{"meta":{"query_hash":"4f1cdcbff395","filters":{"venue":"International Journal of Speech Technology"},"cohort_total":28,"direct_labels_cover":0,"predictions_cover":28,"exported":28,"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/4f1cdcbff395","api":"https://metacan.xera.ac/api/v1/cohort?venue=International+Journal+of+Speech+Technology"},"results":[{"id":"W1506669403","doi":"10.1023/a:1011323308477","title":"VoiceGrip: A Tool for Programming-by-Voice","year":2001,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Digital Accessibility for Disabilities","field":"Social Sciences","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"National Research Council Canada","keywords":"Computer science; Programmer; Syntax; Programming language; Usability; Symbol (formal); Code (set theory); Confusion; Range (aeronautics); Speech recognition; Artificial intelligence; Human–computer interaction","score_opus":0.017852888560412856,"score_gpt":0.3474971288228051,"score_spread":0.32964424026239225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1506669403","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.947059,0.000311679,0.0024039873,0.04063853,0.0014035018,0.00036160724,0.00002963048,0.00014250037,0.0076495656],"genre_scores_gemma":[0.98657197,0.00010039889,0.009612439,0.00019718615,0.00065105874,0.000023758128,0.0000045475517,0.000013255534,0.002825368],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984671,0.0000229182,0.00048695065,0.0001516523,0.00059589546,0.00027548976],"domain_scores_gemma":[0.99807084,0.00019456593,0.0003487528,0.0001163889,0.0012118038,0.000057667443],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076174625,0.00009741348,0.00018403279,0.00031809066,0.00010244073,0.00018914779,0.0012214538,0.00016902451,0.00010304222],"category_scores_gemma":[0.0024232962,0.000089724395,0.00015864475,0.00030020732,0.0005552167,0.00073058606,0.00007844502,0.00019777866,0.000022239112],"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":[0.0001645616,0.000365187,0.035236116,0.000007838581,0.0001589865,0.000045087567,0.00069260434,0.0000014939855,0.00044849282,0.052772935,0.0067628366,0.90334386],"study_design_scores_gemma":[0.00047563342,0.00018358069,0.00019962316,0.0000324295,0.000012882072,0.000111414156,0.0028504706,0.0000022550355,0.0010739069,0.0762451,0.9187052,0.00010749536],"about_ca_topic_score_codex":0.00013080772,"about_ca_topic_score_gemma":0.00038122284,"teacher_disagreement_score":0.91194236,"about_ca_system_score_codex":0.0002941587,"about_ca_system_score_gemma":0.00018576371,"threshold_uncertainty_score":0.36588547},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53696674,0.00052485464,0.45082673,0.0078301355,0.0026766777,0.00027339565,0.000027526417,0.00008328895,0.00079063844],"genre_scores_gemma":[0.91343945,0.000086444394,0.085902035,0.0001277947,0.0003498298,0.000008320448,0.000001938896,0.000011903165,0.000072286406],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99812716,0.00004945345,0.0005737797,0.00016235876,0.00082021987,0.00026702858],"domain_scores_gemma":[0.9978858,0.00026101636,0.00062729226,0.00022758558,0.00090399676,0.00009431333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009445513,0.00014828905,0.0003471565,0.0008181737,0.000035369667,0.0000440769,0.0016007422,0.00017343489,0.000066132765],"category_scores_gemma":[0.0004425246,0.00011964414,0.00024321431,0.00019765741,0.000086275635,0.00059244153,0.00018568269,0.0002442145,0.000016215961],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000356793,0.00014688514,0.009803661,0.000013551541,0.00032046193,0.00005033211,0.00008281356,0.000005714831,0.009412422,0.011878276,0.0012668783,0.9666622],"study_design_scores_gemma":[0.004428855,0.0013965489,0.003405634,0.00024394477,0.000073117684,0.0042107143,0.000069697955,0.0016589591,0.8930755,0.05262996,0.038452093,0.00035496688],"about_ca_topic_score_codex":0.0000027964084,"about_ca_topic_score_gemma":0.000002171513,"teacher_disagreement_score":0.9663072,"about_ca_system_score_codex":0.00016117356,"about_ca_system_score_gemma":0.0000802042,"threshold_uncertainty_score":0.48789462},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056820333,0.0002124956,0.89286715,0.04373778,0.0029167372,0.00045922786,0.000031790012,0.00049221545,0.0024622635],"genre_scores_gemma":[0.042646643,0.000021091291,0.9559304,0.00034048114,0.00062549737,0.000025075802,0.000020069507,0.000017739787,0.00037299254],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982233,0.000056184566,0.00049542024,0.00028191908,0.0006975232,0.00024565388],"domain_scores_gemma":[0.9966002,0.000095778785,0.0006075789,0.00020164443,0.0023630038,0.00013178962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085382623,0.00018503459,0.00031855665,0.0012463201,0.000064457054,0.00017840775,0.0014334789,0.0003029805,0.000039022667],"category_scores_gemma":[0.0007487368,0.00016531721,0.00018458844,0.0006621903,0.00007793523,0.00074030063,0.00013139936,0.00041933582,0.00005174612],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056380897,0.00019143506,0.0006021734,0.000009706159,0.00017320957,0.00008819615,0.0000622904,0.000012682157,0.00037903123,0.0012924374,0.027126975,0.9700055],"study_design_scores_gemma":[0.0099973045,0.0024184922,0.00042202842,0.00049493386,0.00018466798,0.07194811,0.0017984937,0.3562468,0.14505336,0.21887952,0.19113976,0.0014165429],"about_ca_topic_score_codex":0.00000767473,"about_ca_topic_score_gemma":0.000010989466,"teacher_disagreement_score":0.96858895,"about_ca_system_score_codex":0.00026863534,"about_ca_system_score_gemma":0.00028312564,"threshold_uncertainty_score":0.67414397},"labels":[],"label_agreement":null},{"id":"W2011408835","doi":"10.1007/s10772-014-9244-6","title":"Dialogue POMDP components (part I): learning states and observations","year":2014,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and dialogue systems","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":"Partially observable Markov decision process; Computer science; Artificial intelligence; Context (archaeology); Machine learning; Process (computing); Set (abstract data type); Markov model; Markov chain","score_opus":0.018496216936909258,"score_gpt":0.24163162216468634,"score_spread":0.22313540522777708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011408835","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8241432,0.000300736,0.15476322,0.017149698,0.0027711405,0.00007988347,0.000004446675,0.00015794864,0.0006297681],"genre_scores_gemma":[0.9671596,0.00014976536,0.031908732,0.00024498586,0.00040521508,0.000002305037,0.0000077479735,0.0000077774785,0.000113826376],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99878603,0.00005897107,0.00044086677,0.00016602293,0.00037446222,0.00017367011],"domain_scores_gemma":[0.99869835,0.00014844631,0.0003972089,0.00016506786,0.00051871716,0.00007219689],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049767096,0.000104564504,0.00020396795,0.00056412455,0.00006947244,0.0001196884,0.0010986616,0.000105317915,0.000006832442],"category_scores_gemma":[0.00046237095,0.0000935503,0.00005269419,0.00022989162,0.00009360532,0.00040013474,0.0002557283,0.000316152,0.000022478353],"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":[0.000088646055,0.0002542544,0.19416645,0.000019082774,0.00047517617,0.00043643572,0.0006681437,0.0006003429,0.048112202,0.32394168,0.0054768366,0.42576075],"study_design_scores_gemma":[0.004566984,0.0014535249,0.061649147,0.00040134595,0.000038780676,0.0064229965,0.0004182909,0.02675566,0.03694387,0.2990374,0.56154263,0.00076934893],"about_ca_topic_score_codex":0.00005125562,"about_ca_topic_score_gemma":0.000018254172,"teacher_disagreement_score":0.5560658,"about_ca_system_score_codex":0.00005023282,"about_ca_system_score_gemma":0.00004075106,"threshold_uncertainty_score":0.38148704},"labels":[],"label_agreement":null},{"id":"W2015313388","doi":"10.1007/s10772-014-9224-x","title":"Dialogue