0006999316,0.0003593423,0.00047493097,0.0010134537,0.0013494105,0.0011534826,0.004272381],"category_scores_gemma":[0.0042730784,0.00041623137,0.0008055381,0.0002872627,0.0008554693,0.0029493116,0.003247894,0.0026847494,0.002135323],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011505845,0.000361496,0.0018653047,0.00019956166,0.00013629536,0.0002963371,0.00056243053,0.40459383,0.109458104,0.016224628,0.0040365485,0.46111497],"study_design_scores_gemma":[0.00001730847,0.00009768721,0.0002960512,0.000011338784,0.000017867133,0.00003336594,0.000035879344,0.9705865,0.022368414,0.0055339905,0.0009884969,0.000013122623],"about_ca_topic_score_codex":0.0021034481,"about_ca_topic_score_gemma":0.0031189169,"teacher_disagreement_score":0.004272381,"about_ca_system_score_codex":0.0006683051,"about_ca_system_score_gemma":0.00078564003,"threshold_uncertainty_score":0.014292479},"labels":[],"label_agreement":null},{"id":"W4415987807","doi":"10.48550/arxiv.2508.21193","title":"Benchmarking Large Pretrained Multilingual Models on Québec French Speech Recognition","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Benchmarking; Pipeline (software); Benchmark (surveying); Variety (cybernetics); Language model; Word error rate","score_opus":0.08065248834183726,"score_gpt":0.2909048515514014,"score_spread":0.21025236320956414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415987807","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64257365,0.015953058,0.14552781,0.0031624946,0.0030565436,0.0013672415,0.063988745,0.08550067,0.038869847],"genre_scores_gemma":[0.69220495,0.0019261426,0.081064284,0.0012995505,0.0003130937,0.0009323952,0.19187231,0.0028797206,0.027507538],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9968172,0.0008483496,0.00016683705,0.0012278756,0.0005077063,0.00043201464],"domain_scores_gemma":[0.9951788,0.0017334248,0.000096002484,0.0007349897,0.0020044218,0.0002523445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034441983,0.00574999,0.0014927875,0.0021535512,0.002045101,0.0025948207,0.0037249546,0.002284487,0.010231552],"category_scores_gemma":[0.009263452,0.00084709947,0.0015771204,0.002048162,0.0011135946,0.002075325,0.0024228538,0.003159025,0.008385903],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016921709,0.00096215826,0.012742747,0.0011345609,0.0017846648,0.0009883194,0.00071677536,0.357443,0.016733283,0.002346391,0.16074404,0.44271192],"study_design_scores_gemma":[0.00026410373,0.0003790623,0.012116057,0.00017692403,0.0003807597,0.00030855276,0.00080058875,0.93953097,0.017812328,0.0015843246,0.02647465,0.0001716166],"about_ca_topic_score_codex":0.64905775,"about_ca_topic_score_gemma":0.6875228,"teacher_disagreement_score":0.35094225,"about_ca_system_score_codex":0.008143876,"about_ca_system_score_gemma":0.006735001,"threshold_uncertainty_score":0.70601803},"labels":[],"label_agreement":null},{"id":"W4415991972","doi":"10.48550/arxiv.2508.21631","title":"Towards Improved Speech Recognition through Optimized Synthetic Data Generation","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Synthetic data; Training set; Voice activity detection; Speech synthesis; Acoustic model; Encoding (memory); Pattern recognition (psychology)","score_opus":0.19076982838371884,"score_gpt":0.3255550460538047,"score_spread":0.13478521767008586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415991972","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06365796,0.00035476856,0.9256714,0.00032280793,0.00015080279,0.00016346821,0.0009396846,0.006839592,0.0018995444],"genre_scores_gemma":[0.50494874,0.00022757052,0.48332858,0.0002156757,0.00007673363,0.00059845333,0.005817663,0.0011232039,0.0036633238],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998283,0.00079870207,0.000098584926,0.00036041305,0.00033557205,0.00012369566],"domain_scores_gemma":[0.99584866,0.002051927,0.00015243827,0.0006346073,0.0011892705,0.00012309501],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024564492,0.0013319656,0.0007851211,0.000664289,0.00032089735,0.0009361204,0.0014667127,0.0011233707,0.0025687646],"category_scores_gemma":[0.007481427,0.0004881849,0.00057182775,0.00052355806,0.0007236759,0.0010378377,0.0013661648,0.0014751027,0.0017827775],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00063948403,0.00035861952,0.0023200756,0.00039903252,0.0000998596,0.00037859133,0.00053992803,0.57588434,0.13434286,0.0065021235,0.009371433,0.26916373],"study_design_scores_gemma":[0.000038950177,0.00013186908,0.00040891147,0.000014816735,0.000018539564,0.00010452057,0.000067023044,0.9450072,0.048518278,0.0020798575,0.0035862196,0.0000238494],"about_ca_topic_score_codex":0.0054460587,"about_ca_topic_score_gemma":0.0066028917,"teacher_disagreement_score":0.0054460587,"about_ca_system_score_codex":0.00075063936,"about_ca_system_score_gemma":0.0010045269,"threshold_uncertainty_score":0.01299113},"labels":[],"label_agreement":null},{"id":"W4416143831","doi":"10.65148/ecn/2025019","title":"Personalized Text to Speech Synthesis through Few Shot Speaker Adaptation with Contrastive Learning","year":2025,"lang":"en","type":"article","venue":"Elaris Computing Nexus","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trinity College","funders":"","keywords":"Naturalness; Similarity (geometry); Speaker recognition; Mean opinion score; Speech synthesis; Encoder; Feature learning; Word error rate; Speaker diarisation","score_opus":0.02728395361844038,"score_gpt":0.2702029549770197,"score_spread":0.2429190013585793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416143831","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043609742,0.00035384647,0.95006,0.000091094815,0.00012557064,0.00006738661,0.00012630546,0.0034006066,0.002165473],"genre_scores_gemma":[0.63391626,0.00023328156,0.3573038,0.0002594212,0.00009064517,0.00020738819,0.00082047004,0.00051843957,0.0066502937],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997205,0.000056657056,0.000014445736,0.00011300951,0.00007430035,0.00002118495],"domain_scores_gemma":[0.99966466,0.00016091547,0.000024062634,0.00006057457,0.00006644332,0.000023285837],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041005638,0.0006769203,0.00052302034,0.00025105797,0.00017777667,0.00037013157,0.00075049634,0.00060834025,0.0023553562],"category_scores_gemma":[0.0011988796,0.00020737352,0.0006826473,0.00019074441,0.00029782497,0.0007980988,0.00077193807,0.00094267656,0.0012949532],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007681867,0.00029604742,0.0008727784,0.00020317531,0.00015048982,0.00029322915,0.00021706792,0.17978221,0.25455385,0.0032564257,0.0035363864,0.5560701],"study_design_scores_gemma":[0.00003537472,0.00018661117,0.00051921787,0.000008539743,0.00003267374,0.00015642273,0.000031183565,0.94202435,0.052549973,0.0023409892,0.0020897756,0.000024876743],"about_ca_topic_score_codex":0.00096625846,"about_ca_topic_score_gemma":0.0017608771,"teacher_disagreement_score":0.0023553562,"about_ca_system_score_codex":0.00022529022,"about_ca_system_score_gemma":0.00030730915,"threshold_uncertainty_score":0.007879496},"labels":[],"label_agreement":null},{"id":"W4416250889","doi":"10.1109/ijcnn64981.2025.11228198","title":"A Hybrid Neural Approach to Speaker Verification with an Improved Additive Angular Margin Loss","year":2025,"lang":"","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Softmax function; Pattern recognition (psychology); Artificial neural network; Feature extraction; Margin (machine learning); Feature (linguistics); Noise (video); Speaker recognition; Context (archaeology)","score_opus":0.015968510006563092,"score_gpt":0.23797865633334325,"score_spread":0.22201014632678015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416250889","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011595004,0.00027528574,0.9860512,0.00008550635,0.00003834481,0.000028887127,0.00004048957,0.00096915464,0.00091613526],"genre_scores_gemma":[0.5821012,0.00032989235,0.4054547,0.00032040215,0.00013146015,0.00014502242,0.00044912085,0.00023449124,0.0108338175],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991677,0.00019228093,0.000044973083,0.00025974208,0.00025477968,0.000080505255],"domain_scores_gemma":[0.99944645,0.00015378639,0.00005847079,0.00011278691,0.00020137776,0.000027094578],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012948494,0.0010217427,0.0007355024,0.0006737817,0.00031719985,0.00066862296,0.0017794449,0.0009836133,0.0024654965],"category_scores_gemma":[0.001910584,0.0003837645,0.000719389,0.0004443891,0.0005315684,0.0018831419,0.0020103736,0.0013606151,0.0012483966],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043584948,0.00018966492,0.0011538343,0.00011777686,0.0001452763,0.00013039271,0.000117602445,0.19076633,0.06932091,0.008818098,0.0030164479,0.7257878],"study_design_scores_gemma":[0.0000061520823,0.000059915812,0.0002924128,0.000004816067,0.000016786962,0.000051907435,0.000008232003,0.9847109,0.011990782,0.0020745073,0.0007743647,0.000009261724],"about_ca_topic_score_codex":0.0022798781,"about_ca_topic_score_gemma":0.0036850804,"teacher_disagreement_score":0.0024654965,"about_ca_system_score_codex":0.00059095677,"about_ca_system_score_gemma":0.0006456416,"threshold_uncertainty_score":0.008247852},"labels":[],"label_agreement":null},{"id":"W4416336084","doi":"10.18280/isi.300921","title":"An Efficient Speaker Identification System with High-Level Feature Extraction and Database Dimensionality Reduction","year":2025,"lang":"","type":"article","venue":"Ingénierie des systèmes d information","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Dimensionality reduction; Pattern recognition (psychology); Speaker identification; Feature extraction; Feature (linguistics); Identification (biology)","score_opus":0.019282352263271244,"score_gpt":0.25361598978372674,"score_spread":0.2343336375204555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416336084","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027817314,0.00053686945,0.95784456,0.00015541656,0.00017774026,0.00020483354,0.00037930222,0.011024695,0.0018592423],"genre_scores_gemma":[0.18466493,0.00042051068,0.80316603,0.0003231632,0.0001898701,0.00052731886,0.00171166,0.00026746906,0.008729116],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994754,0.000060775677,0.00004366567,0.00014047865,0.0002314355,0.00004835101],"domain_scores_gemma":[0.9996718,0.000061129744,0.000017519695,0.00006767194,0.00015750669,0.00002437726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004460406,0.00052266754,0.0011788579,0.000540138,0.0005061134,0.0007332206,0.0009370101,0.000618332,0.0036688016],"category_scores_gemma":[0.00063266547,0.00038610134,0.0004453568,0.00045321832,0.00015233006,0.0008586265,0.00079332606,0.0005887235,0.004041798],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00053540315,0.00019573056,0.0007927814,0.00012506165,0.00010730184,0.00010766316,0.00005905427,0.0029155067,0.34452733,0.0012533871,0.009568051,0.63981277],"study_design_scores_gemma":[0.00027574087,0.0009237664,0.010044623,0.000036131372,0.00039179428,0.001789037,0.00008106365,0.5184142,0.4275284,0.0020397918,0.038300924,0.00017454744],"about_ca_topic_score_codex":0.0013807288,"about_ca_topic_score_gemma":0.0024162934,"teacher_disagreement_score":0.0036688016,"about_ca_system_score_codex":0.00021569057,"about_ca_system_score_gemma":0.0007431485,"threshold_uncertainty_score":0.012273431},"labels":[],"label_agreement":null},{"id":"W4416397568","doi":"10.1016/j.specom.2025.103330","title":"Towards unsupervised speech recognition without pronunciation models","year":2025,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Institute for Information and Communications Technology Promotion","keywords":"Pronunciation; Word (group theory); Pipeline (software); Unsupervised learning; Segmentation; Vocabulary; Word error rate; Speech corpus; Joint (building)","score_opus":0.0460206974990346,"score_gpt":0.28150528242701406,"score_spread":0.23548458492797947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416397568","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035430149,0.00021819223,0.990738,0.00011019683,0.00011306189,0.00003282159,0.00020544644,0.0037060925,0.0013331058],"genre_scores_gemma":[0.09837645,0.0005565032,0.8796084,0.0004461844,0.00026736569,0.00020752876,0.0031170088,0.0012689717,0.016151695],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99843293,0.0004430867,0.000097902695,0.00051317114,0.00038906754,0.00012373403],"domain_scores_gemma":[0.9967728,0.0013983896,0.000112695416,0.00075809966,0.00087285775,0.00008518793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013466945,0.0016554774,0.0014631881,0.00088600744,0.0006551541,0.002121523,0.0016553978,0.0019671847,0.0052346657],"category_scores_gemma":[0.004251966,0.0010404349,0.0014308841,0.00075071555,0.0007378102,0.002339576,0.0022037642,0.00280195,0.012106891],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033963876,0.00017284926,0.00096567237,0.00030627617,0.00016406263,0.00017275664,0.00018811415,0.03075035,0.15535505,0.014679134,0.008715241,0.78819084],"study_design_scores_gemma":[0.00004334112,0.00016920175,0.0015537187,0.00006692796,0.00014366693,0.0004685615,0.00011057952,0.8325859,0.12518147,0.020417446,0.019197607,0.00006160209],"about_ca_topic_score_codex":0.003137919,"about_ca_topic_score_gemma":0.0058038994,"teacher_disagreement_score":0.0052346657,"about_ca_system_score_codex":0.00042684437,"about_ca_system_score_gemma":0.0014842856,"threshold_uncertainty_score":0.017511666},"labels":[],"label_agreement":null},{"id":"W4416581044","doi":"10.1016/j.csl.2025.101907","title":"A robust framework for noisy speech recognition using Frequency-Guided-Swin Transformer","year":2025,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Transformer; Robustness (evolution); Convolutional neural network; Word error rate; Pattern recognition (psychology); Deep neural networks; Artificial neural network; Deep learning","score_opus":0.06383290841893033,"score_gpt":0.3086372540781378,"score_spread":0.24480434565920747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416581044","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008472891,0.00005042122,0.998248,0.000014367496,0.000014308876,0.000011267566,0.000024618235,0.00055187027,0.0002378258],"genre_scores_gemma":[0.117629245,0.0003745622,0.8753018,0.00011976398,0.000095298215,0.00010537129,0.00053271774,0.0005972671,0.005244052],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922323,0.00013927388,0.000050814928,0.00016864261,0.00032788454,0.000089994035],"domain_scores_gemma":[0.99957544,0.00010406097,0.000040217452,0.000102350976,0.00014804935,0.000029898307],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009314664,0.0010555931,0.0011959432,0.00089224364,0.00048601444,0.0012587963,0.0017807878,0.0010283632,0.004593009],"category_scores_gemma":[0.0013630963,0.0005430847,0.0012037983,0.0006182271,0.0006864148,0.0013355898,0.0015502844,0.0011649716,0.0035049405],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000702434,0.00018609241,0.00043915506,0.0002168583,0.00013183411,0.000328314,0.00011696497,0.10735609,0.23751782,0.04961456,0.0047033085,0.5986866],"study_design_scores_gemma":[0.000014622891,0.00008007599,0.0001606889,0.000011332242,0.000031200645,0.00018292661,0.000020700198,0.9416095,0.04529644,0.007413917,0.0051535596,0.000025000158],"about_ca_topic_score_codex":0.0039000285,"about_ca_topic_score_gemma":0.0059554204,"teacher_disagreement_score":0.004593009,"about_ca_system_score_codex":0.0004959121,"about_ca_system_score_gemma":0.0010082398,"threshold_uncertainty_score":0.015365183},"labels":[],"label_agreement":null},{"id":"W4416610221","doi":"10.48550/arxiv.2505.23170","title":"ZIPA: A family of efficient models for multilingual phone recognition","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Phone; Leverage (statistics); Training set; Set (abstract data type); Noisy data; Data set","score_opus":0.12812033766292624,"score_gpt":0.3082748997877475,"score_spread":0.18015456212482128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416610221","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0067861816,0.00074976834,0.9760307,0.00027102238,0.0002024638,0.000093902796,0.001798937,0.012147221,0.0019198627],"genre_scores_gemma":[0.27441418,0.0016406885,0.68452775,0.0008480059,0.00046141216,0.0010741684,0.016765237,0.003778021,0.016490538],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880695,0.0003290169,0.00007115951,0.00039107958,0.00029751088,0.00010414869],"domain_scores_gemma":[0.9979997,0.00090255996,0.00008756888,0.0004707008,0.00042899686,0.00011043962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017917627,0.002078814,0.0013499523,0.0012655123,0.00073686906,0.0017106509,0.0031625153,0.0014421,0.008122645],"category_scores_gemma":[0.0073978724,0.0010042771,0.0016389358,0.0011292003,0.0005906122,0.0026993952,0.0031637992,0.0034555986,0.011496416],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006152875,0.00020480921,0.002580171,0.00034100784,0.0002920664,0.00021589975,0.0002019715,0.33486855,0.0138480235,0.0126583,0.031625707,0.60254824],"study_design_scores_gemma":[0.000017067192,0.000053239004,0.00019741303,0.000014439099,0.00002268078,0.000075135606,0.00002010832,0.98286414,0.002911448,0.0075112404,0.006293281,0.0000197265],"about_ca_topic_score_codex":0.006196272,"about_ca_topic_score_gemma":0.009744847,"teacher_disagreement_score":0.008122645,"about_ca_system_score_codex":0.00080215314,"about_ca_system_score_gemma":0.0015743312,"threshold_uncertainty_score":0.027172983},"labels":[],"label_agreement":null},{"id":"W4416756303","doi":"10.1109/taslpro.2025.3633090","title":"Towards Effective and Efficient Non-Autoregressive Decoders for Conformer and LLM-Based ASR Using Block-Based Attention Mask","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","keywords":"Decoding methods; Speedup; Inference; Autoregressive model; Connectionism; Language model; Speech processing; Speech