{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":46,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":46,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"04728ae03c4c","filters":{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1292222086999065,"gpt":0.3216646469651708,"spread":0.1924424382652643,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000849393,0.0001111027,0.0001093186,0.0001069505,0.0001885127,0.0000477805,0.0003318925,0.00009997638,0.001392001],"category_scores_gemma":[0.0001535566,0.00009266398,0.0000498102,0.0002279872,0.00008316319,0.0001345675,0.00004642819,0.0003316194,0.0003426016],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006529731,"about_ca_system_score_gemma":0.00002351155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001675658,"about_ca_topic_score_gemma":0.0005115237,"domain_scores_codex":[0.9983785,0.0008264795,0.0002275871,0.0001852902,0.0001780668,0.0002041135],"domain_scores_gemma":[0.9986574,0.0002452382,0.0001480084,0.0008145161,0.00009059758,0.00004425428],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0003081119,0.004186741,0.1713544,0.0000854215,0.0003127695,0.00006894298,0.03596525,0.0003388362,0.009310821,0.203743,0.07997547,0.4943503],"study_design_scores_gemma":[0.008170331,0.0002018555,0.5204642,0.001257715,0.000103189,0.0003883691,0.074673,0.0007336372,0.06855717,0.1444089,0.179482,0.001559596],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8648627,0.000898025,0.0008550075,0.004661061,0.0004166341,0.0005258512,0.00001837139,0.0001144632,0.1276479],"genre_scores_gemma":[0.9952732,0.0002988669,0.002379301,0.0006597357,0.00002315643,0.00005384753,0.0001299866,0.00001820346,0.001163751],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4927907,"threshold_uncertainty_score":0.9995208,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03613621209312245,"gpt":0.287530217985311,"spread":0.2513940058921886,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003778731,0.0001197486,0.0001582697,0.0001184616,0.0001834044,0.0002963725,0.0006702747,0.0000924326,0.00000350308],"category_scores_gemma":[0.0001004475,0.0001086779,0.00003407129,0.0001783451,0.00007255808,0.0004244907,0.0001668176,0.0001090811,0.000006260069],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001742898,"about_ca_system_score_gemma":0.00001326355,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001035914,"about_ca_topic_score_gemma":0.000008903427,"domain_scores_codex":[0.9992449,0.00006641619,0.0001720906,0.0002455338,0.0001123406,0.0001587053],"domain_scores_gemma":[0.9986256,0.0003242698,0.00008244895,0.0008530842,0.00008060039,0.00003397893],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000006374274,0.00003612979,0.00004266059,0.000003452777,0.000006321788,0.000001325418,0.0002664836,1.225135e-7,0.003367946,0.006180189,0.0002531927,0.9898358],"study_design_scores_gemma":[0.004841542,0.001587212,0.04260873,0.0002834401,0.00003426604,0.0005027884,0.002107626,0.05544677,0.6391944,0.2009033,0.05091089,0.001579057],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6891873,0.008743736,0.2578022,0.03442496,0.0001435172,0.001749422,0.0000260164,0.002186286,0.005736556],"genre_scores_gemma":[0.366828,0.002180407,0.6302824,0.0005946833,0.00001734405,0.00002248766,0.00001382004,0.000005870767,0.00005497511],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9882568,"threshold_uncertainty_score":0.4431754,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05788706227852394,"gpt":0.351197851375106,"spread":0.293310789096582,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005126637,0.0001234039,0.0002069406,0.0001401664,0.0001105822,0.000020082,0.0005760718,0.0002423025,0.001588001],"category_scores_gemma":[0.0002129646,0.000123218,0.00006517058,0.000240762,0.0003230082,0.00008012992,0.0001848137,0.0008474339,0.0004808047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000348945,"about_ca_system_score_gemma":0.00004210125,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01030408,"about_ca_topic_score_gemma":0.00732191,"domain_scores_codex":[0.9985963,0.0003414887,0.0003274003,0.0002386652,0.0002065823,0.0002896065],"domain_scores_gemma":[0.997389,0.0004057563,0.0002060228,0.001567933,0.0003452025,0.00008614681],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.000198896,0.0002544624,0.005804174,0.000003116025,0.0001056056,0.000002847022,0.00497308,2.235991e-7,0.9070809,0.0009721114,0.000215132,0.08038943],"study_design_scores_gemma":[0.001232652,0.0001575951,0.4925218,0.00001306824,0.00002548585,0.00001033113,0.001171767,0.0001184624,0.4877593,0.007297878,0.009522271,0.0001693651],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9769204,0.000354729,0.0002562717,0.00041646,0.0005942563,0.0003094733,0.00006999279,0.000044739,0.02103371],"genre_scores_gemma":[0.9953008,0.0001443518,0.003362241,0.00005371868,0.00006488366,0.00003291891,0.0001290956,0.0000215227,0.0008905033],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4867176,"threshold_uncertainty_score":0.9993247,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.08252491668061658,"gpt":0.3914586177801657,"spread":0.3089337010995491,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001791926,0.00007483161,0.0001121801,0.0001349985,0.00007980395,0.000005648981,0.0001846081,0.00007956821,0.0008685583],"category_scores_gemma":[0.00007116349,0.00007418171,0.00003438147,0.0002184754,0.0001022213,0.0001332898,0.00002884264,0.000175949,0.00008387389],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007982803,"about_ca_system_score_gemma":0.00003743572,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004201441,"about_ca_topic_score_gemma":0.0003068774,"domain_scores_codex":[0.9992067,0.0001699677,0.0002553537,0.0001285321,0.0001359539,0.0001034482],"domain_scores_gemma":[0.9992574,0.00006712124,0.0001354643,0.0003855951,0.0001337089,0.00002070574],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002841569,0.003298848,0.05651484,0.0001373124,0.00013832,0.0000275844,0.2627161,0.0001374186,0.1559682,0.1450604,0.006888127,0.3662713],"study_design_scores_gemma":[0.00530016,0.0003361586,0.9483557,0.0001870502,0.00001549222,0.00006997833,0.02813831,0.003632402,0.01110543,0.001284805,0.001226723,0.00034783],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8688986,0.000161433,0.0002681845,0.0001404323,0.0000426636,0.000241659,0.000007149866,0.0000330118,0.1302069],"genre_scores_gemma":[0.995483,0.00003681117,0.00334178,0.00004419197,0.00002177267,0.00004299068,0.0001058726,0.000009787434,0.0009137786],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8918408,"threshold_uncertainty_score":0.9510105,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06925915415323883,"gpt":0.3367045598930625,"spread":0.2674454057398237,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009509036,0.0000614639,0.0001016143,0.0001344657,0.00005775228,0.00001192358,0.0001139786,0.00005372066,0.00002877452],"category_scores_gemma":[0.001136673,0.00006232123,0.00002716358,0.0004148404,0.00005299348,0.0001583551,0.00004818152,0.0001212199,0.0000639714],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008179383,"about_ca_system_score_gemma":0.00001739485,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006604894,"about_ca_topic_score_gemma":0.0002145825,"domain_scores_codex":[0.9987173,0.0006452889,0.0001888838,0.0001628034,0.0001643519,0.0001213459],"domain_scores_gemma":[0.9990593,0.0002519191,0.00005308641,0.0005474376,0.0000523008,0.00003594473],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.000008409158,0.00009567614,0.007076161,0.00001643113,3.451896e-7,0.000001140983,0.002735465,0.00002326702,0.9072881,0.002685046,0.00001435912,0.08005556],"study_design_scores_gemma":[0.0002565838,0.000094024,0.6803122,0.00009209192,0.000002484715,0.00001428706,0.0004176176,0.0005965318,0.3148148,0.001627358,0.001634224,0.0001378703],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9941437,0.00001384003,0.0001195923,0.001337284,0.00004946809,0.0003697698,0.000002289333,0.00002502251,0.003938998],"genre_scores_gemma":[0.9912617,0.00006269269,0.008342027,0.0002485434,0.00001157721,0.00002091316,0.000002276629,0.000007699817,0.00004260814],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.673236,"threshold_uncertainty_score":0.2541386,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03390941946555964,"gpt":0.2998207171212208,"spread":0.2659112976556612,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004597358,0.0001083353,0.0001031612,0.00007493769,0.0003213752,0.0001706121,0.0005189822,0.00007100602,0.000003573621],"category_scores_gemma":[0.0001086791,0.0001040842,0.00003349165,0.0001929404,0.00005046402,0.001112449,0.0001781457,0.0001097535,0.000009183477],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005753657,"about_ca_system_score_gemma":0.0000283453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004873599,"about_ca_topic_score_gemma":0.0000153378,"domain_scores_codex":[0.999227,0.00006168074,0.0001560482,0.0001778505,0.0001349128,0.000242503],"domain_scores_gemma":[0.9988203,0.0001109446,0.0001183012,0.0007661422,0.0001065934,0.00007772683],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003460749,0.0002884244,0.02377885,0.0001141171,0.00005454465,3.674055e-7,0.005978219,0.00007099264,0.2235007,0.01563733,0.002087479,0.7284544],"study_design