POMDP components (Part II): learning the reward function","year":2014,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and dialogue systems","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":"Université Laval","funders":"","keywords":"Partially observable Markov decision process; Computer science; Reinforcement learning; Markov decision process; Context (archaeology); Artificial intelligence; Function (biology); Process (computing); Bellman equation; Machine learning; Markov process; Markov chain; Markov model; Mathematical optimization; Mathematics","score_opus":0.012141879733216104,"score_gpt":0.23098924759122247,"score_spread":0.21884736785800638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015313388","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5561238,0.00045509666,0.36389452,0.0556067,0.017737832,0.00021160764,0.000003179053,0.00039062035,0.0055766352],"genre_scores_gemma":[0.9933823,0.00003619267,0.0046292795,0.00040456245,0.0012086554,0.0000034407112,0.0000035295445,0.00000905379,0.00032298575],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983177,0.00011331395,0.0005220455,0.00019227293,0.0006307104,0.0002239559],"domain_scores_gemma":[0.9983395,0.00013428627,0.0005779582,0.00030336497,0.000585362,0.000059553637],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010202642,0.00012780463,0.00021403762,0.00054074393,0.00017216403,0.00011084212,0.0022109323,0.0001486557,0.000020150253],"category_scores_gemma":[0.00056815875,0.00009043097,0.00012266946,0.00032842887,0.00011043816,0.00034351498,0.00042221352,0.0005680202,0.00009507399],"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":[0.0002357017,0.00024877532,0.01787568,0.000008288701,0.0005571417,0.00025649858,0.00046612092,0.0005704037,0.026064582,0.27070573,0.01723238,0.6657787],"study_design_scores_gemma":[0.0017218804,0.0013021171,0.005123965,0.00013639033,0.0000275207,0.0032930044,0.00014412358,0.0030393174,0.013936832,0.08650152,0.8844827,0.0002906403],"about_ca_topic_score_codex":0.000037445738,"about_ca_topic_score_gemma":0.000014029427,"teacher_disagreement_score":0.8672503,"about_ca_system_score_codex":0.000089584624,"about_ca_system_score_gemma":0.000057438105,"threshold_uncertainty_score":0.4108499},"labels":[],"label_agreement":null},{"id":"W2016053816","doi":"10.1007/s10772-012-9186-9","title":"MCRA noise estimation for KLT-VRE-based speech enhancement","year":2013,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and Audio Processing","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":"Université de Moncton","funders":"","keywords":"Computer science; Speech recognition; Noise (video); Estimation; Speech enhancement; Artificial intelligence; Pattern recognition (psychology); Noise reduction","score_opus":0.00989396939828999,"score_gpt":0.2753188794034044,"score_spread":0.26542491000511437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016053816","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09264034,0.00013909837,0.8716668,0.033842526,0.0011447547,0.00020707241,0.0000019505878,0.00009594494,0.00026152402],"genre_scores_gemma":[0.44127756,0.000013973641,0.5578227,0.0005504243,0.00018514578,0.000020216761,0.0000024983692,0.000008746184,0.00011871014],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99833953,0.000013610355,0.00058834505,0.00023224922,0.0005584691,0.00026779587],"domain_scores_gemma":[0.99750364,0.000091506365,0.00061956415,0.0002540952,0.0014589303,0.000072265175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033859242,0.00015392105,0.00022153762,0.00084079185,0.00007117983,0.00023595574,0.001862505,0.00013985056,0.0001165906],"category_scores_gemma":[0.00032889066,0.00013628518,0.000121825775,0.00033314223,0.000076651995,0.0008470313,0.00014139187,0.00024713087,0.00009086724],"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":[0.000024029605,0.00013200827,0.0005131642,0.000011371582,0.00006941082,0.000057562043,0.000031192503,0.00016827592,0.06267606,0.0019282225,0.0026630142,0.9317257],"study_design_scores_gemma":[0.0011310409,0.00031472827,0.00022513392,0.00012036307,0.000009864285,0.00039944574,0.000027050803,0.014244523,0.9021384,0.07533997,0.005886765,0.00016267427],"about_ca_topic_score_codex":0.0000093998515,"about_ca_topic_score_gemma":0.0000034858463,"teacher_disagreement_score":0.931563,"about_ca_system_score_codex":0.00018526638,"about_ca_system_score_gemma":0.00019996439,"threshold_uncertainty_score":0.5557548},"labels":[],"label_agreement":null},{"id":"W2018093467","doi":"10.1007/s10772-009-9039-3","title":"Synthetic speech in foreign language learning: an evaluation by learners","year":2008,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and dialogue systems","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":"University of Toronto","funders":"","keywords":"Computer science; Natural (archaeology); Active listening; Speech synthesis; Comprehension; Speech recognition; Natural language processing; Foreign language; Linguistics; Artificial intelligence; Psychology; Communication","score_opus":0.017741914160635894,"score_gpt":0.28750836916179695,"score_spread":0.26976645500116103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2018093467","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98087263,0.0006185736,0.011980828,0.0021899745,0.0007693579,0.00014492159,0.0000018421282,0.00010468045,0.003317189],"genre_scores_gemma":[0.9886299,0.00008061798,0.010839107,0.000076382385,0.00017655367,0.0000054907428,0.0000061416326,0.000011559875,0.00017429834],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99784833,0.00014002832,0.0005459419,0.00026186657,0.00095724704,0.00024657144],"domain_scores_gemma":[0.99861264,0.00006654876,0.00042380378,0.00027758942,0.00054188404,0.00007752316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011447904,0.0001367471,0.00024130184,0.0011615931,0.000048450987,0.00005633767,0.0016999572,0.0001894709,0.000051093524],"category_scores_gemma":[0.0006574838,0.00012728006,0.00007851654,0.00049151684,0.00010940589,0.00062060234,0.00013144885,0.00052132143,0.00004806688],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015338212,0.00053914357,0.048301067,0.000007736735,0.0001702291,0.004556858,0.0025577547,0.0010135843,0.07548686,0.014786237,0.0023579046,0.8500692],"study_design_scores_gemma":[0.01460865,0.0047301273,0.008594538,0.0005679797,0.000073362,0.0773701,0.0123903705,0.078066275,0.6707118,0.09930039,0.031658806,0.0019275723],"about_ca_topic_score_codex":0.00010695418,"about_ca_topic_score_gemma":0.00003316126,"teacher_disagreement_score":0.8481417,"about_ca_system_score_codex":0.00026038595,"about_ca_system_score_gemma":0.00021109922,"threshold_uncertainty_score":0.519033},"labels":[],"label_agreement":null},{"id":"W2022504354","doi":"10.1007/s10772-013-9203-7","title":"A novel sub-band adaptive filtering for acoustic echo cancellation based on empirical mode decomposition algorithm","year":2013,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and Audio Processing","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":"Carleton University","funders":"","keywords":"Computer