{"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8648627,0.000898025,0.0008550075,0.0046610613,0.00041663405,0.0005258512,0.000018371386,0.00011446319,0.12764794],"genre_scores_gemma":[0.9952732,0.0002988669,0.0023793012,0.0006597357,0.000023156432,0.00005384753,0.00012998657,0.000018203456,0.0011637514],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99837846,0.0008264795,0.00022758706,0.00018529018,0.0001780668,0.00020411346],"domain_scores_gemma":[0.9986574,0.00024523822,0.0001480084,0.0008145161,0.000090597576,0.00004425428],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00084939296,0.00011110265,0.00010931864,0.00010695049,0.00018851273,0.0000477805,0.00033189252,0.00009997638,0.0013920012],"category_scores_gemma":[0.00015355657,0.000092663984,0.0000498102,0.00022798723,0.00008316319,0.00013456745,0.00004642819,0.0003316194,0.0003426016],"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":[0.00030811186,0.0041867406,0.17135438,0.000085421496,0.00031276952,0.00006894298,0.03596525,0.0003388362,0.009310821,0.20374298,0.07997547,0.49435028],"study_design_scores_gemma":[0.008170331,0.00020185552,0.5204642,0.0012577149,0.00010318903,0.0003883691,0.074673004,0.0007336372,0.068557166,0.14440893,0.17948203,0.001559596],"about_ca_topic_score_codex":0.00016756583,"about_ca_topic_score_gemma":0.00051152374,"teacher_disagreement_score":0.49279067,"about_ca_system_score_codex":0.00006529731,"about_ca_system_score_gemma":0.000023511551,"threshold_uncertainty_score":0.99952084},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5301093,0.000058490663,0.46441096,0.00017658119,0.000014769565,0.00015887438,0.0000019985835,0.00006593287,0.005003089],"genre_scores_gemma":[0.758909,0.00018421125,0.24079083,0.00004285834,0.000005498059,0.000003427355,0.0000045982415,0.000007323465,0.000052292657],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988186,0.00014010545,0.00032017607,0.00019211505,0.0003769251,0.00015207537],"domain_scores_gemma":[0.9983856,0.00017737494,0.00019483796,0.0010251981,0.00015346831,0.0000635162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041377606,0.00012952437,0.0001844538,0.00022550332,0.00015464218,0.000052007716,0.00063382904,0.00006888285,0.00011160283],"category_scores_gemma":[0.000024393725,0.00011212942,0.00010512652,0.00047089552,0.000031770156,0.0004915123,0.00006648175,0.00015662024,0.000019061108],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009911569,0.00029600994,0.00045303899,0.000018730922,0.000022479067,5.158151e-7,0.00031583046,0.486833,0.0065046414,0.00024104596,0.000037689482,0.5052671],"study_design_scores_gemma":[0.00024190084,0.00008146688,0.004127994,0.000095984404,0.000012735216,0.0000040571026,0.000008158696,0.9839834,0.010917963,0.00037437314,0.000031558364,0.00012041271],"about_ca_topic_score_codex":0.000024592187,"about_ca_topic_score_gemma":0.0000012562098,"teacher_disagreement_score":0.5051467,"about_ca_system_score_codex":0.00016284987,"about_ca_system_score_gemma":0.000041189647,"threshold_uncertainty_score":0.45725048},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08645426,0.00082435156,0.8807885,0.0026049307,0.0002555735,0.0007864938,0.000015538659,0.00025578987,0.028014563],"genre_scores_gemma":[0.5703635,0.00001960005,0.42938945,0.00007995018,0.00002195224,0.00003307713,0.0000139799995,0.000007351243,0.0000711494],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982392,0.0002997413,0.00042206302,0.00028281528,0.00053489226,0.00022126365],"domain_scores_gemma":[0.9965823,0.00031141235,0.0003802421,0.0016156435,0.0010063098,0.00010404115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022996324,0.0001381957,0.00026641352,0.00010308467,0.00014645673,0.00012188719,0.001676625,0.00008190829,0.000002790541],"category_scores_gemma":[0.00054163154,0.00013368402,0.00008765596,0.00036929306,0.0000818302,0.00062491157,0.0003746255,0.00016534966,0.000005555904],"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":[0.00014421318,0.0011381691,0.013331174,0.00026128208,0.00019301187,0.000002707921,0.005300456,0.0005390358,0.17685458,0.05749653,0.005991304,0.73874754],"study_design_scores_gemma":[0.0014640772,0.00018578136,0.012197083,0.00008919135,0.000020931075,0.000008411301,0.000461269,0.0070408722,0.9099165,0.06403054,0.0042611123,0.000324185],"about_ca_topic_score_codex":0.00014643212,"about_ca_topic_score_gemma":0.000067115616,"teacher_disagreement_score":0.73842335,"about_ca_system_score_codex":0.00014699853,"about_ca_system_score_gemma":0.00037865996,"threshold_uncertainty_score":0.54514766},"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":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68918735,0.008743736,0.25780216,0.034424957,0.00014351725,0.0017494223,0.000026016398,0.0021862865,0.0057365564],"genre_scores_gemma":[0.366828,0.0021804068,0.6302824,0.00059468334,0.000017344051,0.000022487657,0.000013820037,0.000005870767,0.000054975106],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992449,0.000066416185,0.0001720906,0.00024553383,0.00011234063,0.00015870533],"domain_scores_gemma":[0.99862564,0.00032426981,0.00008244895,0.0008530842,0.00008060039,0.000033978926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037787313,0.000119748576,0.00015826973,0.00011846161,0.00018340437,0.00029637245,0.00067027466,0.0000924326,0.0000035030796],"category_scores_gemma":[0.000100447505,0.00010867786,0.000034071287,0.00017834507,0.000072558076,0.00042449066,0.00016681755,0.000109081084,0.000006260069],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000063742737,0.00003612979,0.000042660587,0.0000034527775,0.0000063217876,0.0000013254182,0.00026648358,1.225135e-7,0.0033679458,0.0061801886,0.0002531927,0.9898358],"study_design_scores_gemma":[0.0048415423,0.0015872122,0.042608727,0.00028344014,0.000034266035,0.0005027884,0.002107626,0.05544677,0.63919437,0.20090328,0.050910894,0.0015790566],"about_ca_topic_score_codex":0.000010359139,"about_ca_topic_score_gemma":0.000008903427,"teacher_disagreement_score":0.98825675,"about_ca_system_score_codex":0.000017428982,"about_ca_system_score_gemma":0.000013263554,"threshold_uncertainty_score":0.44317544},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21005622,0.00040910963,0.77135956,0.0028344083,0.0004987789,0.0011053481,0.000024572857,0.00057755696,0.013134477],"genre_scores_gemma":[0.21176846,0.00020051465,0.787325,0.00042398865,0.00005190046,0.000044551598,0.000032008742,0.000023947969,0.00012958354],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983822,0.00020990137,0.00041547563,0.00037409112,0.000282855,0.00033547822],"domain_scores_gemma":[0.9978473,0.00043704972,0.00020759889,0.0011887028,0.00021352548,0.00010582027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006671723,0.00019431906,0.00021866968,0.00020788285,0.00032919092,0.0002892508,0.0009800403,0.0001351289,0.00016478138],"category_scores_gemma":[0.00025483718,0.00021002805,0.00016302112,0.00037723876,0.00006282613,0.00095773005,0.0001883868,0.00020838284,0.00028041558],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007682936,0.00015173377,0.000036034777,0.000014763438,0.000016787299,0.0000039657198,0.00023433102,0.000020968175,0.0011503792,0.00008622273,0.0005260454,0.99775106],"study_design_scores_gemma":[0.0009415189,0.000107882275,0.00034661804,0.0001857237,0.000046679113,0.00032600405,0.00016266544,0.933767,0.04964767,0.0072818026,0.0066076512,0.00057876174],"about_ca_topic_score_codex":0.000077866054,"about_ca_topic_score_gemma":0.00005249754,"teacher_disagreement_score":0.9971723,"about_ca_system_score_codex":0.00014526922,"about_ca_system_score_gemma":0.0000177979,"threshold_uncertainty_score":0.8564695},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9627612,0.00007557751,0.00011397144,0.0028648062,0.000663864,0.0005535494,0.00012828523,0.00020496493,0.032633767],"genre_scores_gemma":[0.9882657,0.00023776211,0.009480495,0.0007362265,0.00021617812,0.000060567072,0.00021779149,0.000060105842,0.0007252106],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9969773,0.0005093246,0.0004783607,0.0008173953,0.0008336381,0.0003839225],"domain_scores_gemma":[0.99511456,0.0020266778,0.00038654808,0.001949287,0.00030614313,0.00021675954],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00053049735,0.00034276964,0.00034418696,0.00020141306,0.0006088173,0.00032447683,0.0012655866,0.0003303159,0.0006125743],"category_scores_gemma":[0.0031505453,0.00032536918,0.00016494459,0.00040150023,0.00053317775,0.0006296723,0.00045194887,0.0010530443,0.00052301923],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023647115,0.0004350112,0.0033217992,0.000015367226,0.000044585064,0.000028183043,0.0128118135,0.00006958979,0.83391285,0.014247855,0.0002054791,0.13467099],"study_design_scores_gemma":