coding","score_opus":0.01155468110483668,"score_gpt":0.27968695103775804,"score_spread":0.26813226993292133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416756303","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024712257,0.00035661575,0.96844167,0.0001885438,0.00006722126,0.000059339698,0.00016301162,0.0042603603,0.001751019],"genre_scores_gemma":[0.39477554,0.0003120694,0.5955893,0.0003504049,0.000088625646,0.00022991427,0.0009068275,0.00043336998,0.0073138997],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99948907,0.00010968071,0.000042136493,0.0001421887,0.00016033993,0.000056487013],"domain_scores_gemma":[0.9993913,0.00024589017,0.00005492949,0.00010117639,0.00016334126,0.000043292355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006752406,0.0008556157,0.000598044,0.00040868606,0.00027590658,0.0008529112,0.0012270076,0.00073036173,0.0032233207],"category_scores_gemma":[0.002227355,0.00037960924,0.0004058101,0.00034626928,0.00034116278,0.0012639656,0.0009772484,0.0011941281,0.002279326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055776385,0.00017828429,0.0016532509,0.00013703413,0.000096906246,0.0001954499,0.00018533789,0.072167054,0.1705937,0.016056685,0.005593521,0.7325851],"study_design_scores_gemma":[0.00002413881,0.00009999077,0.0003538776,0.00000938155,0.000022842834,0.00011614796,0.000023465142,0.9273089,0.06476362,0.0037061358,0.0035563551,0.000015005263],"about_ca_topic_score_codex":0.0048120352,"about_ca_topic_score_gemma":0.008595301,"teacher_disagreement_score":0.0048120352,"about_ca_system_score_codex":0.0006039963,"about_ca_system_score_gemma":0.0014166806,"threshold_uncertainty_score":0.010783136},"labels":[],"label_agreement":null},{"id":"W4417001668","doi":"10.48550/arxiv.2512.02201","title":"Swivuriso: The South African Next Voices Multilingual Speech Dataset","year":2025,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Pretoria; International Development Research Centre; Nvidia; Bill and Melinda Gates Foundation","keywords":"Benchmarking; Domain (mathematical analysis); Baseline (sea); Data collection; Speech technology; Computational linguistics","score_opus":0.12330761746984963,"score_gpt":0.2252155139685487,"score_spread":0.10190789649869907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417001668","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12790175,0.0018282003,0.024808807,0.0017181372,0.0010642199,0.0011501678,0.8038745,0.010709915,0.0269444],"genre_scores_gemma":[0.08338336,0.0003835029,0.01790966,0.00029143022,0.00015379424,0.0017043621,0.8874772,0.00043905427,0.008257512],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99894565,0.00027213988,0.000115479896,0.0002201818,0.00029775058,0.00014881603],"domain_scores_gemma":[0.9987638,0.00030292996,0.000085180654,0.0003359569,0.0003772772,0.00013490647],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010635164,0.0010072811,0.0006171477,0.0019239491,0.001036412,0.00090846024,0.0010010804,0.0012632597,0.009860591],"category_scores_gemma":[0.0035971077,0.00022899699,0.00046868963,0.0013365314,0.00053717935,0.0009375701,0.0020751571,0.0009910421,0.012240162],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016042079,0.00058964064,0.014062156,0.002097376,0.00016915194,0.001173434,0.002146567,0.0044603506,0.030919453,0.00573796,0.7018362,0.23520334],"study_design_scores_gemma":[0.00040405378,0.00036805696,0.06939569,0.000395747,0.00009896402,0.0014707522,0.002776546,0.017652655,0.020995976,0.004896762,0.8813249,0.0002198328],"about_ca_topic_score_codex":0.014172006,"about_ca_topic_score_gemma":0.020458238,"teacher_disagreement_score":0.014172006,"about_ca_system_score_codex":0.000647203,"about_ca_system_score_gemma":0.0013471877,"threshold_uncertainty_score":0.032987},"labels":[],"label_agreement":null},{"id":"W4417169656","doi":"10.1109/icecs66544.2025.11270693","title":"Low-Power Real-Time Keyword Spotting for Autonomous Edge Devices","year":2025,"lang":"","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Keyword spotting; Dynamic time warping; Feature extraction; Signal processing; Feature (linguistics); Latency (audio); Enhanced Data Rates for GSM Evolution; Key (lock); Power consumption; Window (computing)","score_opus":0.0165185287494423,"score_gpt":0.2672267519714799,"score_spread":0.25070822322203756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417169656","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09374602,0.0011413781,0.8754402,0.00019414596,0.00024173381,0.00022227358,0.000456156,0.016831564,0.011726502],"genre_scores_gemma":[0.71351725,0.00047529922,0.26520044,0.00028133916,0.00013117981,0.00022672326,0.0006103053,0.001053454,0.018504055],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9997228,0.000030806532,0.000018621562,0.0000583311,0.00014396623,0.00002546606],"domain_scores_gemma":[0.9996172,0.00012370493,0.00004705269,0.00005838137,0.00012220297,0.000031366635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019568515,0.0006798102,0.00060916063,0.0004718301,0.0002343965,0.00063005486,0.0009805864,0.00042177847,0.007905044],"category_scores_gemma":[0.0007221716,0.0002282541,0.00016087422,0.00030136848,0.00015014103,0.00071067817,0.0004088961,0.00028026602,0.003665622],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008280066,0.000075375654,0.0012389673,0.00044119396,0.000033030967,0.000503009,0.00018954498,0.001283936,0.56867576,0.0012870118,0.006359058,0.41908512],"study_design_scores_gemma":[0.0001482288,0.0013670482,0.007746444,0.00008896167,0.00012859098,0.0043065255,0.00015578663,0.07823559,0.8464855,0.0018236968,0.059363313,0.00015029997],"about_ca_topic_score_codex":0.00021108886,"about_ca_topic_score_gemma":0.0003888475,"teacher_disagreement_score":0.007905044,"about_ca_system_score_codex":0.00015981284,"about_ca_system_score_gemma":0.00019159801,"threshold_uncertainty_score":0.026444972},"labels":[],"label_agreement":null},{"id":"W4417275930","doi":"10.1162/tacl.a.54","title":"The Impact of Automatic Speech Transcription on Speaker Attribution","year":2025,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université TÉLUQ; Université du Québec à Montréal","funders":"","keywords":"Attribution; Transcription (linguistics); Task (project management); Speaker diarisation; Phonetic transcription; Speech processing","score_opus":0.018552587854670767,"score_gpt":0.296895449186917,"score_spread":0.2783428613322462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417275930","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.922733,0.001250912,0.06596328,0.00078412244,0.00063300703,0.00014946754,0.00067223073,0.003159028,0.0046550254],"genre_scores_gemma":[0.98836356,0.00017739546,0.009109929,0.00015305459,0.000104016035,0.000033431483,0.00076779973,0.00044417454,0.0008467015],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.96177024,0.02243109,0.0029727789,0.0046029193,0.007254244,0.0009686448],"domain_scores_gemma":[0.63117677,0.29191208,0.021598045,0.031641115,0.021343224,0.0023287397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0181842,0.0010880143,0.0008494884,0.0010292875,0.0010067031,0.0026159761,0.0010232369,0.0012367283,0.0021407674],"category_scores_gemma":[0.22789109,0.00042846528,0.00038979814,0.0011191192,0.0014089161,0.0024953685,0.0022098592,0.0015754737,0.0020500235],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008938152,0.0008559735,0.1188267,0.0014863713,0.0007077683,0.0012966581,0.006582418,0.12743634,0.17676246,0.0019333714,0.0072918767,0.5478819],"study_design_scores_gemma":[0.00021513167,0.004442165,0.22772919,0.0006374141,0.0006670598,0.002714825,0.0045610247,0.39416787,0.3484959,0.009045025,0.006651521,0.00067297544],"about_ca_topic_score_codex":0.0027458053,"about_ca_topic_score_gemma":0.0016129268,"teacher_disagreement_score":0.0181842,"about_ca_system_score_codex":0.0009321132,"about_ca_system_score_gemma":0.0009023989,"threshold_uncertainty_score":0.0961684},"labels":[],"label_agreement":null},{"id":"W4417423602","doi":"10.48550/arxiv.2507.10827","title":"Supporting SENĆOTEN Language Documentation Efforts with Automatic Speech Recognition","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Pipeline (software); Documentation; Vocabulary; Word error rate; Language model; Constructed language; Set (abstract data type); Speech technology","score_opus":0.030550187482115333,"score_gpt":0.3052722171440733,"score_spread":0.27472202966195797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417423602","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20466691,0.0024931142,0.4297511,0.0030712862,0.0013367976,0.0007022186,0.020439476,0.28240198,0.055137146],"genre_scores_gemma":[0.49169144,0.0012892399,0.3837042,0.0008503791,0.00024470536,0.0004072323,0.08051552,0.005796309,0.035501048],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977331,0.00057944236,0.0001728323,0.00065763824,0.00067568186,0.00018122433],"domain_scores_gemma":[0.9951997,0.0008962371,0.00022121744,0.0013716631,0.0020746517,0.00023648962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018334142,0.0015743665,0.000978599,0.0022941804,0.0013666169,0.0024736056,0.0014788582,0.0012080076,0.009442844],"category_scores_gemma":[0.007167422,0.00059858576,0.0007456651,0.0015743895,0.0007044701,0.0027933936,0.0030083288,0.002812019,0.01944747],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003254934,0.00021805357,0.0038930667,0.0005334605,0.00007472867,0.0008487421,0.0012330359,0.008051001,0.04037294,0.0026798127,0.0996538,0.84211594],"study_design_scores_gemma":[0.00023588524,0.0004149951,0.013304728,0.00039463316,0.00012818046,0.0014857996,0.0032823132,0.5078349,0.1648723,0.012158248,0.29556724,0.00032072864],"about_ca_topic_score_codex":0.030358832,"about_ca_topic_score_gemma":0.049685284,"teacher_disagreement_score":0.030358832,"about_ca_system_score_codex":0.0011020582,"about_ca_system_score_gemma":0.0038763946,"threshold_uncertainty_score":0.060364246},"labels":[],"label_agreement":null},{"id":"W4417530737","doi":"10.1145/3714394.3754429","title":"Poster: Recognizing Hidden-in-the-Ear Private Key for Reliable Silent Speech Interface Using Multi-Task Learning","year":2025,"lang":"","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Interface (matter); Decoding methods; Spelling; Key (lock); Authentication (law); Conjunction (astronomy); User interface; Identification (biology)","score_opus":0.05784036500355474,"score_gpt":0.3165426386370176,"score_spread":0.2587022736334629,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417530737","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06910223,0.0010549005,0.9008148,0.0016385602,0.0022781678,0.00022108585,0.00062790565,0.006768392,0.017493973],"genre_scores_gemma":[0.62658143,0.00067798235,0.26136455,0.00070196297,0.0010360869,0.00012391554,0.002298051,0.0008064087,0.10640964],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99969876,0.000052313586,0.000025253832,0.000086569606,0.000100097495,0.00003705441],"domain_scores_gemma":[0.9994362,0.00010338901,0.000026675081,0.00012597264,0.00023031869,0.00007738098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073055906,0.00067782315,0.00036712448,0.00021610761,0.0003836367,0.0006902405,0.0006183067,0.0009472336,0.024329716],"category_scores_gemma":[0.0011235056,0.00016964402,0.00032216395,0.00011331356,0.00042185953,0.0012072681,0.00097652245,0.0010433224,0.0146078775],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014969931,0.00029946613,0.0013493898,0.00027500323,0.000081106584,0.0006178623,0.00022613945,0.007573416,0.38402098,0.006024043,0.063846596,0.53418905],"study_design_scores_gemma":[0.0001193834,0.0015804416,0.003271046,0.000052250827,0.00009625431,0.0017982477,0.00019009889,0.33199796,0.5503064,0.007623317,0.10286745,0.00009719547],"about_ca_topic_score_codex":0.00036106817,"about_ca_topic_score_gemma":0.0006236501,"teacher_disagreement_score":0.024329716,"about_ca_system_score_codex":0.0001948252,"about_ca_system_score_gemma":0.00032678794,"threshold_uncertainty_score":0.08139104},"labels":[],"label_agreement":null},{"id":"W6888789972","doi":"10.23641/asha.14167058","title":"Forced alignment of child speech (Mahr et al., 2021)","year":2021,"lang":"en","type":"article","venue":"figshare ASHA Publications","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Two-alternative forced choice; Segmentation; Sample (material); Speech processing; Phonetics; Speech segmentation; Interval (graph theory); Electroglottograph; Process (computing)","score_opus":0.04140962456034709,"score_gpt":0.2830461045837347,"score_spread":0.2416364800233876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6888789972","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32936972,0.0048630834,0.5789277,0.00095881516,0.0012370601,0.002134249,0.028362444,0.0135731725,0.040573765],"genre_scores_gemma":[0.35040227,0.0013316154,0.60837764,0.000555956,0.00013821006,0.0018062999,0.016443534,0.0028042844,0.018140133],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971046,0.00077357906,0.00026643692,0.0009362852,0.0008000906,0.0001189764],"domain_scores_gemma":[0.9928508,0.0022351467,0.0007754128,0.00138741,0.0026054345,0.00014592873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037290354,0.00097443315,0.0004468799,0.0012494178,0.000689717,0.0014266362,0.00093537156,0.00075105723,0.015886996],"category_scores_gemma":[0.016116517,0.0005212392,0.0007620789,0.0012270877,0.0005663934,0.0011582462,0.0011664713,0.00079509744,0.00836789],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011052045,0.00008092791,0.026109187,0.0012900986,0.00022511405,0.00046296293,0.002797381,0.0026323884,0.10225627,0.0034645617,0.026160331,0.8334157],"study_design_scores_gemma":[0.00022431795,0.0013503303,0.51668125,0.00075987633,0.00051957025,0.007318592,0.0031772722,0.039895643,0.18929358,0.0055937087,0.2346452,0.00054059434],"about_ca_topic_score_codex":0.01243517,"about_ca_topic_score_gemma":0.030511389,"teacher_disagreement_score":0.015886996,"about_ca_system_score_codex":0.00079321954,"about_ca_system_score_gemma":0.0017442262,"threshold_uncertainty_score":0.053147256},"labels":[],"label_agreement":null},{"id":"W6892655041","doi":"10.5281/zenodo.11726402","title":"driving test pdf book","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Test (biology); Download; Government (linguistics); Agency (philosophy); Table (database); State (computer science)","score_opus":0.026210869389717464,"score_gpt":0.23542793802921627,"score_spread":0.2092170686394988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6892655041","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015126413,0.0010471366,0.0020639275,0.0021195228,0.0028991876,0.000574748,0.021575889,0.0078081647,0.9603988],"genre_scores_gemma":[0.0030090432,0.00063243794,0.0010143336,0.0009084748,0.00028966166,0.00016989707,0.01606682,0.0008961691,0.97701323],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995198,0.000022570377,0.000024524434,0.00005187636,0.00033783785,0.000043437758],"domain_scores_gemma":[0.99829644,0.00013784149,0.000034284443,0.0001343803,0.0011983189,0.00019882366],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00032439255,0.0010225227,0.0010271373,0.0015283171,0.0009288777,0.0025433057,0.0015610392,0.0015682201,0.8219102],"category_scores_gemma":[0.0022488108,0.00045432738,0.0006071418,0.0010503337,0.00015491988,0.0018186762,0.0011806549,0.001390746,0.7303692],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029933017,0.00006348972,0.00009186369,0.000055800832,0.0000017445636,0.000026273017,0.000005621304,0.00005028475,0.00015460799,0.00028446905,0.94673085,0.05250499],"study_design_scores_gemma":[0.00002879025,0.000073024516,0.0012277432,0.00007301797,0.0000044865983,0.00014788036,0.00003823517,0.00021281434,0.00034322214,0.00043277998,0.99740195,0.000015911332],"about_ca_topic_score_codex":0.0040967157,"about_ca_topic_score_gemma":0.0068277013,"teacher_disagreement_score":0.1780898,"about_ca_system_score_codex":0.0005575922,"about_ca_system_score_gemma":0.0008487125,"threshold_uncertainty_score":0.2540235},"labels":[],"label_agreement":null},{"id":"W6892787335","doi":"10.5281/zenodo.12278899","title":"apprendre windows 10 pdf","year":2024,"lang":"fr","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Paraphernalia; TSG101; Dysgeusia; Filter (signal processing); Point (geometry)","score_opus":0.047591060985396144,"score_gpt":0.24449635005133402,"score_spread":0.19690528906593788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6892787335","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007026778,0.001262909,0.017205343,0.0011916673,0.002817759,0.0010876859,0.085837774,0.16136637,0.7285278],"genre_scores_gemma":[0.0031905493,0.001160436,0.013067312,0.0013135218,0.0008401718,0.0011549509,0.042844612,0.08029607,0.8561323],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989064,0.00010477016,0.000100416895,0.00024096596,0.00048333599,0.0001642075],"domain_scores_gemma":[0.9964071,0.00082802965,0.00017060296,0.0005533338,0.0015679471,0.0004730951],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0015847204,0.0027935319,0.002195604,0.002850578,0.0012144372,0.007180868,0.0035436905,0.0021081285,0.92870474],"category_scores_gemma":[0.008011164,0.00197587,0.0016145464,0.0024027776,0.00058548665,0.007956125,0.0030914268,0.0028377871,0.913949],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000089997484,0.000027228625,0.000032690965,0.0003048655,0.0000062346417,0.00003821746,0.00003455519,0.00004213389,0.0004996831,0.00050502527,0.9706562,0.027763117],"study_design_scores_gemma":[0.000053673528,0.000026918133,0.00037340316,0.00012596457,0.000008502386,0.00008797628,0.000050127324,0.00011304741,0.0011987834,0.0009423583,0.9969867,0.00003247117],"about_ca_topic_score_codex":0.0023585295,"about_ca_topic_score_gemma":0.0030097594,"teacher_disagreement_score":0.07129526,"about_ca_system_score_codex":0.0009800919,"about_ca_system_score_gemma":0.001383744,"threshold_uncertainty_score":0.10169393},"labels":[],"label_agreement":null},{"id":"W6921056807","doi":"10.60864/1s30-t715","title":"Less peaky and more accurate CTC forced alignment by label priors","year":2024,"lang":"en","type":"article","venue":"IEEE SIGPORT","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Offset (computer science); Security token; Pipeline (software); Hidden Markov model; Pattern recognition (psychology); Bayesian probability; Prior probability; Training