science; Hilbert–Huang transform; Algorithm; Microphone; Echo (communications protocol); Adaptive filter; Transfer function; SIGNAL (programming language); Mode (computer interface); Noise (video); Speech recognition; Filter (signal processing); Artificial intelligence; Telecommunications","score_opus":0.019891338903754226,"score_gpt":0.34177033193445233,"score_spread":0.3218789930306981,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022504354","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043626297,0.000037411828,0.948161,0.007212384,0.000630215,0.00015034243,0.000009389947,0.00006966652,0.00010328005],"genre_scores_gemma":[0.54664975,0.0000056131203,0.45277473,0.00034510434,0.00019238495,0.0000121359,0.0000022318172,0.000007501819,0.000010525139],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99876326,0.00001136462,0.00038728767,0.00022223999,0.00040500707,0.00021082108],"domain_scores_gemma":[0.9983399,0.00013611656,0.00039425012,0.00014616188,0.000922932,0.00006067063],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016077724,0.0001359134,0.00018481986,0.0007032868,0.00007295926,0.00014876248,0.000839095,0.00013774067,0.00001307065],"category_scores_gemma":[0.00010585363,0.00012337201,0.00009113991,0.00024042572,0.00004943876,0.0005171514,0.000059809725,0.00026250613,0.000009907029],"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":[0.000065491404,0.00014713457,0.00016362731,0.000005954617,0.000062319225,0.000043571632,0.000051563053,0.016846031,0.38660866,0.0001388278,0.0005660632,0.5953008],"study_design_scores_gemma":[0.00082959904,0.00033105692,0.00016079312,0.000110322006,0.0000069036428,0.00028959604,0.000018853603,0.49414256,0.49595815,0.007905412,0.00014190318,0.00010485561],"about_ca_topic_score_codex":0.000011804033,"about_ca_topic_score_gemma":0.0000070516317,"teacher_disagreement_score":0.5951959,"about_ca_system_score_codex":0.00027551068,"about_ca_system_score_gemma":0.00015162362,"threshold_uncertainty_score":0.50309646},"labels":[],"label_agreement":null},{"id":"W2031495521","doi":"10.1007/s10772-011-9104-6","title":"Using speech rhythm knowledge to improve dysarthric speech recognition","year":2011,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Phonetics and Phonology Research","field":"Psychology","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":"Institut National de la Recherche Scientifique; Université du Québec à Montréal; Université de Moncton","funders":"","keywords":"Computer science; Speech recognition; Dysarthria; Intelligibility (philosophy); Rhythm; Hidden Markov model; Classifier (UML); Artificial intelligence; Pattern recognition (psychology); Psychology","score_opus":0.10366588810498256,"score_gpt":0.3905004229513346,"score_spread":0.286834534846352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2031495521","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9755401,0.000588168,0.001422055,0.0016163153,0.00607961,0.00025571746,0.000040592317,0.0000761772,0.014381247],"genre_scores_gemma":[0.9501797,0.00010383568,0.047174353,0.0002264809,0.0011112451,0.000013778738,0.000005508885,0.00005293866,0.0011321362],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977152,0.00010151557,0.0008296167,0.00038960757,0.00042553977,0.0005385351],"domain_scores_gemma":[0.99721426,0.000089439294,0.00047460155,0.0003977989,0.0016447599,0.00017916044],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00078383036,0.00024312532,0.0004055889,0.0023111552,0.000070132206,0.00003606527,0.001231898,0.0004293287,0.0029166287],"category_scores_gemma":[0.00031523482,0.00023558382,0.00016837487,0.0007212864,0.0002464298,0.00017591524,0.00034662985,0.0010511635,0.0015042217],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006703621,0.0006261935,0.0029034512,0.000006375495,0.00062405097,0.0031990835,0.0017240362,6.8750353e-7,0.07272698,0.0013961112,0.002481866,0.9136408],"study_design_scores_gemma":[0.005328129,0.00336891,0.013626066,0.00032181817,0.00015519807,0.051782347,0.0021927494,0.00010762804,0.75357807,0.13465267,0.03387162,0.0010147617],"about_ca_topic_score_codex":0.00024764758,"about_ca_topic_score_gemma":0.00012219742,"teacher_disagreement_score":0.912626,"about_ca_system_score_codex":0.00023251459,"about_ca_system_score_gemma":0.0001737823,"threshold_uncertainty_score":0.99927324},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06907795,0.0005206947,0.9171021,0.0121286,0.00050381286,0.00026323253,0.000016485063,0.00022632685,0.0001607926],"genre_scores_gemma":[0.097160645,0.00014639333,0.90167135,0.00040460986,0.00048567046,0.000026975216,0.0000027379463,0.00001941761,0.000082187114],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99835104,0.000022547341,0.0006107537,0.00035062674,0.00038099047,0.00028403982],"domain_scores_gemma":[0.99793994,0.0001014191,0.00049854605,0.00031983858,0.0010469484,0.000093324554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042927786,0.00018559066,0.0002998471,0.0019616375,0.00013992445,0.0001616804,0.0016355143,0.0002893265,0.000036864978],"category_scores_gemma":[0.00012627599,0.00018119239,0.00009894162,0.0005850838,0.00017182711,0.00071521674,0.00025821244,0.00031727008,0.00001713392],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000070042083,0.00012312476,0.0001360287,0.0000025318109,0.00009459504,0.000046891455,0.00005417845,0.0000082164715,0.012405897,0.006416903,0.00012691777,0.9805777],"study_design_scores_gemma":[0.002828685,0.0005963357,0.00013556027,0.00017089548,0.000094786534,0.020132344,0.0017416895,0.0802945,0.5306677,0.14323749,0.21931808,0.00078194955],"about_ca_topic_score_codex":0.0000051693846,"about_ca_topic_score_gemma":0.000017734832,"teacher_disagreement_score":0.97979575,"about_ca_system_score_codex":0.00014624647,"about_ca_system_score_gemma":0.000112316986,"threshold_uncertainty_score":0.7388811},"labels":[],"label_agreement":null},{"id":"W2061284695","doi":"10.1007/s10772-013-9189-1","title":"Computational auditory models in predicting noise reduction performance for wideband telephony applications","year":2013,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and Audio Processing","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":"Western University","funders":"","keywords":"Computer science; Speech recognition; Noise (video); Wideband; Noise reduction; Reliability (semiconductor); Wideband audio; Reduction (mathematics); Telephony; Quality (philosophy); Artificial intelligence; Speech