[0.001365454,0.00025488262,0.09283722,0.00022928411,0.00006776122,0.000017135277,0.002891391,0.002891149,0.77356374,0.116902806,0.008168673,0.0008105005],"about_ca_topic_score_codex":0.04424783,"about_ca_topic_score_gemma":0.0033924065,"teacher_disagreement_score":0.13386048,"about_ca_system_score_codex":0.0001930917,"about_ca_system_score_gemma":0.00015458453,"threshold_uncertainty_score":0.99991983},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6931064,0.00042050917,0.00015425388,0.00022393094,0.00011608724,0.0006626512,0.00008689755,0.00008129135,0.30514798],"genre_scores_gemma":[0.9948298,0.00019482784,0.002857395,0.0001101751,0.00008350947,0.000068215355,0.0005595752,0.000019714294,0.0012767855],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990086,0.0002395876,0.00032087095,0.00015782547,0.00014451456,0.00012862476],"domain_scores_gemma":[0.9984619,0.0002032474,0.0003099883,0.0005658729,0.0004197376,0.00003923739],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00038618472,0.00010360906,0.00017220834,0.000111819914,0.000057083973,0.0000075201597,0.00021071146,0.00013338274,0.0016615223],"category_scores_gemma":[0.00042752016,0.00009813159,0.000062475054,0.0002487067,0.000102675054,0.00015404666,0.000043010074,0.00016436867,0.00016569065],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011424625,0.0027274585,0.0011224296,0.00017947463,0.0002729044,0.0000023951925,0.060011256,0.0000046531522,0.011252538,0.0030119026,0.03946949,0.88080305],"study_design_scores_gemma":[0.0108029265,0.002768425,0.00852532,0.0010952934,0.00036032806,0.000062190855,0.066723615,0.00016175676,0.81711555,0.0049152668,0.08645038,0.0010189575],"about_ca_topic_score_codex":0.00038969168,"about_ca_topic_score_gemma":0.0007266981,"teacher_disagreement_score":0.87978405,"about_ca_system_score_codex":0.000051389194,"about_ca_system_score_gemma":0.000023887957,"threshold_uncertainty_score":0.99925107},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99482495,0.000027769162,0.0011200403,0.00094390986,0.00006670769,0.0016273516,0.000008672131,0.000045145654,0.0013354714],"genre_scores_gemma":[0.98983455,0.000059261984,0.0095809465,0.00021448637,0.000012487771,0.00018783816,0.000019658824,0.000017188539,0.00007355528],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99826795,0.00037185446,0.00038655123,0.00034948887,0.00036423985,0.00025992945],"domain_scores_gemma":[0.9984686,0.0004907344,0.00012561292,0.000775671,0.00007698893,0.00006239638],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009830905,0.0001313289,0.00017498223,0.000097248194,0.00020793147,0.00007171103,0.0004073326,0.00007597538,0.000046035417],"category_scores_gemma":[0.0011823445,0.00012488966,0.00006289142,0.00017085734,0.00015240695,0.00027540303,0.00014448725,0.00021513863,0.00010187995],"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":[0.00004489491,0.00028125662,0.0026928915,0.000041633804,0.0000052484916,5.6495327e-7,0.0017466743,0.00013822746,0.93565065,0.0006709486,0.00029704047,0.058429986],"study_design_scores_gemma":[0.0013108953,0.00034435553,0.5484438,0.00015750839,0.000014082807,0.000016418056,0.0014893997,0.013424971,0.41543722,0.013187479,0.005727525,0.00044632994],"about_ca_topic_score_codex":0.0010224418,"about_ca_topic_score_gemma":0.00013527005,"teacher_disagreement_score":0.5457509,"about_ca_system_score_codex":0.00049940456,"about_ca_system_score_gemma":0.000032412507,"threshold_uncertainty_score":0.5092852},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88968337,0.0020065375,0.09898572,0.004634294,0.000074414085,0.0003135085,8.732116e-7,0.00005314158,0.004248175],"genre_scores_gemma":[0.56120914,0.0004878164,0.4377607,0.0004412689,0.000019812622,0.000009229567,0.0000029229982,0.0000069985276,0.00006212033],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987222,0.00018904792,0.00025263467,0.0002607741,0.00029671847,0.00027862916],"domain_scores_gemma":[0.9985318,0.00012783291,0.0001243256,0.0011096317,0.00006352953,0.000042870877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079692964,0.00013905927,0.0001361549,0.00011319373,0.00029176564,0.0003198287,0.0012211294,0.000057132187,0.000028429922],"category_scores_gemma":[0.0000436466,0.00011279748,0.000024954728,0.0005429999,0.00007834613,0.00057279784,0.00032176712,0.000231485,0.000021665272],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028931036,0.00076284714,0.0072873924,0.00009832086,0.000056678895,0.00010617089,0.028967803,0.0007711025,0.07406516,0.0017422971,0.0021122713,0.884001],"study_design_scores_gemma":[0.005328243,0.0003855533,0.009163622,0.0009981787,0.000054094755,0.0010675682,0.003261744,0.5709387,0.3536303,0.038416672,0.014740163,0.0020151804],"about_ca_topic_score_codex":0.000090475616,"about_ca_topic_score_gemma":0.00008663704,"teacher_disagreement_score":0.88198584,"about_ca_system_score_codex":0.0000635915,"about_ca_system_score_gemma":0.000019235435,"threshold_uncertainty_score":0.4599748},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9159302,0.0024814224,0.000024052217,0.0021356803,0.00033617538,0.0002159954,0.0000059605936,0.00009323074,0.07877724],"genre_scores_gemma":[0.99064296,0.0010235334,0.0010228478,0.00017628528,0.00017622703,0.000025434889,0.00001996821,0.000025471389,0.00688729],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9986475,0.00038106623,0.00021326175,0.00025820872,0.00018614008,0.00031382876],"domain_scores_gemma":[0.9985892,0.00020940798,0.00007610838,0.00094008324,0.00008171764,0.000103443694],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00048540134,0.00012403897,0.00016089035,0.00012417197,0.00023749743,0.00004857437,0.00046312166,0.000193293,0.003316322],"category_scores_gemma":[0.00006504374,0.00013050792,0.000038744933,0.00019503124,0.00029159302,0.00007352962,0.00027278299,0.0004915162,0.0025462497],"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":[0.0003142546,0.0017421317,0.008718122,0.000037316593,0.00033499894,0.00009399452,0.015925167,0.000001771734,0.016074134,0.009148887,0.317017,0.6305922],"study_design_scores_gemma":[0.0044215918,0.002011873,0.51348156,0.0000762353,0.00009063648,0.00072036637,0.0021860232,0.0039463732,0.0069030263,0.010027577,0.45496005,0.0011746666],"about_ca_topic_score_codex":0.00031283713,"about_ca_topic_score_gemma":0.000088757326,"teacher_disagreement_score":0.6294176,"about_ca_system_score_codex":0.000036609417,"about_ca_system_score_gemma":0.000009797215,"threshold_uncertainty_score":0.9982304},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5740828,0.007384897,0.4129843,0.0020545193,0.0003934902,0.00061518326,0.000004217732,0.00028534856,0.0021952468],"genre_scores_gemma":[0.5863629,0.000067877096,0.41329128,0.00013221016,0.00004847722,0.000011420973,0.000010088074,0.000008191956,0.000067543704],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999227,0.000061680745,0.00015604825,0.00017785045,0.00013491276,0.00024250295],"domain_scores_gemma":[0.9988203,0.000110944595,0.00011830121,0.0007661422,0.00010659336,0.00007772683],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045973583,0.00010833535,0.0001031612,0.00007493769,0.00032137524,0.00017061205,0.0005189822,0.00007100602,0.0000035736211],"category_scores_gemma":[0.00010867913,0.00010408422,0.000033491655,0.00019294037,0.00005046402,0.001112449,0.00017814568,0.00010975351,0.000009183477],"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":[0.000034607492,0.00028842437,0.023778852,0.00011411711,0.000054544653,3.6740548e-7,0.0059782187,0.00007099264,0.2235007,0.015637333,0.0020874788,0.72845435],"study_design_scores_gemma":[0.0014174605,0.000082764804,0.116994485,0.00018864911,0.000065676875,0.00013467878,0.0004649513,0.02426201,0.8029146,0.007589765,0.04495444,0.00093048107],"about_ca_topic_score_codex":0.000048735987,"about_ca_topic_score_gemma":0.0000153378,"teacher_disagreement_score":0.72752386,"about_ca_system_score_codex":0.000057536574,"about_ca_system_score_gemma":0.000028345301,"threshold_uncertainty_score":0.42444313},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19019267,0.000043727447,0.80069745,0.0009904177,0.000020174257,0.0003228243,0.0000017677428,0.00035923804,0.0073717344],"genre_scores_gemma":[0.5395692,0.00001515369,0.4601377,0.00016314251,0.0000116524125,0.0000065146774,0.000018668012,0.0000122951915,0.00006566752],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983379,0.00009101233,0.00037528278,0.00032125687,0.00059564755,0.0002788603],"domain_scores_gemma":[0.997558,0.00012258894,0.0003765188,0.0015046794,0.00035625676,0.000081940605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069371687,0.00019520953,0.00020894293,0.00030236584,0.00023598378,0.00008826025,0.0013251659,0.000126822,0.0000052422047],"category_scores_gemma":[0.00004565