_scores_gemma":[0.001417461,0.0000827648,0.1169945,0.0001886491,0.00006567688,0.0001346788,0.0004649513,0.02426201,0.8029146,0.007589765,0.04495444,0.0009304811],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5740828,0.007384897,0.4129843,0.002054519,0.0003934902,0.0006151833,0.000004217732,0.0002853486,0.002195247],"genre_scores_gemma":[0.5863629,0.0000678771,0.4132913,0.0001322102,0.00004847722,0.00001142097,0.00001008807,0.000008191956,0.0000675437],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7275239,"threshold_uncertainty_score":0.4244431,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.01161796156250955,"gpt":0.2341338141597233,"spread":0.2225158525972137,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005397872,0.0001670144,0.0001481927,0.0001509331,0.0003015009,0.0002323111,0.001167727,0.00007652944,0.00007260541],"category_scores_gemma":[0.0000324215,0.0001690933,0.00005976278,0.0004794013,0.00004577783,0.0004605046,0.0001597669,0.0001902268,0.0005993756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001466962,"about_ca_system_score_gemma":0.00009283637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001120338,"about_ca_topic_score_gemma":0.00005988046,"domain_scores_codex":[0.998456,0.0001422662,0.0003109388,0.0003343087,0.000483275,0.0002732367],"domain_scores_gemma":[0.9979538,0.0001232721,0.0001956438,0.001509617,0.0001650481,0.00005262303],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003403743,0.0006920836,0.0001647108,0.0000281779,0.0000099464,0.000008079116,0.0002967945,0.002190016,0.08429638,0.002102332,0.009309744,0.9008677],"study_design_scores_gemma":[0.0004787057,0.0001061009,0.0008939627,0.0000875066,0.000006204218,0.000005548074,0.00001721872,0.2332469,0.7512218,0.006206179,0.007473773,0.0002560699],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07996207,0.0003479706,0.7843447,0.008751964,0.0001946074,0.0005590159,0.000004311991,0.0006340101,0.1252014],"genre_scores_gemma":[0.5297372,0.00001651868,0.4682294,0.0006152238,0.00005505516,0.00002380788,0.00008492412,0.00001295452,0.001224898],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9006116,"threshold_uncertainty_score":0.7703961,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2621689721373435,"gpt":0.4781006234133592,"spread":0.2159316512760158,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002586858,0.0001355164,0.0002140076,0.0001676618,0.0007729523,0.00001054063,0.0003905928,0.0002802092,0.0000947165],"category_scores_gemma":[0.0003868898,0.0001295194,0.00003228222,0.0003021299,0.000080899,0.0001432301,0.0001612785,0.00063279,0.0006650614],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006103876,"about_ca_system_score_gemma":0.00179619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006297028,"about_ca_topic_score_gemma":0.0002765057,"domain_scores_codex":[0.9971578,0.001212933,0.0006884783,0.0002135172,0.0002871007,0.0004401742],"domain_scores_gemma":[0.9972349,0.0002760001,0.000419067,0.001236063,0.000608425,0.0002254748],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001545103,0.001025036,0.6543431,0.0009953649,0.00007881365,0.00004065132,0.05069892,0.000767968,0.02040202,0.09393778,0.077275,0.09889027],"study_design_scores_gemma":[0.005414462,0.0001952731,0.2079471,0.000586247,0.00005479245,0.00002589893,0.007381091,0.04937036,0.0018663,0.009064588,0.7172501,0.0008437616],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9147454,0.0006091946,0.01681705,0.008283746,0.0009452873,0.001665744,0.00001684077,0.0003319493,0.05658481],"genre_scores_gemma":[0.8886596,0.00007990644,0.1064281,0.003955293,0.0001102986,0.0001586478,0.0002893089,0.00002704017,0.0002917977],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6399751,"threshold_uncertainty_score":0.854824,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04427373960832048,"gpt":0.3575666027056751,"spread":0.3132928630973546,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0004854013,0.000124039,0.0001608904,0.000124172,0.0002374974,0.00004857437,0.0004631217,0.000193293,0.003316322],"category_scores_gemma":[0.00006504374,0.0001305079,0.00003874493,0.0001950312,0.000291593,0.00007352962,0.000272783,0.0004915162,0.00254625],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003660942,"about_ca_system_score_gemma":0.000009797215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003128371,"about_ca_topic_score_gemma":0.00008875733,"domain_scores_codex":[0.9986475,0.0003810662,0.0002132618,0.0002582087,0.0001861401,0.0003138288],"domain_scores_gemma":[0.9985892,0.000209408,0.00007610838,0.0009400832,0.00008171764,0.0001034437],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0003142546,0.001742132,0.008718122,0.00003731659,0.0003349989,0.00009399452,0.01592517,0.000001771734,0.01607413,0.009148887,0.317017,0.6305922],"study_design_scores_gemma":[0.004421592,0.002011873,0.5134816,0.0000762353,0.00009063648,0.0007203664,0.002186023,0.003946373,0.006903026,0.01002758,0.45496,0.001174667],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9159302,0.002481422,0.00002405222,0.00213568,0.0003361754,0.0002159954,0.000005960594,0.00009323074,0.07877724],"genre_scores_gemma":[0.990643,0.001023533,0.001022848,0.0001762853,0.000176227,0.00002543489,0.00001996821,0.00002547139,0.00688729],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6294176,"threshold_uncertainty_score":0.9982304,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.09210451389678387,"gpt":0.319805237014836,"spread":0.2277007231180522,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009830905,0.0001313289,0.0001749822,0.00009724819,0.0002079315,0.00007171103,0.0004073326,0.00007597538,0.00004603542],"category_scores_gemma":[0.001182345,0.0001248897,0.00006289142,0.0001708573,0.000152407,0.000275403,0.0001444872,0.0002151386,0.00010188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004994046,"about_ca_system_score_gemma":0.00003241251,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001022442,"about_ca_topic_score_gemma":0.00013527,"domain_scores_codex":[0.9982679,0.0003718545,0.0003865512,0.0003494889,0.0003642399,0.0002599295],"domain_scores_gemma":[0.9984686,0.0004907344,0.0001256129,0.000775671,0.00007698893,0.00006239638],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00004489491,0.0002812566,0.002692892,0.0000416338,0.000005248492,5.649533e-7,0.001746674,0.0001382275,0.9356506,0.0006709486,0.0002970405,0.05842999],"study_design_scores_gemma":[0.001310895,0.0003443555,0.5484438,0.0001575084,0.00001408281,0.00001641806,0.0014894,0.01342497,0.4154372,0.01318748,0.005727525,0.0004463299],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9948249,0.00002776916,0.00112004,0.0009439099,0.00006670769,0.001627352,0.000008672131,0.00004514565,0.001335471],"genre_scores_gemma":[0.9898345,0.00005926198,0.009580947,0.0002144864,0.00001248777,0.0001878382,0.00001965882,0.00001718854,0.00007355528],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5457509,"threshold_uncertainty_score":0.5092852,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03139239909841487,"gpt":0.3060649651961495,"spread":0.2746725660977347,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005304973,0.0003427696,0.000344187,0.0002014131,0.0006088173,0.0003244768,0.001265587,0.0003303159,0.0006125743],"category_scores_gemma":[0.003150545,0.0003253692,0.0001649446,0.0004015002,0.0005331778,0.0006296723,0.0004519489,0.001053044,0.0005230192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001930917,"about_ca_system_score_gemma":0.0001545845,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04424783,"about_ca_topic_score_gemma":0.003392407,"domain_scores_codex":[0.9969773,0.0005093246,0.0004783607,0.0008173953,0.0008336381,0.0003839225],"domain_scores_gemma":[0.9951146,0.002026678,0.0003865481,0.001949287,0.0003061431,0.0002167595],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002364712,0.0004350112,0.003321799,0.00001536723,0.00004458506,0.00002818304,0.01281181,0.00006958979,0.8339128,0.01424786,0.0002054791,0.134671],"study_design_scores_gemma":[0.001365454,0.0002548826,0.09283722,0.0002292841,0.00006776122,0.00001713528,0.002891391,0.002891149,0.7735637,0.1169028,0.008168673,0.0008105005],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9627612,0.00007557751,0.0001139714,0.002864806,0.000663864,0.0005535494,0.0001282852,0.0002049649,0.03263377],"genre_scores_gemma":[0.9882657,0.0002377621,0.009480495,0.0007362265,0.0002161781,0.00006056707,0.0002177915,0.00006010584,0.0007252106],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1338605,"threshold_uncertainty_score":0.9999198,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0246555604296593,"gpt":0.3149615319571959,"spread":0.2903059715275366,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003861847,0.0001036091,0.0001722083,0.0001118199,0.00005708397,0.00000752016,0.0002107115,0.0001333827,0.001661522],"category_scores_gemma":[0.0004275202,0.00009813159,0.00006247505,0.0002487067,0.0001026751,0.0001540467,0.00004301007,0.0001643687,0.0001656907],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005138919,"about_ca_system_score_gemma":0.00002388796,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003896917,"about_ca_topic_score_gemma":0.0007266981,"domain_scores_codex":[0.9990086,0.0002395876,0.000320871,0.0001578255,0.0001445146,0.0001286248],"domain