coding; Telecommunications; Mathematics","score_opus":0.009768127122746243,"score_gpt":0.2514530187062966,"score_spread":0.24168489158355036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061284695","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3467234,0.00014996798,0.6461827,0.0058086244,0.00067632634,0.0002163518,0.000001829669,0.00006470294,0.00017606124],"genre_scores_gemma":[0.7435564,0.000039628758,0.25581425,0.00007046564,0.00041215724,0.000056900142,0.0000021193368,0.000006812242,0.000041320458],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987277,0.000010061718,0.0005319019,0.00019536237,0.00034972563,0.00018523949],"domain_scores_gemma":[0.99827343,0.000069335736,0.00043976982,0.00013157213,0.0010425588,0.000043339824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026806557,0.000101924925,0.00015536559,0.0008366195,0.0000742166,0.00010806637,0.0010564104,0.00011071243,0.000008618798],"category_scores_gemma":[0.000067415625,0.00009828065,0.000055997247,0.00036846066,0.00007517279,0.0014532075,0.000106622596,0.0002716154,0.000010828628],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029404826,0.00015339264,0.0050962092,0.000021158665,0.00007262567,0.000012456155,0.00023211961,0.03827256,0.025085025,0.0031142063,0.0012469849,0.9266639],"study_design_scores_gemma":[0.0026093205,0.00034207175,0.0041043423,0.00032997754,0.000014393739,0.002741729,0.00035982192,0.32256174,0.1705374,0.4917199,0.004282964,0.0003963289],"about_ca_topic_score_codex":0.0000072938506,"about_ca_topic_score_gemma":0.0000015554509,"teacher_disagreement_score":0.9262675,"about_ca_system_score_codex":0.0001681935,"about_ca_system_score_gemma":0.00016313222,"threshold_uncertainty_score":0.40077686},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18050732,0.00035136484,0.710793,0.096877515,0.0031740277,0.00019448418,0.000021483358,0.00045348902,0.0076272623],"genre_scores_gemma":[0.54223526,0.0002896435,0.4538623,0.0023163427,0.0009797737,0.00000412475,0.000009248794,0.000018092258,0.00028524513],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983664,0.00003853336,0.0005971957,0.00020043935,0.00060964446,0.00018775497],"domain_scores_gemma":[0.99724525,0.00007201037,0.00047123485,0.00021482984,0.0019252505,0.00007143352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040760703,0.00013231051,0.00019350063,0.0013399019,0.0000530575,0.0001267293,0.0014758832,0.00018774244,0.00039103083],"category_scores_gemma":[0.000483252,0.00012362868,0.00012560947,0.00045345427,0.000074907766,0.00091031694,0.00015325673,0.00029624972,0.00046140404],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020337196,0.00010131265,0.00022418196,0.0000014005395,0.00006524965,0.00022229574,0.000044490465,0.00000896611,0.005128833,0.0031662395,0.000931942,0.99008477],"study_design_scores_gemma":[0.0018435365,0.00042413134,0.00041877586,0.00018950825,0.000034473913,0.016277835,0.00025803348,0.008722926,0.7235506,0.064151704,0.183653,0.00047547542],"about_ca_topic_score_codex":0.000007665699,"about_ca_topic_score_gemma":0.000019925907,"teacher_disagreement_score":0.9896093,"about_ca_system_score_codex":0.000179689,"about_ca_system_score_gemma":0.0000979588,"threshold_uncertainty_score":0.5930569},"labels":[],"label_agreement":null},{"id":"W2085830557","doi":"10.1007/s10772-009-9025-9","title":"A noise-robust front-end for distributed speech recognition in mobile communications","year":2007,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and Audio Processing","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; Speech recognition; Front and back ends; Formant; Mel-frequency cepstrum; GSM; Speech processing; Cepstrum; Noise (video); Task (project management); Artificial intelligence; Feature extraction; Telecommunications","score_opus":0.029785846712475042,"score_gpt":0.30922723126381185,"score_spread":0.2794413845513368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2085830557","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21763939,0.0008595312,0.76848763,0.011301841,0.0008529912,0.0002478095,0.00003769718,0.000108803746,0.000464276],"genre_scores_gemma":[0.4639674,0.0001498496,0.5354713,0.00017044086,0.00016764988,0.000013429254,0.000022800254,0.000009461645,0.000027631411],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984379,0.000019762185,0.0007086261,0.0001968709,0.00035303543,0.00028380976],"domain_scores_gemma":[0.9977721,0.00021049526,0.00054134213,0.00037388064,0.001041169,0.00006104348],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009784137,0.00012560599,0.00022403487,0.0011318666,0.00007061364,0.00010090046,0.0026367737,0.00018118552,0.00002335919],"category_scores_gemma":[0.00040366864,0.0001239397,0.00010017242,0.00051490695,0.00013111232,0.00064302987,0.00031185185,0.00044413703,0.000018404413],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056273024,0.00018381086,0.0020878925,0.0000049652576,0.000047748665,0.00015547631,0.00007731113,0.00002594408,0.012456763,0.0005478512,0.00037011915,0.98398584],"study_design_scores_gemma":[0.0040656473,0.00061255344,0.0030508614,0.00040577524,0.0000279009,0.0037709707,0.00077815185,0.0029522025,0.8012758,0.120893665,0.061688136,0.0004783451],"about_ca_topic_score_codex":0.000012140932,"about_ca_topic_score_gemma":0.00015147043,"teacher_disagreement_score":0.9835075,"about_ca_system_score_codex":0.00028009363,"about_ca_system_score_gemma":0.000117846386,"threshold_uncertainty_score":0.5054114},"labels":[],"label_agreement":null},{"id":"W2134558312","doi":"10.1007/s10772-012-9157-1","title":"The CARES corpus: a database of older adult actor simulated emergency dialogue for developing a personal emergency response system","year":2012,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Social Robot Interaction and HRI","field":"Psychology","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Rehabilitation Institute; University of Toronto","funders":"Canadian Institutes of Health Research; University of Toronto; Toronto Rehabilitation Institute","keywords":"Computer science; Emergency response; Human–computer interaction; Multimedia; World Wide Web; Database; Natural language processing; Medical emergency; Medicine","score_opus":0.03739795723703559,"score_gpt":0.38223702902467155,"score_spread":0.34483907178763595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134558312","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9647874,0.0016836683,0.0060097454,0.006168011,0.020624543,0.00029862477,0.00011713347,0.00006318595,0.00024766853],"genre_scores_gemma":[0.9971651,0.00022172254,0.0009774518,0.000056113386,0.0008951921,0.000022781176,0.000012793622,0.00002619972,0.0006226425],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99800104,0.00014581454,0.0009819998,0.00015094658,0.00039082806,0.0003293647],"domain_scores_gemma":[0.99610436,0.0004071103,0.0010425842,0.00018657646,0.00219075,0.00006860259],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007611246,0.0001646503,0.00027821455,0.0005236366,0.00013570905,0.000012819278,0.0007221475,0.00023490515,0.00042817555],"category_scores_gemma":[0.0014645656,0.0001270808,0.00023571323,0.00028244968,0.000103070364,0.00020027309,0.00008951272,0.000368727,0.00003584247],"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":[0.03032968,0.0016571513,0.15965398,0.00022004617,0.008431888,0.00040122095,0.03081247,0.000022318995,0.15675738,0.39363375,0.087696634,0.13038346],"study_design_scores_gemma":[0.023239665,0.003662491,0.11451299,0.0028461877,0.001161877,0.010710307,0.2478224,0.0010648145,0.1424898,0.007164588,0.4423462,0.002978694],"about_ca_topic_score_codex":0.00008019287,"about_ca_topic_score_gemma":0.000057470035,"teacher_disagreement_score":0.3864692,"about_ca_system_score_codex":0.00023936437,"about_ca_system_score_gemma":0.000119703494,"threshold_uncertainty_score":0.5182205},"labels":[],"label_agreement":null},{"id":"W2158112478","doi":"10.1007/s10772-008-9007-3","title":"VoiceMarks: restructuring hierarchical voice menus for improving navigation","year":2006,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and dialogue systems","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":"University of Manitoba","funders":"","keywords":"Computer science; Ticket; Human–computer interaction; Process (computing); Schedule; Interface (matter); User interface; Telephony; Multimedia; Telecommunications; Computer