{"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","author_layer_release":"2026-06-26"},"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","authors":[{"name":"Roddy Cowie","is_ca":true},{"name":"Randolph R. Cornelius","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002495614,0.0004324502,0.0001222143,0.0004049506,0.0003446333,0.001380607,0.0002254752,0.0006474412,0.002247947],"category_scores_gemma":[0.001331771,0.00006739388,0.0001835601,0.0004016891,0.0004809723,0.0008270071,0.0002560223,0.0005817686,0.000818355],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001784574,"about_ca_system_score_gemma":0.0001340079,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004719295,"about_ca_topic_score_gemma":0.0007088305,"domain_scores_codex":[0.999928,0.00002878018,0.000007642575,0.00001061398,0.00001424523,0.00001070828],"domain_scores_gemma":[0.9996046,0.0002550781,0.00004600222,0.00002296121,0.0000537523,0.00001757394],"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":[0.001211,0.0001448084,0.01107748,0.001907424,0.0001048664,0.003117366,0.02248928,0.006147998,0.2485251,0.2074394,0.02928621,0.4685491],"study_design_scores_gemma":[0.00006917164,0.0008887461,0.127855,0.002038316,0.0003981616,0.01400883,0.02433158,0.0545734,0.1252844,0.1671466,0.4830977,0.000308117],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3753654,0.0228036,0.3255789,0.00545522,0.003792794,0.0003048495,0.002038441,0.001043462,0.2636173],"genre_scores_gemma":[0.9357519,0.008004852,0.03269966,0.0009914354,0.0008899213,0.0001687279,0.0009585546,0.0001286237,0.0204063],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002247947,"threshold_uncertainty_score":0.007520199,"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","authors":[{"name":"Óscar Saz","is_ca":false},{"name":"Shou-Chun Yin","is_ca":true},{"name":"Eduardo Lleida","is_ca":false},{"name":"Richard C. Rose","is_ca":true},{"name":"Carlos Vaquero","is_ca":false},{"name":"William Ricardo Rodríguez Dueñas","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009782535,0.0006074231,0.0004801459,0.001370468,0.0003953548,0.001858198,0.0008355408,0.0009736389,0.02341073],"category_scores_gemma":[0.002108076,0.0002506213,0.0003735719,0.000736122,0.0006289083,0.001783401,0.001614422,0.0007441778,0.006454371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002983957,"about_ca_system_score_gemma":0.0007312082,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005809189,"about_ca_topic_score_gemma":0.0008541734,"domain_scores_codex":[0.9992954,0.0001648197,0.00005784988,0.00006253238,0.0003794279,0.00003991217],"domain_scores_gemma":[0.999128,0.0004562007,0.00004260218,0.0001378193,0.0001880647,0.00004720401],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001225677,0.00007527263,0.0003422521,0.0004883637,0.00002714416,0.0002826976,0.0003421056,0.001239216,0.03165745,0.04152733,0.01785597,0.9060395],"study_design_scores_gemma":[0.0001259959,0.0005369078,0.003076134,0.001149836,0.0001704774,0.004823703,0.0006327901,0.02068212,0.0695498,0.09418691,0.8049407,0.0001245407],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005773862,0.008962193,0.9373915,0.0008067717,0.0005706322,0.000231004,0.0003532348,0.005323655,0.04058713],"genre_scores_gemma":[0.08684479,0.01129199,0.8464442,0.0006710762,0.0003145253,0.0008001901,0.0007326561,0.0006639512,0.05223655],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02341073,"threshold_uncertainty_score":0.07831675,"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","authors":[{"name":"Murray J. Munro","is_ca":true},{"name":"Tracey M. Derwing","is_ca":true},{"name":"Clifford