_scores_gemma":[0.9984619,0.0002032474,0.0003099883,0.0005658729,0.0004197376,0.00003923739],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001142462,0.002727458,0.00112243,0.0001794746,0.0002729044,0.000002395192,0.06001126,0.000004653152,0.01125254,0.003011903,0.03946949,0.880803],"study_design_scores_gemma":[0.01080293,0.002768425,0.00852532,0.001095293,0.0003603281,0.00006219085,0.06672361,0.0001617568,0.8171155,0.004915267,0.08645038,0.001018957],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6931064,0.0004205092,0.0001542539,0.0002239309,0.0001160872,0.0006626512,0.00008689755,0.00008129135,0.305148],"genre_scores_gemma":[0.9948298,0.0001948278,0.002857395,0.0001101751,0.00008350947,0.00006821535,0.0005595752,0.00001971429,0.001276786],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.879784,"threshold_uncertainty_score":0.9992511,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1220393955396209,"gpt":0.3603572703539774,"spread":0.2383178748143565,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001959662,0.0001191674,0.0001642899,0.0001023561,0.0001342957,0.00001698567,0.0003545623,0.0001444172,0.009805555],"category_scores_gemma":[0.0001035425,0.0001130551,0.00006011337,0.0002362294,0.0001633676,0.0002011436,0.00005488278,0.0002633536,0.00105354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005879539,"about_ca_system_score_gemma":0.00003891532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006483794,"about_ca_topic_score_gemma":0.0004288519,"domain_scores_codex":[0.9988142,0.0002991746,0.0003740015,0.0002154513,0.0001610277,0.0001361308],"domain_scores_gemma":[0.9985017,0.00006790197,0.000237835,0.0008451177,0.0002925521,0.00005489396],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0005376874,0.002851294,0.01024211,0.00003421563,0.0001591202,0.000009007004,0.1540754,0.000002587161,0.062699,0.07030751,0.005816773,0.6932653],"study_design_scores_gemma":[0.002201201,0.0004634068,0.8211455,0.000154698,0.0001376107,0.00005937113,0.02885377,0.001607643,0.07764145,0.06322881,0.003848872,0.0006576504],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7065324,0.0001047004,0.001907133,0.0002554139,0.0001379778,0.0003599947,0.00001447639,0.0001036191,0.2905842],"genre_scores_gemma":[0.9747019,0.00004344635,0.02271392,0.0001028569,0.00004015335,0.00004175005,0.0001221126,0.00001783786,0.002215986],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8109034,"threshold_uncertainty_score":0.9997243,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04368881874748969,"gpt":0.284747555239647,"spread":0.2410587364921573,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000361275,0.0002140086,0.000230004,0.00008932281,0.0003607159,0.0003165478,0.002031693,0.00008359571,0.00009070845],"category_scores_gemma":[0.0001106538,0.0002205413,0.00007979489,0.0007244993,0.00007195138,0.0008237677,0.0009448768,0.0002918649,0.0001987388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001641948,"about_ca_system_score_gemma":0.0001309441,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004740887,"about_ca_topic_score_gemma":0.00001453097,"domain_scores_codex":[0.9981797,0.0001603442,0.0004060541,0.0004451865,0.0004414251,0.0003673392],"domain_scores_gemma":[0.9979851,0.00007384207,0.0002531804,0.001320279,0.0001853692,0.0001822167],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006696849,0.0003459427,0.0008600813,0.0001043337,0.00008762155,0.00003891609,0.003521014,0.000212262,0.6666241,0.001240387,0.005850593,0.3210478],"study_design_scores_gemma":[0.0006702003,0.0001327715,0.0003138608,0.0001167354,0.00002038177,0.00002663539,0.000125358,0.05651174,0.9252821,0.001372497,0.0150557,0.0003720743],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4924265,0.001610021,0.4753863,0.01897955,0.0002399899,0.0007441871,0.000005324005,0.0006477091,0.009960418],"genre_scores_gemma":[0.5947099,0.0001157936,0.4021926,0.002722727,0.00007331811,0.00001719236,0.00002157767,0.00001810311,0.0001287712],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3206757,"threshold_uncertainty_score":0.8993412,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02314098288413063,"gpt":0.3089829522845727,"spread":0.285841969400442,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002246876,0.00004095342,0.00007117274,0.00002389013,0.0001742902,0.00001109396,0.0001267034,0.00003744655,0.00001593939],"category_scores_gemma":[0.0001253865,0.0000261168,0.00001622849,0.00008570102,0.0002839054,0.00003809863,0.0000772608,0.00009074169,0.00001380286],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007365046,"about_ca_system_score_gemma":0.00001989067,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006482785,"about_ca_topic_score_gemma":0.0001600758,"domain_scores_codex":[0.9996065,0.00004291067,0.0001124037,0.00005765547,0.0001090364,0.00007145292],"domain_scores_gemma":[0.9991266,0.00009959624,0.00006115853,0.0005690496,0.0001173664,0.00002625779],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0004967934,0.000363452,0.1637324,0.0001166636,0.0001226903,0.00000138969,0.008309446,8.999551e-8,0.02957664,0.02799824,0.008460463,0.7608217],"study_design_scores_gemma":[0.001680521,0.0009099627,0.7767814,0.0002944272,0.00009057257,0.0000435786,0.003039225,0.0005762899,0.06319994,0.1005207,0.05266502,0.0001984448],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9851727,0.0007903526,0.0001053913,0.004018961,0.00002156776,0.0001305362,5.82939e-7,0.00001483551,0.009745102],"genre_scores_gemma":[0.9965622,0.001626713,0.001301388,0.000163931,0.00001932291,0.000003877212,0.000006655925,0.000004370281,0.0003115844],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7606233,"threshold_uncertainty_score":0.1340517,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"","keywords":"Auditory system; Medial geniculate body; Neuroscience; Auditory cortex; Inferior colliculus; Computer science; Speech recognition; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.1177692497664533,"gpt":0.3288631377643537,"spread":0.2110938879979004,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000824808,0.0001242746,0.0001442261,0.0000717469,0.000762275,0.0001936873,0.0006234455,0.00007099996,0.000002919158],"category_scores_gemma":[0.001526141,0.0001131778,0.00002928397,0.0001878874,0.0001799622,0.0003517243,0.0002246035,0.0001520652,0.000003018172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006168713,"about_ca_system_score_gemma":0.00004668561,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002488783,"about_ca_topic_score_gemma":0.000007776285,"domain_scores_codex":[0.9986052,0.0002239324,0.0002320145,0.0005097089,0.000189881,0.0002392693],"domain_scores_gemma":[0.9981523,0.0009162128,0.0001713438,0.0006015673,0.0000942263,0.00006436418],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002157888,0.0002593817,0.0003662242,0.0006156761,0.000005998583,0.000006420315,0.00007445909,0.000103201,0.8777992,0.05197707,0.002817693,0.06575896],"study_design_scores_gemma":[0.002500328,0.000646969,0.003334221,0.0003421879,0.0001129317,0.0006416743,0.0002763084,0.6804886,0.2486755,0.008058777,0.05411265,0.000809807],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7613578,0.0001855758,0.2305788,0.0008276422,0.001109745,0.002835596,0.000357405,0.000393042,0.002354345],"genre_scores_gemma":[0.973785,0.00001829588,0.02573908,0.0001204665,0.0000662678,0.0000544683,0.00005883753,0.00001750467,0.0001400798],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6803855,"threshold_uncertainty_score":0.586288,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02789165738821853,"gpt":0.3013961836864198,"spread":0.2735045262982013,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001249267,0.00008594067,0.00006923007,0.00007654609,0.0003842826,0.0001169524,0.001068324,0.0000519626,0.000004049296],"category_scores_gemma":[0.0001351452,0.00006678628,0.00004452082,0.0002417981,0.00004457383,0.0003260824,0.0001817697,0.0001656962,0.00001408634],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005728145,"about_ca_system_score_gemma":0.00002431193,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008845324,"about_ca_topic_score_gemma":0.000003515864,"domain_scores_codex":[0.9992815,0.00003834522,0.0001785483,0.0001677155,0.0001501228,0.0001837879],"domain_scores_gemma":[0.9984953,0.0002265781,0.0001124158,0.001012141,0.0001228361,0.00003075862],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004399037,0.00008916893,0.000009039447,0.00001579319,0.00001085455,8.97686e-7,0.0006736756,0.00008754047,0.1759371,0.02473861,0.002282097,0.7961112],"study_design_scores_gemma":[0.00007537382,0.00006738753,0.00005873033,0.00005265939,0.000002186143,0.00001446123,0.00005801311,0.003166975,0.982033,0.007016954,0.007361716,0.00009260351],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0589159,0.0001117533,0.9312132,0.004620777,0.00009546683,0.0003460087,8.014727e-7,0.0003202948,0.004375815],"genre_scores_gemma":[0.42184,0.00002932842,0.5776727,0.0002294192,0.00007187215,0.00002817414,0.000005104453,0.000007590954,0.0001157588],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8060958,"threshold_uncertainty_score":0.295563,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01507833896096016,"gpt":0.2599297186008326,"spread":0.2448513796398724,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006937169,0.0001