{"meta":{"query_hash":"04728ae03c4c","filters":{"venue":"Speech Communication"},"cohort_total":46,"direct_labels_cover":0,"predictions_cover":46,"exported":46,"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/04728ae03c4c","api":"https://metacan.xera.ac/api/v1/cohort?venue=Speech+Communication"},"results":[{"id":"W1964469912","doi":"10.1016/s0167-6393(02)00071-7","title":"Describing the emotional states that are expressed in speech","year":2003,"lang":"en","type":"article","venue":"Speech Communication","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":603,"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":"Cognitive psychology; Relation (database); Psychology; Arousal; Reductionism; Control (management); Cognitive appraisal; Emotion classification; Computer science; Cognitive science; Cognition; Social psychology; Artificial intelligence; Epistemology","score_opus":0.12922220869990647,"score_gpt":0.3216646469651708,"score_spread":0.1924424382652643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964469912","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":[0.37536544,0.0228036,0.3255789,0.0054552197,0.0037927937,0.00030484947,0.0020384414,0.001043462,0.26361728],"genre_scores_gemma":[0.9357519,0.008004852,0.032699656,0.0009914354,0.0008899213,0.00016872791,0.0009585546,0.00012862367,0.020406304],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.999928,0.000028780183,0.000007642575,0.000010613984,0.000014245225,0.000010708283],"domain_scores_gemma":[0.99960464,0.0002550781,0.00004600222,0.000022961209,0.000053752305,0.000017573939],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002495614,0.00043245024,0.00012221432,0.00040495064,0.00034463333,0.0013806071,0.00022547522,0.0006474412,0.0022479468],"category_scores_gemma":[0.0013317708,0.00006739388,0.00018356006,0.0004016891,0.0004809723,0.0008270071,0.0002560223,0.0005817686,0.00081835495],"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":[0.001211,0.00014480841,0.0110774785,0.001907424,0.000104866405,0.0031173662,0.022489276,0.0061479984,0.24852505,0.2074394,0.029286208,0.4685491],"study_design_scores_gemma":[0.00006917164,0.0008887461,0.12785503,0.0020383159,0.00039816162,0.014008834,0.02433158,0.0545734,0.12528442,0.16714658,0.4830977,0.00030811704],"about_ca_topic_score_codex":0.00047192952,"about_ca_topic_score_gemma":0.00070883054,"teacher_disagreement_score":0.0022479468,"about_ca_system_score_codex":0.00017845735,"about_ca_system_score_gemma":0.00013400792,"threshold_uncertainty_score":0.007520199},"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":"W1971872909","doi":"10.1016/j.specom.2015.02.001","title":"Objective measures for quality assessment of noise-suppressed speech","year":2015,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":9,"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; University of Toronto; University Health Network","funders":"Swenson College of Science and Engineering, University of Minnesota Duluth; Natural Science Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Computer science; Speech recognition; Speech enhancement; Distortion (music); PESQ; Noise (video); Active listening; Residual; PSQM; Speech processing; Speech coding; Quality (philosophy); Background noise; Noise reduction; Speech perception; Voice activity detection; Artificial intelligence; Perception; Algorithm; Psychology; Telecommunications","score_opus":0.10011630823513624,"score_gpt":0.3762995965308839,"score_spread":0.2761832882957477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971872909","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":[0.67109704,0.011783523,0.2953502,0.0001639333,0.00028974153,0.0015467367,0.006368599,0.00061036943,0.012789873],"genre_scores_gemma":[0.86970896,0.0045282976,0.11598758,0.00021866978,0.0002502203,0.001082668,0.0037360182,0.0002073782,0.0042801932],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99719065,0.0006292408,0.00028389491,0.0002429053,0.001572152,0.00008120859],"domain_scores_gemma":[0.99414873,0.001962464,0.0008889086,0.00029777634,0.0024542336,0.0002478785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025760124,0.0007842582,0.00060218794,0.0018104857,0.00027872794,0.00092744373,0.0004691037,0.0007553732,0.0024328504],"category_scores_gemma":[0.00809373,0.00018498077,0.00040967934,0.0009666484,0.000302217,0.0007417755,0.00063683395,0.000536992,0.00065463386],"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":[0.007409317,0.0011612636,0.11246168,0.0034067666,0.00086836505,0.00038245542,0.00096670096,0.005451837,0.46961874,0.001655125,0.0029592277,0.39365858],"study_design_scores_gemma":[0.00056130893,0.011504237,0.6695083,0.000677986,0.0016076718,0.0037184118,0.0013894425,0.033421263,0.26336676,0.0020182866,0.01189228,0.00033409707],"about_ca_topic_score_codex":0.00088226376,"about_ca_topic_score_gemma":0.0018412102,"teacher_disagreement_score":0.0025760124,"about_ca_system_score_codex":0.0002968903,"about_ca_system_score_gemma":0.00039079867,"threshold_uncertainty_score":0.013623416},"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":"W2011460727","doi":"10.1016/j.specom.2010.04.001","title":"Do nonnative listeners benefit as much as native listeners from spatial cues that release speech from masking?","year":2010,"lang":"en","type":"article","venue":"Speech Communication","topic":"Hearing Loss and Rehabilitation","field":"Neuroscience","cited_by":35,"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 Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Masking (illustration); Speech perception; Speech recognition; Vocabulary; Phonetics; Computer science; Psychology; Audiology; Linguistics; Perception; Medicine","score_opus":0.03139239909841487,"score_gpt":0.3060649651961495,"score_spread":0.27467256609773466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011460727","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":[0.99343735,0.0008604249,0.0009895929,0.00058349327,0.00008141609,0.000008203896,0.000088168985,0.000024306737,0.0039270706],"genre_scores_gemma":[0.9976089,0.0006544884,0.00041576824,0.00029858798,0.000053353557,0.0000066251905,0.00005444733,0.000010668126,0.000897039],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9998677,0.00001768736,0.0000072992943,0.000031604108,0.000039899514,0.000035839137],"domain_scores_gemma":[0.9993123,0.00028501003,0.00014575571,0.00007273091,0.000085213695,0.000098966106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042336946,0.00024864438,0.0002767177,0.00014593283,0.00015587962,0.00058026396,0.00020295387,0.0008086494,0.0025598905],"category_scores_gemma":[0.0025849335,0.00019391284,0.00012513426,0.00006372295,0.0005595493,0.0011728001,0.00027493865,0.0002958386,0.0006834229],"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":[0.007928092,0.0005952256,0.088202894,0.0006398241,0.00031396264,0.0015548526,0.0026910317,0.00038330324,0.6841307,0.0016821276,0.002840857,0.20903705],"study_design_scores_gemma":[0.00023909901,0.0012951953,0.90804756,0.00008451003,0.00035968158,0.0041491236,0.006302515,0.0015253673,0.06655755,0.0071191774,0.004275812,0.000044389697],"about_ca_topic_score_codex":0.0006125038,"about_ca_topic_score_gemma":0.0014021023,"teacher_disagreement_score":0.0025598905,"about_ca_system_score_codex":0.00007018055,"about_ca_system_score_gemma":0.00019523209,"threshold_uncertainty_score":0.008563697},"labels":[],"label_agreement":null},{"id":"W2012782795","doi":"10.1016/j.specom.2004.09.010","title":"Recognition of affective prosody by speakers of English as a first or foreign language","year":2005,"lang":"en","type":"article","venue":"Speech Communication","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":35,"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 Western Hospital; University of Toronto","funders":"","keywords":"Prosody; Intonation (linguistics); First language; Psychology; Linguistics; Perception; Foreign language; English as a foreign language; Computer science; Speech recognition","score_opus":0.0246555604296593,"score_gpt":0.3149615319571959,"score_spread":0.29030597152753657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012782795","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":[0.9982449,0.000054963206,0.00013649007,0.000025044523,0.000024730118,0.000005139285,0.000040659455,0.0000066107705,0.0014614327],"genre_scores_gemma":[0.9978288,0.00008800869,0.00019597236,0.00006438417,0.000020485353,0.000011137714,0.00013934489,0.000010836157,0.0016410061],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99989676,0.000030974465,0.0000061668466,0.000020539988,0.00002383078,0.000021624817],"domain_scores_gemma":[0.99932134,0.00035749984,0.000087376065,0.000034507168,0.00009668771,0.00010266434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032606316,0.00021931759,0.00023826554,0.00014229502,0.00021248056,0.00077850616,0.00010523993,0.00030464146,0.00247089],"category_scores_gemma":[0.0021059245,0.00011341711,0.00014509365,0.00006489189,0.00016926302,0.00030098716,0.0003052779,0.00039600703,0.0005605173],"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":[0.0072057564,0.0002941276,0.110139005,0.00015420541,0.00014781443,0.0006269966,0.0070007853,0.000110199435,0.84506637,0.00026759357,0.00093863386,0.02804858],"study_design_scores_gemma":[0.000088284156,0.0012006117,0.9559788,0.000020705485,0.00011691479,0.0011931552,0.0037830481,0.0016225426,0.03479177,0.00016163486,0.0010098077,0.000032603577],"about_ca_topic_score_codex":0.0007384042,"about_ca_topic_score_gemma":0.0010198904,"teacher_disagreement_score":0.00247089,"about_ca_system_score_codex":0.00007892784,"about_ca_system_score_gemma":0.00008128459,"threshold_uncertainty_score":0.0082659125},"labels":[],"label_agreement":null},{"id":"W2014925606","doi":"10.1016/j.specom.2013.04.001","title":"Objective speech intelligibility measurement for cochlear implant users in complex listening environments","year":2013,"lang":"en","type":"article","venue":"Speech Communication","topic":"Hearing Loss and Rehabilitation","field":"Neuroscience","cited_by":46,"is_retracted":false,"has_abstract":false,"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":"National Institute on Deafness and Other Communication Disorders; Natural Sciences and Engineering Research Council of Canada","keywords":"Active listening; Cochlear implant; Intelligibility (philosophy); Reverberation; Computer science; Speech recognition; Audiology; Speech perception; Perception; Acoustics; Psychology; Medicine","score_opus":0.09210451389678387,"score_gpt":0.31980523701483604,"score_spread":0.22770072311805217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014925606","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":[0.99287885,0.0002996593,0.004427548,0.000017331948,0.0000121443645,0.0000617842,0.00040307458,0.000056794863,0.0018427473],"genre_scores_gemma":[0.9937185,0.00025846227,0.003896139,0.000041661973,0.000016005026,0.00009175731,0.00039450257,0.000035182242,0.0015478571],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9992706,0.00013803708,0.00010948202,0.00013621271,0.0002720942,0.00007356629],"domain_scores_gemma":[0.99777466,0.001180973,0.0001936006,0.00008529567,0.0005954544,0.00017003871],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006831644,0.00082088157,0.00044154027,0.0005467969,0.00036770085,0.00072067074,0.00033675498,0.00063428143,0.003383632],"category_scores_gemma":[0.0041432283,0.0001911918,0.00031273387,0.00028636714,0.00032188426,0.00063784595,0.0007544211,0.0002417693,0.0008031945],"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":[0.019941442,0.0009177886,0.2135455,0.0013282929,0.0002489216,0.00081495434,0.0034742514,0.0010295688,0.58595026,0.0002199548,0.00071537285,0.17181364],"study_design_scores_gemma":[0.00017962969,0.010025072,0.7725749,0.00007796618,0.00043748933,0.0046806904,0.0020797346,0.004422345,0.20341745,0.00020520674,0.0017736154,0.0001258623],"about_ca_topic_score_codex":0.0009853556,"about_ca_topic_score_gemma":0.0014261391,"teacher_disagreement_score":0.003383632,"about_ca_system_score_codex":0.00016206405,"about_ca_system_score_gemma":0.00032587143,"threshold_uncertainty_score":0.011319399},"labels":[],"label_agreement":null},{"id":"W2015926323","doi":"10.1016/s0167-6393(00)00081-9","title":"Speech