S. Burgess","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003991848,0.0003364339,0.0004104782,0.0005165944,0.0004495706,0.000633464,0.0002917731,0.0005831375,0.00490562],"category_scores_gemma":[0.002259083,0.0002364276,0.0001397417,0.0001910582,0.000285549,0.0006860541,0.000664409,0.0004128634,0.001065535],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000172011,"about_ca_system_score_gemma":0.0003811624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007825744,"about_ca_topic_score_gemma":0.001629714,"domain_scores_codex":[0.9997752,0.000029562,0.00001255707,0.00007197566,0.00006951634,0.00004119402],"domain_scores_gemma":[0.9990151,0.0005170792,0.00006315507,0.0000766697,0.0001980147,0.0001299878],"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":[0.0007211967,0.0000350913,0.003307899,0.00006787494,0.000007441317,0.0001465493,0.0003417544,0.00001647189,0.9832275,0.0001500353,0.00008702342,0.01189123],"study_design_scores_gemma":[0.0001043527,0.00125191,0.4201143,0.00004719243,0.0001713762,0.003611254,0.0009968751,0.004974053,0.5653908,0.0009028435,0.002387742,0.00004732741],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.994184,0.0001024982,0.002821371,0.00004389505,0.00004877672,0.00002868155,0.00011504,0.00006146739,0.002594368],"genre_scores_gemma":[0.9926717,0.0001507118,0.004623262,0.00009426665,0.00005103767,0.00004405735,0.0002521754,0.00006749589,0.002045307],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00490562,"threshold_uncertainty_score":0.01641089,"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","authors":[{"name":"Marc D. Pell","is_ca":true},{"name":"Vera Skorup","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006906741,0.0002518378,0.0002662425,0.0001838449,0.0002711681,0.001458226,0.0002687574,0.0004267811,0.00473857],"category_scores_gemma":[0.007005431,0.0001808076,0.0001526613,0.000120886,0.0004352342,0.001272442,0.0009610219,0.0006890885,0.0004824922],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001624079,"about_ca_system_score_gemma":0.0002348918,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000434395,"about_ca_topic_score_gemma":0.0006640845,"domain_scores_codex":[0.9997308,0.00005575111,0.00001892297,0.00007551711,0.00006848046,0.00005046977],"domain_scores_gemma":[0.9983467,0.0009715211,0.0002190337,0.0001392153,0.0001931289,0.0001304588],"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":[0.008686759,0.0003258255,0.0272239,0.0003507236,0.00008800334,0.000521871,0.007079844,0.0003303712,0.9177882,0.00241287,0.0003179436,0.03487378],"study_design_scores_gemma":[0.0003998818,0.002016275,0.8407293,0.0001387476,0.0003630909,0.002859608,0.008678707,0.007443289,0.1293051,0.005214089,0.002730371,0.0001215134],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9968199,0.00005068734,0.0004629296,0.00002834979,0.00002409434,0.000004614604,0.00002818322,0.000005941708,0.002575344],"genre_scores_gemma":[0.9968898,0.00008748533,0.0005550402,0.00005026242,0.00001872782,0.00001516966,0.00007101995,0.00002603326,0.002286456],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00473857,"threshold_uncertainty_score":0.01585209,"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","authors":[{"name":"Keith R. Kluender","is_ca":false},{"name":"Jeffry A. Coady","is_ca":false},{"name":"Michael Kiefte","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000707922,0.0002487397,0.0003320299,0.0006838786,0.0001604927,0.000449315,0.0002245771,0.0005481147,0.003167251],"category_scores_gemma":[0.008292489,0.0002625127,0.0002837472,0.0001700434,0.0004068294,0.0003574031,0.0005911895,0.000784974,0.0003109904],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002647737,"about_ca_system_score_gemma":0.0001373177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00113814,"about_ca_topic_score_gemma":0.0004896447,"domain_scores_codex":[0.9995089,0.0001094974,0.00003660179,0.0001333314,0.0001451921,0.00006645488],"domain_scores_gemma":[0.9963722,0.002280736,0.0002997342,0.000312074,0.0003701196,0.0003651354],"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":[0.01030431,0.0004392109,0.06424771,0.0002633532,0.0002210648,0.001428