network","score_opus":0.0069514658770851835,"score_gpt":0.25311129350439066,"score_spread":0.24615982762730548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158112478","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47873768,0.00034368533,0.50623053,0.009362458,0.0041723093,0.00022383462,0.000010431881,0.00016835099,0.0007506863],"genre_scores_gemma":[0.8487534,0.0000037243158,0.14991389,0.000060098224,0.0011678215,0.0000070313818,0.0000054389884,0.000009709761,0.00007887012],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99843436,0.000025087473,0.0006110314,0.00021691884,0.0004743726,0.00023821589],"domain_scores_gemma":[0.9983263,0.00013381845,0.00055161555,0.00022238096,0.0007179693,0.000047927606],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046446154,0.000122466,0.00020000216,0.00068787066,0.000066688044,0.00013771065,0.0015588157,0.00017112237,0.0000033158287],"category_scores_gemma":[0.00028215785,0.000111274916,0.00011802265,0.00025986537,0.000072001836,0.00048622434,0.00018204865,0.00030208213,0.000009263946],"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":[0.00021728575,0.00013188588,0.0028791497,0.00004387751,0.0001577442,0.0007813558,0.00012145447,0.00026182778,0.20049864,0.23793916,0.0021563473,0.55481124],"study_design_scores_gemma":[0.0028843267,0.00063933106,0.0029627967,0.00021243532,0.000028941438,0.008662566,0.000103903854,0.008816002,0.35784432,0.5881464,0.029250056,0.00044891905],"about_ca_topic_score_codex":0.00010623079,"about_ca_topic_score_gemma":0.00002069205,"teacher_disagreement_score":0.55436236,"about_ca_system_score_codex":0.00016997551,"about_ca_system_score_gemma":0.00013537731,"threshold_uncertainty_score":0.45376593},"labels":[],"label_agreement":null},{"id":"W2163339323","doi":"10.1007/s10772-011-9116-2","title":"Bayesian on-line spectral change point detection: a soft computing approach for on-line ASR","year":2011,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":36,"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 Moncton; Université du Québec à Montréal","funders":"","keywords":"Computer science; Noise (video); Line (geometry); Speech recognition; Dynamic mode decomposition; Artificial intelligence; Pattern recognition (psychology); Machine learning","score_opus":0.06346383785389761,"score_gpt":0.3007303888762885,"score_spread":0.2372665510223909,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163339323","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02016373,0.00010276083,0.9705269,0.0064388695,0.0013481546,0.00018392422,0.0000038077997,0.0001731482,0.0010587572],"genre_scores_gemma":[0.6815831,0.00001235386,0.31662425,0.0006905753,0.0010340834,0.0000066651423,0.0000012353158,0.000014495036,0.00003319149],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982154,0.000020999294,0.00057390967,0.0003499279,0.0004889745,0.00035082383],"domain_scores_gemma":[0.9983466,0.000075592754,0.00061209744,0.0002692269,0.0006050561,0.00009137434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005010103,0.0002125567,0.00030104583,0.0010819347,0.00011475157,0.000094509014,0.0018034047,0.00018404183,0.000019631361],"category_scores_gemma":[0.0002173918,0.00018427729,0.00017603108,0.0004119295,0.00009490371,0.00040227603,0.00019128318,0.00056964246,0.000012676134],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022447912,0.00041612514,0.00024283276,0.000012069735,0.0001562469,0.00027338925,0.00032278994,0.00021792676,0.0029237426,0.0070464914,0.00011378628,0.9880501],"study_design_scores_gemma":[0.0023461862,0.0038236522,0.000272209,0.00023427959,0.000022629452,0.0044203466,0.00018632847,0.06356257,0.8689614,0.0542979,0.0014696404,0.0004028611],"about_ca_topic_score_codex":0.000007028195,"about_ca_topic_score_gemma":0.000005220154,"teacher_disagreement_score":0.98764724,"about_ca_system_score_codex":0.00016566509,"about_ca_system_score_gemma":0.00007356112,"threshold_uncertainty_score":0.75146097},"labels":[],"label_agreement":null},{"id":"W2479628911","doi":"10.1007/s10772-016-9352-6","title":"Audio steganalysis using deep belief networks","year":2016,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Music and Audio Processing","field":"Computer Science","cited_by":29,"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":"Steganalysis; Computer science; Artificial intelligence; Support vector machine; Pattern recognition (psychology); Steganography; Deep belief network; Classifier (UML); Mixture model; Speech recognition; Deep learning; Image (mathematics)","score_opus":0.010908966867149933,"score_gpt":0.2630156662380046,"score_spread":0.25210669937085467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2479628911","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.057232432,0.00047746018,0.92311585,0.017904202,0.0009396946,0.000019999841,4.3538128e-7,0.000056641424,0.0002532716],"genre_scores_gemma":[0.87515473,0.0001139885,0.12365868,0.0004564685,0.00048575996,5.2283644e-7,1.17034595e-7,0.0000075631883,0.00012213523],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986679,0.000021163267,0.00047211008,0.00018304668,0.00044745,0.00020834038],"domain_scores_gemma":[0.99833924,0.00006239722,0.0005911736,0.00022681795,0.000726276,0.000054117143],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034034182,0.00011003266,0.00021468526,0.00079107913,0.000057732042,0.00009284325,0.0019587174,0.00013254081,0.00006326356],"category_scores_gemma":[0.00014645673,0.00007338994,0.00011843705,0.00047605185,0.000106086576,0.00062534754,0.00032658697,0.00021213408,0.0000124639255],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010496723,0.00003537931,0.0026033032,0.0000012504528,0.0002177368,0.00035309626,0.000034563203,0.0004843402,0.013290308,0.012238289,0.00029362968,0.9704376],"study_design_scores_gemma":[0.0076319925,0.0008708109,0.0028820003,0.001993237,0.000323907,0.02738545,0.00033053433,0.22854936,0.29678696,0.33007383,0.101262495,0.001909393],"about_ca_topic_score_codex":0.000004028304,"about_ca_topic_score_gemma":0.0000047442463,"teacher_disagreement_score":0.9685282,"about_ca_system_score_codex":0.00016230658,"about_ca_system_score_gemma":0.00009590791,"threshold_uncertainty_score":0.36398166},"labels":[],"label_agreement":null},{"id":"W2799838911","doi":"10.1007/s10772-018-9507-8","title":"Gain optimization for millimeter wave reflectarray antennas based on a phase gradient approach","year":2018,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Advanced Antenna and Metasurface Technologies","field":"Engineering","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":"Concordia University","funders":"","keywords":"Computer science; Extremely high frequency; Linear phase; Bandwidth (computing); Phase (matter); Base station; Unit (ring theory); Antenna (radio); Millimeter; Electronic