enhancement using fourth-order cumulants and optimum filters in the subband domain","year":2002,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech and Audio Processing","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":"Carleton University","funders":"","keywords":"Speech recognition; Speech enhancement; Computer science; Noise (video); Frequency domain; Gaussian noise; Noise reduction; Speech processing; Spectrogram; Linear predictive coding; Mathematics; Algorithm; Artificial intelligence","score_opus":0.0416666573999727,"score_gpt":0.2793254558020496,"score_spread":0.2376587984020769,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015926323","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023569144,0.0006799663,0.9726846,0.00014433231,0.00007124922,0.00001940577,0.000039450133,0.0003083591,0.002483505],"genre_scores_gemma":[0.16817322,0.0012245114,0.8230682,0.00010903901,0.00015894098,0.000047358128,0.00015924837,0.00018482702,0.006874657],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99970007,0.00007429513,0.000017446991,0.00003913843,0.00013559971,0.000033537333],"domain_scores_gemma":[0.99922884,0.0004206312,0.0000712454,0.000092456736,0.00016115024,0.000025712632],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053614506,0.0006609115,0.00064662343,0.00066864246,0.00028792568,0.00071470503,0.00034575272,0.0007272692,0.0023588908],"category_scores_gemma":[0.0017664555,0.0002765099,0.00074494735,0.0005075519,0.00042631212,0.0010303687,0.0003951024,0.0006988305,0.0008343498],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013271134,0.00021163559,0.00091332063,0.00041441515,0.00015145686,0.00020315815,0.00019304882,0.076823674,0.32313406,0.04953032,0.0030477853,0.5440501],"study_design_scores_gemma":[0.00005901329,0.00017092402,0.00228001,0.000046068642,0.00011794055,0.0003942755,0.00003452926,0.8343133,0.14280573,0.011317926,0.008405898,0.000054429765],"about_ca_topic_score_codex":0.00076271425,"about_ca_topic_score_gemma":0.0020551914,"teacher_disagreement_score":0.0023588908,"about_ca_system_score_codex":0.0003793057,"about_ca_system_score_gemma":0.00047566838,"threshold_uncertainty_score":0.007891238},"labels":[],"label_agreement":null},{"id":"W2021788671","doi":"10.1016/s0167-6393(01)00012-7","title":"Auditory, visual and audiovisual clear speech","year":2002,"lang":"en","type":"article","venue":"Speech Communication","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":58,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre des Aînés Côte-des-Neiges; Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Intelligibility (philosophy); Perception; Audiology; Stimulus (psychology); Speech recognition; Speech perception; Psychology; Modality (human–computer interaction); Modalities; Vowel; Computer science; Cognitive psychology; Artificial intelligence; Medicine","score_opus":0.044273739608320484,"score_gpt":0.3575666027056751,"score_spread":0.3132928630973546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021788671","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":[0.89278275,0.017689608,0.007291924,0.0009525521,0.00074566645,0.000099932186,0.0006081894,0.00008584496,0.07974351],"genre_scores_gemma":[0.9755434,0.00407454,0.0016440406,0.00035008186,0.00035245882,0.000050391376,0.00032406749,0.000036506335,0.017624412],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99932826,0.00014783103,0.000046331195,0.000101923826,0.00030081611,0.00007485207],"domain_scores_gemma":[0.9962392,0.0021531805,0.00030519962,0.00024652164,0.00066107116,0.00039488915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001062068,0.0004776366,0.00026558887,0.0010255176,0.0005093366,0.0016378252,0.00046735813,0.0009424858,0.018636333],"category_scores_gemma":[0.007669659,0.0003571255,0.00022118325,0.00032447884,0.0014066971,0.0022361053,0.0012540526,0.0007673955,0.0014645569],"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":[0.03043938,0.00087800296,0.030537125,0.003367142,0.00033134207,0.0024556406,0.005776777,0.0011560575,0.53540665,0.0284666,0.0062153814,0.3549699],"study_design_scores_gemma":[0.0007929071,0.0050966246,0.8391783,0.00047723477,0.00057036744,0.0069112573,0.010328996,0.002192562,0.07199462,0.038459074,0.02384046,0.0001575674],"about_ca_topic_score_codex":0.0017061229,"about_ca_topic_score_gemma":0.0044234446,"teacher_disagreement_score":0.018636333,"about_ca_system_score_codex":0.00040988618,"about_ca_system_score_gemma":0.0007159048,"threshold_uncertainty_score":0.06234479},"labels":[],"label_agreement":null},{"id":"W2028124797","doi":"10.1016/j.specom.2012.08.007","title":"Multitaper MFCC and PLP features for speaker verification using i-vectors","year":2012,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":91,"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","funders":"National Institute of Standards and Technology","keywords":"Multitaper; Mel-frequency cepstrum; Computer science; NIST; Speech recognition; Pattern recognition (psychology); Cepstrum; Speaker recognition; Artificial intelligence; Feature extraction","score_opus":0.03390941946555964,"score_gpt":0.2998207171212208,"score_spread":0.2659112976556612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028124797","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0710517,0.0018972938,0.91378534,0.00022676721,0.00021486274,0.0001599411,0.0013145085,0.0058813305,0.005468351],"genre_scores_gemma":[0.43989554,0.0013669834,0.5414621,0.00013676634,0.00017108466,0.00027525245,0.0046079564,0.0005263121,0.011557881],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99938226,0.00013718159,0.000056999033,0.00011723606,0.0002271194,0.00007923795],"domain_scores_gemma":[0.9991406,0.00026093892,0.000065648135,0.00016529346,0.00032627696,0.000041243326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006205595,0.00084545085,0.00067318603,0.0009052348,0.00044761377,0.00068908953,0.00069818215,0.0009408582,0.008409541],"category_scores_gemma":[0.0019204436,0.00029708337,0.000549058,0.00077244727,0.00019818533,0.0012064334,0.00074937684,0.00070759107,0.006367714],"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":[0.00083910784,0.00012182139,0.0006279353,0.00016572828,0.000044096472,0.00008726698,0.00004650228,0.00316787,0.21330227,0.00095592317,0.0033616691,0.77727985],"study_design_scores_gemma":[0.00014274419,0.000774202,0.01357831,0.00010346593,0.00027943714,0.0008954371,0.0001768461,0.3657354,0.59954184,0.0017253378,0.016915204,0.00013179777],"about_ca_topic_score_codex":0.001633215,"about_ca_topic_score_gemma":0.0027257318,"teacher_disagreement_score":0.008409541,"about_ca_system_score_codex":0.00016097318,"about_ca_system_score_gemma":0.000481638,"threshold_uncertainty_score":0.028132677},"labels":[],"label_agreement":null},{"id":"W2030534537","doi":"10.1016/j.specom.2007.04.007","title":"Monaural speech segregation based on fusion of source-driven with model-driven techniques","year":2007,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Codebook; Speech recognition; Monaural; Source separation; Spectral envelope; Estimator; A priori and a posteriori; Speech coding; Algorithm; Artificial intelligence; Mathematics","score_opus":0.015078338960960162,"score_gpt":0.2599297186008326,"score_spread":0.2448513796398724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030534537","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010169406,0.00021596452,0.9877372,0.000052258983,0.00007036494,0.000022715674,0.00005426203,0.00091534486,0.000762375],"genre_scores_gemma":[0.3404439,0.0005933228,0.6537781,0.00015638363,0.00015420804,0.00009521589,0.0006867457,0.0005888223,0.0035033368],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99936825,0.00013267358,0.000039525563,0.00011657607,0.00028350702,0.000059405727],"domain_scores_gemma":[0.9992105,0.00027635533,0.000063403895,0.00011827345,0.00028340146,0.000048175556],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010937554,0.0011545857,0.001482551,0.0011888666,0.00037974585,0.0012764917,0.0008817964,0.0010833988,0.002142713],"category_scores_gemma":[0.0025401106,0.000663329,0.0013028571,0.00080831617,0.0002940945,0.0016711768,0.001398926,0.0010224112,0.0018316068],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001188177,0.00029315357,0.0013358657,0.00032429682,0.00029153153,0.0001751076,0.00014965581,0.120024495,0.23922946,0.005657399,0.0019921595,0.6293387],"study_design_scores_gemma":[0.000033305096,0.000078773526,0.00093078066,0.000017429324,0.00007129482,0.00017321312,0.00001513697,0.94764465,0.045308173,0.0037318424,0.0019557904,0.00003957032],"about_ca_topic_score_codex":0.0008931609,"about_ca_topic_score_gemma":0.0021333385,"teacher_disagreement_score":0.002142713,"about_ca_system_score_codex":0.0003380866,"about_ca_system_score_gemma":0.0006287702,"threshold_uncertainty_score":0.007168114},"labels":[],"label_agreement":null},{"id":"W2034149345","doi":"10.1016/j.specom.2010.05.005","title":"Discrete cosine transform particle filter speech enhancement","year":2010,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":10,"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; University of Ottawa; Innovation, Science and Economic Development Canada","funders":"Siemens","keywords":"Discrete cosine transform; Speech enhancement; Speech recognition; Computer science; Autoregressive model; Algorithm; Noise reduction; Filter (signal processing); Intelligibility (philosophy); Mathematics; Artificial intelligence; Computer vision; Statistics","score_opus":0.014379124667717466,"score_gpt":0.27041677189870006,"score_spread":0.2560376472309826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034149345","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012059551,0.0006913686,0.9796926,0.00031339962,0.0005839033,0.00008035031,0.00010961157,0.00081227755,0.005656946],"genre_scores_gemma":[0.23980097,0.0022146169,0.71193033,0.00057346537,0.00038884953,0.00016282978,0.00069914636,0.00036566207,0.043864097],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995498,0.0000566977,0.000022869523,0.00008330263,0.00025125634,0.000036023786],"domain_scores_gemma":[0.99937135,0.00014511478,0.000034677214,0.00009357804,0.0003352239,0.000020041094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005878082,0.0008074059,0.0006286926,0.00046349785,0.00035818643,0.0008482501,0.00037886412,0.0009452493,0.0047347033],"category_scores_gemma":[0.0017190735,0.00035138484,0.0005017694,0.00055635103,0.00029371624,0.0007772186,0.0006204945,0.0009878569,0.0026852053],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006576634,0.00016960641,0.0010959887,0.00022152429,0.00006889631,0.00023357967,0.00008762722,0.03341838,0.15159662,0.008099025,0.007975412,0.79637575],"study_design_scores_gemma":[0.00006326106,0.00028436803,0.00516535,0.000049350812,0.00012102341,0.0007466094,0.00005860297,0.78017235,0.17941989,0.0025030773,0.031365324,0.000050790306],"about_ca_topic_score_codex":0.0023728365,"about_ca_topic_score_gemma":0.0024494205,"teacher_disagreement_score":0.0047347033,"about_ca_system_score_codex":0.00029966974,"about_ca_system_score_gemma":0.00091622514,"threshold_uncertainty_score":0.01583916},"labels":[],"label_agreement":null},{"id":"W2045224822","doi":"10.1016/s0167-6393(02)00093-6","title":"Sensitivity