set","score_opus":0.03190628355525705,"score_gpt":0.281614336227028,"score_spread":0.24970805267177093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6921056807","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06685081,0.0007096278,0.8976541,0.0006648112,0.00041503357,0.000102493694,0.0011436108,0.02781118,0.0046484526],"genre_scores_gemma":[0.61979705,0.00024005382,0.35269493,0.000988069,0.00017286799,0.00023538899,0.007140159,0.0051069017,0.013624495],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99872726,0.00027995868,0.000047880436,0.0005598116,0.00025175803,0.00013330801],"domain_scores_gemma":[0.99616647,0.0017353246,0.00022325634,0.0011032356,0.0006376774,0.0001340882],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015153217,0.0014602538,0.0009121165,0.00065214094,0.0008101781,0.0016743356,0.0014454218,0.0017002537,0.007037659],"category_scores_gemma":[0.008362426,0.0007233515,0.0007403162,0.0008757072,0.000770029,0.002883719,0.0015726935,0.0039885333,0.0059232474],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007772357,0.0003092457,0.0063842908,0.00022918278,0.00013216352,0.00030564668,0.00033605364,0.20108971,0.053448543,0.008125641,0.036432013,0.6924303],"study_design_scores_gemma":[0.00005333667,0.00007999951,0.0014271617,0.00003521666,0.000028344131,0.0001418176,0.000057693684,0.9613915,0.02244147,0.007839755,0.0064671594,0.000036478366],"about_ca_topic_score_codex":0.00925243,"about_ca_topic_score_gemma":0.01968565,"teacher_disagreement_score":0.00925243,"about_ca_system_score_codex":0.0009311594,"about_ca_system_score_gemma":0.0020052649,"threshold_uncertainty_score":0.023543358},"labels":[],"label_agreement":null},{"id":"W6930431502","doi":"10.5281/zenodo.11464895","title":")-(`! [[[[WhatsApp ((( (+27) 736616875))) *____**)) TOP QUALITY COUNTERFEIT MONEY FOR SALE South Korea Lushnjë Free State\\\\EUROPE USA 3","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nucleofection; Hyporeflexia; Diafiltration; Fusible alloy; Pretext; Articular cartilage damage","score_opus":0.05270579122096652,"score_gpt":0.2747553673391952,"score_spread":0.22204957611822868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930431502","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004904002,0.00013763618,0.000662225,0.0012564425,0.0014211395,0.00009747681,0.0017327929,0.0030100807,0.9911919],"genre_scores_gemma":[0.0012899521,0.00009314217,0.00026152827,0.00044031919,0.00009526898,0.000020741405,0.00050942606,0.00071322656,0.9965765],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9996051,0.000030082185,0.0000149013085,0.00007667892,0.0001592591,0.00011407042],"domain_scores_gemma":[0.9985008,0.00011583506,0.000060442915,0.00015026424,0.0007230646,0.00044954495],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00047900242,0.00075084256,0.0004557193,0.0009388833,0.0019931013,0.004810606,0.00071569165,0.0016946476,0.94213045],"category_scores_gemma":[0.0024400686,0.00042874803,0.00052714115,0.0007288102,0.00049686764,0.0032850339,0.0025797777,0.0012853605,0.92151076],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017418668,0.000017719938,0.00010246379,0.000037495298,9.5182224e-7,0.000027307406,0.00003764112,0.000010831362,0.00021350135,0.0014083325,0.9713289,0.026797548],"study_design_scores_gemma":[0.0000044718113,0.000008339748,0.0002864605,0.000023208491,7.7438256e-7,0.00003824741,0.000047623278,0.000018336139,0.00011203255,0.00012556279,0.9993304,0.0000044942526],"about_ca_topic_score_codex":0.0053528845,"about_ca_topic_score_gemma":0.008766276,"teacher_disagreement_score":0.057869554,"about_ca_system_score_codex":0.0010252354,"about_ca_system_score_gemma":0.00085317576,"threshold_uncertainty_score":0.08254379},"labels":[],"label_agreement":null},{"id":"W6939194750","doi":"10.60692/38hgp-2s302","title":"Synthetic Speech Dataset","year":2019,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Speech synthesis; Speech processing; Spoken language; Natural language; Speech corpus; Speech technology","score_opus":0.031170796375344853,"score_gpt":0.20937472157760784,"score_spread":0.17820392520226297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939194750","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016755925,0.0009774595,0.006605426,0.00054706587,0.0010635853,0.0005250137,0.95355606,0.008290272,0.011679245],"genre_scores_gemma":[0.0067145373,0.00014794728,0.0028098966,0.00012881347,0.00004241854,0.0003478418,0.98650545,0.00015082226,0.0031521793],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985311,0.00041725754,0.0001440333,0.00032077925,0.00042204984,0.00016467168],"domain_scores_gemma":[0.9977863,0.00062658417,0.00009173715,0.0006043216,0.00067890226,0.00021214827],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013221551,0.003058478,0.0016447322,0.0016495397,0.0010590516,0.0013337479,0.0028410868,0.0028461802,0.035789926],"category_scores_gemma":[0.003828477,0.00050310703,0.0015184684,0.0014956298,0.0005344246,0.0010668798,0.0017196654,0.0022599471,0.060530506],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013585093,0.0009767936,0.002205077,0.0017609597,0.00032335042,0.0005152372,0.00014178047,0.009898364,0.00907511,0.0015728453,0.8990965,0.073075496],"study_design_scores_gemma":[0.0017384877,0.0011326923,0.019968832,0.00039302715,0.0003173002,0.0018129224,0.0005764456,0.045617186,0.019569645,0.0033403006,0.90519965,0.00033352792],"about_ca_topic_score_codex":0.013969012,"about_ca_topic_score_gemma":0.02081316,"teacher_disagreement_score":0.035789926,"about_ca_system_score_codex":0.000889234,"about_ca_system_score_gemma":0.0016512122,"threshold_uncertainty_score":0.11972928},"labels":[],"label_agreement":null},{"id":"W6958761994","doi":"10.6084/m9.figshare.16828541.v1","title":"Influence of drinking water quality on the formation of corrosion scales in lead-bearing drinking water distribution systems","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Corrosion; Water quality; Lead (geology); Water supply; Water treatment; Soft water; Erosion corrosion of copper water tubes; Groundwater","score_opus":0.05980036939291211,"score_gpt":0.2688810242796449,"score_spread":0.20908065488673278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958761994","genre_codex":"empirical","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99925274,0.00003917005,0.00013434453,0.0000043065343,5.2456267e-7,0.0000046318482,0.00016978092,0.000005056396,0.0003894936],"genre_scores_gemma":[0.99936396,0.000041280327,0.00017233434,0.0000025581903,3.8159095e-7,0.0000018082337,0.00018139803,0.0000031324357,0.00023329869],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99968815,0.000039989365,0.000016323847,0.00006219676,0.000113710485,0.000079672354],"domain_scores_gemma":[0.9993882,0.000114698916,0.00014009421,0.000025048996,0.00027886845,0.00005297848],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027547288,0.00020751315,0.00020738105,0.00080768595,0.00036215238,0.0007411071,0.00016242852,0.00014647457,0.0004574552],"category_scores_gemma":[0.0008129002,0.00015239979,0.00020522358,0.0008990492,0.0004196673,0.0002024336,0.00030704236,0.0001429996,0.000100320154],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005198375,0.000048015547,0.8705446,0.000063063984,0.00007896489,0.00023280874,0.0010802143,0.0014891024,0.11294795,0.000066166045,0.00009792612,0.012831259],"study_design_scores_gemma":[0.0000011717564,0.00005371777,0.98809844,0.0000021677288,0.000016092232,0.000025075913,0.00044199848,0.00054867944,0.010549192,0.000012610032,0.0002458001,0.0000050926983],"about_ca_topic_score_codex":0.28828236,"about_ca_topic_score_gemma":0.46714833,"teacher_disagreement_score":0.28828236,"about_ca_system_score_codex":0.0013067662,"about_ca_system_score_gemma":0.0006593356,"threshold_uncertainty_score":0.57320875},"labels":[],"label_agreement":null},{"id":"W6964075530","doi":"10.25384/sage.21317302","title":"sj-docx-1-cjo-10.1177_00084174221129947 - Supplemental material for Review and Consultations of Canadian Financial Education Programs for Individuals with Disabilities","year":2022,"lang":"en","type":"article","venue":"Sage Journals Data","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Quarter (Canadian coin); Financial literacy; Formal education","score_opus":0.06687970547653425,"score_gpt":0.3224906653711449,"score_spread":0.25561095989461063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6964075530","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018216507,0.0016731088,0.0009311791,0.00605792,0.0036714752,0.001228171,0.64904857,0.0075307777,0.3296767],"genre_scores_gemma":[0.0030939777,0.003999905,0.003439204,0.004779612,0.0012690439,0.0017710278,0.2600102,0.008113481,0.71352357],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9961046,0.00021986486,0.0003165722,0.0002649215,0.0027521756,0.00034195615],"domain_scores_gemma":[0.9468934,0.008787804,0.0010623959,0.0016069936,0.038355626,0.0032937366],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003464747,0.0011685977,0.0015347354,0.008213219,0.0021903254,0.005991398,0.003877722,0.0023352015,0.9521815],"category_scores_gemma":[0.040968556,0.0011770328,0.00077079725,0.010528555,0.0011872969,0.0035227453,0.0031039491,0.0017925006,0.8128617],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007969347,0.0000051101333,0.000021600032,0.00020951137,9.5213585e-7,0.0000048145325,0.000011364856,0.0000067854694,0.000018870414,0.000086655935,0.99191827,0.007708067],"study_design_scores_gemma":[0.00003396038,0.0000057437815,0.0006204732,0.00041620774,0.0000053502968,0.000021553782,0.0001088974,0.000019053263,0.00010059422,0.00020572913,0.99844736,0.000015105251],"about_ca_topic_score_codex":0.27646396,"about_ca_topic_score_gemma":0.3854905,"teacher_disagreement_score":0.9521815,"about_ca_system_score_codex":0.008031941,"about_ca_system_score_gemma":0.017010327,"threshold_uncertainty_score":0.5497095},"labels":[],"label_agreement":null},{"id":"W6979728622","doi":"","title":"Acoustic/Phonetic Transcription Using a Polynomial Classifier and Hidden Markov Models","year":2022,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Hidden Markov model; Maximum-entropy Markov model; Classifier (UML); Pattern recognition (psychology); Hidden semi-Markov model; Transcription (linguistics); Markov model","score_opus":0.03649342766834752,"score_gpt":0.21748616550352848,"score_spread":0.18099273783518097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6979728622","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02663005,0.00011455516,0.9601019,0.0001649632,0.00027891152,0.00015576514,0.0012184337,0.007387352,0.003947993],"genre_scores_gemma":[0.3415989,0.0003224178,0.63093764,0.00007858228,0.00017306632,0.00020790016,0.005394551,0.0015765905,0.019710388],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994803,0.00006725421,0.000031073792,0.00017308182,0.00016048874,0.00008785139],"domain_scores_gemma":[0.99897575,0.00023793791,0.000035051926,0.00015241976,0.0005397625,0.000059172216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058069825,0.0006627,0.0006351852,0.0010475836,0.00075835746,0.0013687043,0.0006924684,0.00082153425,0.015185917],"category_scores_gemma":[0.002269378,0.00037441208,0.0009291923,0.001038405,0.0003714476,0.00091357983,0.0008040932,0.0014273763,0.015148139],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007924641,0.00014999976,0.0016324447,0.0001680339,0.00003742448,0.00031002783,0.00017751302,0.021806652,0.10523346,0.0042096185,0.006303943,0.85917836],"study_design_scores_gemma":[0.00007024753,0.00020622162,0.0053302348,0.000043498752,0.00007804124,0.00035418884,0.00030041332,0.8913033,0.08455868,0.004369685,0.013314218,0.00007120415],"about_ca_topic_score_codex":0.011423642,"about_ca_topic_score_gemma":0.012729496,"teacher_disagreement_score":0.015185917,"about_ca_system_score_codex":0.0005189224,"about_ca_system_score_gemma":0.001926621,"threshold_uncertainty_score":0.050801992},"labels":[],"label_agreement":null},{"id":"W6997174494","doi":"","title":"Utilization of Multiple Units in Human And Machine Recognition of Continuous Speech---- Perceptual Evidence And A Proposal For An Asr System","year":2022,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perception; Pattern recognition (psychology); Human–machine system; Human–machine interface","score_opus":0.09954456807472184,"score_gpt":0.27332700525050446,"score_spread":0.17378243717578262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6997174494","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30792442,0.004284234,0.6504594,0.003293616,0.0005842343,0.00015680531,0.00023635926,0.0008948444,0.032166045],"genre_scores_gemma":[0.82765615,0.0006128008,0.16664892,0.00025166932,0.00019105591,0.00012845248,0.00007213011,0.00012133092,0.0043175854],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989152,0.00035042566,0.00011948289,0.00032631756,0.00021170458,0.00007688578],"domain_scores_gemma":[0.9955155,0.002366661,0.00025394405,0.0010679684,0.000638756,0.00015721962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029191636,0.00046166923,0.0006689551,0.0008270509,0.00057772244,0.0027994185,0.001508578,0.001405551,0.0040276814],"category_scores_gemma":[0.0067117675,0.00066283986,0.00058049156,0.0007069016,0.0023311367,0.005429582,0.0014303541,0.0011948154,0.0009255414],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024266366,0.00020540509,0.006081905,0.00054303894,0.00017381988,0.00092093315,0.0023316112,0.00528065,0.25791633,0.25213403,0.0016008189,0.4703849],"study_design_scores_gemma":[0.00039592915,0.0026041456,0.03147158,0.0004286947,0.00062833895,0.0054249046,0.0031472454,0.28749546,0.19802426,0.4446929,0.025291013,0.00039550796],"about_ca_topic_score_codex":0.0007836919,"about_ca_topic_score_gemma":0.00080612046,"teacher_disagreement_score":0.0040276814,"about_ca_system_score_codex":0.0003838723,"about_ca_system_score_gemma":0.0004506954,"threshold_uncertainty_score":0.015438199},"labels":[],"label_agreement":null},{"id":"W7000383101","doi":"","title":"Experiments on The Use of Demisyllables For Automatic Speech Recognition","year":2022,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Voice activity detection; Speech processing; Acoustic model; Speaker recognition; Pattern recognition (psychology); Automatic target recognition","score_opus":0.14526471405056032,"score_gpt":0.26103017194622447,"score_spread":0.11576545789566414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7000383101","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90122056,0.0004963295,0.08369474,0.00024652932,0.00018091511,0.0005868152,0.0013756794,0.0045375,0.0076609175],"genre_scores_gemma":[0.894139,0.00031036956,0.08909794,0.00021623379,0.000042477284,0.00026696752,0.0024249544,0.00074453145,0.012757557],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986626,0.0004310691,0.00014216911,0.00028046052,0.0003171691,0.00016654415],"domain_scores_gemma":[0.9917014,0.005870818,0.00012660859,0.0007592199,0.0013085607,0.00023330387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019060485,0.0009868935,0.00088770257,0.00067060033,0.0006439632,0.0007764391,0.0014754708,0.0014290478,0.009241439],"category_scores_gemma":[0.009118146,0.00052770646,0.00050904875,0.0006391421,0.00047453752,0.0014786419,0.00070368435,0.00069273904,0.0029110694],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00780927,0.002368202,0.0026478681,0.0012262466,0.00017673003,0.0012370138,0.002258288,0.007432286,0.6687719,0.0010909954,0.0027978383,0.30218333],"study_design_scores_gemma":[0.00085233327,0.0066633453,0.01365675,0.00005914249,0.0003492302,0.001483329,0.001140816,0.06493097,0.8988584,0.0007167468,0.011133338,0.00015565575],"about_ca_topic_score_codex":0.0073833796,"about_ca_topic_score_gemma":0.0055889627,"teacher_disagreement_score":0.009241439,"about_ca_system_score_codex":0.00036253012,"about_ca_system_score_gemma":0.00040684312,"threshold_uncertainty_score":0.030915678},"labels":[],"label_agreement":null},{"id":"W7001204461","doi":"","title":"Issues of bilingualism in likelihood ratio-based forensic voice comparison","year":2021,"lang":"en","type":"dissertation","venue":"White Rose eTheses Online (University of Leeds, The University of Sheffield, University of York)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Formant; Linear discriminant analysis; Matching (statistics); Situated; Neuroscience of multilingualism; Speaker recognition; Software","score_opus":0.0240817240188065,"score_gpt":0.24365453749311639,"score_spread":0.21957281347430987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7001204461","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4265699,0.006017434,0.5116956,0.011349132,0.0005367371,0.0003148059,0.00028314552,0.0010942781,0.042138882],"genre_scores_gemma":[0.9122904,0.0008635982,0.08339499,0.0007086791,0.00023578622,0.00015315025,0.000088248824,0.00031613308,0.0019490785],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.96037954,0.029826527,0.0016599692,0.0027273777,0.0048113377,0.0005953303],"domain_scores_gemma":[0.89075,0.08631583,0.006721979,0.00834697,0.00686385,0.0010013323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07026698,0.00066915783,0.00094267656,0.0013640898,0.0011881839,0.0044910274,0.0015772674,0.0011684875,0.0041905018],"category_scores_gemma":[0.183109,0.00056514447,0.00055047206,0.0008914036,0.0053881058,0.0045826435,0.0047043026,0.0018400521,0.0011652664],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030179732,0.00028404858,0.12281613,0.00086090685,0.0004161204,0.0013585556,0.017732164,0.009520455,0.03427429,0.15706688,0.0024124866,0.65024006],"study_design_scores_gemma":[0.0007496089,0.0047417628,0.22500849,0.0014621224,0.0005668458,0.011990158,0.015492387,0.14332896,0.09305853,0.45602158,0.046488825,0.0010908331],"about_ca_topic_score_codex":0.0032642903,"about_ca_topic_score_gemma":0.003981797,"teacher_disagreement_score":0.07026698,"about_ca_system_score_codex":0.0012113606,"about_ca_system_score_gemma":0.0020466412,"threshold_uncertainty_score":0.3716117},"labels":[],"label_agreement":null},{"id":"W7002446300","doi":"","title":"Nivelrikko-oppaan harjoitteluohjeiden kääntäminen arabian kielelle. Kommentoitu käännös.","year":2019,"lang":"fi","type":"other","venue":"Theseus (Ammattikorkeakoulujen)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Government (linguistics); Mercantilism","score_opus":0.030569287495678853,"score_gpt":0.25262348639020915,"score_spread":0.2220541988945303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7002446300","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09250799,0.004703832,0.0014207966,0.015206877,0.002249025,0.00015034241,0.005597988,0.0003289105,0.8778342],"genre_scores_gemma":[0.12297593,0.0018588769,0.0025706613,0.0016054112,0.00009306744,0.000085698586,0.0022468602,0.00020857085,0.8683549],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993025,0.00005049634,0.000021790238,0.00012927174,0.0003140394,0.00018194578],"domain_scores_gemma":[0.9995017,0.00004472503,0.000035408768,0.000025523152,0.00025993917,0.00013270484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005874713,0.00037318768,0.0002017813,0.0005687832,0.0033272628,0.0031520892,0.0005260384,0.0011692401,0.12489959],"category_scores_gemma":[0.0009424494,0.00025185585,0.0002661653,0.00062498834,0.00069686427,0.0012328277,0.0019461233,0.0012784926,0.024577145],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007909801,0.00032876735,0.047690064,0.0008807459,0.00004823344,0.001326562,0.017714461,0.00036842728,0.024462895,0.052488223,0.44538513,0.40851554],"study_design_scores_gemma":[0.0000071626764,0.000028510907,0.023125183,0.00011981215,0.000008367879,0.00011152895,0.0059286724,0.0000631744,0.0018447014,0.00065371284,0.96809286,0.000016301345],"about_ca_topic_score_codex":0.1349789,"about_ca_topic_score_gemma":0.3711242,"teacher_disagreement_score":0.1349789,"about_ca_system_score_codex":0.004422124,"about_ca_system_score_gemma":0.0061909417,"threshold_uncertainty_score":0.41783077},"labels":[],"label_agreement":null},{"id":"W7006028432","doi":"","title":"Speech Recognition Based Upon a Segment Classification and Labelling Technique and Hidden Markov Model","year":2022,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Hidden Markov model; Pattern recognition (psychology); Labelling; Markov model; Acoustic model; Maximum-entropy Markov model","score_opus":0.03500273309650751,"score_gpt":0.22743946707279994,"score_spread":0.19243673397629243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7006028432","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010113625,0.00013753683,0.983952,0.000055876313,0.00012704934,0.00006345362,0.00031519984,0.0037032296,0.001532046],"genre_scores_gemma":[0.119391024,0.0003077182,0.8641369,0.000115480085,0.00009816383,0.00021353105,0.0020363475,0.0005193852,0.013181395],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996455,0.000053496136,0.000022531683,0.00011197973,0.00012008769,0.000046364115],"domain_scores_gemma":[0.998855,0.0004432436,0.00004702166,0.00016782254,0.0004399939,0.00004691572],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066087657,0.0007106608,0.0009300887,0.0009940587,0.0006702732,0.0009920823,0.000821623,0.00093611644,0.006066029],"category_scores_gemma":[0.001220286,0.0005152419,0.00089867285,0.0008751758,0.00041541655,0.000830038,0.0006215729,0.0012668933,0.006917756],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005015883,0.000120992925,0.00079575635,0.00014609906,0.00007735826,0.00013632639,0.00014994516,0.009873516,0.21600027,0.0052212044,0.005412217,0.76156473],"study_design_scores_gemma":[0.00005558139,0.00026689822,0.005939726,0.000054780514,0.0001795651,0.0003840485,0.000116075906,0.78572065,0.18646239,0.005944078,0.014777976,0.00009823146],"about_ca_topic_score_codex":0.0065416447,"about_ca_topic_score_gemma":0.0155623825,"teacher_disagreement_score":0.0065416447,"about_ca_system_score_codex":0.00048058206,"about_ca_system_score_gemma":0.0012558756,"threshold_uncertainty_score":0.020292878},"labels":[],"label_agreement":null},{"id":"W7009343680","doi":"","title":"The Effect of LPC Order on The Performance of Vector Quantization in Isolated-Word Recognition","year":2022,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Vector quantization; Quantization (signal processing); Pattern recognition (psychology); Order (exchange); Control theory (sociology)","score_opus":0.012971245003816393,"score_gpt":0.20651318531538204,"score_spread":0.19354194031156566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7009343680","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94637144,0.002131053,0.045087125,0.00033950896,0.00034055865,0.0000380534,0.00040161156,0.0011187856,0.0041718083],"genre_scores_gemma":[0.97607654,0.00082740345,0.01854129,0.00012215775,0.000112454814,0.00002091805,0.00069507776,0.0003947929,0.0032095334],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982967,0.0006048678,0.00022255267,0.00024091973,0.00045194576,0.00018297017],"domain_scores_gemma":[0.9440167,0.049897153,0.00082667,0.0015337717,0.0032612954,0.00046442685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020052763,0.000553873,0.00061824184,0.00047733987,0.00048403014,0.00117703,0.00040614876,0.0009293021,0.004616364],"category_scores_gemma":[0.02462258,0.0004629322,0.00022585328,0.00076255907,0.0005406788,0.0019727778,0.00045270578,0.0009896797,0.0015120719],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.020583713,0.0010183982,0.013474778,0.0006500515,0.00015317526,0.0006202072,0.00061404414,0.063144535,0.47699448,0.0019368745,0.0025479107,0.41826183],"study_design_scores_gemma":[0.00037964433,0.00455729,0.04888135,0.000147834,0.00032592023,0.0012529333,0.0005076776,0.38611197,0.5539596,0.0015772388,0.0020622283,0.00023624809],"about_ca_topic_score_codex":0.004463415,"about_ca_topic_score_gemma":0.004271073,"teacher_disagreement_score":0.004616364,"about_ca_system_score_codex":0.00036918168,"about_ca_system_score_gemma":0.0006632908,"threshold_uncertainty_score":0.015443206},"labels":[],"label_agreement":null},{"id":"W7019613109","doi":"","title":"Hierarchical Recognition of French Vowels by Expert System Iroise-Serac","year":2022,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Expert system; Hierarchical control system; Legal expert system; Pattern recognition (psychology); Knowledge base","score_opus":0.019236881012785003,"score_gpt":0.21382764349238406,"score_spread":0.19459076247959906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7019613109","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32991168,0.0011757498,0.6308335,0.00023753224,0.00022105542,0.00023072878,0.0014548268,0.025004016,0.010930901],"genre_scores_gemma":[0.7101182,0.00026547664,0.26962563,0.00020453126,0.00009061888,0.00014510521,0.0024206424,0.00048744277,0.016642468],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99960357,0.00006190174,0.00002043539,0.00017057163,0.000058709593,0.00008483394],"domain_scores_gemma":[0.9995278,0.00010068915,0.000015497359,0.000054565742,0.0002630074,0.00003847078],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043712833,0.00078577374,0.00057918427,0.0011206159,0.0005198727,0.0007973667,0.0003916891,0.00095624704,0.00626984],"category_scores_gemma":[0.00075523293,0.00022293738,0.00051268656,0.00023957672,0.00014037044,0.00036228946,0.0003573515,0.00030573228,0.003931073],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007607534,0.00011326445,0.005124719,0.00013092226,0.000065956265,0.00029308515,0.00022330215,0.0074013313,0.39977217,0.00064171763,0.004897503,0.5805753],"study_design_scores_gemma":[0.00013204182,0.0006105325,0.05492388,0.000050753235,0.00020891902,0.0006954194,0.00045902852,0.6029063,0.3193143,0.0009177668,0.019684933,0.00009609353],"about_ca_topic_score_codex":0.017204357,"about_ca_topic_score_gemma":0.020849528,"teacher_disagreement_score":0.017204357,"about_ca_system_score_codex":0.00038556117,"about_ca_system_score_gemma":0.0005869304,"threshold_uncertainty_score":0.034208417},"labels":[],"label_agreement":null},{"id":"W7022136763","doi":"","title":"Introduction","year":2020,"lang":"en","type":"article","venue":"eYLS (Yale Law School)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"The arctic; Arctic; Multidisciplinary approach; Corporate governance; Indigenous; Work (physics); Fishing","score_opus":0.02161385027929595,"score_gpt":0.23265043975838118,"score_spread":0.2110365894790852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7022136763","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012881574,0.006608767,0.00614307,0.010217002,0.008451065,0.00020966555,0.0043447358,0.001348142,0.9613894],"genre_scores_gemma":[0.009177685,0.007402426,0.004979624,0.005131879,0.002019522,0.00022461891,0.005733313,0.00071325735,0.9646177],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983546,0.00019236041,0.00009990621,0.0004043567,0.00074159674,0.00020716392],"domain_scores_gemma":[0.99873954,0.00019642568,0.000057439316,0.00017589408,0.0006258018,0.00020503592],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000958579,0.0009911781,0.00080778106,0.0015744639,0.0025453751,0.006086813,0.0021244173,0.0030486234,0.4417043],"category_scores_gemma":[0.003699438,0.00039441898,0.0007983403,0.0017382867,0.0010395967,0.00451866,0.003636192,0.0024253663,0.2718234],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004272046,0.000051249794,0.00053321116,0.00031503564,0.0000067494902,0.0001702671,0.0007706672,0.00020756463,0.00043524452,0.056853864,0.7588169,0.18179643],"study_design_scores_gemma":[0.0000017782772,0.0000065250465,0.00016156572,0.000090313675,0.0000010874508,0.000067428315,0.000115111885,0.000026361902,0.00004531574,0.002069655,0.9974112,0.0000036507893],"about_ca_topic_score_codex":0.006545681,"about_ca_topic_score_gemma":0.0076268674,"teacher_disagreement_score":0.5582957,"about_ca_system_score_codex":0.0027453927,"about_ca_system_score_gemma":0.0035958823,"threshold_uncertainty_score":0.79634106},"labels":[],"label_agreement":null},{"id":"W7024091935","doi":"","title":"Promoting Inclusive Systems for Migrants in Education","year":2024,"lang":"en","type":"other","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Promotion (chess); Inclusion (mineral); Quality (philosophy); Capability approach; Youth studies; Higher education","score_opus":0.01791785218485285,"score_gpt":0.29081109361695856,"score_spread":0.2728932414321057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024091935","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2460078,0.005531003,0.01552356,0.02963822,0.0013029964,0.00022276913,0.00005052993,0.0003247788,0.70139825],"genre_scores_gemma":[0.8440958,0.003881535,0.011387715,0.0028409117,0.00028717663,0.00022451587,0.000051850653,0.0001660221,0.13706447],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.998738,0.00070229685,0.000037022048,0.00008028743,0.00014564222,0.0002968235],"domain_scores_gemma":[0.9992895,0.00020207328,0.00010750736,0.000103100225,0.00006511871,0.00023266632],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021572197,0.00038276633,0.00021403626,0.0009086949,0.0062690144,0.008687013,0.00073041534,0.0012662447,0.0068564164],"category_scores_gemma":[0.0019633397,0.00019877673,0.000283592,0.0008307916,0.006202291,0.006176624,0.012219471,0.0013869334,0.0009437491],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004196531,0.00013928374,0.0042156386,0.00046081768,0.000012113842,0.0010340334,0.32441097,0.0005259996,0.0015312047,0.46931833,0.025493741,0.17281587],"study_design_scores_gemma":[0.000011664242,0.0000931988,0.0033789927,0.0005651093,0.000009705464,0.0006680884,0.16205685,0.0002348082,0.0008012261,0.04574259,0.78642064,0.000017233635],"about_ca_topic_score_codex":0.0014977582,"about_ca_topic_score_gemma":0.0038048448,"teacher_disagreement_score":0.008687013,"about_ca_system_score_codex":0.0019494903,"about_ca_system_score_gemma":0.002850899,"threshold_uncertainty_score":0.022937},"labels":[],"label_agreement":null},{"id":"W7024242503","doi":"","title":"Proceso de internacionalización de las medianas empresas: caso de estudio del sector alimenticio del casco central de la provincia de Heredia en el período 2005-2010","year":2016,"lang":"es","type":"other","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Private sector; Primary sector of the economy; Economic sector; Quarter (Canadian coin)","score_opus":0.012075088849600606,"score_gpt":0.27611303714122293,"score_spread":0.2640379482916223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024242503","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9959835,0.00028793357,0.00015904524,0.00015957227,0.0000054508096,0.000009705274,0.0006197178,0.000008495604,0.0027666916],"genre_scores_gemma":[0.99578804,0.0002699276,0.00023931808,0.000032395594,0.0000050320255,0.000017461834,0.00056438387,0.0000046776636,0.0030788863],"study_design_codex":"observational","study_design_gemma":"case_report","domain_scores_codex":[0.9996182,0.0000707463,0.000018154586,0.00011295506,0.00005525297,0.00012464661],"domain_scores_gemma":[0.9988192,0.00019857183,0.00036856192,0.0000860489,0.0003170195,0.00021069474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005980657,0.00022447543,0.00022119252,0.0006938947,0.00070265174,0.0015351365,0.0004355222,0.00027477698,0.002595439],"category_scores_gemma":[0.0012669723,0.00018336116,0.0003414513,0.0017979548,0.00068362843,0.0005585185,0.0011901531,0.00038772292,0.0002813122],"study_design_candidate":"case_report","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008144949,0.000019923635,0.9828706,0.00004729005,0.000051502724,0.00015630285,0.0088954335,0.00021519721,0.0004527719,0.00034553214,0.0005521951,0.0063117873],"study_design_scores_gemma":[7.323869e-7,0.000012524394,0.9904945,0.000014441483,0.000010515935,0.000012326987,0.0076211556,0.000076034856,0.000057255256,0.000037964364,0.0016598633,0.0000026978296],"about_ca_topic_score_codex":0.44489428,"about_ca_topic_score_gemma":0.6188869,"teacher_disagreement_score":0.44489428,"about_ca_system_score_codex":0.0034198589,"about_ca_system_score_gemma":0.0030073924,"threshold_uncertainty_score":0.8846094},"labels":[],"label_agreement":null},{"id":"W7024469088","doi":"","title":"Sequential decision modeling in uncertain conditions","year":2023,"lang":"fr","type":"dissertation","venue":"Papyrus : Institutional Repository (Université de Montréal)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Decision process; Context (archaeology); Decision theory","score_opus":0.030841804608981224,"score_gpt":0.22930683564816084,"score_spread":0.19846503103917962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024469088","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017679332,0.00086476735,0.97043985,0.0007618278,0.00018052627,0.00010865631,0.00055077625,0.0003597789,0.0090545155],"genre_scores_gemma":[0.7719056,0.002228527,0.20270228,0.0003087114,0.000307515,0.00044335765,0.0011215333,0.00015469006,0.020827789],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980578,0.0006568693,0.00013493496,0.0005036795,0.000411541,0.0002351199],"domain_scores_gemma":[0.9943011,0.0044012484,0.00040246037,0.00019322676,0.0005218655,0.0001801109],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023769438,0.0013807452,0.0015396938,0.0009105045,0.00071488693,0.0032009552,0.0013810403,0.001834954,0.0102788955],"category_scores_gemma":[0.006882588,0.0007718701,0.0018960156,0.0010428275,0.001259576,0.0027318345,0.0015106357,0.0021194112,0.0010736898],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017512502,0.000043869444,0.0009927433,0.00018986287,0.00007784084,0.00021655948,0.00014965887,0.88563985,0.00075696374,0.08302376,0.001140585,0.027593147],"study_design_scores_gemma":[0.000013506206,0.000031297663,0.00014025008,0.000020620015,0.000016906024,0.00002485776,0.000025528916,0.9697077,0.00032491094,0.027675984,0.0020038912,0.000014514331],"about_ca_topic_score_codex":0.01221363,"about_ca_topic_score_gemma":0.01086425,"teacher_disagreement_score":0.01221363,"about_ca_system_score_codex":0.0021844807,"about_ca_system_score_gemma":0.0019999307,"threshold_uncertainty_score":0.034386396},"labels":[],"label_agreement":null},{"id":"W7025064530","doi":"","title":"Une continuité essentielle toujours engagée dans la réussite collégiale : mémoire présenté à la Commission parlementaire de l'éducation sur l'enseignement collégial québécois /","year":2015,"lang":"fr","type":"other","venue":"Bibliothèque et Archives nationales du Québec (Québec government)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Commission; Context (archaeology); Government (linguistics); Legislation","score_opus":0.017892423987609707,"score_gpt":0.24635385212684802,"score_spread":0.2284614281392383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7025064530","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05114646,0.046199087,0.007559782,0.58223283,0.011142116,0.00017718297,0.00059984036,0.0002726075,0.30067012],"genre_scores_gemma":[0.3844562,0.021809287,0.0048203915,0.025440311,0.0025784958,0.00011968492,0.00041915587,0.00024262421,0.56011385],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9934157,0.001088486,0.00017362143,0.0005183715,0.0028252504,0.0019785615],"domain_scores_gemma":[0.9869838,0.0016722945,0.000533658,0.00067982276,0.006494286,0.0036361422],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008085366,0.00049198326,0.00043718642,0.0018167313,0.016231515,0.015678558,0.0018870834,0.0059645255,0.020748591],"category_scores_gemma":[0.009495166,0.00038855104,0.00046879594,0.0025311606,0.009497849,0.0053256615,0.0056875194,0.0063410187,0.0023855008],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006751221,0.000101152495,0.006318837,0.00046479056,0.000023949575,0.0007531754,0.06185622,0.00026321894,0.0019969824,0.16665095,0.5693151,0.19218823],"study_design_scores_gemma":[0.000005000941,0.000012111093,0.0074857227,0.00033781672,0.0000060672264,0.00013744984,0.01611078,0.00007929114,0.00027499002,0.0022831415,0.9732389,0.000028742279],"about_ca_topic_score_codex":0.89102536,"about_ca_topic_score_gemma":0.9603184,"teacher_disagreement_score":0.9467972,"about_ca_system_score_codex":0.053202793,"about_ca_system_score_gemma":0.124834254,"threshold_uncertainty_score":0.38601512},"labels":[],"label_agreement":null},{"id":"W7025243928","doi":"","title":"TonB-protein interactions in nutrient uptake systems of «Escherichia coli»","year":2010,"lang":"en","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Nutrient; Bacteria; Mechanism (biology); Essential