engineering; Telecommunications; Optics; Physics; Mathematics; Engineering","score_opus":0.026951814528730033,"score_gpt":0.2978482421224721,"score_spread":0.27089642759374205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2799838911","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.101832464,0.0001852762,0.8945724,0.0013796951,0.0010202553,0.00018247613,0.000023727784,0.00032317467,0.0004805259],"genre_scores_gemma":[0.6582069,0.00008238435,0.34138072,0.00009220578,0.00016917326,0.000011843087,0.000008274299,0.000024798655,0.00002376287],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894494,0.000009025289,0.00040528647,0.00015943023,0.00024634562,0.00023496516],"domain_scores_gemma":[0.9989236,0.000048478763,0.00018277857,0.00018759878,0.00062024704,0.00003730584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020476256,0.00017014948,0.00024695275,0.001005632,0.000041558742,0.00002113817,0.0004563137,0.00018989782,0.000027434082],"category_scores_gemma":[0.0002805197,0.0001441889,0.00011923199,0.00027801836,0.00017991084,0.00012352351,0.000027355647,0.00027563624,0.00000462663],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012767868,0.00079515716,0.0001176909,0.000053113097,0.0007826992,0.00024192846,0.00024040257,0.19628505,0.39566755,0.004520303,0.002663927,0.3973554],"study_design_scores_gemma":[0.0025815254,0.0014353063,0.000004311921,0.000099882156,0.00003278741,0.000287932,0.00023773583,0.65161246,0.3320474,0.0034572922,0.007990222,0.00021314273],"about_ca_topic_score_codex":5.6130733e-7,"about_ca_topic_score_gemma":0.0000012673456,"teacher_disagreement_score":0.5563744,"about_ca_system_score_codex":0.00015631989,"about_ca_system_score_gemma":0.000022746812,"threshold_uncertainty_score":0.58798534},"labels":[],"label_agreement":null},{"id":"W2901429777","doi":"10.1007/s10772-018-09564-8","title":"Evaluating noise suppression methods for recovering the Lombard speech from vocal output in an external noise field","year":2018,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and Audio Processing","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":"University of Ottawa","funders":"","keywords":"QUIET; Computer science; Noise (video); Noise reduction; Headphones; Acoustics; Background noise; Microphone; Speech recognition; Intelligibility (philosophy); Speech perception; Speech enhancement; Perception; Sound pressure; Telecommunications; Physics; Artificial intelligence; Psychology","score_opus":0.053492707641162304,"score_gpt":0.42766334640486187,"score_spread":0.37417063876369955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901429777","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45307928,0.00020971148,0.5380644,0.00664218,0.0017848356,0.000097757256,0.0000022382212,0.00004119777,0.00007834695],"genre_scores_gemma":[0.35386923,0.000021762133,0.64465344,0.00048267434,0.0009185776,0.0000063054576,8.693737e-7,0.000011421484,0.000035741636],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9979442,0.00012541859,0.0007202434,0.00035862654,0.00053006527,0.00032147573],"domain_scores_gemma":[0.9974669,0.0005295207,0.00059710146,0.00040084886,0.00093258795,0.00007300541],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017587323,0.00017889368,0.00028511765,0.00060970784,0.00012107429,0.00026917335,0.0030646292,0.00021588724,0.000040035186],"category_scores_gemma":[0.0014586169,0.0001331601,0.00012342067,0.00033166356,0.00011863025,0.00091245194,0.00049107755,0.0005843984,0.000009031238],"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":[0.00012656774,0.000048552614,0.00228841,0.0000022264448,0.000028413066,0.00006009173,0.00021145186,0.000037813585,0.18967968,0.00018295879,0.000104252016,0.8072296],"study_design_scores_gemma":[0.0011004857,0.0007593477,0.0013314146,0.0002888394,0.0000135358105,0.00051436847,0.00012977589,0.025530027,0.8920302,0.075923786,0.00220856,0.00016969861],"about_ca_topic_score_codex":0.000046347308,"about_ca_topic_score_gemma":0.000043225125,"teacher_disagreement_score":0.8070599,"about_ca_system_score_codex":0.00014850988,"about_ca_system_score_gemma":0.00016944799,"threshold_uncertainty_score":0.5694894},"labels":[],"label_agreement":null},{"id":"W2982012035","doi":"10.1007/s10772-019-09642-5","title":"Maximum entropy PLDA for robust speaker recognition under speech coding distortion","year":2019,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and Audio Processing","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":"Université de Moncton","funders":"","keywords":"Computer science; Speech recognition; TIMIT; Robustness (evolution); Artificial intelligence; Pattern recognition (psychology); Hidden Markov model","score_opus":0.021086434745969065,"score_gpt":0.263887749614766,"score_spread":0.24280131486879697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2982012035","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31563005,0.00014705719,0.6699391,0.01071779,0.002856176,0.00016240761,0.0000062872928,0.00010621892,0.0004349017],"genre_scores_gemma":[0.61068445,0.00008910765,0.3878233,0.0004658403,0.00060133677,0.0000053229573,0.000010020857,0.00001995313,0.00030066277],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99834114,0.000017763048,0.00055712106,0.00028168736,0.0005247849,0.00027748596],"domain_scores_gemma":[0.9979651,0.00007982938,0.00067181373,0.00021732796,0.0010059752,0.000059976323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041065365,0.00015654168,0.0002470798,0.0007885654,0.00006152739,0.00017367315,0.0012835583,0.0001796969,0.000100642916],"category_scores_gemma":[0.0001739134,0.00014533549,0.00014978136,0.00032338806,0.000057633766,0.0008721648,0.00016738694,0.00034117379,0.000103806364],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001305783,0.00014026591,0.0032513575,0.000021731283,0.00019143442,0.00016440783,0.000068052446,0.00019185724,0.08508002,0.0058036754,0.0011567378,0.9037999],"study_design_scores_gemma":[0.0024918932,0.0004679186,0.0007582408,0.00031006048,0.000030088624,0.0031296841,0.00022208774,0.0023197187,0.7548128,0.22295094,0.012143517,0.00036308417],"about_ca_topic_score_codex":0.000003923715,"about_ca_topic_score_gemma":0.0000053746853,"teacher_disagreement_score":0.9034368,"about_ca_system_score_codex":0.00030483198,"about_ca_system_score_gemma":0.00012042692,"threshold_uncertainty_score":0.59266096},"labels":[],"label_agreement":null},{"id":"W3007770218","doi":"10.1007/s10772-020-09688-w","title":"Low-complexity disordered speech quality estimation","year":2020,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":1,"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 du Québec en Outaouais; Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Speech recognition; Quality (philosophy); Estimation; Artificial intelligence","score_opus":0.03829898257176356,"score_gpt":0.3238917484867665,"score_spread":0.28559276591500293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3007770218","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31963035,0.00015119318,0.58518153,0.09358549,0.0006784578,0.00006573751,0.000004028248,0.00019553833,0.00050765823],"genre_scores_gemma":[0.6732583,0.00002643279,0.32557613,0.0008802302,0.00023401447,9.978269e-7,0.0000018051038,0.000007257375,0.000014844246],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9980585,0.000039279395,0.0007081537,0.0002600418,0.00071672257,0.00021732702],"domain_scores_gemma":[0.99812746,0.000058398327,0.0007148446,0.00022274286,0.00076578517,0.000110773886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003742287,0.00014980645,0.00028334654,0.00039378591,0.000064886786,0.00017500452,0.0024765756,0.00013564412,0.000058427664],"category_scores_gemma":[0.00086347165,0.00013812515,0.00011846371,0.0005914504,0.0001431242,0.0008244732,0.000371155,0.00045795797,0.00006602907],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053578704,0.000111604364,0.0020493818,0.000018124747,0.000074506584,0.0003286507,0.00022631121,0.00010172859,0.033811335,0.014081325,0.0006012202,0.94854224],"study_design_scores_gemma":[0.0014085737,0.0002779364,0.0020873942,0.00009879944,0.00001075205,0.0011246417,0.00016620684,0.005885327,0.7979011,0.18734412,0.0033973749,0.00029778687],"about_ca_topic_score_codex":0.000008335094,"about_ca_topic_score_gemma":0.00000589792,"teacher_disagreement_score":0.94824445,"about_ca_system_score_codex":0.0000968486,"about_ca_system_score_gemma":0.00015555392,"threshold_uncertainty_score":0.56325805},"labels":[],"label_agreement":null},{"id":"W3013233519","doi":"10.1007/s10772-020-09697-9","title":"Correction