952095,0.0002089429,0.0003023658,0.0002359838,0.00008826025,0.001325166,0.000126822,0.000005242205],"category_scores_gemma":[0.00004565345,0.0001697504,0.00006239284,0.0006562066,0.0001087015,0.0005488519,0.000232969,0.0002890735,0.000009882424],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001263952,"about_ca_system_score_gemma":0.000112013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006267484,"about_ca_topic_score_gemma":0.0001026333,"domain_scores_codex":[0.9983379,0.00009101233,0.0003752828,0.0003212569,0.0005956476,0.0002788603],"domain_scores_gemma":[0.997558,0.0001225889,0.0003765188,0.001504679,0.0003562568,0.00008194061],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001523502,0.0003190445,0.002789064,0.0000507492,0.00001482681,0.000006500023,0.0007954547,0.01918821,0.1079873,0.002033686,0.0002220322,0.8664408],"study_design_scores_gemma":[0.0002931983,0.0001750573,0.0006773836,0.00020955,0.000007414609,0.000009032946,0.00003640033,0.3665683,0.6301605,0.001427484,0.0002611946,0.0001745323],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1901927,0.00004372745,0.8006974,0.0009904177,0.00002017426,0.0003228243,0.000001767743,0.000359238,0.007371734],"genre_scores_gemma":[0.5395692,0.00001515369,0.4601377,0.0001631425,0.00001165241,0.000006514677,0.00001866801,0.00001229519,0.00006566752],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8662663,"threshold_uncertainty_score":0.6922221,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1407854790236767,"gpt":0.2975063171245893,"spread":0.1567208381009126,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006671723,0.0001943191,0.0002186697,0.0002078829,0.0003291909,0.0002892508,0.0009800403,0.0001351289,0.0001647814],"category_scores_gemma":[0.0002548372,0.0002100281,0.0001630211,0.0003772388,0.00006282613,0.0009577301,0.0001883868,0.0002083828,0.0002804156],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001452692,"about_ca_system_score_gemma":0.0000177979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007786605,"about_ca_topic_score_gemma":0.00005249754,"domain_scores_codex":[0.9983822,0.0002099014,0.0004154756,0.0003740911,0.000282855,0.0003354782],"domain_scores_gemma":[0.9978473,0.0004370497,0.0002075989,0.001188703,0.0002135255,0.0001058203],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007682936,0.0001517338,0.00003603478,0.00001476344,0.0000167873,0.00000396572,0.000234331,0.00002096817,0.001150379,0.00008622273,0.0005260454,0.9977511],"study_design_scores_gemma":[0.0009415189,0.0001078823,0.000346618,0.0001857237,0.00004667911,0.0003260041,0.0001626654,0.933767,0.04964767,0.007281803,0.006607651,0.0005787617],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2100562,0.0004091096,0.7713596,0.002834408,0.0004987789,0.001105348,0.00002457286,0.000577557,0.01313448],"genre_scores_gemma":[0.2117685,0.0002005147,0.787325,0.0004239886,0.00005190046,0.0000445516,0.00003200874,0.00002394797,0.0001295835],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9971723,"threshold_uncertainty_score":0.8564695,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0416666573999727,"gpt":0.2793254558020496,"spread":0.2376587984020769,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007969296,0.0001390593,0.0001361549,0.0001131937,0.0002917656,0.0003198287,0.001221129,0.00005713219,0.00002842992],"category_scores_gemma":[0.0000436466,0.0001127975,0.00002495473,0.0005429999,0.00007834613,0.0005727978,0.0003217671,0.000231485,0.00002166527],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000635915,"about_ca_system_score_gemma":0.00001923543,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009047562,"about_ca_topic_score_gemma":0.00008663704,"domain_scores_codex":[0.9987222,0.0001890479,0.0002526347,0.0002607741,0.0002967185,0.0002786292],"domain_scores_gemma":[0.9985318,0.0001278329,0.0001243256,0.001109632,0.00006352953,0.00004287088],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002893104,0.0007628471,0.007287392,0.00009832086,0.00005667889,0.0001061709,0.0289678,0.0007711025,0.07406516,0.001742297,0.002112271,0.884001],"study_design_scores_gemma":[0.005328243,0.0003855533,0.009163622,0.0009981787,0.00005409475,0.001067568,0.003261744,0.5709387,0.3536303,0.03841667,0.01474016,0.00201518],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8896834,0.002006538,0.09898572,0.004634294,0.00007441409,0.0003135085,8.732116e-7,0.00005314158,0.004248175],"genre_scores_gemma":[0.5612091,0.0004878164,0.4377607,0.0004412689,0.00001981262,0.000009229567,0.000002922998,0.000006998528,0.00006212033],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8819858,"threshold_uncertainty_score":0.4599748,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05377732500004698,"gpt":0.3627955179644349,"spread":0.3090181929643879,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007527452,0.00007400076,0.0001266865,0.0001865443,0.0000696624,0.00002159257,0.0008127998,0.0001087847,0.0001495104],"category_scores_gemma":[0.0003334889,0.00005421493,0.00002486066,0.0006699962,0.0001935641,0.00002990118,0.00003634508,0.0004090169,0.00005486278],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002183725,"about_ca_system_score_gemma":0.000018455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003446811,"about_ca_topic_score_gemma":0.0001968653,"domain_scores_codex":[0.9981415,0.00107994,0.0002626445,0.0001488035,0.000218681,0.0001484377],"domain_scores_gemma":[0.9980312,0.0005992351,0.0001112549,0.001176382,0.00006287627,0.0000190244],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0004497326,0.00351024,0.2453276,0.00008733542,0.0002260158,0.00004031164,0.1036576,0.0004274873,0.2075104,0.3873195,0.003318196,0.04812557],"study_design_scores_gemma":[0.0002358791,0.00007918802,0.9726125,0.00001119533,0.000005327758,0.000006615405,0.0004682112,0.00001159569,0.004133395,0.02208618,0.000294223,0.00005571123],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9938463,0.0004255692,0.00001370794,0.0003701702,0.00005431076,0.0002285912,0.000006379388,0.000007244323,0.005047718],"genre_scores_gemma":[0.9993846,0.0001320369,0.0002118265,0.00008636124,0.000004966096,0.00002870427,0.00001579571,0.000005343787,0.000130375],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7272849,"threshold_uncertainty_score":0.221082,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02518451701706984,"gpt":0.2855548098378459,"spread":0.2603702928207761,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006152118,0.0002003914,0.0002240077,0.0001783416,0.0005009518,0.0003988429,0.001088387,0.00008738112,0.00004111895],"category_scores_gemma":[0.000251646,0.0002081612,0.00005755185,0.0006023476,0.0001203685,0.001064468,0.0003417417,0.0003949264,0.00009346439],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000769932,"about_ca_system_score_gemma":0.00008674568,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000843598,"about_ca_topic_score_gemma":0.0001629389,"domain_scores_codex":[0.9984049,0.0002421495,0.0003451237,0.0003931856,0.0002850644,0.0003295377],"domain_scores_gemma":[0.9977835,0.0002696919,0.0001911202,0.001466276,0.0001546743,0.0001346985],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000006505342,0.0001650543,0.01850497,0.0000383212,0.00006478572,0.000009202618,0.001285936,0.000008893289,0.006874356,0.009196317,0.002169691,0.9616759],"study_design_scores_gemma":[0.001959346,0.0001631933,0.01675905,0.0002859285,0.00007901772,0.0004268049,0.001201322,0.002028478,0.6834959,0.1198857,0.1723558,0.001359372],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6252322,0.003114203,0.2481055,0.01161846,0.0004775496,0.0008074836,0.00001144697,0.0009395509,0.1096936],"genre_scores_gemma":[0.6852992,0.0002750743,0.3136933,0.0001976622,0.00002751191,0.00001200794,0.00001830258,0.00001600326,0.0004608902],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9603166,"threshold_uncertainty_score":0.8488569,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.016970777521193,"gpt":0.2775899563125778,"spread":0.2606191787913847,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008460579,0.0002782499,0.0002857435,0.0002888037,0.0006333877,0.0009178516,0.001162329,0.0001788825,0.00001302555],"category_scores_gemma":[0.0001291172,0.0002886415,0.0000755756,0.0007563096,0.0001220126,0.001919567,0.0004289577,0.0003975792,0.00003422788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001988771,"about_ca_system_score_gemma":0.00009842038,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004429924,"about_ca_topic_score_gemma":0.0001839632,"domain_scores_codex":[0.9978665,0.0001092095,0.000538916,0.0005205956,0.0005269948,0.0004377782],"domain_scores_gemma":[0.9977065,0.0002425719,0.0003276047,0.00139402,0.0002199672,0.0001093347],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002849943,0.00018333,0.006722182,0.00004716385,0.00001484662,0.00003021194,0.0004534889,0.001753026,0.07137515,0.001884514,0.0002628677,0.9172447],"study_design_scores_gemma":[0.001047961,0.00007439136,0.02712332,0.0004401292,0.00003417994,0.0004234381,0.00006411294,0.2806074,0.5885929,0.100216,0.0007132339,0.0006628961],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6091188,0.0009379066,0.3874026,0.0004584204,0.0001078902,0.0002171325,0.000001515212,0.0001864739,0.001569294],"genre_scores_gemma":[0.5253203,0.00008507202,0.4743923,0.00007277699,