to change in perception of speech","year":2003,"lang":"en","type":"article","venue":"Speech Communication","topic":"Hearing Loss and Rehabilitation","field":"Neuroscience","cited_by":95,"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 Institute on Deafness and Other Communication Disorders","keywords":"Perception; Coarticulation; Speech perception; Psychoacoustics; Modalities; Contrast (vision); Speech recognition; Computer science; Cognitive psychology; Neurophysiology; Stimulus (psychology); Auditory perception; Categorical perception; Psychology; Artificial intelligence; Neuroscience","score_opus":0.06925915415323883,"score_gpt":0.3367045598930625,"score_spread":0.26744540573982367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045224822","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":[0.99485505,0.00024000881,0.00092513993,0.00007320434,0.000050272898,0.00002850796,0.0001038768,0.00003148224,0.0036923531],"genre_scores_gemma":[0.9987023,0.00010331309,0.00020729912,0.000101455604,0.000020200932,0.000014324443,0.000088408575,0.0000150607575,0.0007475847],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99950886,0.00010949737,0.000036601792,0.00013333144,0.00014519207,0.00006645488],"domain_scores_gemma":[0.9963722,0.0022807356,0.00029973415,0.00031207397,0.0003701196,0.00036513543],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000707922,0.0002487397,0.0003320299,0.0006838786,0.00016049271,0.00044931503,0.00022457712,0.0005481147,0.003167251],"category_scores_gemma":[0.008292489,0.00026251274,0.00028374724,0.00017004338,0.00040682938,0.0003574031,0.0005911895,0.000784974,0.00031099038],"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":[0.010304309,0.0004392109,0.064247705,0.00026335317,0.0002210648,0.0014284427,0.0013389607,0.0011718401,0.8803101,0.00048576313,0.0006726001,0.039116576],"study_design_scores_gemma":[0.00008054581,0.0038584108,0.8995895,0.000041103092,0.00014960025,0.0041047586,0.0006430988,0.0020104237,0.08733131,0.00090385595,0.0012417204,0.000045693345],"about_ca_topic_score_codex":0.0011381404,"about_ca_topic_score_gemma":0.0004896447,"teacher_disagreement_score":0.003167251,"about_ca_system_score_codex":0.00026477373,"about_ca_system_score_gemma":0.00013731771,"threshold_uncertainty_score":0.0105955005},"labels":[],"label_agreement":null},{"id":"W2047706895","doi":"10.1016/j.specom.2010.02.013","title":"Detection of nonnative speaker status from content-masked speech","year":2010,"lang":"en","type":"article","venue":"Speech Communication","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":116,"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; Simon Fraser University","funders":"","keywords":"Mandarin Chinese; Czech; Speech recognition; Computer science; Speech production; Quality (philosophy); Speech processing; Linguistics","score_opus":0.05788706227852394,"score_gpt":0.351197851375106,"score_spread":0.29331078909658204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047706895","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":[0.99418396,0.00010249818,0.0028213707,0.00004389505,0.000048776717,0.000028681547,0.00011503997,0.00006146739,0.0025943676],"genre_scores_gemma":[0.9926717,0.00015071183,0.004623262,0.00009426665,0.000051037667,0.00004405735,0.00025217538,0.000067495894,0.0020453066],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99977523,0.000029562003,0.0000125570705,0.000071975664,0.00006951634,0.00004119402],"domain_scores_gemma":[0.9990151,0.0005170792,0.00006315507,0.0000766697,0.00019801466,0.00012998779],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039918476,0.00033643394,0.0004104782,0.00051659445,0.00044957057,0.000633464,0.00029177315,0.0005831375,0.0049056197],"category_scores_gemma":[0.0022590829,0.00023642756,0.0001397417,0.00019105822,0.00028554897,0.00068605406,0.00066440896,0.00041286345,0.0010655345],"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":[0.0007211967,0.0000350913,0.0033078992,0.00006787494,0.0000074413174,0.00014654934,0.00034175444,0.000016471886,0.9832275,0.00015003525,0.00008702342,0.011891233],"study_design_scores_gemma":[0.00010435267,0.0012519102,0.42011434,0.00004719243,0.00017137625,0.0036112538,0.0009968751,0.004974053,0.56539077,0.00090284355,0.002387742,0.00004732741],"about_ca_topic_score_codex":0.00078257435,"about_ca_topic_score_gemma":0.0016297144,"teacher_disagreement_score":0.0049056197,"about_ca_system_score_codex":0.00017201103,"about_ca_system_score_gemma":0.00038116236,"threshold_uncertainty_score":0.016410887},"labels":[],"label_agreement":null},{"id":"W2055595076","doi":"10.1016/s0167-6393(02)00028-6","title":"Age differences in the influence of metrical structure on phonetic identification","year":2003,"lang":"en","type":"article","venue":"Speech Communication","topic":"Phonetics and Phonology Research","field":"Psychology","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":"McGill University","funders":"Medical Research Council","keywords":"Stress (linguistics); Psychology; Voice-onset time; Context (archaeology); Audiology; Age groups; Identification (biology); Word (group theory); Cognitive psychology; Linguistics; Perception; History; Medicine","score_opus":0.053777325000046984,"score_gpt":0.3627955179644349,"score_spread":0.30901819296438787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055595076","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":[0.9960567,0.0003840193,0.00042959422,0.00004239878,0.000030338688,0.000005202142,0.0002027876,0.000011215182,0.0028377837],"genre_scores_gemma":[0.9981419,0.0001626122,0.00017829181,0.000019133693,0.000013394567,0.000003949526,0.00011527347,0.00001840522,0.0013470391],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9995474,0.0000939854,0.00005047847,0.00011349817,0.00013751129,0.000057021665],"domain_scores_gemma":[0.994709,0.0026237785,0.0010297681,0.00060379656,0.0006831088,0.00035053008],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089881546,0.00022068483,0.00022431026,0.0005961708,0.00015844076,0.00064048904,0.00016668107,0.0002980454,0.0037799694],"category_scores_gemma":[0.0069349003,0.00019784868,0.00017306657,0.00029382575,0.00035932774,0.000567327,0.0003953486,0.00031871677,0.00069829397],"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":[0.005677108,0.0003718339,0.43520567,0.00014228935,0.00022410975,0.0013791677,0.0066726897,0.0007267925,0.4736224,0.002482382,0.0009568862,0.07253867],"study_design_scores_gemma":[0.000013589831,0.00057574833,0.9878271,0.000008689888,0.000038577167,0.00059988914,0.00044505447,0.00026528633,0.0087389685,0.0005072423,0.000963571,0.000016352056],"about_ca_topic_score_codex":0.0010603999,"about_ca_topic_score_gemma":0.0014167535,"teacher_disagreement_score":0.0037799694,"about_ca_system_score_codex":0.00013186029,"about_ca_system_score_gemma":0.00015945271,"threshold_uncertainty_score":0.012645304},"labels":[],"label_agreement":null},{"id":"W2066004852","doi":"10.1016/j.specom.2006.06.004","title":"Wavelet speech enhancement based on time–scale adaptation","year":2006,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":69,"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 Sherbrooke; Université du Québec à Rimouski","funders":"","keywords":"Wavelet packet decomposition; Wavelet; Computer science; Speech recognition; Wavelet transform; Artificial intelligence; Noise (video); Second-generation wavelet transform; Network packet; Pattern recognition (psychology)","score_opus":0.011617961562509545,"score_gpt":0.23413381415972329,"score_spread":0.22251585259721374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066004852","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":[0.045695644,0.0004991501,0.9493916,0.00012541686,0.00018569028,0.00003839665,0.00004271805,0.00059075205,0.0034306198],"genre_scores_gemma":[0.3577166,0.001373688,0.6277644,0.00015583227,0.00021114963,0.000060184215,0.00023836823,0.0002242423,0.012255548],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999014,0.000019505003,0.0000060910306,0.000019496261,0.00004270075,0.00001077186],"domain_scores_gemma":[0.9997631,0.00009339741,0.000015610683,0.00004049026,0.00007399315,0.000013423592],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002857396,0.00043023645,0.00033013007,0.0002325398,0.00011850479,0.00027880658,0.0002083647,0.00034200738,0.0026131633],"category_scores_gemma":[0.0006340363,0.00015280666,0.0003958919,0.00029883097,0.00017644744,0.00045914855,0.00031232357,0.00041996123,0.0010943182],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00053468405,0.00008327587,0.00038330158,0.00008805278,0.000037774465,0.00014252374,0.000046299727,0.0071641146,0.65871876,0.003289475,0.0011266172,0.3283852],"study_design_scores_gemma":[0.000066179084,0.00029876071,0.005225408,0.000024003588,0.0001777107,0.00080247375,0.00003493051,0.4875503,0.48870525,0.0020275293,0.015048657,0.000038962935],"about_ca_topic_score_codex":0.00030104368,"about_ca_topic_score_gemma":0.00051774894,"teacher_disagreement_score":0.0026131633,"about_ca_system_score_codex":0.000078033605,"about_ca_system_score_gemma":0.00013130033,"threshold_uncertainty_score":0.008741856},"labels":[],"label_agreement":null},{"id":"W2074359113","doi":"10.1016/j.specom.2008.03.006","title":"Implicit processing of emotional prosody in a foreign versus native language","year":2008,"lang":"en","type":"article","venue":"Speech Communication","topic":"Multisensory perception and integration","field":"Psychology","cited_by":112,"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":"Prosody; Emotional prosody; Psychology; Facial expression; Emotional expression; Active listening; Priming (agriculture); Foreign language; Linguistics; Cognitive psychology; Speech recognition; Communication; Computer