345,0.00016975042,0.00006239284,0.00065620657,0.000108701504,0.0005488519,0.000232969,0.0002890735,0.000009882424],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015235021,0.00031904448,0.0027890638,0.0000507492,0.000014826809,0.000006500023,0.0007954547,0.019188209,0.10798729,0.0020336863,0.00022203222,0.8664408],"study_design_scores_gemma":[0.00029319827,0.00017505728,0.00067738356,0.00020955002,0.0000074146087,0.000009032946,0.000036400328,0.36656827,0.6301605,0.0014274839,0.00026119457,0.00017453234],"about_ca_topic_score_codex":0.00006267484,"about_ca_topic_score_gemma":0.000102633276,"teacher_disagreement_score":0.86626625,"about_ca_system_score_codex":0.0001263952,"about_ca_system_score_gemma":0.000112013004,"threshold_uncertainty_score":0.6922221},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6431033,0.00046172913,0.2918312,0.027496504,0.00043433072,0.00057310925,0.0000044161743,0.00051902654,0.035576396],"genre_scores_gemma":[0.75693756,0.00007403601,0.24186532,0.00041614438,0.000045751513,0.000026262267,0.000014594029,0.00001031176,0.00061004236],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99870133,0.00005392284,0.00029722863,0.0002859418,0.0003265737,0.0003350145],"domain_scores_gemma":[0.99789923,0.00006663898,0.000110034016,0.0016831906,0.00012743668,0.0001134773],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005414985,0.00015132123,0.0001428887,0.00005081008,0.00030378922,0.00028971926,0.0016029418,0.0000753124,0.00015195468],"category_scores_gemma":[0.000048186506,0.00013855658,0.000061661434,0.0003621744,0.000091492926,0.0009160937,0.00026489794,0.0003788996,0.00023467887],"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":[0.0000106183215,0.00014103418,0.00034271076,0.000015337164,0.000013370897,0.0000041909693,0.00068564934,0.000002611256,0.3856892,0.0047123595,0.0009425389,0.6074404],"study_design_scores_gemma":[0.00035171592,0.00004865702,0.0006540225,0.000034670677,0.000005942304,0.000024441802,0.000025650774,0.0032864287,0.9698549,0.00826428,0.01725244,0.00019686398],"about_ca_topic_score_codex":0.000041939784,"about_ca_topic_score_gemma":0.00021075239,"teacher_disagreement_score":0.60724354,"about_ca_system_score_codex":0.00003551885,"about_ca_system_score_gemma":0.000057548586,"threshold_uncertainty_score":0.56501734},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9941437,0.000013840026,0.00011959229,0.0013372839,0.000049468086,0.0003697698,0.0000022893332,0.00002502251,0.0039389976],"genre_scores_gemma":[0.99126166,0.00006269269,0.008342027,0.00024854342,0.00001157721,0.000020913165,0.0000022766294,0.000007699817,0.00004260814],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9987173,0.0006452889,0.00018888383,0.00016280336,0.00016435195,0.00012134585],"domain_scores_gemma":[0.9990593,0.0002519191,0.00005308641,0.00054743764,0.0000523008,0.000035944726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009509036,0.0000614639,0.0001016143,0.00013446572,0.000057752284,0.00001192358,0.00011397857,0.000053720658,0.000028774519],"category_scores_gemma":[0.0011366727,0.000062321225,0.000027163578,0.0004148404,0.000052993477,0.0001583551,0.00004818152,0.00012121988,0.0000639714],"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":[0.000008409158,0.00009567614,0.0070761614,0.00001643113,3.4518956e-7,0.0000011409832,0.0027354648,0.000023267017,0.90728813,0.002685046,0.000014359116,0.080055565],"study_design_scores_gemma":[0.00025658382,0.000094024,0.68031216,0.00009209192,0.0000024847152,0.000014287058,0.00041761762,0.00059653184,0.31481478,0.0016273585,0.0016342244,0.00013787032],"about_ca_topic_score_codex":0.0006604894,"about_ca_topic_score_gemma":0.00021458254,"teacher_disagreement_score":0.673236,"about_ca_system_score_codex":0.00008179383,"about_ca_system_score_gemma":0.000017394852,"threshold_uncertainty_score":0.2541386},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97692037,0.00035472895,0.00025627168,0.00041645995,0.00059425633,0.00030947334,0.00006999279,0.000044738998,0.021033706],"genre_scores_gemma":[0.99530077,0.00014435184,0.0033622414,0.000053718675,0.00006488366,0.000032918906,0.0001290956,0.000021522697,0.00089050335],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99859625,0.00034148872,0.00032740028,0.00023866523,0.00020658229,0.00028960645],"domain_scores_gemma":[0.99738896,0.00040575632,0.00020602277,0.001567933,0.00034520254,0.000086146814],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005126637,0.00012340385,0.00020694056,0.00014016639,0.00011058216,0.000020081998,0.0005760718,0.00024230254,0.0015880006],"category_scores_gemma":[0.00021296465,0.000123218,0.00006517058,0.00024076196,0.00032300822,0.000080129925,0.00018481373,0.0008474339,0.00048080465],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019889604,0.00025446236,0.0058041736,0.0000031160253,0.000105605555,0.0000028470215,0.00497308,2.2359914e-7,0.90708095,0.00097211136,0.00021513201,0.080389425],"study_design_scores_gemma":[0.001232652,0.00015759507,0.4925218,0.000013068238,0.000025485848,0.000010331128,0.0011717667,0.00011846243,0.48775932,0.0072978777,0.009522271,0.00016936514],"about_ca_topic_score_codex":0.01030408,"about_ca_topic_score_gemma":0.0073219095,"teacher_disagreement_score":0.4867176,"about_ca_system_score_codex":0.000034894496,"about_ca_system_score_gemma":0.00004210125,"threshold_uncertainty_score":0.9993247},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9938463,0.00042556925,0.000013707941,0.00037017022,0.000054310764,0.00022859116,0.000006379388,0.000007244323,0.0050477176],"genre_scores_gemma":[0.9993846,0.00013203688,0.00021182647,0.000086361244,0.0000049660957,0.000028704268,0.000015795706,0.0000053437866,0.00013037502],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99814147,0.0010799405,0.00026264446,0.00014880349,0.00021868096,0.0001484377],"domain_scores_gemma":[0.9980312,0.0005992351,0.00011125489,0.0011763824,0.00006287627,0.000019024397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007527452,0.00007400076,0.00012668649,0.00018654426,0.0000696624,0.000021592572,0.0008127998,0.0001087847,0.00014951041],"category_scores_gemma":[0.00033348886,0.00005421493,0.000024860661,0.0006699962,0.00019356412,0.000029901177,0.000036345078,0.0004090169,0.000054862783],"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":[0.0004497326,0.00351024,0.24532758,0.00008733542,0.00022601579,0.00004031164,0.10365755,0.00042748728,0.20751044,0.38731954,0.0033181964,0.04812557],"study_design_scores_gemma":[0.00023587912,0.000079188016,0.9726125,0.000011195328,0.0000053277577,0.0000066154053,0.00046821116,0.000011595686,0.0041333954,0.02208618,0.00029422305,0.000055711233],"about_ca_topic_score_codex":0.00034468106,"about_ca_topic_score_gemma":0.0001968653,"teacher_disagreement_score":0.7272849,"about_ca_system_score_codex":0.000021837246,"about_ca_system_score_gemma":0.000018455,"threshold_uncertainty_score":0.22108205},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.079962075,0.0003479706,0.7843447,0.008751964,0.00019460743,0.0005590159,0.000004311991,0.0006340101,0.12520136],"genre_scores_gemma":[0.52973723,0.000016518676,0.46822935,0.0006152238,0.00005505516,0.00002380788,0.00008492412,0.000012954516,0.0012248979],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998456,0.00014226619,0.0003109388,0.0003343087,0.00048327504,0.00027323674],"domain_scores_gemma":[0.9979538,0.00012327214,0.00019564379,0.0015096166,0.00016504811,0.00005262303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053978723,0.00016701435,0.00014819275,0.00015093309,0.00030150093,0.00023231111,0.0011677268,0.00007652944,0.00007260541],"category_scores_gemma":[0.000032421503,0.00016909333,0.00005976278,0.00047940126,0.000045777833,0.00046050464,0.0001597669,0.00019022681,0.00059937563],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003403743,0.00069208356,0.00016471076,0.000028177901,0.0000099464,0.000008079116,0.00029679452,0.0021900162,0.08429638,0.0021023317,0.0093097435,0.9008677],"study_design_scores_gemma":[0.00047870568,0.00010610094,0.00089396274,0.0000875066,0.000006204218,0.0000055480737,0.000017218716,0.2332469,0.75122184,0.006206179,0.0074737733,0.00025606988],"about_ca_topic_score_codex":0.000112033835,"about_ca_topic_score_gemma":0.000059880458,"teacher_disagreement_score":0.90061164,"about_ca_system_score_codex":0.00014669618,"about_ca_system_score_gemma":0.000092836366,"threshold_uncertainty_score":0.7703961},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86889863,0.00016143297,0.00026818452,0.0001404323,0.000042663603,0.00024165897,0.000007149866,0.000033011802,0.13020685],"genre_scores_gemma":[0.99548304,0.000036811165,0.0033417798,0.000044191973,0.000021772672,0.000042990683,0.000105872576,0.000009787434,0.00091377855