0.00006298595,0.000003608515,0.00001467771,0.00001643651,0.00003186541],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9165818,"threshold_uncertainty_score":0.9999565,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01657203052775897,"gpt":0.27139861829223,"spread":0.254826587764471,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003474426,0.00009315072,0.0000868507,0.00007940747,0.0002619789,0.0001301982,0.0006142791,0.00007093588,0.000003832183],"category_scores_gemma":[0.0001189604,0.00008874824,0.00003169762,0.0001618902,0.00006841955,0.0005159042,0.0001019948,0.0002244294,0.0000105791],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001658477,"about_ca_system_score_gemma":0.0000342008,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001383003,"about_ca_topic_score_gemma":0.00001626965,"domain_scores_codex":[0.999316,0.0000322392,0.0001480307,0.0002258717,0.000127916,0.0001499423],"domain_scores_gemma":[0.9987928,0.0001053032,0.00009518958,0.0008589277,0.00008836605,0.0000593688],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003578404,0.0001148455,0.00006719822,0.00002527251,0.00001125951,5.786602e-7,0.0008137965,0.00005849788,0.3576224,0.01984017,0.002683991,0.6187262],"study_design_scores_gemma":[0.0007934775,0.0001860409,0.001242045,0.00006591906,0.00001162074,0.00006122565,0.00005852764,0.02123389,0.9152856,0.04510804,0.01563942,0.0003141267],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.86878,0.0002049662,0.1138382,0.0134281,0.0005026437,0.0004142168,0.000003541312,0.0002624019,0.002565991],"genre_scores_gemma":[0.6383135,0.00003887184,0.3611675,0.00023903,0.00005899778,0.0000213149,0.00001056984,0.000007950257,0.0001422802],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6184121,"threshold_uncertainty_score":0.3619048,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05304061750017006,"gpt":0.3635451708443765,"spread":0.3105045533442065,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004690043,0.0001730474,0.0002830965,0.0004854355,0.0005183739,0.00009171679,0.0006168519,0.00009672132,0.0004716054],"category_scores_gemma":[0.0000574018,0.0002033179,0.00005072558,0.000658426,0.0001010708,0.00009882904,0.0004134057,0.001060345,0.0000611502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001453719,"about_ca_system_score_gemma":0.00003482467,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02158283,"about_ca_topic_score_gemma":0.002076336,"domain_scores_codex":[0.9976906,0.000927178,0.000339971,0.0004388923,0.0002606024,0.0003427475],"domain_scores_gemma":[0.9984034,0.0005592188,0.00006280586,0.0008301027,0.00004469123,0.00009973688],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0004235689,0.000427933,0.03667945,0.00001220763,0.0003117983,0.0001259342,0.2794617,0.003392375,0.5885921,0.0001066875,0.0004927445,0.08997354],"study_design_scores_gemma":[0.003945468,0.0005609139,0.8600052,0.0002508861,0.0001472564,0.00002803772,0.05775184,0.01093898,0.04655702,0.008308261,0.01023063,0.001275519],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9926462,0.002234636,0.0002536796,0.001293681,0.0001791675,0.0002480803,0.00002115187,0.0000591439,0.003064221],"genre_scores_gemma":[0.9969611,0.000162778,0.002076085,0.000304587,0.00003620824,0.00004742813,0.0002091967,0.00003731973,0.0001652776],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8233258,"threshold_uncertainty_score":0.9849325,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04949166615472159,"gpt":0.4204073798418991,"spread":0.3709157136871775,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002308281,0.00009411758,0.0002849819,0.0003163051,0.000172377,0.00004875693,0.00172578,0.00004651143,0.00001117117],"category_scores_gemma":[0.0002655881,0.00009278595,0.0001938154,0.004667305,0.0000441356,0.0002524471,0.000342634,0.00009051208,0.00003621207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003033387,"about_ca_system_score_gemma":0.00006505632,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000143492,"about_ca_topic_score_gemma":0.000008220425,"domain_scores_codex":[0.9988523,0.0001808458,0.0003967443,0.0002446022,0.0001499303,0.0001755669],"domain_scores_gemma":[0.9968178,0.0004825612,0.0002900831,0.001978557,0.0003836343,0.00004732413],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[9.695559e-7,0.00003027036,0.00006636212,0.0007680681,0.00008961511,8.239046e-8,0.0000596365,0.00001341071,0.003144926,0.003545287,0.002262654,0.9900187],"study_design_scores_gemma":[0.0004065501,0.00006206008,0.001107008,0.0017499,0.0006367487,0.000009197296,0.00007242428,0.03175378,0.4742948,0.07949772,0.4098972,0.0005126336],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00008080137,0.02310532,0.9700283,0.003520116,0.00002566262,0.0005368682,0.000005426763,0.000247528,0.002449941],"genre_scores_gemma":[0.00143164,0.02153805,0.9758331,0.0005713511,0.00001684301,0.0002741674,0.0001218761,0.000008615581,0.0002043409],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9895061,"threshold_uncertainty_score":0.3783701,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04052135051112452,"gpt":0.3337434522729866,"spread":0.2932221017618621,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001292754,0.0001963926,0.0003047217,0.00009196564,0.0006232469,0.0001077374,0.000394234,0.0001175157,0.000005272724],"category_scores_gemma":[0.004889871,0.0001544163,0.00008689181,0.0004653555,0.001043354,0.0003153424,0.0004047748,0.0003333201,0.000001771597],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001538358,"about_ca_system_score_gemma":0.0001336523,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001968038,"about_ca_topic_score_gemma":0.0002768308,"domain_scores_codex":[0.998041,0.0004337743,0.0004606711,0.00049961,0.0003304807,0.0002345179],"domain_scores_gemma":[0.9924264,0.005421292,0.000315752,0.0007920733,0.0009666782,0.00007781397],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008024799,0.001151867,0.005877674,0.0006832749,0.0002405852,0.00000725495,0.09224138,0.0002388065,0.4653876,0.08765407,0.0004240779,0.3452909],"study_design_scores_gemma":[0.001097469,0.0004736784,0.08230476,0.0002513825,0.00004483179,0.00001216793,0.01015026,0.008552738,0.8257689,0.06992979,0.001068534,0.0003455142],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9900988,0.0003302055,0.0009818161,0.002793996,0.0001079055,0.001045596,0.00007499871,0.00002427216,0.004542374],"genre_scores_gemma":[0.9919069,0.001170522,0.006132183,0.0001311907,0.00002089258,0.00009276008,0.000020011,0.00001986622,0.0005056384],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3603812,"threshold_uncertainty_score":0.6296913,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01437912466771747,"gpt":0.2704167718987001,"spread":0.2560376472309826,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005414985,0.0001513212,0.0001428887,0.00005081008,0.0003037892,0.0002897193,0.001602942,0.0000753124,0.0001519547],"category_scores_gemma":[0.00004818651,0.0001385566,0.00006166143,0.0003621744,0.00009149293,0.0009160937,0.0002648979,0.0003788996,0.0002346789],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003551885,"about_ca_system_score_gemma":0.00005754859,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004193978,"about_ca_topic_score_gemma":0.0002107524,"domain_scores_codex":[0.9987013,0.00005392284,0.0002972286,0.0002859418,0.0003265737,0.0003350145],"domain_scores_gemma":[0.9978992,0.00006663898,0.000110034,0.001683191,0.0001274367,0.0001134773],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001061832,0.0001410342,0.0003427108,0.00001533716,0.0000133709,0.000004190969,0.0006856493,0.000002611256,0.3856892,0.00471236,0.0009425389,0.6074404],"study_design_scores_gemma":[0.0003517159,0.00004865702,0.0006540225,0.00003467068,0.000005942304,0.0000244418,0.00002565077,0.003286429,0.9698549,0.00826428,0.01725244,0.000196864],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6431033,0.0004617291,0.2918312,0.0274965,0.0004343307,0.0005731093,0.000004416174,0.0005190265,0.0355764],"genre_scores_gemma":[0.7569376,0.00007403601,0.2418653,0.0004161444,0.00004575151,0.00002626227,0.00001459403,0.00001031176,0.0006100424],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6072435,"threshold_uncertainty_score":0.5650173,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1001163082351362,"gpt":0.3762995965308839,"spread":0.2761832882957477,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002299632,0.0001381957,0.0002664135,0.0001030847,0.0001464567,0.0001218872,0.001676625,0.00008190829,0.000002790541],"category_scores_gemma":[0.0005416315,0.000133684,0.00008765596,0.0003692931,0.0000818302,0.0006249116,0.0003746255,0.0001653497,0.000005555904],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001469985,"about_ca_system_score_gemma":0.00037866,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001464321,"about_ca_topic_score_gemma":0.00006711562,"domain_scores_codex":[0.9982392,0.0002997413,0.000422063,0.0002828153,0.0005348923,0.0002212636],"domain_scores_gemma":[0.9965823,0.0003114124,0.0003802421,0.001615644,0.00100631,0.0001040412],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001442132,0.001138169,0.01333117,0.0002612821,0.0001930119,0.000002707921,0.005300456,0.0005390358,0.1768546,0.05749653,0.005991304,0.7387475],"study_design_scores_gemma":[0.001464077,0.0001857814,0.