science","score_opus":0.08252491668061658,"score_gpt":0.39145861778016566,"score_spread":0.3089337010995491,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074359113","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":[0.99681985,0.000050687337,0.00046292957,0.000028349787,0.000024094341,0.000004614604,0.00002818322,0.0000059417075,0.0025753444],"genre_scores_gemma":[0.99688977,0.00008748533,0.0005550402,0.000050262417,0.000018727822,0.000015169665,0.000071019946,0.00002603326,0.0022864556],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99973077,0.00005575111,0.00001892297,0.00007551711,0.00006848046,0.000050469775],"domain_scores_gemma":[0.9983467,0.0009715211,0.00021903371,0.00013921528,0.00019312889,0.00013045876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006906741,0.00025183783,0.00026624245,0.00018384487,0.00027116807,0.0014582264,0.00026875737,0.00042678113,0.0047385697],"category_scores_gemma":[0.0070054308,0.00018080763,0.0001526613,0.000120885954,0.00043523416,0.0012724416,0.0009610219,0.00068908854,0.00048249224],"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":[0.008686759,0.0003258255,0.027223904,0.00035072363,0.00008800334,0.00052187097,0.0070798444,0.00033037123,0.9177882,0.0024128698,0.0003179436,0.034873784],"study_design_scores_gemma":[0.00039988177,0.0020162754,0.8407293,0.00013874756,0.00036309092,0.0028596078,0.008678707,0.007443289,0.12930511,0.0052140886,0.002730371,0.00012151345],"about_ca_topic_score_codex":0.00043439504,"about_ca_topic_score_gemma":0.0006640845,"teacher_disagreement_score":0.0047385697,"about_ca_system_score_codex":0.00016240793,"about_ca_system_score_gemma":0.0002348918,"threshold_uncertainty_score":0.015852094},"labels":[],"label_agreement":null},{"id":"W2077673277","doi":"10.1016/j.specom.2011.05.011","title":"Categorical processing of negative emotions from speech prosody","year":2011,"lang":"en","type":"article","venue":"Speech Communication","topic":"Multisensory perception and integration","field":"Psychology","cited_by":34,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Disgust; Psychology; Sadness; Prosody; Cognitive psychology; Facial expression; Emotional prosody; Valence (chemistry); Anger; Affect (linguistics); Nonverbal communication; Emotional expression; Active listening; Perception; Speech recognition; Communication; Social psychology; Computer science","score_opus":0.12203939553962093,"score_gpt":0.3603572703539774,"score_spread":0.23831787481435648,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077673277","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":[0.9577693,0.0006677197,0.013703175,0.00039919798,0.0002106908,0.00007222033,0.0005837578,0.000095286574,0.02649862],"genre_scores_gemma":[0.99239314,0.00040439153,0.0044814725,0.00012453522,0.00010685048,0.000081749495,0.0005931978,0.00010173539,0.001712945],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9996871,0.000062070016,0.000014935738,0.000066572924,0.00012292537,0.000046577625],"domain_scores_gemma":[0.99889886,0.000582164,0.00014873927,0.000076039694,0.00019160379,0.000102557926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000473081,0.00036622086,0.0003582735,0.00046861992,0.00037726926,0.0015843131,0.00027739763,0.00052950974,0.004315729],"category_scores_gemma":[0.00494027,0.0002802799,0.00028154644,0.00032166464,0.00055046735,0.001108979,0.0016556218,0.0008923379,0.0005119111],"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":[0.0014114083,0.00005826747,0.0068656392,0.00028334607,0.00003905165,0.0002449655,0.0016178235,0.0004243901,0.94089955,0.0033636326,0.0007082085,0.04408375],"study_design_scores_gemma":[0.00014399667,0.0005058832,0.8778769,0.00016204626,0.00017470938,0.0017587172,0.0023484095,0.012792689,0.07453702,0.026236124,0.0033312135,0.00013229123],"about_ca_topic_score_codex":0.00038432048,"about_ca_topic_score_gemma":0.0006961905,"teacher_disagreement_score":0.004315729,"about_ca_system_score_codex":0.00026502175,"about_ca_system_score_gemma":0.00026094913,"threshold_uncertainty_score":0.014437556},"labels":[],"label_agreement":null},{"id":"W2084178137","doi":"10.1016/j.specom.2006.10.002","title":"Noise estimation using speech/non-speech frame decision and subband spectral tracking","year":2006,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Ontario Centres of Excellence","keywords":"Speech recognition; Computer science; Noise (video); Speech enhancement; Microphone; Spectral density; Signal-to-noise ratio (imaging); Mean opinion score; Background noise; Noise measurement; Noise power; Power (physics); Noise reduction; Artificial intelligence; Telecommunications; Engineering; Physics","score_opus":0.016970777521193005,"score_gpt":0.27758995631257777,"score_spread":0.26061917879138474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084178137","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021516556,0.00024695104,0.9763757,0.00005400724,0.000076986296,0.000029692981,0.00005988094,0.0007138307,0.00092638837],"genre_scores_gemma":[0.24402055,0.00055195374,0.7487478,0.0001511416,0.00011208819,0.00009529163,0.000440456,0.0002694267,0.005611317],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993617,0.000115230236,0.000045318364,0.00016623424,0.00022055517,0.000091089096],"domain_scores_gemma":[0.99893385,0.00046919045,0.000069050075,0.000092944596,0.00038566094,0.000049187314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000878825,0.0012966698,0.0014741009,0.0014115961,0.00069966115,0.0010788826,0.00073553674,0.0012752527,0.0022354268],"category_scores_gemma":[0.003048745,0.00061365054,0.00076053216,0.0006529777,0.00037969372,0.0012343145,0.00073989615,0.0008913344,0.002281509],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016615244,0.00021914097,0.002028145,0.00017815917,0.00015828859,0.00012896168,0.00012179144,0.022948528,0.19457684,0.002310128,0.0011513538,0.774517],"study_design_scores_gemma":[0.00008791403,0.00020631988,0.004779548,0.000033260698,0.00020158142,0.0002629619,0.000060378825,0.81849307,0.170608,0.002108193,0.0031120381,0.00004671689],"about_ca_topic_score_codex":0.0035869684,"about_ca_topic_score_gemma":0.008685053,"teacher_disagreement_score":0.0035869684,"about_ca_system_score_codex":0.00038037775,"about_ca_system_score_gemma":0.0011273206,"threshold_uncertainty_score":0.0074781775},"labels":[],"label_agreement":null},{"id":"W2091902892","doi":"10.1016/s0167-6393(02)00123-5","title":"Interactions between speech coders and disordered speech","year":2003,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech and Audio Processing","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":"Western University","funders":"","keywords":"Code-excited linear prediction; Speech recognition; Computer science; Speech coding; Speech perception; PSQM; Voice activity detection; Linear predictive coding; Speech processing; Audiology; Perception; Psychology; Medicine","score_opus":0.025184517017069835,"score_gpt":0.2855548098378459,"score_spread":0.26037029282077606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091902892","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":[0.99948645,0.00011448472,0.00022437093,0.000010075669,0.0000027321398,0.0000072691946,0.000022387472,0.000005712996,0.00012656953],"genre_scores_gemma":[0.9992648,0.00006972818,0.0004732427,0.000013218569,0.0000059817203,0.000005953032,0.000056167,0.000004684144,0.00010621556],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99751294,0.0010672566,0.00018098592,0.00028582913,0.00081317197,0.00013985159],"domain_scores_gemma":[0.9757317,0.018005079,0.0028799581,0.00086638104,0.0016059218,0.00091091095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017795034,0.00045788888,0.00041957767,0.0005811221,0.00023969759,0.0004975852,0.00018228976,0.00039018813,0.0009054375],"category_scores_gemma":[0.023907946,0.0001984391,0.00025744076,0.00021057644,0.00046002562,0.0002808625,0.0004811688,0.00032504267,0.00023453127],"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":[0.013770723,0.0011537675,0.7698121,0.00034368268,0.00043073852,0.0022578135,0.0036016882,0.0013077919,0.13015407,0.00009439671,0.00023351585,0.07683968],"study_design_scores_gemma":[0.00009773519,0.014370904,0.9491232,0.000026043272,0.00035672478,0.0037384725,0.0010507518,0.0025267694,0.0280092,0.00012734142,0.0005240393,0.000048692604],"about_ca_topic_score_codex":0.0012691409,"about_ca_topic_score_gemma":0.0019015325,"teacher_disagreement_score":0.0017795034,"about_ca_system_score_codex":0.0002908483,"about_ca_system_score_gemma":0.0002113813,"threshold_uncertainty_score":0.009410977},"labels":[],"label_agreement":null},{"id":"W2093990655","doi":"10.1016/s0167-6393(02)00103-6","title":"Descending system and plasticity for auditory signal processing: neuroethological data for speech scientists","year":2003,"lang":"en","type":"article","venue":"Speech Communication","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":27,"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":"Auditory system; Medial geniculate body; Neuroscience; Auditory cortex; Inferior colliculus; Computer science; Speech recognition; Psychology","score_opus":0.11776924976645327,"score_gpt":0.32886313776435366,"score_spread":0.2110938879979004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2093990655","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":[0.9479896,0.02197875,0.0147665255,0.0029077842,0.0001640261,0.000025963393,0.00020728575,0.000039468287,0.011920619],"genre_scores_gemma":[0.977995,0.012520524,0.004223113,0.00035035965,0.00017872945,0.000028019324,0.00013129807,0.000019887671,0.004553102],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99995375,0.000007783498,0.000005119666,0.000013112659,0.000012382748,0.000007830419],"domain_scores_gemma":[0.99951744,0.00017591429,0.00004528006,0.000084177824,0.000111992515,0.0000652171],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026581256,0.0001923421,0.00021932198,0.00043343398,0.00037064092,0.0006093886,0.00029578814,0.00043353788,0.00242707],"category_scores_gemma":[0.0009931499,0.00007397289,0.00012030614,0.00028797373,0.0013824807,0.00078834814,0.0003414215,0.0007165171,0.00025804873],"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":[0.0027277598,0.00039354825,0.04300232,0.000716814,0.00015799585,0.0016744066,0.00095407356,0.0013823207,0.6415806,0.058087625,0.0012719629,0.24805066],"study_design_scores_gemma":[0.00022926803,0.0033225839,0.5497364,0.00026545333,0.00046966827,0.011376988,0.0016906969,0.008408287,0.25620338,0.12834097,0.039854966,0.000101332844],"about_ca_topic_score_codex":0.0011569837,"about_ca_topic_score_gemma":0.0013828046,"teacher_disagreement_score":0.00242707,"about_ca_system_score_codex":0.000276771,"about_ca_system_score_gemma":0.00042981835,"threshold_uncertainty_score":0.008119345},"labels":[],"label_agreement":null},{"id":"W2116379893","doi":"10.1016/j.specom.2007.02.002","title":"On the optimal linear filtering techniques for noise reduction","year":2007,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech and Audio Processing","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":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Wiener filter; Noise reduction; Computer science; Speech enhancement; Noise (video); Filter (signal processing); Reduction (mathematics); A priori and a posteriori; Algorithm; Speech recognition; Subspace topology; Signal-to-noise ratio (imaging); Linear filter; Noise measurement; Distortion (music); Mathematics; Artificial intelligence; Telecommunications; Computer