],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9992067,0.00016996768,0.0002553537,0.00012853206,0.00013595389,0.00010344821],"domain_scores_gemma":[0.9992574,0.00006712124,0.00013546435,0.00038559514,0.00013370893,0.000020705742],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017919258,0.00007483161,0.00011218014,0.00013499848,0.00007980395,0.000005648981,0.00018460808,0.000079568206,0.0008685583],"category_scores_gemma":[0.000071163486,0.000074181706,0.000034381468,0.00021847543,0.0001022213,0.00013328977,0.000028842636,0.00017594897,0.00008387389],"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":[0.0028415688,0.003298848,0.056514844,0.00013731241,0.00013832001,0.000027584403,0.26271608,0.00013741855,0.1559682,0.14506043,0.006888127,0.36627126],"study_design_scores_gemma":[0.0053001596,0.00033615858,0.9483557,0.00018705025,0.000015492216,0.00006997833,0.028138306,0.0036324016,0.011105434,0.0012848054,0.0012267231,0.00034783004],"about_ca_topic_score_codex":0.0004201441,"about_ca_topic_score_gemma":0.0003068774,"teacher_disagreement_score":0.8918408,"about_ca_system_score_codex":0.00007982803,"about_ca_system_score_gemma":0.000037435715,"threshold_uncertainty_score":0.95101047},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7065324,0.00010470037,0.0019071331,0.00025541388,0.00013797783,0.00035999474,0.0000144763935,0.000103619146,0.29058424],"genre_scores_gemma":[0.97470194,0.000043446355,0.022713918,0.00010285688,0.00004015335,0.000041750045,0.00012211257,0.000017837856,0.0022159857],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9988142,0.00029917457,0.00037400154,0.00021545129,0.00016102774,0.00013613082],"domain_scores_gemma":[0.9985017,0.00006790197,0.00023783503,0.00084511767,0.00029255208,0.000054893964],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00019596619,0.00011916743,0.0001642899,0.000102356076,0.00013429565,0.000016985674,0.00035456227,0.00014441724,0.009805555],"category_scores_gemma":[0.00010354249,0.00011305505,0.000060113372,0.00023622943,0.00016336764,0.00020114356,0.000054882785,0.00026335358,0.0010535404],"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":[0.00053768745,0.0028512944,0.010242111,0.000034215627,0.00015912016,0.000009007004,0.15407537,0.0000025871614,0.062699,0.07030751,0.005816773,0.6932653],"study_design_scores_gemma":[0.002201201,0.0004634068,0.82114553,0.00015469796,0.00013761071,0.000059371134,0.028853767,0.0016076425,0.07764145,0.06322881,0.0038488724,0.0006576504],"about_ca_topic_score_codex":0.0064837937,"about_ca_topic_score_gemma":0.00042885187,"teacher_disagreement_score":0.81090343,"about_ca_system_score_codex":0.000058795387,"about_ca_system_score_gemma":0.00003891532,"threshold_uncertainty_score":0.99972427},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6091188,0.0009379066,0.38740256,0.0004584204,0.00010789018,0.00021713247,0.0000015152117,0.00018647395,0.0015692938],"genre_scores_gemma":[0.5253203,0.00008507202,0.4743923,0.00007277699,0.00006298595,0.0000036085148,0.000014677709,0.000016436506,0.00003186541],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9978665,0.00010920952,0.00053891604,0.00052059564,0.0005269948,0.00043777816],"domain_scores_gemma":[0.9977065,0.00024257193,0.00032760474,0.0013940197,0.00021996722,0.00010933469],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008460579,0.0002782499,0.00028574353,0.00028880374,0.0006333877,0.00091785163,0.0011623285,0.00017888247,0.000013025551],"category_scores_gemma":[0.00012911721,0.00028864155,0.000075575605,0.0007563096,0.00012201261,0.0019195675,0.00042895766,0.00039757925,0.000034227884],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028499428,0.00018333005,0.006722182,0.000047163845,0.000014846622,0.000030211942,0.00045348893,0.0017530258,0.07137515,0.0018845142,0.00026286772,0.91724473],"study_design_scores_gemma":[0.001047961,0.000074391355,0.027123319,0.00044012917,0.00003417994,0.00042343806,0.00006411294,0.28060737,0.58859295,0.100216016,0.0007132339,0.0006628961],"about_ca_topic_score_codex":0.00044299237,"about_ca_topic_score_gemma":0.00018396325,"teacher_disagreement_score":0.9165818,"about_ca_system_score_codex":0.00019887708,"about_ca_system_score_gemma":0.00009842038,"threshold_uncertainty_score":0.99995655},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6252322,0.0031142028,0.24810551,0.011618456,0.00047754956,0.0008074836,0.000011446972,0.00093955087,0.10969358],"genre_scores_gemma":[0.6852992,0.0002750743,0.3136933,0.00019766223,0.00002751191,0.000012007939,0.000018302577,0.000016003256,0.00046089024],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984049,0.00024214954,0.00034512373,0.00039318556,0.00028506437,0.00032953772],"domain_scores_gemma":[0.99778354,0.0002696919,0.00019112024,0.0014662762,0.00015467433,0.0001346985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006152118,0.00020039144,0.00022400774,0.00017834164,0.0005009518,0.0003988429,0.0010883869,0.000087381115,0.000041118954],"category_scores_gemma":[0.000251646,0.00020816125,0.000057551853,0.0006023476,0.0001203685,0.001064468,0.0003417417,0.0003949264,0.00009346439],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006505342,0.00016505425,0.018504968,0.000038321195,0.000064785716,0.0000092026185,0.0012859365,0.000008893289,0.0068743564,0.009196317,0.0021696908,0.96167594],"study_design_scores_gemma":[0.001959346,0.00016319325,0.016759053,0.00028592855,0.00007901772,0.00042680485,0.0012013218,0.0020284778,0.68349594,0.11988574,0.17235579,0.0013593724],"about_ca_topic_score_codex":0.000084359795,"about_ca_topic_score_gemma":0.00016293887,"teacher_disagreement_score":0.9603166,"about_ca_system_score_codex":0.0000769932,"about_ca_system_score_gemma":0.000086745684,"threshold_uncertainty_score":0.8488569},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76135784,0.00018557583,0.23057884,0.0008276422,0.0011097445,0.0028355964,0.00035740502,0.00039304196,0.0023543448],"genre_scores_gemma":[0.973785,0.000018295881,0.025739081,0.00012046646,0.0000662678,0.000054468295,0.000058837526,0.00001750467,0.0001400798],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986052,0.00022393237,0.00023201453,0.00050970895,0.00018988102,0.00023926934],"domain_scores_gemma":[0.99815226,0.0009162128,0.00017134375,0.0006015673,0.0000942263,0.00006436418],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000824808,0.0001242746,0.00014422605,0.0000717469,0.000762275,0.00019368726,0.0006234455,0.00007099996,0.0000029191576],"category_scores_gemma":[0.0015261412,0.00011317783,0.000029283974,0.00018788745,0.00017996217,0.0003517243,0.00022460354,0.00015206521,0.0000030181718],"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":[0.00021578876,0.0002593817,0.00036622424,0.0006156761,0.000005998583,0.0000064203145,0.00007445909,0.00010320102,0.87779915,0.05197707,0.0028176934,0.06575896],"study_design_scores_gemma":[0.0025003285,0.00064696895,0.003334221,0.00034218794,0.00011293165,0.00064167427,0.00027630845,0.68048865,0.2486755,0.008058777,0.054112647,0.00080980704],"about_ca_topic_score_codex":0.000002488783,"about_ca_topic_score_gemma":0.000007776285,"teacher_disagreement_score":0.6803855,"about_ca_system_score_codex":0.000061687126,"about_ca_system_score_gemma":0.000046685607,"threshold_uncertainty_score":0.58628803},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0589159,0.00011175335,0.9312132,0.004620777,0.00009546683,0.00034600866,8.0147265e-7,0.0003202948,0.0043758154],"genre_scores_gemma":[0.42184,0.00002932842,0.5776727,0.00022941915,0.00007187215,0.000028174145,0.000005104453,0.000007590954,0.00011575879],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99928147,0.000038345217,0.00017854835,0.00016771547,0.00015012283,0.00018378792],"domain_scores_gemma":[0.9984953,0.00022657812,0.000112415786,0.0010121409,0.0001228361,0.000030758623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012492673,0.00008594067,0.000069230075,0.000076546086,0.00038428255,0.00011695238,0.0010683236,0.000051962605,0.0000040492964],"category_scores_gemma":[0.00013514522,0.000066786284,0.00004452082,0.00024179814,0.00004457383,0.00032608237,0.00018176972,0.00016569623,0.000014086338],"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":[0.00004399037,0.00008916893,0.000009039447,0.000015793194,0.000010854554,8.97686e-7,0.0006736756,0.00008754047,0.1759371,0.024738614,0.0022820965,0.7961112],"study_design_scores_gemma":[0.00007537382,0.000067387526,0.000058730333,0.00005265939,0.0000021861433,0.000014461228,0.00005801311,0.003166975,0.98203295,0.0070169545,0.007361716,0.000092603506],"about_ca_topic_score_codex":0.000008845324,"about_ca_topic_score_gemma":0.000003515864,"teacher_disagreement_score":0.80609584,"about_ca_system_score_codex":0.00005728145,"about_ca_system_score