to: Low-complexity disordered speech quality estimation","year":2020,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and Audio Processing","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 du Québec en Outaouais; Western University","funders":"","keywords":"Mistake; Spelling; Computer science; Estimation; Quality (philosophy); Speech recognition; Artificial intelligence; Linguistics; Epistemology; Philosophy; Law; Management","score_opus":0.03186906875116981,"score_gpt":0.3246419416956319,"score_spread":0.2927728729444621,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013233519","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24893871,0.000060913386,0.67428017,0.0733834,0.0025661439,0.00008212612,0.0000026439823,0.00019127893,0.00049465086],"genre_scores_gemma":[0.7198383,0.000012659248,0.27855286,0.0012445069,0.00029874858,0.0000017281814,0.0000017812799,0.000007925086,0.000041485408],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9981626,0.00003897941,0.00065144873,0.00027412412,0.0006657485,0.00020709132],"domain_scores_gemma":[0.9981924,0.00007581103,0.0005587066,0.00020072643,0.00083670486,0.0001356286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036521352,0.00014404557,0.00025771724,0.00049022783,0.00007114357,0.0001779779,0.0018829657,0.00010277676,0.000044353557],"category_scores_gemma":[0.0015773005,0.00013779075,0.00010168175,0.0007889681,0.00007828502,0.00069540954,0.00032979305,0.0004449971,0.00009304528],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007487811,0.00008723344,0.0019971132,0.000010108075,0.00005008824,0.00014586105,0.00027966715,0.00037758012,0.034547947,0.0030751282,0.0033486616,0.95600575],"study_design_scores_gemma":[0.0013444385,0.0005561989,0.0055439346,0.00020733463,0.0000131051775,0.0014385356,0.00026952484,0.01839743,0.8956306,0.070458256,0.005733466,0.00040717673],"about_ca_topic_score_codex":0.000021109143,"about_ca_topic_score_gemma":0.000018070004,"teacher_disagreement_score":0.95559853,"about_ca_system_score_codex":0.00014248725,"about_ca_system_score_gemma":0.00014482928,"threshold_uncertainty_score":0.56189436},"labels":[],"label_agreement":null},{"id":"W4318350603","doi":"10.1007/s10772-023-10018-z","title":"Plain-to-clear speech video conversion for enhanced intelligibility","year":2023,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and Audio Processing","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":"Social Sciences and Humanities Research Council of Canada; Simon Fraser University","keywords":"Computer science; Intelligibility (philosophy); Speech recognition; Image warping; Perception; Artificial intelligence; Psychology","score_opus":0.01663494020198911,"score_gpt":0.30902520948653456,"score_spread":0.2923902692845454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318350603","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5341864,0.00006816676,0.43235236,0.030217038,0.0022984357,0.00019428582,0.0000066580606,0.00031856872,0.00035803847],"genre_scores_gemma":[0.7956652,0.000074132375,0.20283908,0.00068919576,0.0003644809,0.0000069701855,0.0000026183711,0.00001575364,0.00034254897],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99820787,0.000018459015,0.00055908575,0.00033098695,0.0005562542,0.00032734754],"domain_scores_gemma":[0.99785817,0.00020018365,0.00037068131,0.00029914876,0.0011664954,0.000105328894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079533266,0.00014757278,0.0002635168,0.0013803256,0.00008301856,0.00012953857,0.0024523083,0.00016445908,0.000030759085],"category_scores_gemma":[0.0010733894,0.00013626282,0.00014532471,0.0010156011,0.00008439102,0.00047076243,0.00048398922,0.0003152281,0.00021625236],"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":[0.00020750618,0.000071827635,0.0004942792,0.000017936129,0.00011083081,0.00029472754,0.0002253805,0.00008585022,0.20506494,0.0038539532,0.0057785036,0.7837943],"study_design_scores_gemma":[0.0006242272,0.00036384253,0.00014094442,0.00009390997,0.0000055746555,0.0003698582,0.00014221038,0.0006171866,0.92383367,0.04009324,0.03357654,0.00013879221],"about_ca_topic_score_codex":0.0000037456941,"about_ca_topic_score_gemma":0.000004239607,"teacher_disagreement_score":0.78365546,"about_ca_system_score_codex":0.00018680406,"about_ca_system_score_gemma":0.00014517743,"threshold_uncertainty_score":0.5556637},"labels":[],"label_agreement":null},{"id":"W4324027600","doi":"10.1007/s10772-023-10027-y","title":"The perception of artificial-intelligence (AI) based synthesized speech in younger and older adults","year":2023,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Hearing Loss and Rehabilitation","field":"Neuroscience","cited_by":53,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Baycrest Hospital; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Intelligibility (philosophy); Speech perception; Computer science; Perception; Speech recognition; Speech processing; Voice activity detection; Speech synthesis; Audiology; Masking (illustration); Psychology; Medicine","score_opus":0.021525813469131787,"score_gpt":0.31455021828447377,"score_spread":0.293024404815342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4324027600","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9802378,0.000029352934,0.0007697453,0.018321982,0.00045363174,0.00011899568,0.0000032540588,0.000029298806,0.00003594884],"genre_scores_gemma":[0.9984431,0.00020525679,0.0011459187,0.0001003014,0.00006431869,0.0000044116373,3.4053133e-7,0.000008024145,0.000028281273],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986894,0.0000678256,0.000533822,0.00015717103,0.00040563004,0.00014614077],"domain_scores_gemma":[0.99871266,0.0006202406,0.00023667548,0.000119872086,0.00028645564,0.000024101277],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073530135,0.00007674777,0.00014569312,0.00072876975,0.00005028043,0.000034011657,0.00039730407,0.0001121491,0.00002557982],"category_scores_gemma":[0.0023490945,0.000054194123,0.000056547615,0.0004925544,0.0003041324,0.00014548807,0.000059722526,0.00028407495,0.000017382243],"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":[0.00019440768,0.00007029279,0.0020632427,0.000010487606,0.0000067455358,0.000092700655,0.0001892229,0.00007605443,0.46956122,0.0060246754,0.000019746825,0.5216912],"study_design_scores_gemma":[0.00075569196,0.00042919867,0.109710835,0.0007424982,0.000013403222,0.00051607966,0.0033940156,0.021655846,0.79085845,0.071210206,0.00050093315,0.0002128703],"about_ca_topic_score_codex":0.000028301625,"about_ca_topic_score_gemma":0.000009572533,"teacher_disagreement_score":0.52147835,"about_ca_system_score_codex":0.00006487663,"about_ca_system_score_gemma":0.00005716615,"threshold_uncertainty_score":0.28122553},"labels":[],"label_agreement":null},{"id":"W4378231186","doi":"10.1007/s10772-023-10030-3","title":"Mouth2Audio: intelligible audio synthesis from videos with distinctive vowel articulation","year":2023,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"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; Simon Fraser University","keywords":"Computer science; Speech recognition; Formant; Spectrogram; Manner of articulation; Landmark; Vowel; Articulation (sociology); Artificial