vision","score_opus":0.027891657388218527,"score_gpt":0.30139618368641985,"score_spread":0.2735045262982013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116379893","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017181817,0.0022750834,0.993397,0.0001871479,0.00014453715,0.000009447052,0.000020198233,0.00008207761,0.002166193],"genre_scores_gemma":[0.139634,0.010862827,0.83022416,0.0004984492,0.0013623686,0.0001547667,0.0002502392,0.00022861107,0.016784718],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990395,0.00032049936,0.00006597776,0.00014675476,0.00035283892,0.00007442498],"domain_scores_gemma":[0.9990452,0.0006644959,0.00004579469,0.00008946973,0.00013757873,0.000017469716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011731336,0.0014021832,0.0009815847,0.0008088713,0.00049038505,0.0009990314,0.00079226197,0.0012201576,0.0033353246],"category_scores_gemma":[0.003970146,0.00064232637,0.000854822,0.0010081269,0.0014604074,0.0016594636,0.001112352,0.0019571995,0.0014486208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039703303,0.00010765523,0.00026138415,0.00050319964,0.00013750876,0.00012342498,0.00023029964,0.20134069,0.025853708,0.19057232,0.009630386,0.5708423],"study_design_scores_gemma":[0.00003835849,0.0001094249,0.0002825093,0.00008212713,0.00006641388,0.00016606408,0.000046074325,0.82436943,0.010092912,0.15018915,0.014506459,0.000051045958],"about_ca_topic_score_codex":0.0018876151,"about_ca_topic_score_gemma":0.0020100046,"teacher_disagreement_score":0.0033353246,"about_ca_system_score_codex":0.00042317578,"about_ca_system_score_gemma":0.0006022941,"threshold_uncertainty_score":0.011157751},"labels":[],"label_agreement":null},{"id":"W2138188153","doi":"10.1016/j.specom.2010.02.003","title":"On widely linear Wiener and tradeoff filters for noise reduction","year":2010,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech and Audio Processing","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":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Noise reduction; Noise (video); Reduction (mathematics); Computer science; Context (archaeology); Frequency domain; Filter (signal processing); Wiener filter; Algorithm; Noise measurement; Variance (accounting); Mathematics; Statistics; Speech recognition; Artificial intelligence; Computer vision","score_opus":0.01657203052775897,"score_gpt":0.27139861829223,"score_spread":0.25482658776447104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138188153","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004750703,0.0010328707,0.9922466,0.00013096054,0.000059133115,0.000006411959,0.000016185006,0.000052223677,0.0017048764],"genre_scores_gemma":[0.27627328,0.0053811655,0.69158834,0.0004235528,0.00057169975,0.00012550817,0.00021418776,0.0002005026,0.025221677],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991379,0.00033972476,0.0000490943,0.00013528443,0.00028114286,0.000056952173],"domain_scores_gemma":[0.99784184,0.0016463343,0.000065295295,0.00016390115,0.0002535567,0.000028962042],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019689735,0.001351133,0.00078109914,0.00062544446,0.00041494318,0.0009405087,0.0007226945,0.0017341016,0.0023518004],"category_scores_gemma":[0.00692825,0.0006387551,0.0006998332,0.00097129017,0.0012386279,0.0023118553,0.001576014,0.0016827672,0.00086067506],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00058376277,0.00008853119,0.00042366452,0.00028734346,0.00012236023,0.00016708847,0.0003594942,0.28985363,0.033468112,0.3311981,0.0039457483,0.33950216],"study_design_scores_gemma":[0.000025456395,0.000076540564,0.00019124133,0.00003168148,0.000036895526,0.00011176582,0.000037175574,0.83688873,0.005169335,0.15223762,0.005149494,0.000044035576],"about_ca_topic_score_codex":0.0015851778,"about_ca_topic_score_gemma":0.0023453461,"teacher_disagreement_score":0.0023518004,"about_ca_system_score_codex":0.00056841684,"about_ca_system_score_gemma":0.00046364896,"threshold_uncertainty_score":0.01041311},"labels":[],"label_agreement":null},{"id":"W2142637945","doi":"10.1016/j.specom.2007.04.011","title":"Suitability of a UV-based video recording system for the analysis of small facial motions during speech","year":2007,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech and Audio Processing","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":"Toronto Rehabilitation Institute; University of Toronto","funders":"","keywords":"Articulator; Computer science; Kinematics; Speech recognition; Speech production; Motion capture; Artificial intelligence; Face (sociological concept); Computer vision; Motion (physics)","score_opus":0.03184880997429594,"score_gpt":0.28346839690357334,"score_spread":0.2516195869292774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142637945","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4000064,0.0017435495,0.5836981,0.00047706894,0.00055704766,0.00068559503,0.0011282916,0.002713239,0.008990713],"genre_scores_gemma":[0.7361107,0.001391826,0.25285947,0.0005315389,0.00030947168,0.0006724993,0.0006787871,0.00032020928,0.007125496],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996705,0.00009285245,0.000015379583,0.00008256051,0.000115201336,0.0000234495],"domain_scores_gemma":[0.99909675,0.00041553026,0.000029855388,0.000062211984,0.00033268682,0.00006303591],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005805165,0.00031418595,0.00036759622,0.00032748282,0.00028076104,0.00057259406,0.0006440016,0.0008295873,0.0046045124],"category_scores_gemma":[0.0017283306,0.0001991123,0.00021306159,0.00028990756,0.00020463545,0.00044483683,0.00025619616,0.000331791,0.001702071],"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":[0.0009966025,0.00008446146,0.0028349939,0.00018048214,0.000029276329,0.000112223795,0.00007498022,0.00027588903,0.9025387,0.00025800682,0.00088474905,0.09172959],"study_design_scores_gemma":[0.00029072558,0.0025840327,0.039815575,0.00012597599,0.0002946756,0.004328914,0.00023049269,0.035440553,0.90164524,0.00042090187,0.014726682,0.000096198266],"about_ca_topic_score_codex":0.0008680686,"about_ca_topic_score_gemma":0.0010684467,"teacher_disagreement_score":0.0046045124,"about_ca_system_score_codex":0.00015920901,"about_ca_system_score_gemma":0.00045813536,"threshold_uncertainty_score":0.015403628},"labels":[],"label_agreement":null},{"id":"W2259135914","doi":"10.1016/j.specom.2015.12.001","title":"Cry-based infant pathology classification using GMMs","year":2015,"lang":"en","type":"article","venue":"Speech Communication","topic":"Infant Health and Development","field":"Health Professions","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":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"Bill and Melinda Gates Foundation","keywords":"Mixture model; Discriminative model; Mel-frequency cepstrum; Pattern recognition (psychology); Artificial intelligence; Computer science; Infant crying; Speech recognition; Naive Bayes classifier; Support vector machine; Feature vector; Hidden Markov model; Maximum a posteriori estimation; Feature extraction; Medicine; Mathematics; Maximum likelihood; Crying; Statistics","score_opus":0.26216897213734347,"score_gpt":0.47810062341335924,"score_spread":0.21593165127601577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2259135914","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16910039,0.0009312152,0.8247684,0.00013496452,0.00008302245,0.00008086199,0.00028072542,0.0032407462,0.0013796643],"genre_scores_gemma":[0.7733489,0.00067234674,0.22288796,0.00007041528,0.000056943278,0.0000646268,0.00054177735,0.00013249434,0.0022244316],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996418,0.00009267436,0.00001829854,0.00009383547,0.00009734166,0.000056019544],"domain_scores_gemma":[0.99967325,0.000092261835,0.000036857935,0.000027870667,0.00014098187,0.000028814562],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007186332,0.00057210034,0.0005766763,0.0014243964,0.00017819923,0.00033617264,0.0003702775,0.00039166916,0.000715602],"category_scores_gemma":[0.0014303541,0.00015022724,0.0005314899,0.0005095359,0.00018697749,0.00048333025,0.0005738556,0.00033487444,0.00070109987],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040191467,0.00010871061,0.016531987,0.00012364097,0.000105143896,0.0002331805,0.0002606733,0.03206286,0.112183906,0.0018012034,0.0025963807,0.83359045],"study_design_scores_gemma":[0.000014090345,0.00020337552,0.035814054,0.000027865328,0.00008404439,0.00045629562,0.00019399788,0.915754,0.042750258,0.0019416789,0.0027069815,0.000053377917],"about_ca_topic_score_codex":0.0028378654,"about_ca_topic_score_gemma":0.002204469,"teacher_disagreement_score":0.0028378654,"about_ca_system_score_codex":0.00034402995,"about_ca_system_score_gemma":0.0004130778,"threshold_uncertainty_score":0.0056426525},"labels":[],"label_agreement":null},{"id":"W2791867538","doi":"10.1016/j.specom.2018.03.007","title":"The sound of Passion and Indifference","year":2018,"lang":"en","type":"article","venue":"Speech Communication","topic":"Voice and Speech Disorders","field":"Medicine","cited_by":28,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Passion; Affect (linguistics); Arousal; Psychology; Neutrality; Perception; Context (archaeology); Meaning (existential); Social psychology; Paralanguage; Linguistics; Cognitive psychology; Communication","score_opus":0.02314098288413063,"score_gpt":0.3089829522845727,"score_spread":0.28584196940044204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2791867538","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":[0.044909224,0.014597186,0.025367428,0.32739618,0.024579344,0.000059515263,0.00042383338,0.00048200216,0.56218517],"genre_scores_gemma":[0.8662546,0.0022287252,0.005020276,0.059538525,0.010669261,0.0001026298,0.00012963652,0.00035108678,0.05570513],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9950041,0.00211426,0.00016249725,0.00061467866,0.0016795994,0.00042488068],"domain_scores_gemma":[0.9900592,0.0057413722,0.00076508423,0.0010884788,0.0012332022,0.0011126687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041889795,0.00054402836,0.00059587654,0.0019362727,0.0038845725,0.0072752098,0.0013680455,0.0053774677,0.007459753],"category_scores_gemma":[0.02713272,0.00034044252,0.00040535172,0.00077650347,0.03591754,0.008778909,0.004708435,0.012157514,0.0017549394],"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":[0.00014846951,0.000023660952,0.0016243529,0.000095514544,0.00004214848,0.00083016895,0.042500436,0.00013178393,0.0007612466,0.8602991,0.06629413,0.027248941],"study_design_scores_gemma":[0.00006584124,0.00006103907,0.0016035473,0.00023478088,0.000024802826,0.0022769114,0.020001475,0.0003513618,0.0004410001,0.72350484,0.25135335,0.00008111156],"about_ca_topic_score_codex":0.0019413873,"about_ca_topic_score_gemma":0.001492686,"teacher_disagreement_score":0.007459753,"about_ca_system_score_codex":0.001578858,"about_ca_system_score_gemma":0.0018027185,"threshold_uncertainty_score":0.024955392},"labels":[],"label_agreement":null},{"id":"W2942829305","doi":"10.1016/j.specom.2019.04.009","title":"How modeling entrance loss and flow separation in a two-mass model affects the oscillation and synthesis quality","year":2019,"lang":"en","type":"article","venue":"Speech Communication","topic":"Phonetics and Phonology Research","field":"Psychology","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":"McMaster University","funders":"","keywords":"Phonation; Naturalness; Oscillation (cell signaling); Acoustics; Harmonics; Flow (mathematics); Glottis; Mathematics; Mechanics; Physics; Chemistry; Larynx; Audiology","score_opus":0.054148513811712394,"score_gpt":0.392138184147549,"score_spread":0.3379896703358366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2942829305","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":[0.62650806,0.00025866544,0.3560531,0.0013956571,0.00026228794,0.00006759781,0.00016648156,0.0004617794,0.014826257],"genre_scores_gemma":[0.98774827,0.00006298852,0.009084431,0.000060435017,0.000021101547,0.000021471555,0.00003915091,0.0000661052,0.0028961967],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998574,0.00003959295,0.000006182727,0.000054179163,0.000018339877,0.000024248428],"domain_scores_gemma":[0.9992681,0.00044669554,0.00007654057,0.00004714134,0.00009201263,0.000069450674],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006063741,0.0005503894,0.0004531531,0.0002826947,0.0004788362,0.0018993837,0.00087904703,0.0018630605,0.0039400887],"category_scores_gemma":[0.0026849525,0.0004827867,0.0006332838,0.00017445997,0.0006604695,0.001799692,0.00047831732,0.0010752128,0.0005477517],"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":[0.00013649506,0.000071140385,0.0017259112,0.000026943582,0.000031747903,0.00008332119,0.000106267595,0.9822264,0.0052032457,0.006377138,0.00021463327,0.0037968853],"study_design_scores_gemma":[0.000008948703,0.000014230197,0.00018182734,0.0000025200184,0.000011216794,0.000006721318,0.000012861209,0.99862635,0.00026498397,0.00076066115,0.00010418757,0.0000054988745],"about_ca_topic_score_codex":0.0115771005,"about_ca_topic_score_gemma":0.006198204,"teacher_disagreement_score":0.0115771005,"about_ca_system_score_codex":0.0006292456,"about_ca_system_score_gemma":0.00071523373,"threshold_uncertainty_score":0.023019433},"labels":[],"label_agreement":null},{"id":"W3096879251","doi":"10.1016/j.specom.2020.10.007","title":"Speech enhancement using a DNN-augmented colored-noise Kalman filter","year":2020,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":28,"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; Concordia University","funders":"China Scholarship Council","keywords":"Speech enhancement; Computer science; Kalman filter; Speech recognition; Noise (video); Autoregressive model; Noise reduction; Linear prediction; Colors of noise; Noise measurement; Residual; Artificial intelligence; Algorithm; Mathematics; Statistics","score_opus":0.043688818747489686,"score_gpt":0.28474755523964695,"score_spread":0.24105873649215726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3096879251","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009189451,0.00039115347,0.9873071,0.000079323254,0.00023618081,0.000030772822,0.00006954499,0.0008738616,0.0018225882],"genre_scores_gemma":[0.3498294,0.0008903819,0.6356066,0.00026709624,0.00017019674,0.00010837115,0.0004535806,0.00016782482,0.012506673],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9997093,0.000042849257,0.000019198644,0.00009234095,0.00009847546,0.000037820362],"domain_scores_gemma":[0.9996625,0.00008528161,0.000018368579,0.000029345962,0.00018934956,0.000015127645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005820986,0.0008119824,0.0005552703,0.00032183793,0.00037526825,0.00045924637,0.0005166351,0.00074476073,0.0026035244],"category_scores_gemma":[0.00085368444,0.00033431046,0.000646776,0.0003067536,0.00024138877,0.0006967693,0.0005421979,0.0008500443,0.0012428322],"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":[0.00068726286,0.00019843993,0.001340352,0.00027829327,0.00016365403,0.00021859432,0.00013882342,0.14497927,0.18917501,0.0054912744,0.003913175,0.65341586],"study_design_scores_gemma":[0.000017922865,0.00008101803,0.00085455924,0.00002562679,0.00007293921,0.00007337331,0.000013796103,0.95255065,0.041482862,0.00067597657,0.0041287956,0.000022433022],"about_ca_topic_score_codex":0.007539088,"about_ca_topic_score_gemma":0.014844536,"teacher_disagreement_score":0.007539088,"about_ca_system_score_codex":0.00041425708,"about_ca_system_score_gemma":0.0009309585,"threshold_uncertainty_score":0.014990449},"labels":[],"label_agreement":null},{"id":"W3215538304","doi":"10.1016/j.specom.2021.11.007","title":"The Lombard intelligibility benefit of native and non-native speech for native and non-native listeners","year":2021,"lang":"en","type":"article","venue":"Speech Communication","topic":"Hearing Loss and Rehabilitation","field":"Neuroscience","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 Alberta","funders":"European Commission","keywords":"Native american; Intelligibility (philosophy); QUIET; First language; Speech recognition; Computer science; Linguistics; History; Physics","score_opus":0.040521350511124515,"score_gpt":0.33374345227298663,"score_spread":0.29322210176186214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215538304","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":[0.99660033,0.00017540221,0.0010266204,0.000023534449,0.000009232999,0.000011019534,0.000040247087,0.000019485378,0.0020941426],"genre_scores_gemma":[0.9982673,0.00007647004,0.0008375603,0.000030197725,0.0000069127864,0.000017442151,0.0000780882,0.00001398699,0.00067216443],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9996911,0.00006370477,0.000032831522,0.000060756338,0.00011915053,0.000032482334],"domain_scores_gemma":[0.9983454,0.001043501,0.00011003236,0.00012567946,0.00021005582,0.00016528135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007937287,0.0003367595,0.00037704958,0.0003413554,0.00017797205,0.0006637568,0.00014271095,0.00036867926,0.0028088146],"category_scores_gemma":[0.0046744426,0.00014246594,0.000185674,0.00008098679,0.00039268192,0.000716115,0.0009862639,0.00035379696,0.000425378],"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":[0.0048640165,0.00015908209,0.0207561,0.00031746266,0.00010317303,0.00041657122,0.0021903892,0.00038512246,0.9270811,0.0004214792,0.00018300915,0.04312238],"study_design_scores_gemma":[0.0001407449,0.0034771552,0.86200404,0.00005785675,0.00024211303,0.0020524925,0.0032648535,0.0033482844,0.12180699,0.0014538176,0.0020814927,0.000070115646],"about_ca_topic_score_codex":0.0006023134,"about_ca_topic_score_gemma":0.0011872521,"teacher_disagreement_score":0.0028088146,"about_ca_system_score_codex":0.00012185951,"about_ca_system_score_gemma":0.0001591568,"threshold_uncertainty_score":0.009396374},"labels":[],"label_agreement":null},{"id":"W4229048296","doi":"10.1016/j.specom.2022.05.001","title":"Learning transfer from singing to speech: Insights from vowel analyses in aging amateur singers and non-singers","year":2022,"lang":"en","type":"article","venue":"Speech Communication","topic":"Phonetics and Phonology Research","field":"Psychology","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":"Université Laval","funders":"","keywords":"Vowel; Singing; Psychology; Audiology; Amateur; Optimal distinctiveness theory; Duration (music); Articulation (sociology); Linguistics; Speech recognition; Computer science; Acoustics; Medicine; History","score_opus":0.053040617500170056,"score_gpt":0.36354517084437654,"score_spread":0.31050455334420646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229048296","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":[0.9947832,0.00012804476,0.0029620554,0.00011820937,0.00001711698,0.000020003687,0.00007714186,0.000032266078,0.0018620227],"genre_scores_gemma":[0.9969573,0.00010413234,0.001169366,0.000041577314,0.00001579351,0.00001668302,0.00013071141,0.00002488761,0.0015395884],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9997067,0.00007268679,0.00001806941,0.00008944294,0.00007047827,0.000042644744],"domain_scores_gemma":[0.9984419,0.000730603,0.00012197619,0.0002600477,0.00030501338,0.00014042495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010518122,0.0003108167,0.00043193466,0.0004604573,0.00031339438,0.0010523094,0.0003824016,0.00053430465,0.002181649],"category_scores_gemma":[0.0061699566,0.00020311242,0.00027582582,0.00020407933,0.00056497863,0.0008931538,0.0008016301,0.00067321904,0.00067030225],"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":[0.0016986218,0.0009852536,0.20246793,0.00021043241,0.00025418727,0.0009467851,0.0139440885,0.005928037,0.45740253,0.0020626655,0.0015204429,0.31257898],"study_design_scores_gemma":[0.000024248451,0.00065548264,0.9437426,0.00003075678,0.00008161228,0.0007039327,0.004219291,0.022355288,0.020802673,0.0055426764,0.0017879314,0.000053568387],"about_ca_topic_score_codex":0.003705277,"about_ca_topic_score_gemma":0.0035786377,"teacher_disagreement_score":0.003705277,"about_ca_system_score_codex":0.00024079709,"about_ca_system_score_gemma":0.00035636182,"threshold_uncertainty_score":0.0073673725},"labels":[],"label_agreement":null},{"id":"W4366779161","doi":"10.1016/j.specom.2023.04.003","title":"Comparative analysis of various feature extraction techniques for classification of speech disfluencies","year":2023,"lang":"en","type":"article","venue":"Speech Communication","topic":"Stuttering Research and Treatment","field":"Psychology","cited_by":8,"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":"CSIR-Central Scientific Instruments Organisation; Academy of Scientific and Innovative Research; Queen's University","keywords":"Computer science; Speech recognition; Mel-frequency cepstrum; Spectrogram; Feature extraction; Phrase; Linear prediction; Classifier (UML); Artificial intelligence; Speech processing; Linear predictive coding; Cepstrum; Natural language processing","score_opus":0.10141111822200481,"score_gpt":0.4468027347937438,"score_spread":0.345391616571739,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366779161","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":[0.7086526,0.006993659,0.2772272,0.00025811658,0.00026008888,0.00021052078,0.0015149981,0.00174643,0.0031364365],"genre_scores_gemma":[0.87664,0.002678705,0.11515074,0.000057451052,0.00011660568,0.00017857751,0.0028810631,0.00017526285,0.0021215414],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99943525,0.00010858722,0.000086115615,0.000119368284,0.00014062687,0.000110032575],"domain_scores_gemma":[0.99725217,0.0018517945,0.00011380832,0.000091390444,0.00064277026,0.000048080772],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014893089,0.00071499153,0.00085884414,0.0019952462,0.00030742638,0.00082759594,0.00036380193,0.0004943105,0.0019063015],"category_scores_gemma":[0.0030737123,0.00013062013,0.0009544475,0.0014384682,0.00017584715,0.0007865502,0.00030629447,0.0004257748,0.0005304769],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00199064,0.00026413202,0.0097492775,0.0005027195,0.00028883733,0.00013427905,0.00018485692,0.004445999,0.10576027,0.00032296675,0.0012193073,0.8751366],"study_design_scores_gemma":[0.00029509305,0.0046389694,0.3857629,0.0002684361,0.0024737888,0.001942679,0.0013441294,0.34916893,0.24355568,0.0015371756,0.008770163,0.00024205881],"about_ca_topic_score_codex":0.0023591185,"about_ca_topic_score_gemma":0.0022081062,"teacher_disagreement_score":0.0023591185,"about_ca_system_score_codex":0.00019467666,"about_ca_system_score_gemma":0.0003886344,"threshold_uncertainty_score":0.007876337},"labels":[],"label_agreement":null},{"id":"W4376116537","doi":"10.1016/j.specom.2023.05.002","title":"The cross-linguistics perception of liquids: Motivation for the superclass","year":2023,"lang":"en","type":"article","venue":"Speech Communication","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":2,"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":"Social Sciences and Humanities Research Council of Canada","keywords":"Phonotactics; Perception; Formant; Mandarin Chinese; Space (punctuation); Acoustic space; Computer science; Class (philosophy); Boundary (topology); Speech perception; Speech recognition; Quality (philosophy); Representation (politics); Linguistics; Natural