01219708,0.00008919135,0.00002093107,0.000008411301,0.000461269,0.007040872,0.9099165,0.06403054,0.004261112,0.000324185],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08645426,0.0008243516,0.8807885,0.002604931,0.0002555735,0.0007864938,0.00001553866,0.0002557899,0.02801456],"genre_scores_gemma":[0.5703635,0.00001960005,0.4293894,0.00007995018,0.00002195224,0.00003307713,0.00001398,0.000007351243,0.0000711494],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7384233,"threshold_uncertainty_score":0.5451477,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1914429183652695,"gpt":0.4379504369399535,"spread":0.246507518574684,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001765697,0.00007097732,0.0001056208,0.0003904329,0.0001208441,0.0003069025,0.0009475507,0.00005124403,0.0001033776],"category_scores_gemma":[0.00005141232,0.00006675932,0.00003779947,0.0009383259,0.0001050435,0.0006021062,0.0003448849,0.000179149,0.00006819364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003343778,"about_ca_system_score_gemma":0.00003187745,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001470356,"about_ca_topic_score_gemma":0.00006302957,"domain_scores_codex":[0.99852,0.0004664478,0.000244579,0.0002535166,0.0003822522,0.0001332354],"domain_scores_gemma":[0.9980199,0.0002904899,0.00004684694,0.001410591,0.0001680658,0.00006408406],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000002077649,0.00005998621,0.00004552211,0.00005226129,0.00001159298,0.000003794374,0.001724898,3.33584e-7,0.003191674,0.03772187,0.001329001,0.955857],"study_design_scores_gemma":[0.001005179,0.0005045357,0.100271,0.001743976,0.00009660867,0.0003331484,0.005574261,0.1914187,0.358943,0.08344856,0.2554072,0.00125377],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6488012,0.1464575,0.02216421,0.05016714,0.0008082131,0.001294699,0.00008781446,0.001690193,0.1285291],"genre_scores_gemma":[0.9671032,0.002825239,0.02834483,0.00003398583,0.00006162505,0.00003322728,0.00004005709,0.00001122016,0.00154664],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9546032,"threshold_uncertainty_score":0.2959468,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1014111182220048,"gpt":0.4468027347937438,"spread":0.345391616571739,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004921077,0.0000954247,0.0002980763,0.0005415881,0.00009263071,0.00001263815,0.0002988362,0.0001003295,0.00006136332],"category_scores_gemma":[0.00006685881,0.00008878664,0.0001408059,0.00135867,0.0001216851,0.00007647664,0.00005676611,0.0001191819,0.00002007034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007859932,"about_ca_system_score_gemma":0.00002429771,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004237938,"about_ca_topic_score_gemma":0.0002985501,"domain_scores_codex":[0.9990273,0.0001689852,0.0002707083,0.0001783794,0.0002006014,0.0001539963],"domain_scores_gemma":[0.9979311,0.0005193915,0.0002745248,0.0009328462,0.0003134677,0.0000287219],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001325294,0.002028753,0.0561485,0.0002043359,0.008933214,0.000006727505,0.02165814,0.00009621582,0.3846704,0.03647511,0.02152747,0.4669258],"study_design_scores_gemma":[0.0004266159,0.0003283686,0.8925311,0.00003978815,0.0006071526,0.000002924498,0.00350045,0.001720061,0.09386534,0.001749616,0.005092094,0.0001365072],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9734783,0.0006598536,0.003615667,0.001812909,0.00008101662,0.001298194,0.0002389217,0.0002248357,0.01859035],"genre_scores_gemma":[0.9881356,0.0002070549,0.009820252,0.000007340006,0.0000137629,0.0002889888,0.0006871847,0.000008227291,0.0008316166],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8363826,"threshold_uncertainty_score":0.3620614,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05414851381171239,"gpt":0.392138184147549,"spread":0.3379896703358366,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001239868,0.00008865242,0.0001393616,0.00006564434,0.0001150128,0.00007544686,0.0002161222,0.00008703419,0.00001052593],"category_scores_gemma":[0.00008280596,0.0000753895,0.00001748825,0.000128807,0.00008888951,0.0001392278,0.00008005893,0.000265673,0.00001204222],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003420902,"about_ca_system_score_gemma":0.00001921439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003833705,"about_ca_topic_score_gemma":0.0007650483,"domain_scores_codex":[0.998723,0.0006234825,0.0001410434,0.0002141407,0.000126635,0.0001717348],"domain_scores_gemma":[0.9986449,0.0004693317,0.0000674663,0.0007364227,0.00005315017,0.00002872044],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001810047,0.0007569025,0.215843,0.0003424906,0.0003025286,0.000005945491,0.08741913,0.2553851,0.1643505,0.08542603,0.0003673294,0.187991],"study_design_scores_gemma":[0.0005659803,0.00001827941,0.01786787,0.00002580072,0.000006831646,0.000004283652,0.0003634701,0.9686143,0.0006567165,0.01174487,0.00003423038,0.00009735455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9864725,0.001143293,0.005689202,0.004259018,0.00004032938,0.0004243159,0.000006852788,0.00001716067,0.001947315],"genre_scores_gemma":[0.9973276,0.0006075718,0.00173742,0.0000525419,0.0000120848,0.0000576907,0.00001310053,0.00000954126,0.0001824015],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7132292,"threshold_uncertainty_score":0.3074295,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.03184880997429594,"gpt":0.2834683969035733,"spread":0.2516195869292774,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002762204,0.0001143734,0.000300403,0.0003450837,0.0003693098,0.00006086323,0.001536968,0.00007080902,0.000003801608],"category_scores_gemma":[0.0003655329,0.000096848,0.0002466612,0.001779521,0.00009434148,0.0002108129,0.0002265857,0.0001355258,0.000001047098],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001464774,"about_ca_system_score_gemma":0.00008454707,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000356469,"about_ca_topic_score_gemma":0.0009410071,"domain_scores_codex":[0.9985353,0.0001207767,0.0006133741,0.0002388703,0.0002577167,0.0002339614],"domain_scores_gemma":[0.9963703,0.0008643569,0.0005087062,0.001739591,0.0004724929,0.00004453319],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001719859,0.0005683238,0.07282579,0.001002669,0.000997357,0.00000241918,0.0024837,0.008977053,0.1756973,0.004290478,0.00002707606,0.7329558],"study_design_scores_gemma":[0.0004615657,0.00003749504,0.1027415,0.0001306307,0.0002943456,0.000003073017,0.0004767704,0.05705171,0.8381208,0.0004686172,0.00006164961,0.0001518633],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5016036,0.0001861759,0.497151,0.0003514331,0.00006193789,0.0002745417,0.000009739696,0.00006658716,0.0002949787],"genre_scores_gemma":[0.8095995,0.000009201618,0.1903181,0.00001220215,0.00001610181,0.00001474268,0.00001127282,0.000005970767,0.00001291073],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7328039,"threshold_uncertainty_score":0.3949347,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.08195727356324413,"gpt":0.3490716138896044,"spread":0.2671143403263603,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004137761,0.0001295244,0.0001844538,0.0002255033,0.0001546422,0.00005200772,0.000633829,0.00006888285,0.0001116028],"category_scores_gemma":[0.00002439372,0.0001121294,0.0001051265,0.0004708955,0.00003177016,0.0004915123,0.00006648175,0.0001566202,0.00001906111],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001628499,"about_ca_system_score_gemma":0.00004118965,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002459219,"about_ca_topic_score_gemma":0.00000125621,"domain_scores_codex":[0.9988186,0.0001401054,0.0003201761,0.0001921151,0.0003769251,0.0001520754],"domain_scores_gemma":[0.9983856,0.0001773749,0.000194838,0.001025198,0.0001534683,0.0000635162],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009911569,0.0002960099,0.000453039,0.00001873092,0.00002247907,5.158151e-7,0.0003158305,0.486833,0.006504641,0.000241046,0.00003768948,0.5052671],"study_design_scores_gemma":[0.0002419008,0.00008146688,0.004127994,0.0000959844,0.00001273522,0.000004057103,0.000008158696,0.9839834,0.01091796,0.0003743731,0.00003155836,0.0001204127],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5301093,0.00005849066,0.464411,0.0001765812,0.00001476956,0.0001588744,0.000001998583,0.00006593287,0.005003089],"genre_scores_gemma":[0.758909,0.0001842113,0.2407908,0.00004285834,0.000005498059,0.000003427355,0.000004598242,0.000007323465,0.00005229266],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5051467,"threshold_uncertainty_score":0.4572505,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03177723736601459,"gpt":0.3269485681240554,"spread":0.2951713307580408,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001174581,0.0001618423,0.0001719501,0.0001992716,0.0002226414,0.0006754919,0.001061292,0.00008638292,0.00001333931],"category_scores_gemma":[0.0004734157,0.0001473169,0.00005907312,0.001472409,0.00008177054,0.0005010549,0.000332071,0.0002650325,0.00008982955],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001916649,"about_ca_system_score_gemma":0.000167089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001416646,"about_ca_topic_score_gemma":0.00008986961,"domain_scores_codex":[0.9983522,0.0002824054,0.0002667767,0.0004021724,0.0004715793