443,0.001338961,0.00117184,0.8803101,0.0004857631,0.0006726001,0.03911658],"study_design_scores_gemma":[0.00008054581,0.003858411,0.8995895,0.00004110309,0.0001496003,0.004104759,0.0006430988,0.002010424,0.08733131,0.000903856,0.00124172,0.00004569334],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.994855,0.0002400088,0.0009251399,0.00007320434,0.0000502729,0.00002850796,0.0001038768,0.00003148224,0.003692353],"genre_scores_gemma":[0.9987023,0.0001033131,0.0002072991,0.0001014556,0.00002020093,0.00001432444,0.00008840857,0.00001506076,0.0007475847],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003167251,"threshold_uncertainty_score":0.0105955,"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","authors":[{"name":"Jahangir Alam","is_ca":true},{"name":"Tomi Kinnunen","is_ca":false},{"name":"Patrick Kenny","is_ca":true},{"name":"Pierre Ouellet","is_ca":true},{"name":"Douglas O’Shaughnessy","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006205595,0.0008454508,0.000673186,0.0009052348,0.0004476138,0.0006890895,0.0006981821,0.0009408582,0.008409541],"category_scores_gemma":[0.001920444,0.0002970834,0.000549058,0.0007724473,0.0001981853,0.001206433,0.0007493768,0.0007075911,0.006367714],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001609732,"about_ca_system_score_gemma":0.000481638,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001633215,"about_ca_topic_score_gemma":0.002725732,"domain_scores_codex":[0.9993823,0.0001371816,0.00005699903,0.0001172361,0.0002271194,0.00007923795],"domain_scores_gemma":[0.9991406,0.0002609389,0.00006564814,0.0001652935,0.000326277,0.00004124333],"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":[0.0008391078,0.0001218214,0.0006279353,0.0001657283,0.00004409647,0.00008726698,0.00004650228,0.00316787,0.2133023,0.0009559232,0.003361669,0.7772799],"study_design_scores_gemma":[0.0001427442,0.000774202,0.01357831,0.0001034659,0.0002794371,0.0008954371,0.0001768461,0.3657354,0.5995418,0.001725338,0.0169152,0.0001317978],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0710517,0.001897294,0.9137853,0.0002267672,0.0002148627,0.0001599411,0.001314508,0.00588133,0.005468351],"genre_scores_gemma":[0.4398955,0.001366983,0.5414621,0.0001367663,0.0001710847,0.0002752524,0.004607956,0.0005263121,0.01155788],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008409541,"threshold_uncertainty_score":0.02813268,"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)","authors":[{"name":"Mohammed Bahoura","is_ca":true},{"name":"Jean Rouat","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002857396,0.0004302365,0.0003301301,0.0002325398,0.0001185048,0.0002788066,0.0002083647,0.0003420074,0.002613163],"category_scores_gemma":[0.0006340363,0.0001528067,0.0003958919,0.000298831,0.0001764474,0.0004591485,0.0003123236,0.0004199612,0.001094318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000780336,"about_ca_system_score_gemma":0.0001313003,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003010437,"about_ca_topic_score_gemma":0.0005177489,"domain_scores_codex":[0.9999014,0.000019505,0.000006091031,0.00001949626,0.00004270075,0.00001077186],"domain_scores_gemma":[0.9997631,0.00009339741,0.00001561068,0.00004049026,0.00007399315,0.00001342359],"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":[0.000534684,0.00008327587,0.0003833016,0.00008805278,0.00003777447,0.0001425237,0.00004629973,0.007164115,0.6587188,0.003289475,0.001126617,0.3283852],"study_design_scores_gemma":[0.00006617908,0.0002987607,0.005225408,0.00002400359,0.0001777107,0.0008024737,0.00003493051,0.4875503,0.4887052,0.002027529,0.01504866,0.00003896293],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04569564,0.0004991501,0.9493916,0.0001254169,0.0001856903,0.00003839665,0.00004271805,0.0005907521,0.00343062],"genre_scores_gemma":[0.3577166,0.001373688,0.6277644,0.0001558323,0.0002111496,0.00006018421,0.0002383682,0.0002242423,0.01225555],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002613163,"threshold_uncertainty_score":0.008741856,"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","authors":[{"name":"Hesam