nutrient","score_opus":0.0059942614857877025,"score_gpt":0.16116464028990743,"score_spread":0.1551703788041197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7025243928","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9964148,0.0009942774,0.0005589411,0.00022038663,0.000021591291,0.000007061511,0.00020890754,0.000040767856,0.001533256],"genre_scores_gemma":[0.994001,0.00038343147,0.0009980259,0.00008219748,0.0000044723274,0.000009769626,0.00077585253,0.000018369952,0.003726833],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9998642,0.000020835803,0.000006448128,0.000029915102,0.000048335467,0.000030202162],"domain_scores_gemma":[0.9999223,0.000015932459,0.000010859347,0.000003371144,0.000019682086,0.000027879018],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014715648,0.0002506846,0.00023754669,0.00018563877,0.0008262812,0.00067499315,0.00028950404,0.0004098846,0.0025397795],"category_scores_gemma":[0.00029690558,0.00021983996,0.00012805568,0.00020564397,0.00017254459,0.0002645754,0.00028597863,0.00042547617,0.0007661237],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005066697,0.00014798476,0.0037501804,0.0001388263,0.000025175947,0.00023571635,0.00028137394,0.0006726528,0.98712236,0.000653087,0.001422321,0.0050436747],"study_design_scores_gemma":[0.00010175478,0.00048633,0.10910827,0.00006194974,0.000065598346,0.0012132728,0.0015090384,0.041765064,0.8196746,0.0009981937,0.024918957,0.00009703733],"about_ca_topic_score_codex":0.020226968,"about_ca_topic_score_gemma":0.018886581,"teacher_disagreement_score":0.020226968,"about_ca_system_score_codex":0.0010588196,"about_ca_system_score_gemma":0.00032148833,"threshold_uncertainty_score":0.040218472},"labels":[],"label_agreement":null},{"id":"W7025320981","doi":"","title":"An Ultrasound Investigation of Possible Covert Contrasts in First Language Acquisition: The Case of /sp ~ sw ~ sm/ > [f] Mergers","year":2010,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Covert; Ultrasound; Language understanding; Perspective (graphical)","score_opus":0.00856648009175951,"score_gpt":0.22449331340096626,"score_spread":0.21592683330920676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7025320981","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.958332,0.0012834591,0.0052231383,0.0074768397,0.00018036469,0.00015354123,0.0002676201,0.0001498162,0.0269333],"genre_scores_gemma":[0.99170333,0.0006759471,0.0034336417,0.0009923432,0.0003729732,0.000035503806,0.000051693853,0.0000636849,0.0026708695],"study_design_codex":"case_report","study_design_gemma":"observational","domain_scores_codex":[0.9995578,0.00007608716,0.000042399883,0.00007730666,0.00010073107,0.00014573272],"domain_scores_gemma":[0.99704117,0.0019043784,0.00035769312,0.0002306911,0.00017473649,0.00029142157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053193944,0.00068408105,0.0005750473,0.0024709678,0.0014963014,0.0010126869,0.001560014,0.0054870127,0.005403583],"category_scores_gemma":[0.008187902,0.00068014005,0.0005227916,0.000862503,0.003744595,0.0014719751,0.0013538857,0.003002451,0.0008529685],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000970375,0.00007583792,0.0039674104,0.000039310547,0.0000043250907,0.9844661,0.001101352,0.00010934207,0.0052103307,0.0013596023,0.00029571954,0.0032737153],"study_design_scores_gemma":[0.000022644526,0.00022926067,0.010611086,0.000045123183,0.000019413088,0.977777,0.0013230303,0.0010948488,0.005878722,0.0011331845,0.001837977,0.000027747674],"about_ca_topic_score_codex":0.0067428113,"about_ca_topic_score_gemma":0.0050394144,"teacher_disagreement_score":0.0067428113,"about_ca_system_score_codex":0.000867499,"about_ca_system_score_gemma":0.0010798965,"threshold_uncertainty_score":0.018076777},"labels":[],"label_agreement":null},{"id":"W7025401875","doi":"","title":"Where are the voices coming from? Canadian culture and the legacies of history","year":2004,"lang":"en","type":"book","venue":"CentAUR (University of Reading)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Narrative; Agency (philosophy); Colonialism","score_opus":0.011807440498167204,"score_gpt":0.16576960607504762,"score_spread":0.15396216557688042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7025401875","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019233735,0.058747143,0.00072653254,0.08289088,0.0029853056,0.000033442844,0.0005615986,0.00013184585,0.83468944],"genre_scores_gemma":[0.54213506,0.044071436,0.001488926,0.009113887,0.0008343277,0.000031843338,0.000308932,0.00028820714,0.40172735],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981166,0.00018963152,0.00002358314,0.00012762196,0.0006111581,0.0009315192],"domain_scores_gemma":[0.99848026,0.0002440366,0.00005955156,0.000050880975,0.0007065077,0.00045882186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011990995,0.0009148656,0.0005255926,0.003056173,0.03234926,0.018590547,0.0011735299,0.0022150015,0.021936353],"category_scores_gemma":[0.0032478494,0.00043833922,0.00032526307,0.006614995,0.020579172,0.004204683,0.0021184979,0.004069589,0.0015859341],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007083333,0.000012428453,0.0017981522,0.0002213777,0.000018861265,0.00039631262,0.082552664,0.00021327728,0.00031613422,0.6206718,0.21105866,0.08266951],"study_design_scores_gemma":[0.0000062670556,0.0000064731253,0.003378493,0.0003071893,0.000016029288,0.00012537853,0.044452503,0.000058796588,0.0001514812,0.02022649,0.9312218,0.000049161958],"about_ca_topic_score_codex":0.9928893,"about_ca_topic_score_gemma":0.9975682,"teacher_disagreement_score":0.13464746,"about_ca_system_score_codex":0.13464746,"about_ca_system_score_gemma":0.13700062,"threshold_uncertainty_score":0.9769403},"labels":[],"label_agreement":null},{"id":"W7027868473","doi":"","title":"Deep neural networks for voice control","year":2023,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"","score_opus":0.0219650226790906,"score_gpt":0.25048067043630934,"score_spread":0.22851564775721875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7027868473","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049634025,0.025227878,0.87103534,0.0036547063,0.0024920127,0.00007958809,0.0008257566,0.0037694303,0.043281168],"genre_scores_gemma":[0.69121337,0.0103991255,0.13700867,0.000599839,0.0008566769,0.00011866504,0.0021307878,0.00044692736,0.15722601],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9999151,0.000009239754,0.000003658447,0.000029841682,0.000024651448,0.000017441029],"domain_scores_gemma":[0.99991786,0.000024196162,0.000004752726,0.000009321782,0.000037031197,0.0000067180067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019169578,0.00045562242,0.0002937924,0.00020201209,0.00022270749,0.00059404067,0.00028166565,0.00040619733,0.006163005],"category_scores_gemma":[0.00051222614,0.000164494,0.00021873286,0.00020238147,0.00022724218,0.00055404066,0.00054653845,0.0010217115,0.0017108464],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022041806,0.00008129479,0.0005311794,0.00019873006,0.000066071654,0.00004476455,0.000077409306,0.098148376,0.025801156,0.025940068,0.028100805,0.8207897],"study_design_scores_gemma":[0.000035033856,0.00009647122,0.0020907985,0.00007846422,0.00006579092,0.000045459008,0.00004599232,0.8545086,0.030829253,0.03950132,0.07266658,0.000036290814],"about_ca_topic_score_codex":0.0046960027,"about_ca_topic_score_gemma":0.0053970544,"teacher_disagreement_score":0.006163005,"about_ca_system_score_codex":0.0003427993,"about_ca_system_score_gemma":0.0003559956,"threshold_uncertainty_score":0.020617306},"labels":[],"label_agreement":null},{"id":"W7028486788","doi":"","title":"Fine-tuning an Automatic Speech Recognition model for a Canadian Indigenous counselling program","year":2025,"lang":"en","type":"dissertation","venue":"Mspace (University of Manitoba)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Acoustic model; Adaptability; Outlier; Speech corpus; Software; Speech technology; Hidden Markov model; Language model","score_opus":0.037547961906066595,"score_gpt":0.24052708833876238,"score_spread":0.20297912643269578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7028486788","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62008095,0.0008649302,0.33538184,0.0019078653,0.0004881676,0.0007381786,0.003224101,0.017913107,0.019400885],"genre_scores_gemma":[0.87757665,0.00031413857,0.09099303,0.00048005005,0.00004203043,0.00036010877,0.0033070943,0.0004272549,0.026499625],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995691,0.000061817846,0.00001533491,0.0001585363,0.00011386622,0.000081246704],"domain_scores_gemma":[0.9995246,0.00013336953,0.000015104845,0.00002348934,0.00026342904,0.00003994532],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008803411,0.0008031506,0.00040764426,0.00040758596,0.0007994343,0.0008615773,0.0010947848,0.00079890573,0.0036876146],"category_scores_gemma":[0.0015158614,0.00033767184,0.00060718175,0.00025952148,0.0002951574,0.0004410677,0.00060143595,0.0013289073,0.0021242504],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008057588,0.00042250459,0.016433153,0.00033232768,0.0002295288,0.0004997796,0.0010634535,0.46614653,0.054942023,0.0025895927,0.023375629,0.43315974],"study_design_scores_gemma":[0.000022890406,0.00012423543,0.0051734713,0.000026060268,0.00007720615,0.00006756207,0.00023340466,0.9752637,0.01229283,0.00037603095,0.0062993304,0.000043230033],"about_ca_topic_score_codex":0.3426803,"about_ca_topic_score_gemma":0.35476902,"teacher_disagreement_score":0.65731966,"about_ca_system_score_codex":0.0032385187,"about_ca_system_score_gemma":0.004626368,"threshold_uncertainty_score":0.68137133},"labels":[],"label_agreement":null},{"id":"W7028694018","doi":"","title":"Gastroenteric, Zoonotic and Vectorborne Diseases in Ireland: Quarterly report: Quarter 1, 2024","year":2024,"lang":"en","type":"report","venue":"Lenus, The Irish Health Repository (Dr Steevens Hospital Library)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Hand washing; Shower; Sanitation; Clean water; Contaminated food; Food preparation; Washing hands; Laundry","score_opus":0.01341536060511671,"score_gpt":0.25482735189314404,"score_spread":0.24141199128802732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7028694018","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017619304,0.0070132227,0.0005552316,0.006433553,0.0072772442,0.00076437864,0.89081454,0.0012267601,0.06829574],"genre_scores_gemma":[0.048474636,0.01147428,0.0018120835,0.0042278613,0.0013173656,0.0019661493,0.75181776,0.00049207086,0.17841783],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99870336,0.000092229304,0.00019505122,0.00010801264,0.0004251065,0.00047624204],"domain_scores_gemma":[0.99757177,0.000060542945,0.00036311705,0.000047695048,0.001350586,0.00060640456],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011744217,0.0013655527,0.00077370997,0.002121934,0.00047408044,0.0013356165,0.0011265294,0.0010945345,0.046783667],"category_scores_gemma":[0.0029175095,0.00071979704,0.0012953898,0.0033738953,0.00025978984,0.0013687166,0.002162184,0.0012445351,0.037409306],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020398236,0.0000619281,0.013846793,0.0010409243,0.000023287463,0.000046354056,0.000031197218,0.00016751184,0.0001739905,0.00006481319,0.9642672,0.020071983],"study_design_scores_gemma":[0.0002907753,0.00034279123,0.5004639,0.0018407314,0.000065735934,0.0002595618,0.00076298334,0.0005676809,0.00036574702,0.00012450492,0.49485835,0.000057228066],"about_ca_topic_score_codex":0.19939524,"about_ca_topic_score_gemma":0.19032678,"teacher_disagreement_score":0.19939524,"about_ca_system_score_codex":0.0031313822,"about_ca_system_score_gemma":0.009990416,"threshold_uncertainty_score":0.39646924},"labels":[],"label_agreement":null},{"id":"W7030535816","doi":"","title":"Newsletters - Potters Guild of British Columbia 2006 July 1","year":2006,"lang":"en","type":"other","venue":"Arca (British Columbia Electronic Library Network)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Guild; Assemblage (archaeology); Government (linguistics); Period (music)","score_opus":0.00371546682897417,"score_gpt":0.1612861864951602,"score_spread":0.15757071966618602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7030535816","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00089545903,0.002807888,0.00019991904,0.017389465,0.011116511,0.0001181887,0.004496116,0.00094617845,0.9620302],"genre_scores_gemma":[0.00058869005,0.0003715517,0.00004167683,0.00062802044,0.00018988636,0.0000089808045,0.00065111823,0.000061827945,0.9974583],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994529,0.000030080186,0.000014958122,0.00005655973,0.0003198529,0.00012557603],"domain_scores_gemma":[0.9983455,0.00009221586,0.000042405605,0.00006667814,0.00091788266,0.0005353074],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00051888527,0.0008149186,0.00052901264,0.0010810817,0.0041287416,0.0045455806,0.0006829724,0.002449713,0.56995565],"category_scores_gemma":[0.0016372685,0.00038149243,0.00031206998,0.0011878912,0.00041109635,0.0010282854,0.0012773065,0.0026342762,0.33621356],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000079545225,0.0000053497056,0.000036844285,0.00000927259,3.3711822e-7,0.000015324118,0.000006645498,0.0000040679174,0.0000266685,0.000135147,0.99378514,0.005967235],"study_design_scores_gemma":[0.0000024809558,0.0000044479793,0.000463816,0.000024828933,7.450985e-7,0.000013830786,0.00005498394,0.000013132619,0.0000351761,0.0000402433,0.9993436,0.0000027554179],"about_ca_topic_score_codex":0.14229114,"about_ca_topic_score_gemma":0.4932036,"teacher_disagreement_score":0.8577089,"about_ca_system_score_codex":0.0031783204,"about_ca_system_score_gemma":0.0051856916,"threshold_uncertainty_score":0.61340606},"labels":[],"label_agreement":null},{"id":"W7033575953","doi":"","title":"Renowned Alberta Marketer & Creative Genius @Eric Cheng from 12 Creative chops it up with us on The Business Growth School","year":2019,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Genius; Social media; Value (mathematics); Creativity; Business opportunity; Key (lock)","score_opus":0.010590378243418415,"score_gpt":0.18064254734760848,"score_spread":0.17005216910419008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7033575953","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00064656924,0.0006205605,0.0005867432,0.005775455,0.0019208071,0.00006794413,0.001104748,0.0017474126,0.9875299],"genre_scores_gemma":[0.00050561235,0.00006613675,0.000073916446,0.000187137,0.00003951813,0.0000045683255,0.00010813422,0.00020823786,0.99880683],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99832207,0.00007267013,0.000021602416,0.00027733835,0.0010103937,0.000295892],"domain_scores_gemma":[0.9943962,0.00027057048,0.00009840245,0.00029387802,0.0023082958,0.002632559],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012184074,0.0014772515,0.0008447668,0.001779228,0.0049621225,0.0072134957,0.0012748168,0.003118819,0.8240432],"category_scores_gemma":[0.002782417,0.0008521703,0.0005077958,0.0016194484,0.0015715401,0.0039463476,0.003975618,0.0027566117,0.69348806],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015372945,0.000025959185,0.00013932283,0.000016470445,7.72683e-7,0.00004578869,0.00005084656,0.000019173202,0.00021952091,0.0012642294,0.970889,0.027313625],"study_design_scores_gemma":[0.0000044307535,0.000009153414,0.0003776212,0.000016461476,0.0000013244794,0.000033121592,0.00013494014,0.00004452065,0.0001339148,0.00022677843,0.9990102,0.0000074932104],"about_ca_topic_score_codex":0.08803769,"about_ca_topic_score_gemma":0.27700323,"teacher_disagreement_score":0.91196233,"about_ca_system_score_codex":0.0047535663,"about_ca_system_score_gemma":0.0074075353,"threshold_uncertainty_score":0.25098103},"labels":[],"label_agreement":null},{"id":"W7034498190","doi":"","title":"Toward detecting and classification non-verbal events and biosignals in hearables","year":2022,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Pattern recognition (psychology); Artificial neural network; Noise (video); Signal processing; Feature extraction","score_opus":0.03950968081213772,"score_gpt":0.23418033928138896,"score_spread":0.19467065846925125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7034498190","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23403826,0.0011714473,0.7479086,0.0004342417,0.00018700949,0.00030090378,0.0012882155,0.0035324923,0.011138788],"genre_scores_gemma":[0.4933248,0.0010558777,0.4825298,0.000265042,0.0001320898,0.00017907609,0.0029970494,0.00042074802,0.019095572],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992499,0.00009177679,0.000038344904,0.00027274244,0.00019740139,0.00014988503],"domain_scores_gemma":[0.99811685,0.0005619943,0.000120770055,0.0001526161,0.0009153509,0.00013238544],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000950423,0.00096718274,0.0006871452,0.0023469399,0.00096864335,0.0030449473,0.0012102915,0.001297505,0.0028307254],"category_scores_gemma":[0.0021622335,0.00039682098,0.0006207861,0.0009875181,0.0007252303,0.0012253982,0.001106096,0.0013702583,0.0045812493],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046851387,0.00022474966,0.013631444,0.00017147629,0.00005801723,0.00019187939,0.0004188318,0.0037612326,0.39179626,0.003265051,0.0033315956,0.58268094],"study_design_scores_gemma":[0.00009629395,0.000559573,0.09400605,0.00014742988,0.00033076576,0.0009092828,0.003176092,0.5134787,0.35040313,0.0089554535,0.02779933,0.00013791578],"about_ca_topic_score_codex":0.030106254,"about_ca_topic_score_gemma":0.04260724,"teacher_disagreement_score":0.030106254,"about_ca_system_score_codex":0.00059129624,"about_ca_system_score_gemma":0.0018538126,"threshold_uncertainty_score":0.059862018},"labels":[],"label_agreement":null},{"id":"W7037599012","doi":"","title":"Environmental Impacts of Tunnels in fractured crystalline rocks of the Central Alps","year":2007,"lang":"en","type":"book-chapter","venue":"Research Portal (Queen's University Belfast)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Liquation; Dysgeusia; Diafiltration; Emperipolesis; Triacetin; Durvalumab","score_opus":0.027095911277219904,"score_gpt":0.2566447456166851,"score_spread":0.22954883433946519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7037599012","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9929969,0.0004683071,0.00007953115,0.00016849514,0.000008239139,0.0000060843786,0.00048369856,0.0000113486485,0.005777361],"genre_scores_gemma":[0.9981749,0.00038324425,0.0000976161,0.00000873284,0.000003757112,0.0000034045026,0.00014155528,0.000004942207,0.0011818445],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9997143,0.0000492917,0.000012910042,0.000023887384,0.0000918749,0.000107746484],"domain_scores_gemma":[0.99982846,0.000040638522,0.000043742122,0.000009718493,0.0000378174,0.000039577],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017474084,0.00014679393,0.00027035078,0.00072419125,0.0012331982,0.0012860678,0.00038477613,0.0005429897,0.003534848],"category_scores_gemma":[0.00046696933,0.00016735613,0.0002722449,0.0017391938,0.0010164256,0.00039023,0.0011800735,0.00029905527,0.00021875477],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002733942,0.00045237626,0.7270162,0.0011666942,0.00041231693,0.0127697075,0.016103314,0.059976544,0.027376557,0.010377858,0.0074002338,0.13421421],"study_design_scores_gemma":[0.000030394356,0.00018846395,0.96921396,0.0001652236,0.000041080053,0.00077103224,0.014089227,0.0037556172,0.0006220672,0.0014809001,0.009614614,0.00002744833],"about_ca_topic_score_codex":0.10209737,"about_ca_topic_score_gemma":0.28977215,"teacher_disagreement_score":0.10209737,"about_ca_system_score_codex":0.0015391419,"about_ca_system_score_gemma":0.0010010159,"threshold_uncertainty_score":0.20300621},"labels":[],"label_agreement":null},{"id":"W7043108712","doi":"","title":"A