_gemma":0.000024311932,"threshold_uncertainty_score":0.29556295},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86877996,0.00020496619,0.11383822,0.013428096,0.0005026437,0.00041421683,0.0000035413118,0.00026240194,0.0025659911],"genre_scores_gemma":[0.6383135,0.000038871844,0.3611675,0.00023902999,0.000058997775,0.000021314901,0.000010569842,0.000007950257,0.00014228022],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999316,0.000032239204,0.00014803071,0.00022587168,0.000127916,0.00014994232],"domain_scores_gemma":[0.9987928,0.0001053032,0.00009518958,0.00085892767,0.000088366054,0.000059368802],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034744263,0.000093150724,0.0000868507,0.00007940747,0.00026197894,0.00013019817,0.00061427907,0.00007093588,0.000003832183],"category_scores_gemma":[0.00011896037,0.00008874824,0.00003169762,0.00016189016,0.000068419555,0.00051590416,0.00010199482,0.0002244294,0.000010579095],"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":[0.000035784044,0.00011484554,0.00006719822,0.000025272511,0.000011259512,5.786602e-7,0.00081379653,0.000058497884,0.3576224,0.019840168,0.0026839913,0.6187262],"study_design_scores_gemma":[0.00079347746,0.00018604085,0.0012420448,0.000065919055,0.000011620743,0.00006122565,0.000058527643,0.021233888,0.91528565,0.045108043,0.015639415,0.00031412672],"about_ca_topic_score_codex":0.000013830029,"about_ca_topic_score_gemma":0.00001626965,"teacher_disagreement_score":0.6184121,"about_ca_system_score_codex":0.000016584767,"about_ca_system_score_gemma":0.000034200802,"threshold_uncertainty_score":0.36190483},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5016036,0.00018617591,0.497151,0.00035143315,0.00006193789,0.00027454173,0.000009739696,0.00006658716,0.00029497873],"genre_scores_gemma":[0.8095995,0.000009201618,0.19031806,0.000012202146,0.000016101805,0.0000147426845,0.000011272818,0.0000059707672,0.000012910732],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985353,0.00012077673,0.00061337405,0.0002388703,0.00025771672,0.00023396136],"domain_scores_gemma":[0.9963703,0.00086435693,0.0005087062,0.001739591,0.00047249286,0.000044533193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027622036,0.00011437337,0.00030040301,0.00034508374,0.00036930977,0.00006086323,0.0015369678,0.000070809016,0.0000038016076],"category_scores_gemma":[0.00036553288,0.000096848,0.00024666125,0.0017795205,0.00009434148,0.00021081294,0.00022658572,0.00013552576,0.0000010470984],"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":[0.00017198593,0.00056832377,0.07282579,0.0010026692,0.000997357,0.0000024191804,0.0024837004,0.008977053,0.17569733,0.0042904783,0.00002707606,0.7329558],"study_design_scores_gemma":[0.00046156565,0.000037495036,0.10274148,0.0001306307,0.00029434558,0.0000030730173,0.0004767704,0.05705171,0.8381208,0.00046861722,0.00006164961,0.00015186328],"about_ca_topic_score_codex":0.00035646904,"about_ca_topic_score_gemma":0.0009410071,"teacher_disagreement_score":0.73280394,"about_ca_system_score_codex":0.00014647737,"about_ca_system_score_gemma":0.00008454707,"threshold_uncertainty_score":0.39493468},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9147454,0.00060919457,0.01681705,0.008283746,0.00094528735,0.0016657439,0.000016840768,0.00033194933,0.056584805],"genre_scores_gemma":[0.8886596,0.000079906444,0.106428124,0.003955293,0.00011029857,0.00015864783,0.00028930893,0.000027040169,0.0002917977],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971578,0.0012129332,0.0006884783,0.00021351721,0.00028710073,0.00044017416],"domain_scores_gemma":[0.99723494,0.00027600012,0.00041906702,0.001236063,0.000608425,0.00022547477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025868583,0.00013551635,0.00021400755,0.00016766184,0.0007729523,0.000010540625,0.0003905928,0.00028020923,0.000094716495],"category_scores_gemma":[0.00038688982,0.0001295194,0.000032282223,0.0003021299,0.000080899,0.00014323008,0.00016127853,0.00063279,0.00066506135],"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":[0.001545103,0.0010250355,0.65434307,0.0009953649,0.000078813646,0.000040651317,0.050698917,0.000767968,0.020402024,0.09393778,0.077275,0.09889027],"study_design_scores_gemma":[0.0054144617,0.00019527308,0.2079471,0.00058624696,0.000054792446,0.000025898931,0.0073810914,0.049370363,0.0018663005,0.009064588,0.7172501,0.0008437616],"about_ca_topic_score_codex":0.00062970276,"about_ca_topic_score_gemma":0.00027650566,"teacher_disagreement_score":0.63997513,"about_ca_system_score_codex":0.0006103876,"about_ca_system_score_gemma":0.0017961898,"threshold_uncertainty_score":0.854824},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9851727,0.00079035264,0.00010539132,0.004018961,0.000021567765,0.00013053621,5.82939e-7,0.000014835514,0.009745102],"genre_scores_gemma":[0.9965622,0.0016267126,0.0013013884,0.000163931,0.000019322912,0.0000038772123,0.000006655925,0.0000043702807,0.00031158442],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99960655,0.000042910666,0.00011240367,0.000057655474,0.00010903635,0.00007145292],"domain_scores_gemma":[0.99912655,0.00009959624,0.00006115853,0.0005690496,0.000117366384,0.000026257789],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022468757,0.000040953415,0.00007117274,0.000023890132,0.00017429024,0.000011093962,0.00012670341,0.000037446553,0.000015939393],"category_scores_gemma":[0.00012538646,0.0000261168,0.00001622849,0.000085701016,0.00028390542,0.000038098635,0.0000772608,0.00009074169,0.00001380286],"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":[0.0004967934,0.000363452,0.16373242,0.000116663556,0.00012269028,0.0000013896899,0.008309446,8.999551e-8,0.02957664,0.027998239,0.008460463,0.7608217],"study_design_scores_gemma":[0.0016805206,0.00090996275,0.7767814,0.00029442715,0.00009057257,0.000043578602,0.0030392255,0.0005762899,0.06319994,0.10052066,0.05266502,0.00019844482],"about_ca_topic_score_codex":0.00006482785,"about_ca_topic_score_gemma":0.00016007583,"teacher_disagreement_score":0.7606233,"about_ca_system_score_codex":0.0000073650463,"about_ca_system_score_gemma":0.000019890667,"threshold_uncertainty_score":0.13405173},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9864725,0.0011432931,0.0056892023,0.0042590178,0.00004032938,0.00042431595,0.000006852788,0.000017160668,0.0019473151],"genre_scores_gemma":[0.9973276,0.0006075718,0.0017374201,0.000052541902,0.000012084804,0.0000576907,0.000013100529,0.00000954126,0.00018240155],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998723,0.00062348245,0.0001410434,0.0002141407,0.00012663497,0.00017173485],"domain_scores_gemma":[0.9986449,0.0004693317,0.000067466295,0.00073642266,0.00005315017,0.000028720444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012398679,0.00008865242,0.00013936157,0.00006564434,0.00011501275,0.000075446864,0.00021612221,0.00008703419,0.0000105259305],"category_scores_gemma":[0.00008280596,0.0000753895,0.000017488248,0.00012880698,0.00008888951,0.00013922784,0.00008005893,0.000265673,0.000012042219],"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":[0.0018100472,0.0007569025,0.21584296,0.00034249056,0.00030252864,0.0000059454906,0.08741913,0.25538513,0.16435054,0.085426025,0.0003673294,0.18799098],"study_design_scores_gemma":[0.00056598027,0.000018279408,0.017867865,0.00002580072,0.000006831646,0.000004283652,0.00036347014,0.96861434,0.00065671647,0.011744866,0.00003423038,0.00009735455],"about_ca_topic_score_codex":0.0003833705,"about_ca_topic_score_gemma":0.0007650483,"teacher_disagreement_score":0.7132292,"about_ca_system_score_codex":0.000034209024,"about_ca_system_score_gemma":0.000019214389,"threshold_uncertainty_score":0.30742946},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49242654,0.0016100209,0.47538626,0.01897955,0.00023998992,0.0007441871,0.000005324005,0.0006477091,0.009960418],"genre_scores_gemma":[0.59470993,0.00011579364,0.40219262,0.0027227274,0.00007331811,0.00001719236,0.000021577674,0.000018103106,0.00012877122],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9981797,0.00016034416,0.00040605408,0.00044518648,0.00044142507,0.00036733918],"domain_scores_gemma":[0.9979851,0.00007384207,0.0002531804,0.0013202791,0.00018536921,0.0001822167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000361275,0.00021400864,0.00023000396,0.00008932281,0.0003607159,0.00031654784,0.0020316925,0.00008359571,0.000090708454],"category_scores_gemma":[0.00011065378,0.00022054127,0.00007979489,0.0007244993,0.00007195138,0.0008237677,0.00094487675,0.00029186494,0.00019873875],"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":[0.00006696849,0.00034594268,0.0008600813,0.00010433374,0.00008762155,0.000038916092,0.003521014,0.00021226204,0.6666241,0.0012403872,0.0058505926,0.