Farsaie Alaie","is_ca":true},{"name":"Lina Abou-Abbas","is_ca":true},{"name":"Chakib Tadj","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007186332,0.0005721003,0.0005766763,0.001424396,0.0001781992,0.0003361726,0.0003702775,0.0003916692,0.000715602],"category_scores_gemma":[0.001430354,0.0001502272,0.0005314899,0.0005095359,0.0001869775,0.0004833303,0.0005738556,0.0003348744,0.0007010999],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003440299,"about_ca_system_score_gemma":0.0004130778,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002837865,"about_ca_topic_score_gemma":0.002204469,"domain_scores_codex":[0.9996418,0.00009267436,0.00001829854,0.00009383547,0.00009734166,0.00005601954],"domain_scores_gemma":[0.9996732,0.00009226183,0.00003685793,0.00002787067,0.0001409819,0.00002881456],"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":[0.0004019147,0.0001087106,0.01653199,0.000123641,0.0001051439,0.0002331805,0.0002606733,0.03206286,0.1121839,0.001801203,0.002596381,0.8335904],"study_design_scores_gemma":[0.00001409034,0.0002033755,0.03581405,0.00002786533,0.00008404439,0.0004562956,0.0001939979,0.915754,0.04275026,0.001941679,0.002706981,0.00005337792],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1691004,0.0009312152,0.8247684,0.0001349645,0.00008302245,0.00008086199,0.0002807254,0.003240746,0.001379664],"genre_scores_gemma":[0.7733489,0.0006723467,0.222888,0.00007041528,0.00005694328,0.0000646268,0.0005417774,0.0001324943,0.002224432],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002837865,"threshold_uncertainty_score":0.005642653,"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","authors":[{"name":"Jean‐Pierre Gagné","is_ca":true},{"name":"Anne-Josée Rochette","is_ca":true},{"name":"Monique Charest","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001062068,0.0004776366,0.0002655889,0.001025518,0.0005093366,0.001637825,0.0004673581,0.0009424858,0.01863633],"category_scores_gemma":[0.007669659,0.0003571255,0.0002211832,0.0003244788,0.001406697,0.002236105,0.001254053,0.0007673955,0.001464557],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004098862,"about_ca_system_score_gemma":0.0007159048,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001706123,"about_ca_topic_score_gemma":0.004423445,"domain_scores_codex":[0.9993283,0.000147831,0.0000463312,0.0001019238,0.0003008161,0.00007485207],"domain_scores_gemma":[0.9962392,0.002153181,0.0003051996,0.0002465216,0.0006610712,0.0003948892],"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":[0.03043938,0.000878003,0.03053712,0.003367142,0.0003313421,0.002455641,0.005776777,0.001156057,0.5354066,0.0284666,0.006215381,0.3549699],"study_design_scores_gemma":[0.0007929071,0.005096625,0.8391783,0.0004772348,0.0005703674,0.006911257,0.010329,0.002192562,0.07199462,0.03845907,0.02384046,0.0001575674],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8927827,0.01768961,0.007291924,0.0009525521,0.0007456664,0.00009993219,0.0006081894,0.00008584496,0.07974351],"genre_scores_gemma":[0.9755434,0.00407454,0.001644041,0.0003500819,0.0003524588,0.00005039138,0.0003240675,0.00003650634,0.01762441],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01863633,"threshold_uncertainty_score":0.06234479,"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","authors":[{"name":"João Felipe Santos","is_ca":true},{"name":"Stefano Cosentino","is_ca":false},{"name":"Oldooz Hazrati","is_ca":false},{"name":"Philipos C. Loizou","is_ca":false},{"name":"Tiago