intelligence","score_opus":0.009332505270161847,"score_gpt":0.25164903389289384,"score_spread":0.24231652862273198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378231186","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6299495,0.00010525726,0.35298362,0.015558215,0.00068669097,0.000065835666,0.000008379939,0.00029796737,0.00034447951],"genre_scores_gemma":[0.9127269,0.00004541699,0.08674057,0.00011296808,0.0002553866,0.000006857828,0.000002904837,0.0000129667305,0.00009603897],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983831,0.000025045787,0.00044211448,0.00026604783,0.00064423005,0.00023943234],"domain_scores_gemma":[0.9981897,0.00023445375,0.0005034496,0.00024933217,0.00075693656,0.00006616097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028504623,0.00015089239,0.0002441568,0.0010019637,0.000070703674,0.00016809792,0.0014629991,0.00012072139,0.000039739793],"category_scores_gemma":[0.00048708156,0.00011870521,0.0000817923,0.0009942516,0.00011554428,0.0006971493,0.00026683725,0.0003153616,0.00014761472],"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":[0.0001587786,0.00011579993,0.01938266,0.0000069455773,0.0005636278,0.0019143306,0.00057992653,0.000857681,0.047482673,0.0027470244,0.0013041334,0.9248864],"study_design_scores_gemma":[0.0005555872,0.00016591475,0.009741265,0.00028479012,0.00003345281,0.00078395737,0.00030867523,0.0032622823,0.9078937,0.074584246,0.0021471947,0.00023893871],"about_ca_topic_score_codex":0.00002302739,"about_ca_topic_score_gemma":0.000021495605,"teacher_disagreement_score":0.9246475,"about_ca_system_score_codex":0.00014418062,"about_ca_system_score_gemma":0.00011964867,"threshold_uncertainty_score":0.4840658},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29438448,0.000056110406,0.6832986,0.01892824,0.002364073,0.0002768076,0.000037920057,0.00046541434,0.0001883597],"genre_scores_gemma":[0.92135566,0.0000366927,0.078125685,0.00010343066,0.00019346585,0.000021994061,0.000011996741,0.000014245533,0.00013680129],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986997,0.000027979859,0.000464781,0.00022815625,0.00040416847,0.00017518605],"domain_scores_gemma":[0.99821573,0.00019342279,0.00040206636,0.00020194409,0.00092645554,0.000060365477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046116035,0.00012067762,0.00021658884,0.0011735887,0.000070471644,0.0001216444,0.0008685119,0.0001488878,0.000019247818],"category_scores_gemma":[0.0002633495,0.00010990888,0.00012631243,0.00047242813,0.000062825406,0.0002712327,0.00008216001,0.0001566538,0.00005577456],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024847014,0.0001948172,0.0102312565,0.00010680648,0.00049861305,0.00053480593,0.00012695498,0.000111559806,0.04920394,0.04741565,0.0036130878,0.887714],"study_design_scores_gemma":[0.018497419,0.0015110481,0.051767968,0.002071849,0.00026950767,0.007869053,0.0037462828,0.5049473,0.2740705,0.035527807,0.09776163,0.001959623],"about_ca_topic_score_codex":0.0000053359904,"about_ca_topic_score_gemma":0.000003883126,"teacher_disagreement_score":0.8857544,"about_ca_system_score_codex":0.000140732,"about_ca_system_score_gemma":0.00009189431,"threshold_uncertainty_score":0.4481954},"labels":[],"label_agreement":null},{"id":"W4400357331","doi":"10.1007/s10772-024-10120-w","title":"Pathological voice classification system based on CNN-BiLSTM network using speech enhancement and multi-stream approach","year":2024,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and Audio Processing","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; Speech recognition; Artificial intelligence; Voice activity detection; Natural language processing; Speech processing","score_opus":0.037110030700195654,"score_gpt":0.30198433189472046,"score_spread":0.2648743011945248,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400357331","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12265327,0.00097137695,0.8706538,0.0031528906,0.0014154804,0.00012530744,0.0000025702204,0.00022818994,0.000797124],"genre_scores_gemma":[0.6005708,0.000032961754,0.39892623,0.00012098278,0.0003100552,0.0000036484455,0.0000015572722,0.0000086278515,0.000025116427],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99812144,0.0000541821,0.0005534857,0.00041373484,0.0005850908,0.0002720419],"domain_scores_gemma":[0.9988575,0.00009722728,0.00034435975,0.00024423006,0.00038416684,0.00007254264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007168286,0.0001860888,0.00025365295,0.000691432,0.00009341835,0.0003371354,0.0010627566,0.00021744758,0.0000061656106],"category_scores_gemma":[0.000104469385,0.00015152879,0.00008855407,0.0005596077,0.0001165528,0.00036335888,0.00018311387,0.00053253246,0.000013789743],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007512679,0.00036292127,0.003081065,0.0001068987,0.00017030387,0.0018103595,0.0001015771,0.0014595309,0.0676735,0.015874295,0.00031001683,0.9089744],"study_design_scores_gemma":[0.0007938203,0.00038028078,0.00046388534,0.0009936019,0.000035419547,0.004878587,0.0002668042,0.87936145,0.10790545,0.0027318166,0.0018990393,0.00028983483],"about_ca_topic_score_codex":0.0000027075282,"about_ca_topic_score_gemma":6.915044e-7,"teacher_disagreement_score":0.90868455,"about_ca_system_score_codex":0.00033064693,"about_ca_system_score_gemma":0.00015303383,"threshold_uncertainty_score":0.61791646},"labels":[],"label_agreement":null},{"id":"W586724576","doi":"10.1007/s10772-015-9280-x","title":"Mobile spoken dialogue system using parser dependencies and ontology","year":2015,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and dialogue systems","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":"Université de Moncton; Université du Québec à Montréal","funders":"","keywords":"Computer science; Parsing; Sentence; Natural language processing; Mobile phone; Android (operating system); Artificial intelligence; Spoken language; Dependency (UML)","score_opus":0.029085445274014795,"score_gpt":0.27848607373452006,"score_spread":0.24940062846050526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W586724576","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8807015,0.0024028674,0.10843276,0.0012746255,0.005604409,0.00016988648,0.000007958247,0.00017810205,0.001227928],"genre_scores_gemma":[0.95030826,0.000033480646,0.04915652,0.00006335302,0.00038634092,0.000003933204,9.421356e-7,0.0000079730125,0.000039171915],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"case_report","domain_scores_codex":[0.9984827,0.00005883444,0.000523517,0.00020992136,0.00049552834,0.00022947756],"domain_scores_gemma":[0.9982297,0.000052718337,0.0004555621,0.0002464061,0.0008819017,0.00013372014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006347808,0.00013585994,0.00031724642,0.0007707799,0.0000368979,0.00010025555,0.0014213674,0.00021361226,0.0000026791809],"category_scores_gemma":[0.00022048655,0.00011628197,0.000064367945,0.0002498435,0.00013151554,0.00047109477,0.00037228692,0.0002550818,0.000021402693],"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":[0.0005429697,0.0004557042,0.1159052,0.000087330416,0.001387358,0.017123733,0.004302188,0.0008265605,0.04044711,0.4658716,0.005421596,0.34762865],"study_design_scores_gemma":[0.017121159,0.006441587,0.003907423,0.001317259,0.00022920023,0.37683105,0.018911282,0.03920465,0.18126234,0.20577796,0.14649048,0.0025055977],"about_ca_topic_score_codex":0.00013480554,"about_ca_topic_score_gemma":0.00004823829,"teacher_disagreement_score":0.35970733,"about_ca_system_score_codex":0.00025910724,"about_ca_system_score_gemma":0.00026266713,"threshold_uncertainty_score":0.4741841},"labels":[],"label_agreement":null}]}