,0.0002248071],"domain_scores_gemma":[0.9980279,0.0004400036,0.00008720202,0.001202169,0.0001487461,0.00009398694],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001404343,0.0000662093,0.0003238127,0.00005896544,0.0000230951,0.00001298783,0.0001662126,0.00003357863,0.001058421,0.04330406,0.001126782,0.9538118],"study_design_scores_gemma":[0.001690404,0.0004722529,0.02057329,0.001163049,0.00008056503,0.0001792237,0.0002152697,0.05754531,0.3960955,0.48437,0.03611048,0.0015047],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1839968,0.02010015,0.7233428,0.02370649,0.0006643176,0.0006684769,0.00002626616,0.001642156,0.04585247],"genre_scores_gemma":[0.8551338,0.0001424559,0.1438983,0.0007133162,0.0000309895,0.00001117608,0.000009235687,0.000008239323,0.00005250272],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9523071,"threshold_uncertainty_score":0.6513784,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01252535883379708,"gpt":0.2535649671924412,"spread":0.2410396083586441,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004038709,0.0002143604,0.0002148788,0.0004293406,0.0003296907,0.0002583475,0.001270507,0.0001010063,0.00006791648],"category_scores_gemma":[0.0001012319,0.0001829169,0.0001139452,0.001555812,0.00008704716,0.0006611855,0.0002290922,0.0003189502,0.0001028256],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007505637,"about_ca_system_score_gemma":0.00008019657,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001014024,"about_ca_topic_score_gemma":0.0002243555,"domain_scores_codex":[0.9984303,0.000273595,0.0003065896,0.0003755894,0.0003245982,0.0002893437],"domain_scores_gemma":[0.9979506,0.0002082843,0.0001393809,0.001343247,0.0002863035,0.00007215618],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003648844,0.0001552008,0.001649575,0.00001168661,0.00004256879,0.000005667672,0.0001105106,0.000001479966,0.001389112,0.001203715,0.0006909366,0.9947031],"study_design_scores_gemma":[0.008372426,0.00142435,0.1829309,0.001043789,0.0003223887,0.0006703866,0.0007178404,0.06370573,0.4033119,0.2775002,0.05610684,0.003893213],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8164528,0.0006767344,0.06585564,0.01044565,0.0004079105,0.001049316,0.00001607788,0.001139685,0.1039562],"genre_scores_gemma":[0.8014934,0.0002654075,0.1966169,0.001056322,0.00003638656,0.00009285045,0.00008781493,0.00001412539,0.0003367763],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9908099,"threshold_uncertainty_score":0.7459134,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05891814902745833,"gpt":0.377314962561023,"spread":0.3183968135335646,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001582826,0.0001209117,0.0002353563,0.0002075912,0.0001441252,0.0000468991,0.0003933285,0.00004865906,0.00006958035],"category_scores_gemma":[0.0009239248,0.00008953131,0.00006429667,0.0005767744,0.0003207979,0.0001434144,0.0003147924,0.0006674465,0.000004356366],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003073448,"about_ca_system_score_gemma":0.00008267579,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005844643,"about_ca_topic_score_gemma":0.0006270262,"domain_scores_codex":[0.9982085,0.0003114447,0.0004647515,0.0002448723,0.0005899516,0.0001804707],"domain_scores_gemma":[0.9977837,0.0005960705,0.0001057259,0.001140994,0.000337635,0.0000359162],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005752178,0.001331232,0.9499871,0.0006214182,0.0001291304,0.000007591183,0.003160523,0.001559147,0.03984503,0.0001011079,0.000006979563,0.002675487],"study_design_scores_gemma":[0.0009803178,0.0003756291,0.976831,0.0002029031,0.00003846172,0.00003963884,0.001274698,0.01120147,0.008371102,0.0006170154,8.544156e-7,0.00006692144],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9971057,0.0005283031,0.00026518,0.0002415961,0.0000974807,0.0010037,0.0000141635,0.00004288855,0.0007010442],"genre_scores_gemma":[0.9980584,0.000005805846,0.001669171,0.000004760358,0.00003837958,0.00007240124,0.00001846622,0.00002068788,0.0001119069],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03147392,"threshold_uncertainty_score":0.3650981,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.09756938840414185,"gpt":0.4327188878083705,"spread":0.3351494994042286,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001670148,0.00006202446,0.00007591135,0.00005145888,0.0005902825,0.00004209154,0.0007381688,0.0001017971,0.0000632821],"category_scores_gemma":[0.001665316,0.00004061159,0.00005480886,0.0002874983,0.00035771,0.00001781235,0.0001404721,0.0002129965,0.0001328034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002996945,"about_ca_system_score_gemma":0.00002901204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002455355,"about_ca_topic_score_gemma":0.0001023191,"domain_scores_codex":[0.9991097,0.0002078316,0.000236756,0.0001110532,0.0001390433,0.0001956227],"domain_scores_gemma":[0.995394,0.002890416,0.0000805899,0.001140854,0.0004765437,0.00001762291],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001840645,0.0006252508,0.06670054,0.0001376158,0.0007263176,0.000001779602,0.0555085,0.0006757976,0.05805123,0.3054968,0.1820671,0.3281684],"study_design_scores_gemma":[0.0006776871,0.0002137248,0.853163,0.00001914243,0.00002821198,0.000002614109,0.003325708,0.004891574,0.001706121,0.02880205,0.1070508,0.0001193689],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9859607,0.0005784422,0.0005869681,0.004655757,0.0008276926,0.0007517842,0.00003804382,0.00007608294,0.006524576],"genre_scores_gemma":[0.9955568,0.001062574,0.0002587014,0.00004519111,0.0001240271,0.0001622341,0.0001084372,0.00001480499,0.002667281],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7864625,"threshold_uncertainty_score":0.4540035,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01794925621106189,"gpt":0.29861527863153,"spread":0.2806660224204681,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005372001,0.0001158977,0.0001426799,0.0001297861,0.0005505503,0.0003621324,0.001304711,0.00006717216,0.000002634245],"category_scores_gemma":[0.0001337849,0.0001235794,0.00004344883,0.0004601213,0.00004823969,0.0009496437,0.0001825501,0.0001113726,0.00001142371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007733773,"about_ca_system_score_gemma":0.0001133613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008723318,"about_ca_topic_score_gemma":0.00003400205,"domain_scores_codex":[0.9990284,0.0001007281,0.0002695881,0.0002743312,0.0001239698,0.0002029266],"domain_scores_gemma":[0.9982379,0.0001477621,0.0001845931,0.001203552,0.0001852057,0.00004096437],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002034647,0.0001205008,0.0004738829,0.00005297059,0.00001793498,2.00866e-7,0.0003505463,0.008234283,0.4515667,0.001820419,0.0001765786,0.5371656],"study_design_scores_gemma":[0.0004214061,0.0000160344,0.0004065613,0.00008133463,0.000009445585,0.000003202659,0.00005101712,0.4448139,0.5328132,0.01839431,0.002845082,0.0001445038],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07243154,0.0005220417,0.9249524,0.001199916,0.0001351917,0.0002356087,0.000002590917,0.0001941968,0.000326491],"genre_scores_gemma":[0.3377242,0.00002852641,0.6618302,0.0002875592,0.0000179891,0.00001725442,0.00003110527,0.000006484491,0.00005666037],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5370211,"threshold_uncertainty_score":0.5039422,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01981430678924019,"gpt":0.3696625674197417,"spread":0.3498482606305016,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006355477,0.0001019723,0.0002254194,0.0002821255,0.0000778774,0.00001144188,0.0005207287,0.0001893529,0.0004118041],"category_scores_gemma":[0.0003407794,0.0001097782,0.00007360919,0.000432138,0.0002399103,0.00008243739,0.0001815518,0.0002785613,0.00003647188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000521954,"about_ca_system_score_gemma":0.00006470784,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007724165,"about_ca_topic_score_gemma":0.00009001388,"domain_scores_codex":[0.9986216,0.0003970993,0.0004269838,0.0001970083,0.0001774345,0.0001798276],"domain_scores_gemma":[0.9977707,0.0002711733,0.0002137978,0.0009949938,0.0007211181,0.00002827015],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.000519594,0.001029883,0.01183478,0.0001460354,0.0002823313,0.000001134346,0.05584845,0.000006423356,0.5932961,0.006193236,0.007703613,0.3231384],"study_design_scores_gemma":[0.002012506,0.0005917175,0.7799042,0.000144397,0.00007763162,0.000002832204,0.01969244,0.0003983667,0.1858305,0.006176157,0.004902813,0.0002663433],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.954958,0.0005957679,0.000242394,0.000240066,0.0003309693,0.0003212381,0.00001147691,0.00003672382,0.04326342],"genre_scores_gemma":[0.9955664,0.0002767556,0.002142885,0.00002552706,0.00005132431,0.0000402601,0.00009465061,0.00001139147,0.001790786],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7680694,"threshold_uncertainty_score":0.4508966,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01055337093339996,"gpt":0.2584348436806053,"spread":0.2478814727472053,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001133935,0.0001969559,0.000283944,0.0007189109,0.0003545163,0.0002957833,0.001393469,0.0001240295,0.00001652106],"category_scores_gemma":[0.0004341007,0.0001934447,0.00004938957,0.003484441,0.00007059