32104778],"study_design_scores_gemma":[0.00067020033,0.00013277153,0.0003138608,0.000116735355,0.000020381774,0.00002663539,0.00012535804,0.056511745,0.92528206,0.0013724968,0.015055696,0.00037207428],"about_ca_topic_score_codex":0.000047408867,"about_ca_topic_score_gemma":0.000014530974,"teacher_disagreement_score":0.3206757,"about_ca_system_score_codex":0.0001641948,"about_ca_system_score_gemma":0.00013094413,"threshold_uncertainty_score":0.8993412},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99009883,0.00033020554,0.0009818161,0.0027939964,0.00010790554,0.0010455956,0.00007499871,0.000024272158,0.004542374],"genre_scores_gemma":[0.99190694,0.001170522,0.006132183,0.0001311907,0.000020892581,0.000092760085,0.000020010995,0.000019866222,0.00050563837],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998041,0.0004337743,0.00046067114,0.00049961003,0.00033048075,0.0002345179],"domain_scores_gemma":[0.9924264,0.0054212916,0.00031575203,0.0007920733,0.0009666782,0.00007781397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012927541,0.00019639262,0.00030472173,0.00009196564,0.00062324695,0.000107737374,0.000394234,0.00011751568,0.000005272724],"category_scores_gemma":[0.0048898705,0.00015441627,0.000086891814,0.0004653555,0.0010433542,0.00031534245,0.00040477482,0.00033332006,0.0000017715973],"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":[0.0008024799,0.001151867,0.005877674,0.00068327493,0.00024058517,0.00000725495,0.09224138,0.00023880646,0.46538764,0.08765407,0.00042407788,0.3452909],"study_design_scores_gemma":[0.0010974694,0.00047367843,0.08230476,0.00025138247,0.00004483179,0.000012167932,0.01015026,0.0085527375,0.8257689,0.069929786,0.0010685337,0.0003455142],"about_ca_topic_score_codex":0.00019680383,"about_ca_topic_score_gemma":0.00027683083,"teacher_disagreement_score":0.36038125,"about_ca_system_score_codex":0.00015383582,"about_ca_system_score_gemma":0.00013365228,"threshold_uncertainty_score":0.6296913},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9926462,0.0022346356,0.00025367955,0.0012936809,0.00017916755,0.00024808032,0.000021151867,0.000059143902,0.003064221],"genre_scores_gemma":[0.9969611,0.00016277799,0.0020760847,0.00030458704,0.000036208243,0.000047428133,0.00020919672,0.000037319733,0.00016527761],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9976906,0.00092717796,0.00033997098,0.00043889234,0.0002606024,0.00034274755],"domain_scores_gemma":[0.99840343,0.00055921875,0.000062805855,0.00083010265,0.000044691227,0.00009973688],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046900427,0.00017304737,0.00028309648,0.0004854355,0.0005183739,0.000091716785,0.0006168519,0.00009672132,0.00047160537],"category_scores_gemma":[0.000057401798,0.0002033179,0.00005072558,0.00065842597,0.00010107082,0.00009882904,0.00041340574,0.0010603451,0.000061150204],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042356894,0.00042793303,0.036679447,0.000012207634,0.0003117983,0.00012593417,0.27946168,0.0033923746,0.5885921,0.00010668751,0.0004927445,0.08997354],"study_design_scores_gemma":[0.0039454685,0.00056091393,0.8600052,0.00025088608,0.00014725645,0.000028037724,0.057751838,0.010938984,0.046557024,0.008308261,0.010230625,0.0012755195],"about_ca_topic_score_codex":0.021582834,"about_ca_topic_score_gemma":0.0020763362,"teacher_disagreement_score":0.82332575,"about_ca_system_score_codex":0.00014537195,"about_ca_system_score_gemma":0.000034824672,"threshold_uncertainty_score":0.98493254},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97347826,0.00065985357,0.003615667,0.0018129093,0.000081016624,0.0012981943,0.00023892173,0.00022483575,0.018590346],"genre_scores_gemma":[0.9881356,0.0002070549,0.009820252,0.0000073400056,0.000013762901,0.00028898875,0.0006871847,0.000008227291,0.0008316166],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9990273,0.0001689852,0.0002707083,0.00017837941,0.00020060143,0.00015399628],"domain_scores_gemma":[0.99793106,0.0005193915,0.00027452476,0.0009328462,0.00031346772,0.000028721895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004921077,0.0000954247,0.00029807634,0.0005415881,0.00009263071,0.000012638148,0.00029883618,0.00010032954,0.000061363324],"category_scores_gemma":[0.00006685881,0.00008878664,0.00014080593,0.00135867,0.00012168508,0.000076476645,0.00005676611,0.00011918188,0.000020070343],"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":[0.0013252941,0.0020287533,0.056148503,0.00020433588,0.008933214,0.000006727505,0.021658136,0.000096215816,0.38467044,0.036475115,0.021527467,0.4669258],"study_design_scores_gemma":[0.00042661585,0.00032836862,0.8925311,0.000039788152,0.00060715264,0.0000029244984,0.00350045,0.0017200613,0.09386534,0.0017496159,0.005092094,0.00013650718],"about_ca_topic_score_codex":0.0004237938,"about_ca_topic_score_gemma":0.0002985501,"teacher_disagreement_score":0.83638257,"about_ca_system_score_codex":0.00007859932,"about_ca_system_score_gemma":0.000024297711,"threshold_uncertainty_score":0.3620614},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98596066,0.0005784422,0.0005869681,0.004655757,0.0008276926,0.00075178425,0.00003804382,0.000076082935,0.0065245763],"genre_scores_gemma":[0.9955568,0.0010625744,0.00025870142,0.00004519111,0.00012402708,0.00016223412,0.000108437176,0.000014804986,0.0026672813],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9991097,0.00020783165,0.00023675604,0.00011105315,0.0001390433,0.0001956227],"domain_scores_gemma":[0.995394,0.002890416,0.000080589896,0.0011408536,0.0004765437,0.000017622911],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016701475,0.00006202446,0.00007591135,0.00005145888,0.0005902825,0.000042091542,0.00073816883,0.00010179714,0.0000632821],"category_scores_gemma":[0.0016653164,0.000040611594,0.00005480886,0.00028749835,0.00035770997,0.00001781235,0.00014047207,0.00021299649,0.00013280343],"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":[0.0018406446,0.0006252508,0.06670054,0.00013761582,0.0007263176,0.000001779602,0.055508498,0.0006757976,0.058051232,0.30549678,0.18206713,0.32816842],"study_design_scores_gemma":[0.0006776871,0.00021372481,0.853163,0.000019142426,0.000028211978,0.000002614109,0.0033257082,0.0048915744,0.0017061209,0.028802054,0.10705078,0.000119368946],"about_ca_topic_score_codex":0.00024553554,"about_ca_topic_score_gemma":0.00010231913,"teacher_disagreement_score":0.7864625,"about_ca_system_score_codex":0.000029969453,"about_ca_system_score_gemma":0.000029012039,"threshold_uncertainty_score":0.45400354},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008080137,0.023105316,0.97002834,0.0035201157,0.000025662619,0.00053686823,0.0000054267634,0.000247528,0.0024499414],"genre_scores_gemma":[0.0014316399,0.021538049,0.9758331,0.00057135115,0.000016843009,0.00027416743,0.00012187613,0.0000086155815,0.00020434095],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988523,0.00018084583,0.00039674435,0.00024460215,0.00014993033,0.00017556686],"domain_scores_gemma":[0.9968178,0.00048256115,0.0002900831,0.0019785566,0.00038363432,0.000047324134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023082811,0.00009411758,0.00028498194,0.00031630514,0.00017237695,0.00004875693,0.0017257798,0.000046511428,0.000011171168],"category_scores_gemma":[0.00026558805,0.00009278595,0.00019381539,0.0046673054,0.000044135595,0.00025244712,0.00034263398,0.00009051208,0.000036212074],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.695559e-7,0.000030270357,0.000066362125,0.0007680681,0.00008961511,8.2390464e-8,0.000059636495,0.000013410715,0.0031449257,0.0035452868,0.0022626545,0.9900187],"study_design_scores_gemma":[0.00040655013,0.000062060084,0.0011070084,0.0017498997,0.00063674874,0.000009197296,0.00007242428,0.031753782,0.4742948,0.07949772,0.40989718,0.0005126336],"about_ca_topic_score_codex":0.000014349203,"about_ca_topic_score_gemma":0.000008220425,"teacher_disagreement_score":0.98950607,"about_ca_system_score_codex":0.000030333866,"about_ca_system_score_gemma":0.00006505632,"threshold_uncertainty_score":0.3783701},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18399683,0.020100147,0.72334284,0.023706492,0.0006643176,0.0006684769,0.00002626616,0.0016421559,0.045852475],"genre_scores_gemma":[0.8551338,0.00014245589,0.1438983,0.0007133162,0.000030989504,0.000011176084,0.000009235687,0.000008239323,0.00005250272],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983522,0.00028240535,0.00026677665,0.0004021724,0.00047157926,0.00022480708],"domain_scores_gemma":[0.9980279,0.00044000358,0.000087202025,0.0012021693,0.00014874605,0.00009398694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011745808,0.00016184228,0.0001719501,0.00019927158,0.00022264138,0.00067549193,0.0010612925,0.00008638292,0.00001333931],"category