language processing; Acoustics; Artificial intelligence; Psychology; Mathematics; Vowel; Phonology; Sound (geography); Physics","score_opus":0.09756938840414185,"score_gpt":0.4327188878083705,"score_spread":0.3351494994042286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376116537","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":[0.7757607,0.00156678,0.055742588,0.005989479,0.0003491317,0.00008574849,0.00024459805,0.00022009404,0.16004081],"genre_scores_gemma":[0.98740107,0.00037304332,0.007920986,0.0007134226,0.00020725459,0.000046108937,0.00010217168,0.0002052767,0.003030615],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985923,0.00022780811,0.000054718486,0.00069397385,0.00033183995,0.00009923],"domain_scores_gemma":[0.990303,0.004519928,0.0007253074,0.0022567168,0.0015933475,0.0006016962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026903437,0.00031200843,0.0005608986,0.0011281838,0.0011911246,0.0048052855,0.0011942532,0.0013121783,0.010846837],"category_scores_gemma":[0.009757781,0.00056711916,0.00050052453,0.00065050425,0.0044026496,0.008704568,0.0042532925,0.0023496577,0.00085932633],"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":[0.0011256913,0.00036658978,0.041222032,0.00048641462,0.00016359503,0.00034608867,0.015386942,0.0012898056,0.06404667,0.6856071,0.0027599318,0.18719922],"study_design_scores_gemma":[0.00018531387,0.0004901657,0.21792875,0.00033327565,0.00018789765,0.0012842868,0.0133769745,0.025436977,0.017097186,0.69123304,0.03224236,0.00020372322],"about_ca_topic_score_codex":0.0028959215,"about_ca_topic_score_gemma":0.0018993013,"teacher_disagreement_score":0.010846837,"about_ca_system_score_codex":0.0008455829,"about_ca_system_score_gemma":0.00091446727,"threshold_uncertainty_score":0.036286235},"labels":[],"label_agreement":null},{"id":"W4378188939","doi":"10.1016/j.specom.2023.05.008","title":"Review of analysis methods for speech applications","year":2023,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"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":"Computer science; Speech recognition; Variety (cybernetics); Speech coding; Speech processing; Latency (audio); Coding (social sciences); Artificial intelligence; Telecommunications; Mathematics","score_opus":0.04949166615472159,"score_gpt":0.42040737984189913,"score_spread":0.3709157136871775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378188939","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":[0.0016358098,0.57064897,0.4145879,0.0013518534,0.002273704,0.00012646087,0.0005625309,0.0011851377,0.0076276213],"genre_scores_gemma":[0.022488855,0.56206226,0.39103442,0.0018268033,0.005941133,0.00032822666,0.0017127793,0.00093958643,0.013665897],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972019,0.0005839787,0.00031040015,0.0006070765,0.0012022224,0.00009441325],"domain_scores_gemma":[0.99377835,0.0031880473,0.0002443996,0.0004453762,0.0022526367,0.00009124727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003071441,0.0016586416,0.001936902,0.0042290045,0.0006211983,0.0026806504,0.0024110302,0.001875897,0.0063306554],"category_scores_gemma":[0.008092635,0.0007803158,0.0012616436,0.0042756745,0.0010365093,0.0025301084,0.0012627533,0.0017646218,0.0068204394],"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":[0.00007872306,0.000040500287,0.0003110471,0.003021805,0.00009368962,0.000066203706,0.00007706521,0.0011087939,0.0058035096,0.0060365917,0.014996296,0.9683658],"study_design_scores_gemma":[0.000045521276,0.00022991825,0.003932823,0.0034693705,0.00046438831,0.0017597731,0.00028076654,0.027754845,0.0199136,0.03726897,0.90465766,0.00022241344],"about_ca_topic_score_codex":0.0023352625,"about_ca_topic_score_gemma":0.0017626465,"teacher_disagreement_score":0.0063306554,"about_ca_system_score_codex":0.000729746,"about_ca_system_score_gemma":0.0017191031,"threshold_uncertainty_score":0.021178186},"labels":[],"label_agreement":null},{"id":"W4391825020","doi":"10.1016/j.specom.2024.103044","title":"On intrusive speech quality measures and a global SNR based metric","year":2024,"lang":"en","type":"article","venue":"Speech Communication","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":"Institut National de la Recherche Scientifique","funders":"National Key Research and Development Program of China Stem Cell and Translational Research; National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"PESQ; Computer science; Intelligibility (philosophy); Speech recognition; Metric (unit); Distortion (music); Speech enhancement; Speech processing; Signal-to-noise ratio (imaging); PSQM; Computation; Voice activity detection; Artificial intelligence; Algorithm; Noise reduction; Bandwidth (computing); Telecommunications; Engineering","score_opus":0.031777237366014593,"score_gpt":0.32694856812405537,"score_spread":0.2951713307580408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391825020","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050910316,0.0049609076,0.9290777,0.00026536713,0.00025084877,0.00009761677,0.00029098275,0.00071978266,0.0134265395],"genre_scores_gemma":[0.7191605,0.007246336,0.2575138,0.00040912113,0.0013247121,0.0001265281,0.0011059737,0.00056642026,0.012546578],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99673873,0.0009905483,0.00024384572,0.00058866263,0.0013043006,0.00013399466],"domain_scores_gemma":[0.9934012,0.0033482332,0.00052151305,0.0012799286,0.0013056808,0.00014333776],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023306878,0.0017633314,0.0011047496,0.002320315,0.0003417004,0.0019157196,0.0008851582,0.0011529404,0.0026109768],"category_scores_gemma":[0.008922973,0.00042305133,0.0006455456,0.0020944811,0.0014608004,0.0036579536,0.0020955498,0.0012409573,0.002133982],"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":[0.0012741385,0.0002373841,0.01291816,0.00075319374,0.00037804758,0.001125341,0.00045801862,0.05199174,0.15253033,0.046218336,0.003630034,0.72848535],"study_design_scores_gemma":[0.000055252058,0.002659217,0.050536796,0.00048728788,0.0007654181,0.010690462,0.0007972988,0.7085378,0.14682727,0.052265305,0.026049519,0.00032839243],"about_ca_topic_score_codex":0.0009365411,"about_ca_topic_score_gemma":0.0012665415,"teacher_disagreement_score":0.0026109768,"about_ca_system_score_codex":0.00042323046,"about_ca_system_score_gemma":0.00034024654,"threshold_uncertainty_score":0.012326002},"labels":[],"label_agreement":null},{"id":"W4402945244","doi":"10.1016/j.specom.2024.103144","title":"Feasibility of acoustic features of vowel sounds in estimating the upper airway cross sectional area during wakefulness: A pilot study","year":2024,"lang":"en","type":"article","venue":"Speech Communication","topic":"Obstructive Sleep Apnea Research","field":"Medicine","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":"Public Health Ontario; Toronto Rehabilitation Institute; University of Toronto; University Health Network","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Vowel; Audiology; Wakefulness; Cross-sectional study; Airway; Speech recognition; Acoustics; Computer science; Medicine; Psychology; Mathematics; Electroencephalography; Statistics; Anesthesia; Neuroscience","score_opus":0.05891814902745833,"score_gpt":0.377314962561023,"score_spread":0.31839681353356464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402945244","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":[0.99673116,0.000102050006,0.0025837643,0.000011961061,0.000017349053,0.00019616664,0.00007448039,0.000008429346,0.0002747447],"genre_scores_gemma":[0.9962768,0.00008201536,0.0030173764,0.000041702202,0.000030471312,0.00019888615,0.00008743996,0.000009051149,0.0002561637],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9993662,0.00032834453,0.000029387724,0.00013029542,0.00007942559,0.00006631499],"domain_scores_gemma":[0.9977884,0.0014218665,0.00009319623,0.00017896942,0.0002726796,0.000244899],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020814063,0.00059898925,0.00043848093,0.00044921547,0.00043948772,0.00050434866,0.00037092227,0.0007746329,0.00094476854],"category_scores_gemma":[0.0032486985,0.0003999801,0.00032046903,0.00019149849,0.000786222,0.00058969535,0.00033789745,0.00044448394,0.00027770273],"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":[0.03765466,0.0065606227,0.37851477,0.00021875666,0.00022499713,0.00075864,0.0026307313,0.0007934244,0.51165867,0.00014474825,0.00021667186,0.060623236],"study_design_scores_gemma":[0.00084457354,0.06931897,0.8841865,0.000016121174,0.0003669194,0.0010863964,0.0023686618,0.004810141,0.036046464,0.00012563083,0.0007727986,0.000056833076],"about_ca_topic_score_codex":0.0019864258,"about_ca_topic_score_gemma":0.0024746363,"teacher_disagreement_score":0.0020814063,"about_ca_system_score_codex":0.000101209625,"about_ca_system_score_gemma":0.00037745884,"threshold_uncertainty_score":0.011007667},"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":"W4408395413","doi":"10.1016/j.specom.2025.103223","title":"Enhancing bone-conducted speech with spectrum similarity metric in adversarial learning","year":2025,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech and Audio Processing","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 Windsor","funders":"Natural Science Foundation of Anhui Province; National Natural Science Foundation of China","keywords":"Adversarial system; Metric (unit); Similarity (geometry); Speech recognition; Computer science; Artificial intelligence; Engineering; Operations management","score_opus":0.010553370933399961,"score_gpt":0.25843484368060526,"score_spread":0.2478814727472053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408395413","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016381992,0.00019711167,0.9815258,0.00011362292,0.00008542106,0.000017706601,0.000039795803,0.00030774594,0.0013309069],"genre_scores_gemma":[0.65964216,0.0007109996,0.32914037,0.0003469262,0.00019062815,0.00007071791,0.00034961317,0.00029488455,0.00925373],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99947006,0.00013465776,0.00002033011,0.000098823926,0.00023178257,0.00004441241],"domain_scores_gemma":[0.9991543,0.00044710469,0.00006091692,0.000121817866,0.00016579288,0.000050120118],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000972644,0.0007722327,0.00063673686,0.00039942967,0.00022808593,0.0005466916,0.0007225037,0.0009715081,0.0020190312],"category_scores_gemma":[0.0028308816,0.00026520932,0.00045838804,0.00043602317,0.0005796106,0.0010521304,0.0015598261,0.0010536892,0.0010023147],"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":[0.00054180925,0.00020231931,0.0011926446,0.00018020558,0.000097814846,0.00018732878,0.00012649287,0.5043858,0.08893061,0.015792936,0.0029563354,0.38540563],"study_design_scores_gemma":[0.000005429762,0.00005295231,0.00025330743,0.0000066368793,0.0000150622045,0.000072934454,0.000011861455,0.98641753,0.009795674,0.0025603329,0.0007994089,0.000008858997],"about_ca_topic_score_codex":0.0014166415,"about_ca_topic_score_gemma":0.002037437,"teacher_disagreement_score":0.0020190312,"about_ca_system_score_codex":0.00027606022,"about_ca_system_score_gemma":0.00048747106,"threshold_uncertainty_score":0.006754279},"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":"W4409534126","doi":"10.1016/j.specom.2025.103243","title":"Expectation of speech style improves audio-visual