033,0.000941154,0.0005829866,0.0008160206,0.00002430854],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002626162,"about_ca_system_score_gemma":0.0003078973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004209147,"about_ca_topic_score_gemma":0.001556233,"domain_scores_codex":[0.9981244,0.0002927508,0.0004052832,0.0004411702,0.0003405468,0.0003958804],"domain_scores_gemma":[0.9980907,0.0002744346,0.0002108075,0.001227796,0.0001376421,0.0000586022],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004005369,0.001188709,0.07248937,0.0003876403,0.0002397456,0.0002513301,0.006191874,0.00347849,0.1155196,0.02448535,0.0008605744,0.7745067],"study_design_scores_gemma":[0.002043919,0.0001251672,0.01500827,0.0004813308,0.00002766076,0.00004655093,0.000498617,0.007458315,0.9567771,0.01371875,0.003296103,0.0005182033],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6948755,0.00227716,0.2576107,0.008229449,0.0003750777,0.000660756,0.000001074337,0.000770108,0.03520024],"genre_scores_gemma":[0.8182313,0.0001093243,0.1809614,0.0002214913,0.0000260474,0.00001172855,0.00001201232,0.00001043,0.00041624],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8412575,"threshold_uncertainty_score":0.7888445,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04041305165529514,"gpt":0.3822127607960807,"spread":0.3417997091407856,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007530613,0.00003851745,0.0000979777,0.0001165303,0.0001623896,0.000008492759,0.0002659906,0.00006782709,0.00005058446],"category_scores_gemma":[0.003811746,0.00003985867,0.00002352406,0.00032973,0.0001000364,0.00003757275,0.00007002486,0.00008911317,0.000007676505],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005219628,"about_ca_system_score_gemma":0.0001248088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001118735,"about_ca_topic_score_gemma":0.0005579455,"domain_scores_codex":[0.9991723,0.0003129378,0.0001869797,0.00007144584,0.000189296,0.00006698231],"domain_scores_gemma":[0.9983062,0.0008713314,0.0001511337,0.0002765581,0.0003796122,0.00001516875],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00001599897,0.00006535972,0.003244287,0.0000329825,0.00001210929,1.407401e-7,0.002791573,0.00001689572,0.002606578,0.9845515,0.0001364212,0.006526189],"study_design_scores_gemma":[0.003423097,0.0006085974,0.3162922,0.002082546,0.0001375429,6.333191e-7,0.00510852,0.001421034,0.1541329,0.2979799,0.2182683,0.0005447118],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8122737,0.0003922925,0.001943254,0.003175837,0.001000332,0.0004134085,0.00000448272,0.00006870786,0.1807279],"genre_scores_gemma":[0.9946387,0.0001798463,0.00452211,0.0001300841,0.00001611356,0.000002651703,0.00001370901,0.000002766091,0.000493963],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6865715,"threshold_uncertainty_score":0.4563292,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03229459497336561,"gpt":0.2911705704648505,"spread":0.2588759754914848,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005901216,0.0001514394,0.0002361008,0.0002006441,0.0004382304,0.0002999959,0.001102227,0.00008017746,0.00003284387],"category_scores_gemma":[0.0001006461,0.0001381453,0.0000290458,0.0006062521,0.0001171956,0.0003884391,0.0003553742,0.0002054903,0.00003891671],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005819681,"about_ca_system_score_gemma":0.00009441666,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00023776,"about_ca_topic_score_gemma":0.0002899802,"domain_scores_codex":[0.9987087,0.0002290476,0.0003136754,0.0003006106,0.0002569066,0.0001910887],"domain_scores_gemma":[0.9978466,0.0003700907,0.0001560872,0.001369904,0.0001963457,0.00006097299],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001438642,0.0004510593,0.006821821,0.0001369399,0.0001502942,0.000006420539,0.0006583211,0.00001505958,0.003126193,0.4366918,0.008754456,0.5431733],"study_design_scores_gemma":[0.004615234,0.0005304996,0.1986203,0.002743793,0.0003130606,0.0003897591,0.00161334,0.2029669,0.06005545,0.4316434,0.09430408,0.002204193],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.287688,0.001300658,0.4748065,0.01626859,0.0001978539,0.001251973,0.00001010428,0.00157335,0.216903],"genre_scores_gemma":[0.3625307,0.00005356749,0.6357049,0.000598355,0.000009904761,0.00003226825,0.00002073859,0.000008771533,0.001040781],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5409691,"threshold_uncertainty_score":0.5633401,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.04759745153485321,"gpt":0.442348790165715,"spread":0.3947513386308618,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004396504,0.00008085182,0.0004039374,0.0006655625,0.0001160417,0.00004746142,0.0005792796,0.00005592591,0.0005860448],"category_scores_gemma":[0.0007095496,0.00007249114,0.00004691407,0.00171015,0.0001671845,0.00004563675,0.0001987825,0.0004612107,0.00008708395],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005934693,"about_ca_system_score_gemma":0.00002535608,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005910541,"about_ca_topic_score_gemma":0.001634531,"domain_scores_codex":[0.997245,0.001809084,0.0003722806,0.0001989311,0.0001389424,0.0002357903],"domain_scores_gemma":[0.9965238,0.00166522,0.00007406808,0.001596369,0.0001082966,0.00003225451],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"observational","study_design_scores_codex":[0.0001473859,0.002513257,0.0923797,0.5826558,0.00819944,0.0002034667,0.1543034,0.000006233677,0.01830536,0.08546292,0.04512643,0.01069653],"study_design_scores_gemma":[0.003923563,0.0001628487,0.6690269,0.140032,0.007676064,0.0004004413,0.06670674,0.001541404,0.002637277,0.1056493,0.0006946867,0.001548748],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4663933,0.4368129,0.00007229186,0.003848065,0.00004005431,0.001929414,0.00001372717,0.00004314983,0.09084711],"genre_scores_gemma":[0.9898629,0.005058538,0.0002247784,0.0003608424,0.000002679139,0.0002119111,0.00003109121,0.000007148504,0.004240093],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5766472,"threshold_uncertainty_score":0.641678,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.0460206974990346,"gpt":0.2815052824270141,"spread":0.2354845849279795,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001010655,0.0002089547,0.000244247,0.0003759978,0.0003289724,0.000308789,0.001486378,0.000174352,0.0000706932],"category_scores_gemma":[0.0002463282,0.0002169405,0.0001124885,0.0009634183,0.00005831788,0.001447841,0.0003700171,0.000274669,0.0002772496],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002331193,"about_ca_system_score_gemma":0.0002220518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001970857,"about_ca_topic_score_gemma":0.0001096722,"domain_scores_codex":[0.9980234,0.0003807285,0.0004606577,0.0004295295,0.0004282964,0.0002774136],"domain_scores_gemma":[0.9973208,0.0001474349,0.000173776,0.001698576,0.000582809,0.00007664727],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000142374,0.0001310929,0.0000864354,0.00002091754,0.00002793775,0.000001344237,0.0002338953,0.000009280895,0.0007623464,0.01295717,0.001247294,0.984508],"study_design_scores_gemma":[0.001487086,0.00007388677,0.002406129,0.0004074087,0.00006992715,0.0000346124,0.0002605683,0.260279,0.176331,0.5465824,0.01136145,0.0007065627],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05130233,0.0005846073,0.6044388,0.01438463,0.0004713995,0.001317414,0.00001636034,0.001270779,0.3262137],"genre_scores_gemma":[0.405525,0.0005732451,0.5906923,0.001717726,0.0000380643,0.0001630266,0.0001344164,0.00001907629,0.001137105],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9838015,"threshold_uncertainty_score":0.8846576,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.03937597339703516,"gpt":0.3192036772772741,"spread":0.2798277038802389,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001632728,0.0002692375,0.0002867051,0.002764265,0.0005207018,0.0003953721,0.001920394,0.0002561393,0.00003917181],"category_scores_gemma":[0.00221795,0.0002992577,0.00006019185,0.008999934,0.0001110656,0.001756227,0.0006606664,0.0004318818,0.0004876237],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003293278,"about_ca_system_score_gemma":0.0002937305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005418465,"about_ca_topic_score_gemma":0.00006541511,"domain_scores_codex":[0.997493,0.0003513061,0.000633377,0.0006529809,0.0004528668,0.0004165052],"domain_scores_gemma":[0.9963219,0.0004075884,0.0003334111,0.002009852,0.0007749115,0.0001523831],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001062888,0.0001507438,0.0008652264,0.00005217023,0.00001397166,0.000003261856,0.0002348526,0.000005604279,0.01215618,0.00005872175,0.0006150858,0.9858335],"study_design_scores_gemma":[0.0008959906,0.0006566279,0.01945372,0.00118355,0.00008158935,0.0000949807,0.0002162287,0.03141773,0.696029,0.248735,0.0006000595,0.0006355412],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9363445,0.0005621011,0.04360282,0.01322216,0.0002533828,0.001101086,0.000007617835,0.001558507,0.003347823],"genre_scores_gemma":[0.4216216,0.0001000475,0.5768001,0.0009302253,0.00003053296,0.0002121326,0.0001378715,0.00001824562,0.0001492751],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.985198,"threshold_uncertainty_score":0.9999459,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}