Spectral-Temporal Suppression Hodel for Speech Recognition","year":2022,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Voice activity detection; Speech processing; Speaker recognition; Speech enhancement; Signal processing; Noise (video)","score_opus":0.0376745272477753,"score_gpt":0.24264028282403846,"score_spread":0.20496575557626318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7043108712","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016524404,0.0004992801,0.97361606,0.00008427052,0.00016196047,0.00012301438,0.00020827954,0.00509207,0.0036904882],"genre_scores_gemma":[0.16304293,0.000582576,0.8126288,0.0003765027,0.0002026961,0.00024046071,0.0010825277,0.0004275346,0.021415887],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995295,0.00009082081,0.00002601075,0.0000973271,0.00020023184,0.000056284036],"domain_scores_gemma":[0.99952424,0.00013092205,0.0000166513,0.0000703779,0.00020128457,0.000056529956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007581208,0.00059886795,0.0005973032,0.0010277476,0.00069732533,0.0009161195,0.00088984595,0.00072735175,0.0130106285],"category_scores_gemma":[0.0007467427,0.00029000486,0.0005612923,0.0005186101,0.00033897944,0.0007486441,0.0008294315,0.0005769974,0.0062650614],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010434014,0.00021955594,0.000581628,0.00013075727,0.00007417366,0.00017347024,0.00006231965,0.0034962306,0.36781582,0.0040199,0.0038825895,0.6185002],"study_design_scores_gemma":[0.00015945989,0.0010097248,0.0022687577,0.000041303923,0.00015138781,0.0009656174,0.00015226453,0.4056434,0.54790205,0.0025756268,0.039052982,0.00007750375],"about_ca_topic_score_codex":0.0031578254,"about_ca_topic_score_gemma":0.0071700052,"teacher_disagreement_score":0.0130106285,"about_ca_system_score_codex":0.00033089038,"about_ca_system_score_gemma":0.00079141837,"threshold_uncertainty_score":0.04352486},"labels":[],"label_agreement":null},{"id":"W7067814757","doi":"","title":"Northland Power Inc. Announces Results for the First Quarter of 2011 (MRW)","year":2011,"lang":"en","type":"other","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Power (physics)","score_opus":0.025164371520317162,"score_gpt":0.22900613540276882,"score_spread":0.20384176388245165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067814757","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026348985,0.00080711395,0.004446707,0.012360273,0.0064986944,0.00026522498,0.011056477,0.0060909553,0.95583963],"genre_scores_gemma":[0.0024263521,0.0001517613,0.00051201327,0.00043577666,0.00018193059,0.00002149598,0.0024901803,0.00038866507,0.9933918],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.999076,0.000053476877,0.000016183623,0.00007395295,0.0006230356,0.00015735006],"domain_scores_gemma":[0.99806887,0.00014944955,0.00004154384,0.00014609937,0.0011611962,0.00043289468],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014233082,0.00083880546,0.00047308143,0.0010169161,0.001807345,0.0047275433,0.0008858716,0.0024511185,0.5079463],"category_scores_gemma":[0.0020330795,0.0004097309,0.000472446,0.00081659644,0.00048615347,0.0016822226,0.0011475994,0.0022303446,0.36989194],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000074610616,0.0000570449,0.00012715755,0.000029240684,0.0000024727335,0.000029768507,0.000013675064,0.0000560922,0.0006064013,0.0010827441,0.9736352,0.024285465],"study_design_scores_gemma":[0.000018325174,0.0000708481,0.0010133425,0.000016135737,0.0000051756792,0.00003758303,0.000066968336,0.00030431213,0.0012196847,0.0004872789,0.9967527,0.000007568021],"about_ca_topic_score_codex":0.013985704,"about_ca_topic_score_gemma":0.06574515,"teacher_disagreement_score":0.5079463,"about_ca_system_score_codex":0.0010168261,"about_ca_system_score_gemma":0.0018775166,"threshold_uncertainty_score":0.7018548},"labels":[],"label_agreement":null},{"id":"W7071542273","doi":"","title":"Text Input Using Speaker-Adaptive Connected Syllable Recognition","year":2022,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Syllable; Pattern recognition (psychology); Speech processing; Signal processing; Speaker recognition","score_opus":0.05008207425272345,"score_gpt":0.22521278818215595,"score_spread":0.1751307139294325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071542273","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.114000395,0.0010116193,0.77346134,0.00043843928,0.002626312,0.00055588974,0.0074391197,0.072342694,0.028124278],"genre_scores_gemma":[0.45797235,0.000749,0.46139365,0.00054720277,0.0005470812,0.0004763191,0.013531957,0.0039187963,0.06086366],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9997845,0.000025568213,0.000018129524,0.00006808418,0.00007404563,0.00002966771],"domain_scores_gemma":[0.99942076,0.00017089504,0.000018610417,0.000058317033,0.00028789422,0.000043597207],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018429311,0.001103927,0.00068788294,0.00060703134,0.00034854145,0.00071238796,0.00067914935,0.00095687533,0.036707755],"category_scores_gemma":[0.0010810863,0.00024531147,0.0004097293,0.00053800095,0.00016088279,0.000504961,0.0006279339,0.00051244884,0.017433293],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013667824,0.00012665291,0.00045612248,0.00038054606,0.000047669546,0.0006824353,0.00007729861,0.0031462759,0.44456714,0.00081100664,0.018280508,0.53005767],"study_design_scores_gemma":[0.00015365788,0.0006780279,0.0053212526,0.00008827146,0.0001466485,0.0010470252,0.00022414516,0.3218289,0.6395795,0.0013298274,0.029489692,0.00011307084],"about_ca_topic_score_codex":0.001512849,"about_ca_topic_score_gemma":0.002553979,"teacher_disagreement_score":0.036707755,"about_ca_system_score_codex":0.0001718307,"about_ca_system_score_gemma":0.00027826088,"threshold_uncertainty_score":0.122799695},"labels":[],"label_agreement":null},{"id":"W7071593548","doi":"","title":"Some Considerations on The Definition of Sub-Word Units For a Template- Matching Speech Recognition System","year":2022,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Matching (statistics); Voice activity detection; Pattern recognition (psychology); Speech processing; Speaker recognition; Acoustic model","score_opus":0.0821286735079449,"score_gpt":0.2311703834526719,"score_spread":0.149041709944727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071593548","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0046408996,0.0024850483,0.9632245,0.0045430167,0.0009838948,0.0002048109,0.00021268446,0.00056898704,0.023136312],"genre_scores_gemma":[0.06494822,0.0012550942,0.9192824,0.0020781315,0.0010038365,0.0006642304,0.0003226921,0.00054451934,0.009900828],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99659675,0.0012232964,0.00079939456,0.00042115874,0.0007781123,0.00018120238],"domain_scores_gemma":[0.99361706,0.0030854216,0.00024137259,0.0009222302,0.0018581513,0.00027581523],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0058676857,0.0012550444,0.0019537348,0.0015248429,0.0024496547,0.008302117,0.004832145,0.00424934,0.0077548474],"category_scores_gemma":[0.013553222,0.0012423765,0.0015364095,0.0016122406,0.00557503,0.0072128978,0.0015299122,0.0058768606,0.005455822],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015922217,0.00006789624,0.00034658948,0.00026114634,0.00003446598,0.00041021485,0.00061528146,0.0050949515,0.010986433,0.9158127,0.0073489384,0.05886215],"study_design_scores_gemma":[0.000094716685,0.00034476147,0.0011579113,0.0005240751,0.00010083587,0.002303502,0.00072245573,0.11104099,0.017900098,0.7042938,0.1613071,0.00020980515],"about_ca_topic_score_codex":0.003524013,"about_ca_topic_score_gemma":0.004670032,"teacher_disagreement_score":0.008302117,"about_ca_system_score_codex":0.0012405224,"about_ca_system_score_gemma":0.0018259491,"threshold_uncertainty_score":0.031031668},"labels":[],"label_agreement":null},{"id":"W7083818636","doi":"10.17870/bathspa.30138790","title":"word-process-object_2","year":2025,"lang":"en","type":"dataset","venue":"Bath Spa University","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Thursday; Attendance; Ridiculous; Period (music)","score_opus":0.010233795827676707,"score_gpt":0.2245457471190524,"score_spread":0.2143119512913757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7083818636","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014499445,0.00023509549,0.00097623287,0.0001480547,0.00021490493,0.00012114127,0.986641,0.007000703,0.0032130084],"genre_scores_gemma":[0.0009724771,0.000051038125,0.0009429218,0.000056997716,0.000015205558,0.00016875389,0.99546874,0.0003643044,0.001959635],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99846953,0.00024776754,0.0001701826,0.0005550309,0.00029784974,0.00025968786],"domain_scores_gemma":[0.99865484,0.00026036173,0.000120887365,0.00047540438,0.00032433862,0.00016420966],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015009171,0.005619866,0.0014386538,0.0030952839,0.0015460263,0.0035898737,0.004060452,0.002880721,0.072312124],"category_scores_gemma":[0.003683535,0.0010533616,0.002730698,0.002730585,0.0008781287,0.0027316294,0.0030487697,0.0027575176,0.18748477],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030223606,0.00008922203,0.0013257184,0.0009326259,0.000060968156,0.000066560264,0.00006427268,0.0003220221,0.0007717099,0.0005383169,0.98695785,0.008568484],"study_design_scores_gemma":[0.0005375284,0.00012327929,0.00572745,0.00022343716,0.000060863695,0.00034048595,0.00026945243,0.0019728495,0.0036055911,0.0013132894,0.9857473,0.00007852228],"about_ca_topic_score_codex":0.014892024,"about_ca_topic_score_gemma":0.03182462,"teacher_disagreement_score":0.9276879,"about_ca_system_score_codex":0.0014034817,"about_ca_system_score_gemma":0.0020981838,"threshold_uncertainty_score":0.24190813},"labels":[],"label_agreement":null},{"id":"W7089305642","doi":"10.1017/psj.2025.10102","title":"Survey Insights: Perspectives on the Current Policy Climate","year":2025,"lang":"en","type":"article","venue":"Political Science Today","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kimberly-Clark (Canada)","funders":"","keywords":"Current (fluid); Government (linguistics); Climate change; Public policy","score_opus":0.04186002555645232,"score_gpt":0.340529924898125,"score_spread":0.2986698993416727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7089305642","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04168171,0.02681438,0.015074702,0.71653545,0.001616372,0.00006337112,0.006096684,0.000146618,0.19197069],"genre_scores_gemma":[0.89557064,0.042618696,0.0048485748,0.036856517,0.002972142,0.00025505907,0.002832755,0.00015031389,0.013895415],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9881471,0.007849957,0.0003362406,0.0006505042,0.0018747683,0.0011414853],"domain_scores_gemma":[0.96230024,0.027181912,0.0019117648,0.0013985843,0.006230099,0.000977497],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020608313,0.00068041263,0.0011185803,0.005433469,0.0018204794,0.012423298,0.0013791018,0.0034330655,0.024116766],"category_scores_gemma":[0.063332416,0.0003582759,0.0005790791,0.015124498,0.003611558,0.014798638,0.0028718628,0.0036330943,0.0019431722],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001891798,0.000049387556,0.012188977,0.0005033756,0.00006988148,0.00009064801,0.0033532458,0.0026436567,0.0001339075,0.8117133,0.09816764,0.070896775],"study_design_scores_gemma":[0.000034485598,0.000062642845,0.024359686,0.0025146755,0.000063792766,0.0001354587,0.02319255,0.0064422027,0.00032903312,0.6228015,0.31997037,0.000093521914],"about_ca_topic_score_codex":0.030104425,"about_ca_topic_score_gemma":0.030237392,"teacher_disagreement_score":0.030104425,"about_ca_system_score_codex":0.008387661,"about_ca_system_score_gemma":0.005479594,"threshold_uncertainty_score":0.10898852},"labels":[],"label_agreement":null},{"id":"W7095177847","doi":"","title":"Mixed-mode Multilinguality in TTS: The Case of Canadian French","year":2006,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Pronunciation; Intelligibility (philosophy); French; Context (archaeology); British English","score_opus":0.03380943487620321,"score_gpt":0.2670775767187989,"score_spread":0.2332681418425957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7095177847","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90524465,0.0011565771,0.008258018,0.0025819698,0.00006058681,0.00007230507,0.00054197677,0.00018144255,0.08190248],"genre_scores_gemma":[0.9888205,0.00036971457,0.0035783527,0.00009129555,0.000012061759,0.000011063699,0.00014320736,0.000040608433,0.0069332197],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99801,0.0005261036,0.00006735275,0.00019996671,0.00067191466,0.0005247016],"domain_scores_gemma":[0.99762934,0.00081026234,0.00012626412,0.00015333355,0.0011259983,0.00015483444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014041208,0.0005509856,0.0003430388,0.001112466,0.0074172784,0.0035706246,0.0008006037,0.001244985,0.0032449886],"category_scores_gemma":[0.0055999905,0.00024815887,0.00041619482,0.0019691808,0.0021122522,0.001143997,0.0011197291,0.0007899349,0.00038671796],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023127615,0.00023158107,0.15722704,0.0008511372,0.00030958102,0.05627254,0.15125062,0.043581925,0.044477068,0.21450846,0.022676688,0.3063006],"study_design_scores_gemma":[0.00016357943,0.0004940852,0.2186319,0.00048262518,0.0007539339,0.029114963,0.24747156,0.08421778,0.036347207,0.026033305,0.35530517,0.0009839883],"about_ca_topic_score_codex":0.95713186,"about_ca_topic_score_gemma":0.96345544,"teacher_disagreement_score":0.042868137,"about_ca_system_score_codex":0.014171099,"about_ca_system_score_gemma":0.010156116,"threshold_uncertainty_score":0.102819026},"labels":[],"label_agreement":null},{"id":"W7095779796","doi":"","title":"Mixedmode multilinguality in TTS: The case of Canadian French","year":2006,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Pronunciation; Intelligibility (philosophy); French; Context (archaeology); British English","score_opus":0.026460925611151837,"score_gpt":0.25120654448978397,"score_spread":0.22474561887863212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7095779796","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89316887,0.0011658212,0.0075730784,0.0036719842,0.00006213774,0.00007088162,0.00040402132,0.00016454165,0.09371851],"genre_scores_gemma":[0.9876165,0.00033934083,0.0029740098,0.00012137396,0.000013581932,0.0000112313755,0.0001151916,0.000050594263,0.00875827],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9975253,0.0006011086,0.000073391304,0.00025121486,0.00087154674,0.0006774927],"domain_scores_gemma":[0.99679536,0.0011297524,0.0001779676,0.000210183,0.0014538431,0.0002328034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016671988,0.00053338235,0.00034666798,0.0012974117,0.008272235,0.0041830163,0.00077178876,0.0013590972,0.003697312],"category_scores_gemma":[0.0068266573,0.00026101506,0.00042302112,0.0021140086,0.00289945,0.0013900105,0.0013535983,0.00092771236,0.00041153198],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013706569,0.0001781403,0.12630564,0.0006649799,0.00023344104,0.051251035,0.25451884,0.024980783,0.03132647,0.2153789,0.019882811,0.27390838],"study_design_scores_gemma":[0.000092825096,0.00027713063,0.15782109,0.00037678442,0.0003720302,0.02363591,0.33075687,0.039973006,0.020174917,0.021425067,0.40447658,0.0006177894],"about_ca_topic_score_codex":0.9500088,"about_ca_topic_score_gemma":0.9595993,"teacher_disagreement_score":0.04999119,"about_ca_system_score_codex":0.017393569,"about_ca_system_score_gemma":0.012355129,"threshold_uncertainty_score":0.12619972},"labels":[],"label_agreement":null},{"id":"W7099266526","doi":"","title":"Located in the Oil Sands Region","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Oil sands; Land reclamation; Public opinion; Environmental policy; Public policy; Work (physics); Energy policy; Petroleum industry","score_opus":0.026060234295216356,"score_gpt":0.22614019660103996,"score_spread":0.2000799623058236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7099266526","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5428435,0.0028077136,0.002703651,0.0032686065,0.0004347913,0.0002718336,0.007227473,0.0006528696,0.43978953],"genre_scores_gemma":[0.61228174,0.0013113531,0.0036398936,0.00036113922,0.00005546447,0.000075643184,0.004295706,0.00006204563,0.377917],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99982184,0.000011686885,0.000004728066,0.000028171373,0.000061358835,0.00007216171],"domain_scores_gemma":[0.99979156,0.000024687593,0.000025714846,0.000015645379,0.00007099305,0.000071362585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011343549,0.0002665391,0.00018153818,0.00074217684,0.0027597987,0.0009961402,0.0003803143,0.00041744672,0.027271671],"category_scores_gemma":[0.0004443577,0.00016256132,0.00011237728,0.0012748191,0.0005605699,0.0003436707,0.0010112167,0.0003685668,0.0052727535],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002059151,0.00036766648,0.18505064,0.0011017196,0.00011041541,0.016217837,0.013055798,0.0018602825,0.027280651,0.03809098,0.16925874,0.5455461],"study_design_scores_gemma":[0.000055043805,0.0001321929,0.19269854,0.00021440971,0.000028615072,0.00312158,0.025431216,0.001059387,0.003855194,0.0021843973,0.7711672,0.00005216863],"about_ca_topic_score_codex":0.28356057,"about_ca_topic_score_gemma":0.6280878,"teacher_disagreement_score":0.7164394,"about_ca_system_score_codex":0.002507565,"about_ca_system_score_gemma":0.0076124156,"threshold_uncertainty_score":0.5638201},"labels":[],"label_agreement":null},{"id":"W7110691195","doi":"","title":"Comparing language-specific and cross-language acoustic models for low-resource phonetic forced alignment","year":2025,"lang":"en","type":"article","venue":"ScholarSpace (University of Hawaii at Manoa)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Phone; Acoustic