_scores_gemma":[0.00047341565,0.00014731688,0.00005907312,0.001472409,0.000081770544,0.0005010549,0.00033207104,0.00026503252,0.00008982955],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014043428,0.0000662093,0.00032381268,0.000058965437,0.0000230951,0.000012987828,0.00016621259,0.000033578628,0.0010584207,0.04330406,0.0011267823,0.9538118],"study_design_scores_gemma":[0.0016904039,0.00047225293,0.020573288,0.0011630493,0.00008056503,0.0001792237,0.00021526965,0.05754531,0.3960955,0.48436996,0.036110483,0.0015047],"about_ca_topic_score_codex":0.00014166455,"about_ca_topic_score_gemma":0.00008986961,"teacher_disagreement_score":0.9523071,"about_ca_system_score_codex":0.00019166495,"about_ca_system_score_gemma":0.00016708896,"threshold_uncertainty_score":0.6513784},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99710566,0.0005283031,0.00026518002,0.00024159608,0.0000974807,0.0010036996,0.000014163505,0.00004288855,0.00070104416],"genre_scores_gemma":[0.99805844,0.000005805846,0.0016691713,0.000004760358,0.000038379578,0.00007240124,0.000018466224,0.000020687878,0.00011190687],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982085,0.00031144466,0.0004647515,0.00024487232,0.00058995164,0.00018047068],"domain_scores_gemma":[0.99778366,0.0005960705,0.00010572594,0.0011409943,0.00033763496,0.000035916204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015828265,0.0001209117,0.0002353563,0.00020759116,0.0001441252,0.000046899102,0.0003933285,0.00004865906,0.00006958035],"category_scores_gemma":[0.0009239248,0.00008953131,0.00006429667,0.0005767744,0.00032079793,0.00014341438,0.00031479236,0.00066744647,0.0000043563664],"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":[0.00057521777,0.0013312325,0.9499871,0.00062141824,0.00012913044,0.0000075911826,0.0031605228,0.0015591471,0.039845027,0.000101107886,0.000006979563,0.0026754867],"study_design_scores_gemma":[0.0009803178,0.00037562908,0.976831,0.00020290312,0.000038461716,0.000039638835,0.0012746976,0.011201469,0.008371102,0.00061701535,8.544156e-7,0.00006692144],"about_ca_topic_score_codex":0.0005844643,"about_ca_topic_score_gemma":0.0006270262,"teacher_disagreement_score":0.031473923,"about_ca_system_score_codex":0.0003073448,"about_ca_system_score_gemma":0.00008267579,"threshold_uncertainty_score":0.3650981},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6488012,0.14645746,0.022164207,0.05016714,0.0008082131,0.0012946988,0.00008781446,0.0016901932,0.12852909],"genre_scores_gemma":[0.9671032,0.002825239,0.028344827,0.00003398583,0.000061625055,0.000033227283,0.00004005709,0.000011220163,0.0015466404],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99851996,0.0004664478,0.00024457902,0.00025351657,0.00038225215,0.00013323544],"domain_scores_gemma":[0.99801993,0.00029048993,0.00004684694,0.0014105913,0.00016806582,0.00006408406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017656967,0.00007097732,0.000105620784,0.00039043292,0.00012084414,0.00030690254,0.0009475507,0.00005124403,0.000103377584],"category_scores_gemma":[0.000051412324,0.00006675932,0.000037799466,0.00093832595,0.00010504351,0.0006021062,0.0003448849,0.00017914898,0.000068193636],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020776495,0.000059986214,0.00004552211,0.000052261294,0.000011592979,0.0000037943742,0.0017248981,3.3358396e-7,0.003191674,0.037721872,0.001329001,0.955857],"study_design_scores_gemma":[0.0010051787,0.0005045357,0.10027098,0.0017439759,0.00009660867,0.00033314843,0.005574261,0.19141872,0.35894305,0.08344856,0.2554072,0.00125377],"about_ca_topic_score_codex":0.00014703561,"about_ca_topic_score_gemma":0.00006302957,"teacher_disagreement_score":0.9546032,"about_ca_system_score_codex":0.00003343778,"about_ca_system_score_gemma":0.00003187745,"threshold_uncertainty_score":0.29594684},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6948755,0.0022771598,0.25761068,0.008229449,0.00037507765,0.000660756,0.0000010743368,0.00077010796,0.03520024],"genre_scores_gemma":[0.81823134,0.00010932433,0.1809614,0.00022149128,0.000026047397,0.000011728547,0.000012012319,0.000010429998,0.00041624004],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99812436,0.00029275083,0.0004052832,0.0004411702,0.00034054683,0.00039588043],"domain_scores_gemma":[0.99809074,0.0002744346,0.00021080751,0.0012277963,0.00013764208,0.0000586022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011339347,0.00019695591,0.00028394404,0.0007189109,0.00035451626,0.0002957833,0.0013934692,0.00012402947,0.000016521064],"category_scores_gemma":[0.00043410066,0.00019344466,0.00004938957,0.003484441,0.00007059033,0.000941154,0.00058298657,0.00081602065,0.000024308538],"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":[0.00040053693,0.0011887086,0.072489366,0.00038764035,0.00023974564,0.0002513301,0.006191874,0.0034784903,0.11551964,0.024485348,0.0008605744,0.77450675],"study_design_scores_gemma":[0.0020439192,0.00012516718,0.015008265,0.0004813308,0.00002766076,0.00004655093,0.00049861695,0.0074583148,0.9567771,0.013718755,0.0032961029,0.0005182033],"about_ca_topic_score_codex":0.00042091473,"about_ca_topic_score_gemma":0.001556233,"teacher_disagreement_score":0.84125745,"about_ca_system_score_codex":0.00026261623,"about_ca_system_score_gemma":0.00030789728,"threshold_uncertainty_score":0.78884447},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8164528,0.0006767344,0.065855645,0.010445645,0.00040791053,0.0010493161,0.000016077878,0.0011396854,0.103956185],"genre_scores_gemma":[0.8014934,0.00026540752,0.19661693,0.0010563222,0.000036386562,0.00009285045,0.00008781493,0.000014125386,0.00033677628],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984303,0.00027359504,0.00030658965,0.00037558938,0.00032459816,0.00028934368],"domain_scores_gemma":[0.9979506,0.00020828427,0.00013938092,0.001343247,0.00028630355,0.00007215618],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040387086,0.00021436036,0.00021487876,0.0004293406,0.00032969067,0.0002583475,0.0012705066,0.00010100626,0.00006791648],"category_scores_gemma":[0.00010123193,0.00018291689,0.0001139452,0.0015558123,0.00008704716,0.00066118554,0.00022909217,0.00031895022,0.000102825594],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036488436,0.00015520082,0.001649575,0.0000116866095,0.00004256879,0.000005667672,0.00011051062,0.0000014799658,0.0013891121,0.0012037155,0.0006909366,0.99470305],"study_design_scores_gemma":[0.008372426,0.0014243503,0.18293089,0.0010437886,0.0003223887,0.0006703866,0.0007178404,0.06370573,0.4033119,0.27750024,0.056106836,0.003893213],"about_ca_topic_score_codex":0.00010140238,"about_ca_topic_score_gemma":0.00022435552,"teacher_disagreement_score":0.99080986,"about_ca_system_score_codex":0.00007505637,"about_ca_system_score_gemma":0.000080196565,"threshold_uncertainty_score":0.74591345},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95495796,0.00059576787,0.00024239405,0.00024006596,0.00033096934,0.0003212381,0.000011476915,0.000036723824,0.043263424],"genre_scores_gemma":[0.9955664,0.00027675557,0.0021428845,0.000025527064,0.000051324314,0.000040260096,0.00009465061,0.000011391468,0.0017907862],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99862164,0.00039709933,0.00042698378,0.0001970083,0.00017743447,0.00017982764],"domain_scores_gemma":[0.99777067,0.00027117325,0.00021379779,0.0009949938,0.0007211181,0.000028270146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006355477,0.0001019723,0.0002254194,0.00028212552,0.0000778774,0.000011441878,0.0005207287,0.00018935293,0.00041180413],"category_scores_gemma":[0.00034077937,0.00010977818,0.00007360919,0.000432138,0.00023991027,0.000082437386,0.00018155185,0.00027856132,0.000036471884],"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":[0.000519594,0.0010298833,0.011834778,0.00014603538,0.00028233125,0.0000011343461,0.055848446,0.0000064233564,0.59329605,0.006193236,0.0077036135,0.32313845],"study_design_scores_gemma":[0.0020125057,0.00059171754,0.77990425,0.000144397,0.000077631616,0.0000028322042,0.019692438,0.0003983667,0.18583055,0.0061761574,0.0049028127,0.0002663433],"about_ca_topic_score_codex":0.0007724165,"about_ca_topic_score_gemma":0.00009001388,"teacher_disagreement_score":0.76806945,"about_ca_system_score_codex":0.000052195403,"about_ca_system_score_gemma":0.00006470784,"threshold_uncertainty_score":0.45089662},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07243154,0.0005220417,0.92495245,0.001199916,0.00013519172,0.00023560868,0.000002590917,0.0001941968,0.00032649102],"genre_scores_gemma":[0.33772424,0.000028526414,0.6618302,0.00028755923,0.000017989101,0.000017254415,0.00003110527,0.000006484491,0.000056660374],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99902844,0.000100728124,0.00