H. Falk","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006831644,0.0008208816,0.0004415403,0.0005467969,0.0003677008,0.0007206707,0.000336755,0.0006342814,0.003383632],"category_scores_gemma":[0.004143228,0.0001911918,0.0003127339,0.0002863671,0.0003218843,0.000637846,0.0007544211,0.0002417693,0.0008031945],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001620641,"about_ca_system_score_gemma":0.0003258714,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009853556,"about_ca_topic_score_gemma":0.001426139,"domain_scores_codex":[0.9992706,0.0001380371,0.000109482,0.0001362127,0.0002720942,0.00007356629],"domain_scores_gemma":[0.9977747,0.001180973,0.0001936006,0.00008529567,0.0005954544,0.0001700387],"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":[0.01994144,0.0009177886,0.2135455,0.001328293,0.0002489216,0.0008149543,0.003474251,0.001029569,0.5859503,0.0002199548,0.0007153729,0.1718136],"study_design_scores_gemma":[0.0001796297,0.01002507,0.7725749,0.00007796618,0.0004374893,0.00468069,0.002079735,0.004422345,0.2034175,0.0002052067,0.001773615,0.0001258623],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9928789,0.0002996593,0.004427548,0.00001733195,0.00001214436,0.0000617842,0.0004030746,0.00005679486,0.001842747],"genre_scores_gemma":[0.9937185,0.0002584623,0.003896139,0.00004166197,0.00001600503,0.00009175731,0.0003945026,0.00003518224,0.001547857],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003383632,"threshold_uncertainty_score":0.0113194,"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","authors":[{"name":"Payam Ezzatian","is_ca":true},{"name":"Meital Avivi","is_ca":true},{"name":"Bruce A. Schneider","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004233695,0.0002486444,0.0002767177,0.0001459328,0.0001558796,0.000580264,0.0002029539,0.0008086494,0.002559891],"category_scores_gemma":[0.002584934,0.0001939128,0.0001251343,0.00006372295,0.0005595493,0.0011728,0.0002749386,0.0002958386,0.0006834229],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007018055,"about_ca_system_score_gemma":0.0001952321,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006125038,"about_ca_topic_score_gemma":0.001402102,"domain_scores_codex":[0.9998677,0.00001768736,0.000007299294,0.00003160411,0.00003989951,0.00003583914],"domain_scores_gemma":[0.9993123,0.00028501,0.0001457557,0.00007273091,0.00008521369,0.00009896611],"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":[0.007928092,0.0005952256,0.08820289,0.0006398241,0.0003139626,0.001554853,0.002691032,0.0003833032,0.6841307,0.001682128,0.002840857,0.2090371],"study_design_scores_gemma":[0.000239099,0.001295195,0.9080476,0.00008451003,0.0003596816,0.004149124,0.006302515,0.001525367,0.06655755,0.007119177,0.004275812,0.0000443897],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9934373,0.0008604249,0.0009895929,0.0005834933,0.00008141609,0.000008203896,0.00008816898,0.00002430674,0.003927071],"genre_scores_gemma":[0.9976089,0.0006544884,0.0004157682,0.000298588,0.00005335356,0.000006625191,0.00005444733,0.00001066813,0.000897039],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002559891,"threshold_uncertainty_score":0.008563697,"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","authors":[{"name":"Christopher Dromey","is_ca":false},{"name":"José Silveira","is_ca":true},{"name":"Paul Sandor","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003260632,0.0002193176,0.0002382655,0.000142295,0.0002124806,0.0007785062,0.0001052399,0.0003046415,0.00247089],"category_scores_gemma":[0.002105925,0.0001134171,0.0001450937,0.00006489189,0.000169263,0.0003009872,0.0003052779,0.000396007,0.0005605173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007892784,"about_ca_system_score_gemma":0.00008128459,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007384042,"about_ca_topic_score_gemma":0.00101989,"domain_scores_codex":[0.9998968,0.00003097446,0.000006166847,0.00002053999,0.00002383078,0.00002162482],"domain_scores_gemma":[0.9993213,0.0003574998,0.00008737607,0.00003450717,0.00009668771,0.0001026643],"