model; Homogeneous; Hidden Markov model; Stress (linguistics)","score_opus":0.0166982691697692,"score_gpt":0.2336168389856255,"score_spread":0.21691856981585628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7110691195","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29110658,0.0014579609,0.67798835,0.0006939137,0.0007127142,0.00034722147,0.0028083855,0.01619797,0.008686819],"genre_scores_gemma":[0.7721244,0.0005561315,0.20676295,0.00039416263,0.00009288095,0.00047840484,0.0098055545,0.002285005,0.0075005265],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99827015,0.0006040991,0.00011394438,0.00065438834,0.0002197297,0.00013779553],"domain_scores_gemma":[0.99664307,0.0018613491,0.0001354146,0.00054309843,0.0006980169,0.0001190466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003672811,0.0017323286,0.0009313085,0.0007442006,0.00060608983,0.0016298261,0.0014340312,0.0009933633,0.00473376],"category_scores_gemma":[0.0075179744,0.00064658,0.0014988905,0.0007318771,0.00046702698,0.0024605924,0.0013425978,0.0020104512,0.0044305753],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001701895,0.0004542853,0.018759964,0.0005421167,0.0013778607,0.00030694017,0.0010078904,0.34189835,0.05836635,0.0028785248,0.010051927,0.56265396],"study_design_scores_gemma":[0.000081626815,0.00036112152,0.010486839,0.000058987454,0.0002362556,0.00022144579,0.00047875036,0.9560979,0.023350192,0.0023141704,0.006178706,0.00013410172],"about_ca_topic_score_codex":0.016474463,"about_ca_topic_score_gemma":0.033043038,"teacher_disagreement_score":0.016474463,"about_ca_system_score_codex":0.0008383073,"about_ca_system_score_gemma":0.0014139324,"threshold_uncertainty_score":0.032757103},"labels":[],"label_agreement":null},{"id":"W7116439662","doi":"10.18280/ijsse.150907","title":"Hybrid CNN-BiLSTM for Deepfake Voice Detection: A Comparative Study","year":2025,"lang":"","type":"article","venue":"International Journal of Safety and Security Engineering","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Poison control; Human factors and ergonomics; Vulnerability (computing); Occupational safety and health","score_opus":0.016897535934624185,"score_gpt":0.2777137796706393,"score_spread":0.26081624373601514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7116439662","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8137753,0.015748702,0.14031957,0.0005390413,0.0009929007,0.00019823536,0.0020960763,0.0050569135,0.021273185],"genre_scores_gemma":[0.94900733,0.0019815606,0.036848348,0.00016723013,0.00008831289,0.000056674504,0.0025633778,0.00019869376,0.009088487],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994036,0.00009487245,0.00003010094,0.00014152002,0.00019342058,0.0001365452],"domain_scores_gemma":[0.9991755,0.00029919954,0.000024847472,0.000076823424,0.00037449016,0.00004905613],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012202378,0.001126288,0.0008785617,0.00085180666,0.00033917194,0.0010098562,0.0010919372,0.0013159967,0.0041619493],"category_scores_gemma":[0.0026584677,0.00027684332,0.00050765765,0.00048428326,0.0001939047,0.0018325121,0.0007266049,0.0006669266,0.0016787795],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003582267,0.0007041494,0.009751141,0.0009350762,0.00076394185,0.00039324485,0.00014480423,0.035694234,0.053798087,0.0011002934,0.0067531234,0.8863796],"study_design_scores_gemma":[0.00014467158,0.0021207263,0.02435087,0.0001946184,0.0009231345,0.0009488694,0.00040156324,0.8927072,0.06614613,0.001598327,0.010348829,0.00011504487],"about_ca_topic_score_codex":0.012147432,"about_ca_topic_score_gemma":0.021684816,"teacher_disagreement_score":0.012147432,"about_ca_system_score_codex":0.0005429113,"about_ca_system_score_gemma":0.0007869314,"threshold_uncertainty_score":0.024153471},"labels":[],"label_agreement":null},{"id":"W7117561788","doi":"10.1109/jiot.2025.3649544","title":"Branch-MFA-TDNN: A Parallel Branch Speaker Verification Model for Voice IoT","year":2025,"lang":"","type":"article","venue":"IEEE Internet of Things Journal","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Carleton University","funders":"China University of Mining and Technology; National Natural Science Foundation of China","keywords":"Focus (optics); Construct (python library); Noise (video); Authentication (law); Identity (music); Voice activity detection; Baseline (sea); Internet of Things","score_opus":0.03953475174061769,"score_gpt":0.29180733490534266,"score_spread":0.25227258316472495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117561788","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07147803,0.0023748232,0.916749,0.0005631033,0.000358896,0.00014034558,0.0006189607,0.0032779216,0.004438863],"genre_scores_gemma":[0.8256861,0.00078769284,0.16055585,0.0004214503,0.00017018896,0.00023181592,0.0012802996,0.00018709613,0.010679614],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997359,0.00005132377,0.0000122509855,0.00010322264,0.00005289936,0.000044351327],"domain_scores_gemma":[0.9996493,0.0001247455,0.000021702466,0.00003589766,0.0001462505,0.000022149385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068642653,0.0007345431,0.00065659493,0.0004217805,0.0003229272,0.00048789894,0.0013787984,0.00096825126,0.0025965823],"category_scores_gemma":[0.0013350194,0.0003150345,0.0009065623,0.000322066,0.00023722734,0.0006873499,0.00071045506,0.0014771988,0.0015785723],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006054898,0.00017833628,0.003522658,0.00010249179,0.00019471571,0.00017869653,0.00014620519,0.32458618,0.025619688,0.0029507163,0.006119609,0.63579524],"study_design_scores_gemma":[0.0000037204725,0.000028935952,0.00039036485,0.0000043639993,0.000013115936,0.000023133536,0.0000048307465,0.99735,0.0011004484,0.00058187556,0.00049343985,0.000005739105],"about_ca_topic_score_codex":0.013516176,"about_ca_topic_score_gemma":0.015745223,"teacher_disagreement_score":0.013516176,"about_ca_system_score_codex":0.0006226096,"about_ca_system_score_gemma":0.000805867,"threshold_uncertainty_score":0.02687502},"labels":[],"label_agreement":null},{"id":"W7117562559","doi":"10.18280/ts.420611","title":"Multi-Model Telugu Speech Recognition: Improving ASR with Dialect Classification and Optimization Techniques","year":2025,"lang":"","type":"article","venue":"Traitement du signal","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Telugu; Speech processing; Speech synthesis; Hidden Markov model","score_opus":0.04243502867289677,"score_gpt":0.26085636779599214,"score_spread":0.21842133912309536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117562559","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035002146,0.00089281093,0.9577885,0.00023190916,0.00013872117,0.00005150208,0.00026108985,0.0033888787,0.0022443102],"genre_scores_gemma":[0.34508377,0.0006883191,0.63733447,0.0003589258,0.00019558345,0.00016350322,0.0017233385,0.001317785,0.0131342765],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99917716,0.00027101426,0.000054481618,0.0002474204,0.00017377347,0.00007614085],"domain_scores_gemma":[0.99930143,0.00024319603,0.000053322245,0.00009694505,0.0002758783,0.000029110459],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010399221,0.0015432871,0.0015998998,0.0008807837,0.00039812806,0.0009127277,0.00080273167,0.0008522438,0.0034268494],"category_scores_gemma":[0.0015988644,0.00045638005,0.0011999301,0.0006550636,0.00024270329,0.0012819519,0.00064740476,0.0012389306,0.004027519],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006217118,0.00026806793,0.0012033661,0.00010916007,0.00014127453,0.00006603187,0.000071876246,0.061340567,0.10838645,0.0014086805,0.0041881204,0.8221947],"study_design_scores_gemma":[0.000019023399,0.00008429302,0.0014598417,0.000007713567,0.00007607015,0.00009120639,0.000030369865,0.9705373,0.024764752,0.0006442008,0.0022619313,0.000023332019],"about_ca_topic_score_codex":0.0045724493,"about_ca_topic_score_gemma":0.008834957,"teacher_disagreement_score":0.0045724493,"about_ca_system_score_codex":0.00034635415,"about_ca_system_score_gemma":0.0005559495,"threshold_uncertainty_score":0.01146394},"labels":[],"label_agreement":null},{"id":"W7125949704","doi":"10.1109/smc58881.2025.11343334","title":"Phonetic Analysis of Real and Synthetic Speech Using HuBERT Embeddings: Perspectives for Deepfake Detection","year":2025,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Cégep de l'Outaouais","funders":"","keywords":"Speech synthesis; Synthetic data; Sophistication; Speech processing; Rank (graph theory); Divergence (linguistics); Noise (video)","score_opus":0.01738696341447149,"score_gpt":0.2900737172972532,"score_spread":0.2726867538827817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125949704","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40118048,0.0021717362,0.58672744,0.0008889935,0.00023467829,0.00008897225,0.0014580652,0.003099967,0.0041497713],"genre_scores_gemma":[0.8805142,0.0005505754,0.11080927,0.00013696804,0.0000885914,0.000065353175,0.003019928,0.00024267087,0.004572366],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996184,0.000100166806,0.0000236895,0.00011804109,0.00007638245,0.00006324301],"domain_scores_gemma":[0.99906236,0.0004058588,0.000094736,0.00016184676,0.00020900648,0.00006625122],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006812951,0.00093269773,0.00054883433,0.0010728535,0.00024334884,0.0010247339,0.0005009114,0.0007987147,0.0013175035],"category_scores_gemma":[0.0023929463,0.00023377936,0.00042993348,0.00061536895,0.000540686,0.0012977547,0.00074455276,0.0010968361,0.0011264725],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007524719,0.00037487998,0.013061176,0.0002975566,0.00015124009,0.00050264306,0.0004977616,0.23286517,0.10771521,0.010118966,0.0050386474,0.62862426],"study_design_scores_gemma":[0.000009715015,0.00011778684,0.0054976516,0.000027341048,0.000020579595,0.00012982912,0.00019175206,0.961518,0.023840489,0.006003538,0.0026099589,0.000033385575],"about_ca_topic_score_codex":0.002814301,"about_ca_topic_score_gemma":0.004120388,"teacher_disagreement_score":0.002814301,"about_ca_system_score_codex":0.00041932418,"about_ca_system_score_gemma":0.00049805164,"threshold_uncertainty_score":0.0055958033},"labels":[],"label_agreement":null},{"id":"W7127860883","doi":"","title":"Robustness of neural models for automatic speech processing","year":2025,"lang":"en","type":"article","venue":"theses.fr (ABES)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Robustness (evolution); Speech processing; Error analysis","score_opus":0.04123261635679393,"score_gpt":0.2872287094734819,"score_spread":0.24599609311668796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7127860883","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28917032,0.004990035,0.6865351,0.00196698,0.0005148728,0.00014667674,0.00077375927,0.0036909448,0.012211318],"genre_scores_gemma":[0.9710641,0.0007938483,0.022572929,0.00015571341,0.00010659631,0.00009789396,0.00066147366,0.0002137809,0.004333727],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984218,0.0005371476,0.00010443271,0.00044555953,0.00031611192,0.00017503437],"domain_scores_gemma":[0.9948047,0.003749349,0.00024600665,0.000554411,0.0005425784,0.00010302999],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003556784,0.0015105997,0.00096627726,0.00082022906,0.00064211944,0.0020372325,0.001459025,0.0015652261,0.00349032],"category_scores_gemma":[0.014651451,0.00074669434,0.0011569782,0.000489047,0.0009382165,0.0019206665,0.0016814509,0.0023840782,0.001298384],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033360696,0.000045820878,0.0018570567,0.0001124156,0.00016573722,0.000060052666,0.00008800189,0.92725605,0.0052235257,0.002770719,0.0007287981,0.061358184],"study_design_scores_gemma":[0.000004768039,0.000037189937,0.0006424827,0.000012692795,0.0000129845175,0.000015129248,0.000013638253,0.99533135,0.0014603441,0.002147693,0.0003106377,0.000011068361],"about_ca_topic_score_codex":0.014322315,"about_ca_topic_score_gemma":0.0098927235,"teacher_disagreement_score":0.014322315,"about_ca_system_score_codex":0.0016599599,"about_ca_system_score_gemma":0.0013700854,"threshold_uncertainty_score":0.028477907},"labels":[],"label_agreement":null},{"id":"W7130678234","doi":"10.1109/swc65939.2025.00066","title":"Augmenting Japanese Language Acquisition via LLMs and ASR","year":2025,"lang":"","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University","funders":"Alberta Innovates; Natural Sciences and Engineering Research Council of Canada; Athabasca University","keywords":"Active listening; Japanese language; Language acquisition; Kanji","score_opus":0.009253066351147973,"score_gpt":0.25425679137887,"score_spread":0.245003725027722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7130678234","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37204772,0.00056943926,0.55207694,0.00039001415,0.00018005416,0.0004291977,0.00033558634,0.02242426,0.051546764],"genre_scores_gemma":[0.6300606,0.0003074794,0.34753108,0.00027652926,0.000050598588,0.0002648387,0.00043784737,0.0010369715,0.02003396],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999501,0.0001318438,0.000026687372,0.00012737724,0.00014954427,0.00006358894],"domain_scores_gemma":[0.9993741,0.00023672341,0.00003162567,0.00010459205,0.00019862341,0.000054503267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006872565,0.00081459054,0.00043088454,0.00040831842,0.00022339975,0.0007727131,0.0007632563,0.0004329343,0.008436276],"category_scores_gemma":[0.0017610331,0.00026165938,0.00026275538,0.00023857968,0.0003860483,0.0012664198,0.0015646308,0.0005795175,0.0044009546],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003431032,0.0002534926,0.00209681,0.00029085888,0.00002378698,0.00044609737,0.001439054,0.002927815,0.28360054,0.0018068841,0.0030590093,0.7037125],"study_design_scores_gemma":[0.00034168884,0.0041985284,0.020067107,0.00018816047,0.0002816559,0.0031564021,0.002792292,0.2064016,0.5894187,0.0056509976,0.16722172,0.00028108593],"about_ca_topic_score_codex":0.0019317386,"about_ca_topic_score_gemma":0.0047518164,"teacher_disagreement_score":0.008436276,"about_ca_system_score_codex":0.00020454162,"about_ca_system_score_gemma":0.00044259548,"threshold_uncertainty_score":0.028222084},"labels":[],"label_agreement":null},{"id":"W7132590463","doi":"","title":"Supporting SENĆOŦEN language documentation efforts with Automatic Speech Recognition","year":2025,"lang":"en","type":"article","venue":"NPARC","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Pipeline (software); Documentation; Vocabulary; Word error rate; Speech technology; Language model; Set (abstract data type); Variation (astronomy)","score_opus":0.010882510643594174,"score_gpt":0.2816661806138079,"score_spread":0.2707836699702137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132590463","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09798593,0.0014370978,0.6670179,0.0013907194,0.00059418846,0.00046009303,0.0077483407,0.19707935,0.026286492],"genre_scores_gemma":[0.36224085,0.001069899,0.5709748,0.0005432719,0.0002333519,0.0003824136,0.037834927,0.0037824106,0.022937985],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99793124,0.00046117115,0.00016377972,0.00059707474,0.000687143,0.0001595809],"domain_scores_gemma":[0.995455,0.001073231,0.00024290237,0.001073278,0.0019732153,0.00018232444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017709193,0.0015589559,0.0009802454,0.0020596588,0.0009632243,0.0020392975,0.0013397895,0.0010712888,0.008242586],"category_scores_gemma":[0.0062474757,0.0005735395,0.0008253271,0.0012696281,0.0006259591,0.0021753386,0.0021987956,0.0024399883,0.020944208],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026096372,0.00014521356,0.0020404744,0.0004991424,0.000058695536,0.00043728025,0.0006033466,0.0071409713,0.05758305,0.0020273912,0.041505095,0.8876983],"study_design_scores_gemma":[0.00017609906,0.000452321,0.0076348283,0.00026929023,0.00012591678,0.0010395618,0.0015795241,0.5253731,0.27510843,0.009794322,0.17820498,0.00024162237],"about_ca_topic_score_codex":0.011708967,"about_ca_topic_score_gemma":0.016534712,"teacher_disagreement_score":0.011708967,"about_ca_system_score_codex":0.00091687473,"about_ca_system_score_gemma":0.0031615263,"threshold_uncertainty_score":0.027574182},"labels":[],"label_agreement":null},{"id":"W7132892771","doi":"","title":"Robustesse des modèles neuronaux pour le traitement automatique de la parole","year":2025,"lang":"en","type":"dissertation","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Robustness (evolution); Training set; Focus (optics); Variation (astronomy); Speech processing; Speech technology; Stress (linguistics)","score_opus":0.015796261104006698,"score_gpt":0.23986411379419034,"score_spread":0.22406785269018364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132892771","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15261559,0.0047647445,0.8295405,0.0012898655,0.0003156463,0.00015718867,0.0004187053,0.0026572885,0.008240482],"genre_scores_gemma":[0.9231927,0.0012660114,0.06588652,0.0001862506,0.00006713275,0.0001885924,0.0002454855,0.00015747269,0.008809798],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99954826,0.00010404653,0.000025538853,0.00014046839,0.00010632405,0.000075453296],"domain_scores_gemma":[0.99857044,0.00090249703,0.00009643445,0.00009152409,0.00029635034,0.000042691358],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015602636,0.0014391231,0.0012099647,0.00035508384,0.00055785483,0.0022139866,0.0014256298,0.002052709,0.0025185703],"category_scores_gemma":[0.0040269126,0.00077035814,0.0012910535,0.00031361825,0.0008082973,0.00094368303,0.0006866784,0.0026297409,0.00095603877],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014853301,0.00003893447,0.0011131321,0.00006816765,0.000106060994,0.000065386106,0.00007146818,0.9508916,0.0076189293,0.0034535537,0.00067149,0.035752695],"study_design_scores_gemma":[0.0000056410095,0.000024940171,0.00020554676,0.000008401609,0.000012297842,0.000013645484,0.000007725029,0.9976841,0.001248371,0.0004664272,0.00031674776,0.0000060493167],"about_ca_topic_score_codex":0.032934416,"about_ca_topic_score_gemma":0.026728654,"teacher_disagreement_score":0.032934416,"about_ca_system_score_codex":0.002648772,"about_ca_system_score_gemma":0.0017432766,"threshold_uncertainty_score":0.06548548},"labels":[],"label_agreement":null},{"id":"W7133044638","doi":"","title":"Scale in