026958805,0.0002743312,0.00012396977,0.00020292657],"domain_scores_gemma":[0.9982379,0.00014776207,0.00018459307,0.0012035525,0.00018520567,0.000040964365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053720013,0.0001158977,0.00014267988,0.00012978613,0.0005505503,0.0003621324,0.0013047112,0.000067172165,0.0000026342454],"category_scores_gemma":[0.00013378494,0.0001235794,0.00004344883,0.00046012126,0.000048239686,0.0009496437,0.00018255007,0.0001113726,0.000011423707],"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":[0.00002034647,0.00012050077,0.0004738829,0.00005297059,0.000017934979,2.0086597e-7,0.0003505463,0.008234283,0.4515667,0.0018204193,0.00017657861,0.53716564],"study_design_scores_gemma":[0.00042140606,0.0000160344,0.00040656127,0.000081334634,0.0000094455845,0.0000032026592,0.00005101712,0.44481394,0.5328132,0.018394314,0.0028450815,0.00014450378],"about_ca_topic_score_codex":0.00008723318,"about_ca_topic_score_gemma":0.000034002052,"teacher_disagreement_score":0.5370211,"about_ca_system_score_codex":0.00007733773,"about_ca_system_score_gemma":0.000113361326,"threshold_uncertainty_score":0.5039422},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28768802,0.0013006582,0.47480646,0.016268592,0.00019785386,0.0012519734,0.000010104279,0.0015733499,0.21690299],"genre_scores_gemma":[0.3625307,0.00005356749,0.63570493,0.00059835496,0.000009904761,0.00003226825,0.00002073859,0.000008771533,0.0010407807],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99870867,0.0002290476,0.00031367538,0.00030061064,0.00025690655,0.00019108868],"domain_scores_gemma":[0.9978466,0.00037009074,0.00015608716,0.001369904,0.00019634566,0.000060972994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005901216,0.00015143935,0.00023610084,0.0002006441,0.0004382304,0.00029999585,0.0011022271,0.00008017746,0.000032843873],"category_scores_gemma":[0.000100646066,0.00013814527,0.000029045796,0.00060625206,0.00011719564,0.00038843913,0.00035537424,0.00020549035,0.000038916707],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000143864245,0.00045105934,0.0068218205,0.00013693985,0.0001502942,0.0000064205387,0.0006583211,0.000015059581,0.003126193,0.43669176,0.008754456,0.5431733],"study_design_scores_gemma":[0.0046152337,0.0005304996,0.1986203,0.0027437932,0.00031306056,0.00038975905,0.0016133398,0.2029669,0.06005545,0.4316434,0.094304085,0.0022041933],"about_ca_topic_score_codex":0.00023776005,"about_ca_topic_score_gemma":0.00028998023,"teacher_disagreement_score":0.54096913,"about_ca_system_score_codex":0.00005819681,"about_ca_system_score_gemma":0.00009441666,"threshold_uncertainty_score":0.5633401},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81227374,0.0003922925,0.0019432543,0.0031758365,0.001000332,0.0004134085,0.0000044827198,0.000068707865,0.18072791],"genre_scores_gemma":[0.99463874,0.00017984629,0.0045221103,0.0001300841,0.00001611356,0.0000026517027,0.000013709014,0.0000027660908,0.000493963],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99917233,0.0003129378,0.00018697973,0.000071445844,0.00018929603,0.00006698231],"domain_scores_gemma":[0.9983062,0.0008713314,0.00015113373,0.00027655807,0.00037961223,0.000015168754],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075306126,0.000038517446,0.000097977696,0.00011653026,0.00016238964,0.000008492759,0.00026599056,0.00006782709,0.000050584462],"category_scores_gemma":[0.0038117464,0.00003985867,0.000023524057,0.00032972998,0.00010003639,0.000037572754,0.000070024864,0.00008911317,0.0000076765045],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015998967,0.000065359716,0.0032442873,0.0000329825,0.000012109288,1.4074014e-7,0.0027915733,0.000016895718,0.002606578,0.9845515,0.00013642116,0.0065261894],"study_design_scores_gemma":[0.0034230966,0.0006085974,0.31629217,0.0020825465,0.00013754293,6.333191e-7,0.0051085204,0.0014210339,0.15413292,0.2979799,0.21826832,0.00054471183],"about_ca_topic_score_codex":0.0011187354,"about_ca_topic_score_gemma":0.0005579455,"teacher_disagreement_score":0.68657154,"about_ca_system_score_codex":0.00005219628,"about_ca_system_score_gemma":0.00012480878,"threshold_uncertainty_score":0.4563292},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9363445,0.00056210114,0.04360282,0.013222164,0.00025338275,0.0011010856,0.000007617835,0.0015585069,0.003347823],"genre_scores_gemma":[0.42162156,0.00010004749,0.5768001,0.0009302253,0.000030532956,0.0002121326,0.0001378715,0.000018245617,0.00014927513],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99749297,0.00035130608,0.000633377,0.00065298093,0.00045286684,0.0004165052],"domain_scores_gemma":[0.99632186,0.00040758838,0.0003334111,0.0020098516,0.00077491155,0.00015238312],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001632728,0.00026923753,0.00028670512,0.0027642648,0.00052070175,0.00039537213,0.001920394,0.0002561393,0.000039171813],"category_scores_gemma":[0.0022179496,0.0002992577,0.000060191855,0.008999934,0.0001110656,0.0017562273,0.00066066644,0.00043188178,0.00048762374],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010628876,0.00015074377,0.00086522644,0.00005217023,0.000013971664,0.000003261856,0.00023485257,0.000005604279,0.012156184,0.00005872175,0.0006150858,0.9858335],"study_design_scores_gemma":[0.0008959906,0.00065662793,0.01945372,0.0011835503,0.00008158935,0.0000949807,0.00021622865,0.03141773,0.696029,0.24873498,0.0006000595,0.00063554116],"about_ca_topic_score_codex":0.00005418465,"about_ca_topic_score_gemma":0.00006541511,"teacher_disagreement_score":0.985198,"about_ca_system_score_codex":0.00032932777,"about_ca_system_score_gemma":0.00029373047,"threshold_uncertainty_score":0.99994594},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4663933,0.4368129,0.00007229186,0.0038480647,0.000040054307,0.001929414,0.000013727173,0.000043149834,0.09084711],"genre_scores_gemma":[0.9898629,0.005058538,0.00022477836,0.00036084236,0.0000026791386,0.0002119111,0.000031091215,0.000007148504,0.0042400933],"study_design_codex":"systematic_review","study_design_gemma":"observational","domain_scores_codex":[0.99724495,0.0018090835,0.00037228063,0.00019893105,0.00013894244,0.00023579031],"domain_scores_gemma":[0.9965238,0.0016652201,0.000074068084,0.0015963686,0.00010829657,0.000032254506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004396504,0.00008085182,0.0004039374,0.0006655625,0.00011604166,0.000047461417,0.00057927956,0.000055925906,0.0005860448],"category_scores_gemma":[0.00070954964,0.00007249114,0.000046914065,0.0017101503,0.00016718448,0.00004563675,0.0001987825,0.00046121067,0.00008708395],"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":[0.00014738589,0.0025132569,0.092379704,0.58265585,0.00819944,0.00020346671,0.15430342,0.0000062336767,0.018305363,0.08546292,0.045126434,0.010696528],"study_design_scores_gemma":[0.003923563,0.00016284872,0.6690269,0.14003204,0.0076760636,0.00040044126,0.06670674,0.0015414043,0.002637277,0.10564928,0.00069468666,0.0015487485],"about_ca_topic_score_codex":0.0005910541,"about_ca_topic_score_gemma":0.0016345312,"teacher_disagreement_score":0.5766472,"about_ca_system_score_codex":0.00005934693,"about_ca_system_score_gemma":0.000025356081,"threshold_uncertainty_score":0.641678},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05130233,0.0005846073,0.6044388,0.014384633,0.00047139954,0.0013174142,0.000016360336,0.0012707794,0.3262137],"genre_scores_gemma":[0.40552497,0.00057324505,0.59069234,0.0017177255,0.0000380643,0.00016302658,0.00013441643,0.000019076293,0.0011371048],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980234,0.0003807285,0.00046065767,0.0004295295,0.00042829636,0.00027741355],"domain_scores_gemma":[0.9973208,0.00014743491,0.00017377603,0.0016985758,0.000582809,0.000076647266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010106551,0.00020895469,0.000244247,0.00037599777,0.00032897238,0.00030878902,0.0014863776,0.00017435195,0.000070693204],"category_scores_gemma":[0.0002463282,0.00021694049,0.00011248846,0.0009634183,0.000058317877,0.0014478411,0.00037001714,0.00027466897,0.00027724964],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014237403,0.0001310929,0.0000864354,0.000020917543,0.00002793775,0.0000013442367,0.00023389532,0.000009280895,0.00076234643,0.012957174,0.0012472939,0.98450804],"study_design_scores_gemma":[0.0014870858,0.00007388677,0.0024061291,0.00040740866,0.000069927155,0.0000346124,0.00026056825,0.26027897,0.17633101,0.5465824,0.011361446,0.0007065627],"about_ca_topic_score_codex":0.00019708573,"about_ca_topic_score_gemma":0.00010967218,"teacher_disagreement_score":0.9838015,"about_ca_system_score_codex":0.00023311934,"about_ca_system_score_gemma":0.00022205182,"threshold_uncertainty_score":0.8846576},"labels":[],"label_agreement":null}]}