perception of English vowels","year":2025,"lang":"en","type":"article","venue":"Speech Communication","topic":"Phonetics and Phonology Research","field":"Psychology","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; Social Sciences and Humanities Research Council of Canada; Simon Fraser University","keywords":"Speech recognition; Computer science; Perception; Speech perception; Style (visual arts); Audio visual; Psychology; Multimedia; History","score_opus":0.019814306789240194,"score_gpt":0.36966256741974174,"score_spread":0.34984826063050156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409534126","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":[0.996636,0.00008381093,0.0021705881,0.00002701625,0.000010163706,0.000011440534,0.000022082742,0.000046565227,0.0009922495],"genre_scores_gemma":[0.99751353,0.00007295111,0.001574018,0.000035635065,0.000007085902,0.000012132676,0.000043451975,0.000013919457,0.00072727393],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9997218,0.000062912906,0.000033560267,0.00007253409,0.000088526176,0.000020538177],"domain_scores_gemma":[0.9979949,0.001106625,0.00031385943,0.00014558494,0.00024211282,0.00019691614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043160535,0.00019001956,0.00015299094,0.000101093676,0.00006960469,0.0004359311,0.00013074136,0.00028667008,0.0031239365],"category_scores_gemma":[0.0047330526,0.00015232454,0.00016188319,0.000027027127,0.00015032683,0.00035887788,0.00036809524,0.000268975,0.0004142004],"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":[0.0012581401,0.0001342002,0.005100183,0.000113181864,0.000014563327,0.000098227916,0.00043519028,0.00016437063,0.97236246,0.000040384457,0.00008630391,0.020192755],"study_design_scores_gemma":[0.00012274654,0.005997141,0.7722947,0.00006385466,0.00011298241,0.000855607,0.0011243053,0.0065196613,0.21060024,0.0005099317,0.001744701,0.00005412906],"about_ca_topic_score_codex":0.0004408592,"about_ca_topic_score_gemma":0.00051582564,"teacher_disagreement_score":0.0031239365,"about_ca_system_score_codex":0.00008072025,"about_ca_system_score_gemma":0.0001277671,"threshold_uncertainty_score":0.010450602},"labels":[],"label_agreement":null},{"id":"W4409993531","doi":"10.1016/j.specom.2025.103245","title":"An update rule for multiple source variances estimation using microphone arrays","year":2025,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech and Audio Processing","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":"Institut National de la Recherche Scientifique","funders":"National Key Research and Development Program of China Stem Cell and Translational Research; National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Computer science; Microphone; Estimation; Speech recognition; Algorithm; Telecommunications; Engineering","score_opus":0.017949256211061887,"score_gpt":0.29861527863153003,"score_spread":0.2806660224204681,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409993531","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":[0.0012623462,0.00014516135,0.9979888,0.000038354035,0.000050289287,0.00001731714,0.000026195323,0.00018749872,0.00028404305],"genre_scores_gemma":[0.091245644,0.0006070885,0.9028878,0.00015145894,0.00027549927,0.00021271156,0.00030676025,0.0002655699,0.0040474823],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982779,0.0003932958,0.00015756719,0.00040104522,0.0006693117,0.00010095395],"domain_scores_gemma":[0.9964283,0.0020646835,0.00013557276,0.00031345733,0.0009931849,0.00006491157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002150939,0.0010005087,0.0013817686,0.0007875631,0.00047114067,0.0014780128,0.0018859556,0.0014632521,0.0029879],"category_scores_gemma":[0.010025727,0.0010094417,0.00097105827,0.0007866976,0.00060143427,0.0017476826,0.0010932268,0.0026216854,0.0023231271],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036566268,0.00012482915,0.000920684,0.00031226565,0.0001621223,0.00021685984,0.00016655868,0.23477852,0.025847506,0.019746881,0.004585285,0.71277285],"study_design_scores_gemma":[0.000025460657,0.0000471152,0.0004127255,0.00003188841,0.000045125937,0.00014853314,0.000008846194,0.9839189,0.0075745764,0.004848059,0.0029085414,0.00003032069],"about_ca_topic_score_codex":0.0042948425,"about_ca_topic_score_gemma":0.006159831,"teacher_disagreement_score":0.0042948425,"about_ca_system_score_codex":0.0004160189,"about_ca_system_score_gemma":0.00089481345,"threshold_uncertainty_score":0.011375368},"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":"W4410475866","doi":"10.1016/j.specom.2025.103265","title":"Quantifying division of labour: Effects of clause type on intonational meaning","year":2025,"lang":"en","type":"article","venue":"Speech Communication","topic":"Linguistic Variation and Morphology","field":"Social Sciences","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":"Social Sciences and Humanities Research Council of Canada","keywords":"Meaning (existential); Linguistics; Division (mathematics); Type (biology); Computer science; Natural language processing; Speech recognition; Mathematics; Arithmetic; Philosophy; Epistemology","score_opus":0.040413051655295136,"score_gpt":0.3822127607960807,"score_spread":0.34179970914078556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410475866","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":[0.98101085,0.00042089258,0.0119704055,0.000112142254,0.000033000055,0.00012678694,0.00025914185,0.00007747913,0.005989257],"genre_scores_gemma":[0.9925337,0.000101815036,0.006231942,0.00011373127,0.000014350877,0.0001391003,0.00020626209,0.00014338928,0.00051571644],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.995475,0.002342201,0.0003703014,0.00073584355,0.00091433094,0.00016239965],"domain_scores_gemma":[0.93376553,0.05578228,0.0051237466,0.0033813193,0.001393118,0.0005540489],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005017085,0.00059779926,0.00065988,0.0006060211,0.00037423652,0.0024744857,0.00074811815,0.00067542144,0.005465953],"category_scores_gemma":[0.03856648,0.00061055913,0.0005643613,0.00044711618,0.0014457694,0.0023930625,0.0019219733,0.0010632591,0.0004614072],"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":[0.01076987,0.000709885,0.10596424,0.0015456835,0.00076848065,0.00046076812,0.0131322425,0.001828911,0.782065,0.00578725,0.00042313943,0.0765445],"study_design_scores_gemma":[0.00021726255,0.0020524864,0.9039784,0.0001722896,0.0004684273,0.000505218,0.0037498185,0.00596325,0.07347972,0.0077142087,0.001529236,0.00016959262],"about_ca_topic_score_codex":0.0005858791,"about_ca_topic_score_gemma":0.00065607735,"teacher_disagreement_score":0.005465953,"about_ca_system_score_codex":0.00035298738,"about_ca_system_score_gemma":0.0001852676,"threshold_uncertainty_score":0.026533186},"labels":[],"label_agreement":null},{"id":"W4411465948","doi":"10.1016/j.specom.2025.103270","title":"Automatic speech recognition technology to evaluate an audiometric word recognition test: A preliminary investigation","year":2025,"lang":"en","type":"article","venue":"Speech Communication","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":"Hospital for Sick Children","funders":"Hospital for Sick Children","keywords":"Speech recognition; Word recognition; Computer science; Test (biology); Word (group theory); Natural language processing; Artificial intelligence; Mathematics; Linguistics; Reading (process)","score_opus":0.03937597339703516,"score_gpt":0.31920367727727406,"score_spread":0.2798277038802389,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411465948","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":[0.9252547,0.0017948085,0.06262998,0.0003430305,0.00027062328,0.0009055012,0.00045542428,0.00033189525,0.008013943],"genre_scores_gemma":[0.9654916,0.0005251421,0.028595308,0.00034733317,0.00014077469,0.00039528045,0.0005054531,0.00007943582,0.0039196974],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9960497,0.0017825719,0.0003754498,0.0004296711,0.001178025,0.00018462625],"domain_scores_gemma":[0.99012053,0.0058031967,0.00024527317,0.00049961556,0.0030181403,0.00031322424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005615982,0.0009727033,0.00058753375,0.0017093534,0.00055242836,0.0007105475,0.0011255671,0.0018676788,0.0031185492],"category_scores_gemma":[0.013323343,0.00033853197,0.0006826021,0.0004950605,0.0006238388,0.0013641366,0.0005341717,0.0007920665,0.0020939768],"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":[0.009315752,0.0042169127,0.23370296,0.00043480366,0.00021634247,0.0017359791,0.0010387058,0.0015030104,0.57349145,0.0007765312,0.0010793171,0.1724882],"study_design_scores_gemma":[0.00080190174,0.07433543,0.35239428,0.000097173885,0.0009025349,0.012920629,0.0017013262,0.038228348,0.510478,0.0008799444,0.007110106,0.00015032913],"about_ca_topic_score_codex":0.0016349186,"about_ca_topic_score_gemma":0.0019377936,"teacher_disagreement_score":0.005615982,"about_ca_system_score_codex":0.0003618604,"about_ca_system_score_gemma":0.00060568616,"threshold_uncertainty_score":0.029700518},"labels":[],"label_agreement":null},{"id":"W4415746609","doi":"10.1016/j.specom.2025.103324","title":"Ultrasound imaging in second language research: Systematic review and thematic analysis","year":2025,"lang":"en","type":"article","venue":"Speech Communication","topic":"Phonetics and Phonology Research","field":"Psychology","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":"Université du Québec à Montréal; Concordia University; École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Biofeedback; Ultrasound; Pronunciation; Manner of articulation; Perception; Ultrasound imaging; Tongue; Articulation (sociology)","score_opus":0.04759745153485321,"score_gpt":0.44234879016571504,"score_spread":0.3947513386308618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415746609","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0065054484,0.9795222,0.0021063897,0.0011847325,0.0003768912,0.008239947,0.0015784175,0.00003185196,0.00045402962],"genre_scores_gemma":[0.13875301,0.8010714,0.014641445,0.0035733685,0.000358002,0.03973819,0.0013364825,0.000069068774,0.00045896397],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.89477026,0.04405404,0.044533152,0.0054402403,0.009370058,0.0018322051],"domain_scores_gemma":[0.79287094,0.15713745,0.033286612,0.004488551,0.010818094,0.0013982928],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07907268,0.0022138518,0.016471574,0.019168206,0.0017079398,0.006580623,0.0037270004,0.0039226464,0.0045576557],"category_scores_gemma":[0.241719,0.0019410121,0.015503327,0.017052028,0.002985601,0.005823393,0.0062667215,0.0025485454,0.00037801487],"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":[0.000277338,0.000025599804,0.0014602983,0.96836454,0.016896807,0.0000788319,0.0010092411,0.00007572092,0.00014095262,0.0002912593,0.000779512,0.01059987],"study_design_scores_gemma":[0.00080388127,0.00022807393,0.004393834,0.8725888,0.11104958,0.00021739444,0.0022032273,0.00016591322,0.00020229252,0.0008028952,0.0072672497,0.00007683805],"about_ca_topic_score_codex":0.008718606,"about_ca_topic_score_gemma":0.029018415,"teacher_disagreement_score":0.92092735,"about_ca_system_score_codex":0.0096837655,"about_ca_system_score_gemma":0.033444896,"threshold_uncertainty_score":0.4181813},"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}]}