Acoustic Modelling","year":2023,"lang":"","type":"dissertation","venue":"TSpace","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Hidden Markov model; Representation (politics); Pipeline (software); Feature (linguistics); Computation; Event (particle physics); ENCODE; Scale (ratio); Acoustic model; Phone","score_opus":0.06277386535438166,"score_gpt":0.3385953024865143,"score_spread":0.27582143713213264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133044638","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026711035,0.0013660232,0.97863597,0.0012354692,0.0004662085,0.000035895442,0.0002491659,0.00045196322,0.014888171],"genre_scores_gemma":[0.39147547,0.0061505525,0.54855657,0.0020327247,0.0025304398,0.0003654803,0.0009191679,0.0013050275,0.046664525],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989428,0.00031783863,0.00006542235,0.00032346914,0.00026546486,0.00008506439],"domain_scores_gemma":[0.9987698,0.00064185786,0.00013171369,0.00028276362,0.00012412369,0.000049635626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001140034,0.0013200854,0.00071411923,0.0009977615,0.00053658854,0.002779439,0.0017142295,0.0019262423,0.008954638],"category_scores_gemma":[0.0060307174,0.0007590153,0.0016214896,0.0010766279,0.0023414076,0.003327124,0.0023616136,0.003368506,0.0039729],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040899038,0.000022248088,0.0010429827,0.00018685957,0.00006607859,0.0001595456,0.00029410515,0.13004361,0.00374289,0.79597384,0.008134517,0.060292576],"study_design_scores_gemma":[0.000012031497,0.000034925495,0.0007082724,0.00005470187,0.000027984557,0.00020972014,0.000060779716,0.4256323,0.0010602734,0.5162019,0.055941008,0.000056063378],"about_ca_topic_score_codex":0.0054886313,"about_ca_topic_score_gemma":0.0041013625,"teacher_disagreement_score":0.008954638,"about_ca_system_score_codex":0.000940244,"about_ca_system_score_gemma":0.00072102045,"threshold_uncertainty_score":0.029956281},"labels":[],"label_agreement":null},{"id":"W7133331044","doi":"10.1109/ijcb65343.2025.11410671","title":"Text-Independent Speaker Verification Employing A Novel Hybrid Neural Embedding Extractor","year":2025,"lang":"","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Discriminative model; Robustness (evolution); Pattern recognition (psychology); Convolutional neural network; Embedding; Artificial neural network; Feature extraction; Feature (linguistics); Softmax function; Pooling","score_opus":0.03752871438985219,"score_gpt":0.29739213717069957,"score_spread":0.2598634227808474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133331044","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04889015,0.00090588443,0.93883425,0.0002114243,0.00027148917,0.00012171113,0.00035987885,0.007580568,0.0028246487],"genre_scores_gemma":[0.564525,0.00049894914,0.4115885,0.00040175664,0.00016016263,0.00016697362,0.0017401024,0.0003466227,0.020571886],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99929214,0.00009703377,0.000035862256,0.00024020304,0.00025915334,0.000075617776],"domain_scores_gemma":[0.99945396,0.000108666114,0.00005179464,0.0001230879,0.00022930892,0.000033119555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000921298,0.0009901696,0.0008033376,0.00064051134,0.00030197995,0.0006489018,0.0013295772,0.0009413362,0.0035314923],"category_scores_gemma":[0.0014293249,0.00039975822,0.0006399015,0.0003799461,0.0003325789,0.0015215374,0.0014307431,0.0011273796,0.00272028],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005251209,0.00012973702,0.0011191845,0.0001298748,0.00015114815,0.00014943979,0.00008009226,0.021228956,0.15480918,0.0019692595,0.0045952606,0.8151127],"study_design_scores_gemma":[0.00003971828,0.00020833252,0.0017620067,0.000020032496,0.00009514282,0.00038043738,0.00003398286,0.8534684,0.13692652,0.0014388254,0.005584955,0.000041636788],"about_ca_topic_score_codex":0.0028113788,"about_ca_topic_score_gemma":0.0058159824,"teacher_disagreement_score":0.0035314923,"about_ca_system_score_codex":0.00045157637,"about_ca_system_score_gemma":0.0007140539,"threshold_uncertainty_score":0.011813998},"labels":[],"label_agreement":null},{"id":"W7148307382","doi":"10.1109/asru65441.2025.11434672","title":"Maestro-EVC: Controllable Emotional Voice Conversion Guided by References and Explicit Prosody","year":2025,"lang":"","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Research Foundation","keywords":"Prosody; Representation (politics); Identity (music); Emotional prosody; Style (visual arts); Dynamics (music)","score_opus":0.02420264739188317,"score_gpt":0.26149773320609704,"score_spread":0.23729508581421388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7148307382","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032037575,0.0004573182,0.9578109,0.00009495452,0.00013419446,0.00007349969,0.00009255732,0.002059435,0.007239615],"genre_scores_gemma":[0.7109067,0.0003507425,0.27586704,0.0002623151,0.00008144189,0.000222462,0.0004229901,0.00066615146,0.011220079],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9997203,0.00006080378,0.000014123807,0.000079075464,0.00009948097,0.000026130838],"domain_scores_gemma":[0.9997485,0.00011220872,0.000019979754,0.00005970117,0.00003929097,0.000020207406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040550323,0.00055184605,0.00033683173,0.00022104809,0.00021576541,0.00058960763,0.00077939837,0.00047975685,0.0027879132],"category_scores_gemma":[0.0009924094,0.00017736,0.00031060254,0.00011156773,0.00051576714,0.0005393701,0.0011617667,0.0006657499,0.0008363349],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044491448,0.00012338327,0.0006136469,0.00028385854,0.00007149032,0.00050521083,0.000390865,0.04986666,0.6022226,0.02553371,0.003972554,0.31597117],"study_design_scores_gemma":[0.000074010786,0.0003375825,0.0008205121,0.000044989283,0.000044362212,0.00063517067,0.00009820679,0.7050901,0.25572744,0.009794715,0.027260734,0.00007218885],"about_ca_topic_score_codex":0.000384793,"about_ca_topic_score_gemma":0.0007365749,"teacher_disagreement_score":0.0027879132,"about_ca_system_score_codex":0.00014881932,"about_ca_system_score_gemma":0.00020624562,"threshold_uncertainty_score":0.009326518},"labels":[],"label_agreement":null},{"id":"W7148418289","doi":"10.1109/asru65441.2025.11434627","title":"Low-Resource Domain Adaptation for Speech LLMs via Text-Only Fine-Tuning","year":2025,"lang":"","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Optech (Canada)","funders":"","keywords":"Adaptation (eye); Domain (mathematical analysis); Generalization; Domain adaptation; Encoder; Mechanism (biology); Degradation (telecommunications)","score_opus":0.02317349662740988,"score_gpt":0.2601340969287989,"score_spread":0.23696060030138902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7148418289","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03311434,0.0010568302,0.9521017,0.00021648918,0.00023465861,0.00011525803,0.00029322036,0.009918259,0.0029493084],"genre_scores_gemma":[0.60218287,0.0006415938,0.3794839,0.0010754686,0.0002385084,0.0004709554,0.0024045492,0.0014141151,0.012087918],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993031,0.00017378974,0.00004732633,0.00026269082,0.00014337046,0.00006966738],"domain_scores_gemma":[0.9990526,0.00041982564,0.000054360706,0.00022395549,0.00018862703,0.00006072691],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087365735,0.0014483347,0.0011158803,0.00061977486,0.00035819854,0.00074110494,0.0011886038,0.00090630364,0.0043012947],"category_scores_gemma":[0.0036868474,0.0003300155,0.0007036143,0.0005512801,0.00061465404,0.0012360876,0.0015837839,0.0016374298,0.0041006086],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005746156,0.00037675566,0.0010519982,0.00022072332,0.00009419008,0.0002799482,0.00017229437,0.1258726,0.10473931,0.0025671357,0.010065947,0.7539845],"study_design_scores_gemma":[0.0000682647,0.00012802928,0.00081855094,0.000021782846,0.00003644956,0.00020869226,0.00008641169,0.94710124,0.040962193,0.0048815813,0.005646609,0.000040346527],"about_ca_topic_score_codex":0.00243093,"about_ca_topic_score_gemma":0.005062277,"teacher_disagreement_score":0.0043012947,"about_ca_system_score_codex":0.00040430916,"about_ca_system_score_gemma":0.00072198303,"threshold_uncertainty_score":0.014389217},"labels":[],"label_agreement":null},{"id":"W7148467367","doi":"10.1109/asru65441.2025.11434705","title":"Multi-Target Backdoor Attacks Against Speaker Recognition","year":2025,"lang":"","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Backdoor; Speaker recognition; Speaker identification; Task (project management); Speaker diarisation; Speaker verification; Identification (biology)","score_opus":0.04730060825118691,"score_gpt":0.2875064403786451,"score_spread":0.24020583212745816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7148467367","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18160717,0.0011255783,0.80933136,0.0002415795,0.00026336586,0.00012156268,0.00009194253,0.002698742,0.0045187515],"genre_scores_gemma":[0.9500842,0.00022035683,0.046964355,0.00013236328,0.000053787,0.000043343887,0.00006292632,0.00006831709,0.0023704038],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99801624,0.0004075512,0.00008988027,0.0003509974,0.00082304684,0.00031230343],"domain_scores_gemma":[0.9978346,0.00089991186,0.00028401703,0.00060783135,0.00023784593,0.00013572941],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092457887,0.0009090642,0.0010396314,0.00056742574,0.0005219927,0.00080606784,0.0007180523,0.0011567032,0.0018306857],"category_scores_gemma":[0.0026537045,0.0002647957,0.0008376717,0.00022440654,0.00078595796,0.0015980812,0.0023369163,0.0014000975,0.001134478],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001712559,0.00045121167,0.005502642,0.00044243422,0.00045448696,0.0015420882,0.0005080371,0.0850833,0.5283197,0.02405666,0.0027786298,0.3491482],"study_design_scores_gemma":[0.00005440795,0.0014537991,0.002257853,0.000062271916,0.00014683367,0.0041571422,0.00014130301,0.56482065,0.41205406,0.008083312,0.006646995,0.000121414734],"about_ca_topic_score_codex":0.00018248019,"about_ca_topic_score_gemma":0.00019153317,"teacher_disagreement_score":0.0018306857,"about_ca_system_score_codex":0.0002749452,"about_ca_system_score_gemma":0.00034281777,"threshold_uncertainty_score":0.0061243176},"labels":[],"label_agreement":null},{"id":"W7150799232","doi":"10.70675/0f82ff96z8b2cz4523z9426zd8215c37a473","title":"Reconnaissance automatique de la parole à large vocabulaire : des approches hybrides aux approches End-to-End","year":2021,"lang":"","type":"dissertation","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"History of sociology; Lexicography; Digital humanities","score_opus":0.024617067766640684,"score_gpt":0.2906459060132357,"score_spread":0.266028838246595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7150799232","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004643449,0.00047318844,0.9836204,0.00020768362,0.00006450898,0.00011973003,0.000200468,0.0067016524,0.0039689355],"genre_scores_gemma":[0.091473415,0.000881348,0.87964314,0.00035531586,0.00007079531,0.0003959256,0.0019224745,0.001797181,0.023460373],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970004,0.00074280193,0.00024317949,0.00089815375,0.00096989924,0.00014554158],"domain_scores_gemma":[0.99645054,0.0012079926,0.00010268895,0.0011580498,0.00096601434,0.00011474959],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002716499,0.0015973032,0.0011283868,0.0013585985,0.0009217409,0.0032712065,0.0028775297,0.0027147378,0.014889751],"category_scores_gemma":[0.0062480615,0.0009643046,0.0017759452,0.0009952484,0.0010804347,0.004419152,0.0036135658,0.002412229,0.011043293],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000540186,0.00014961463,0.0011749123,0.000789052,0.000219735,0.00066214235,0.002195564,0.023104468,0.09429704,0.016775336,0.010761057,0.8493309],"study_design_scores_gemma":[0.00010117547,0.0005741536,0.0027425059,0.000458611,0.0003262457,0.0019691149,0.0023971954,0.60163796,0.13148516,0.03321135,0.22487094,0.00022556655],"about_ca_topic_score_codex":0.0075748353,"about_ca_topic_score_gemma":0.011500249,"teacher_disagreement_score":0.014889751,"about_ca_system_score_codex":0.00079839735,"about_ca_system_score_gemma":0.0013571804,"threshold_uncertainty_score":0.049811184},"labels":[],"label_agreement":null},{"id":"W7152567113","doi":"10.70675/cd07449cz121az45b9zaa1bz82f77086939d","title":"Robustness of neural models for automatic speech processing","year":2025,"lang":"","type":"dissertation","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Robustness (evolution); Speech processing; Deep neural networks","score_opus":0.05468512467044811,"score_gpt":0.30275509348258994,"score_spread":0.24806996881214183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7152567113","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28645852,0.003854774,0.69477975,0.0015976533,0.00036672576,0.00011394031,0.0006207649,0.0026903395,0.009517578],"genre_scores_gemma":[0.9751312,0.0006404022,0.019965056,0.00012246452,0.00007047988,0.000086144675,0.00044939175,0.00016874385,0.0033661807],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99872017,0.00042702587,0.00008448539,0.0003736472,0.00025184796,0.00014290214],"domain_scores_gemma":[0.99601895,0.0028658216,0.00019570741,0.00043363436,0.00040224165,0.00008362766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029478315,0.001344959,0.00089734746,0.0006817731,0.0005525979,0.0018561815,0.0013372487,0.0014216893,0.0030827995],"category_scores_gemma":[0.012629752,0.0007040315,0.0012006504,0.0004080225,0.00087690115,0.0016369208,0.0014247334,0.0020605312,0.001010882],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025431407,0.000034590154,0.0016278732,0.00010028476,0.00015230618,0.000052989275,0.00007605361,0.9462952,0.006360778,0.0028255556,0.0004826137,0.041737426],"study_design_scores_gemma":[0.0000044033472,0.00003296183,0.0006235798,0.000011614559,0.000013151109,0.000014285908,0.000011771344,0.9953243,0.0015719694,0.0021114228,0.00026994708,0.000010701037],"about_ca_topic_score_codex":0.011524076,"about_ca_topic_score_gemma":0.007611306,"teacher_disagreement_score":0.011524076,"about_ca_system_score_codex":0.0014716842,"about_ca_system_score_gemma":0.0012379285,"threshold_uncertainty_score":0.022913992},"labels":[],"label_agreement":null},{"id":"W7154460112","doi":"10.1109/smartagrisusy68475.2025.11466843","title":"Toward Lightweight IoC Extraction in IoT: The Role of Small Language Models","year":2025,"lang":"","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec en Outaouais","funders":"","keywords":"Information extraction; Extraction (chemistry); Matching (statistics); Key (lock)","score_opus":0.028787555935481192,"score_gpt":0.2586371234694949,"score_spread":0.22984956753401373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7154460112","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04077026,0.00050259917,0.9420013,0.0008777226,0.00008656696,0.00022125429,0.00095774024,0.012164184,0.0024183686],"genre_scores_gemma":[0.3820565,0.00045186133,0.6102899,0.00055283535,0.0000754145,0.00030073282,0.002859464,0.0011554804,0.0022577967],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986002,0.00043663042,0.0001302528,0.00030200783,0.0004520778,0.000078791265],"domain_scores_gemma":[0.9951461,0.0027050264,0.00043776774,0.0009647985,0.00062337297,0.00012296336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018484885,0.0010005077,0.0008933751,0.0015173979,0.0004662457,0.0029062128,0.0012836502,0.00094522047,0.0017665295],"category_scores_gemma":[0.009365654,0.00052803906,0.0012250452,0.0008379068,0.00089318596,0.0054029934,0.00203145,0.0016523062,0.0018507898],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008787555,0.00034186072,0.009927333,0.001189619,0.00029452422,0.0011788915,0.0020753548,0.14105122,0.092009,0.040009595,0.017378028,0.69366586],"study_design_scores_gemma":[0.000031799016,0.00012903792,0.0010936883,0.00008858402,0.00006556059,0.0003304918,0.00041034614,0.9253836,0.029415049,0.028849969,0.014137966,0.00006381983],"about_ca_topic_score_codex":0.0031418635,"about_ca_topic_score_gemma":0.004361044,"teacher_disagreement_score":0.0031418635,"about_ca_system_score_codex":0.000879225,"about_ca_system_score_gemma":0.0018341998,"threshold_uncertainty_score":0.009775877},"labels":[],"label_agreement":null},{"id":"W7160921222","doi":"10.1121/10.0041466","title":"A Praat script for unsupervised phoneme segmentation based on spectro-temporal representation","year":2025,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"TIMIT; Segmentation; Representation (politics); Spectrogram; Set (abstract data type); Measure (data warehouse); Software; Boundary (topology); Data set","score_opus":0.022547207252939523,"score_gpt":0.2854492572117903,"score_spread":0.2629020499588508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7160921222","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029069346,0.0001410056,0.4105851,0.00017057595,0.0004900396,0.0006074856,0.052226376,0.5237089,0.0091635175],"genre_scores_gemma":[0.034169782,0.00023143069,0.6289332,0.0008053906,0.00030443526,0.0034061186,0.094944075,0.20222865,0.034977004],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993931,0.00008057688,0.00009869662,0.00023985852,0.00013371148,0.00005413123],"domain_scores_gemma":[0.9968581,0.0014743054,0.00021707798,0.00045165943,0.00083766284,0.00016114044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001290198,0.0020674684,0.00090978947,0.0011280043,0.00067941926,0.001559994,0.0018307929,0.0009454961,0.25666934],"category_scores_gemma":[0.007961935,0.0011504046,0.0010344406,0.0006449638,0.00045361032,0.0014619986,0.0015584016,0.002186479,0.1428159],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00079441565,0.00014877718,0.0024390998,0.0014241383,0.00014267785,0.0006449958,0.00062597287,0.002930411,0.040083747,0.0043652793,0.72079045,0.2256101],"study_design_scores_gemma":[0.00040086533,0.00026463057,0.010058679,0.00046914397,0.00009971896,0.001731517,0.0003643834,0.07325292,0.09116212,0.020346437,0.8014953,0.00035423978],"about_ca_topic_score_codex":0.0015439895,"about_ca_topic_score_gemma":0.0029830928,"teacher_disagreement_score":0.25666934,"about_ca_system_score_codex":0.00042055093,"about_ca_system_score_gemma":0.0008627249,"threshold_uncertainty_score":0.8586445},"labels":[],"label_agreement":null}]}