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":[0.007205756,0.0002941276,0.110139,0.0001542054,0.0001478144,0.0006269966,0.007000785,0.0001101994,0.8450664,0.0002675936,0.0009386339,0.02804858],"study_design_scores_gemma":[0.00008828416,0.001200612,0.9559788,0.00002070549,0.0001169148,0.001193155,0.003783048,0.001622543,0.03479177,0.0001616349,0.001009808,0.00003260358],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9982449,0.00005496321,0.0001364901,0.00002504452,0.00002473012,0.000005139285,0.00004065946,0.00000661077,0.001461433],"genre_scores_gemma":[0.9978288,0.00008800869,0.0001959724,0.00006438417,0.00002048535,0.00001113771,0.0001393449,0.00001083616,0.001641006],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00247089,"threshold_uncertainty_score":0.008265913,"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","authors":[{"name":"Abhishek Jaywant","is_ca":true},{"name":"Marc D. Pell","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000473081,0.0003662209,0.0003582735,0.0004686199,0.0003772693,0.001584313,0.0002773976,0.0005295097,0.004315729],"category_scores_gemma":[0.00494027,0.0002802799,0.0002815464,0.0003216646,0.0005504673,0.001108979,0.001655622,0.0008923379,0.0005119111],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002650218,"about_ca_system_score_gemma":0.0002609491,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003843205,"about_ca_topic_score_gemma":0.0006961905,"domain_scores_codex":[0.9996871,0.00006207002,0.00001493574,0.00006657292,0.0001229254,0.00004657762],"domain_scores_gemma":[0.9988989,0.000582164,0.0001487393,0.00007603969,0.0001916038,0.0001025579],"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":[0.001411408,0.00005826747,0.006865639,0.0002833461,0.00003905165,0.0002449655,0.001617823,0.0004243901,0.9408996,0.003363633,0.0007082085,0.04408375],"study_design_scores_gemma":[0.0001439967,0.0005058832,0.8778769,0.0001620463,0.0001747094,0.001758717,0.002348409,0.01279269,0.07453702,0.02623612,0.003331213,0.0001322912],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9577693,0.0006677197,0.01370317,0.000399198,0.0002106908,0.00007222033,0.0005837578,0.00009528657,0.02649862],"genre_scores_gemma":[0.9923931,0.0004043915,0.004481473,0.0001245352,0.0001068505,0.00008174949,0.0005931978,0.0001017354,0.001712945],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004315729,"threshold_uncertainty_score":0.01443756,"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","authors":[{"name":"Hongjiang Yu","is_ca":true},{"name":"Wei‐Ping Zhu","is_ca":true},{"name":"Benoı̂t Champagne","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005820986,0.0008119824,0.0005552703,0.0003218379,0.0003752683,0.0004592464,0.0005166351,0.0007447607,0.002603524],"category_scores_gemma":[0.0008536844,0.0003343105,0.000646776,0.0003067536,0.0002413888,0.0006967693,0.0005421979,0.0008500443,0.001242832],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004142571,"about_ca_system_score_gemma":0.0009309585,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007539088,"about_ca_topic_score_gemma":0.01484454,"domain_scores_codex":[0.9997093,0.00004284926,0.00001919864,0.00009234095,0.00009847546,0.00003782036],"domain_scores_gemma":[0.9996625,0.00008528161,0.00001836858,0.00002934596,0.0001893496,0.00001512765],"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":[0.0006872629,0.0001984399,0.001340352,0.0002782933,0.000163654,0.0002185943,0.0001388234,0.1449793,0.189175,0.005491274,0.003913175,0.6534159],"study_design_scores_gemma":[0.00001792286,0.00008101803,0.0008545592,0.00002562679,0.00007293921,0.00007337331,0.0000137961,0.9525506,0.04148286,0.0006759766,0.004128796,0.00002243302],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009189451,0.0003911535,0.9873071,0.00007932325,0.0002361808,0.00003077282,0.00006954499,0.0008738616,0.001822588],"genre_scores_gemma":[0.3498294,0.0008903819,0.6356066,0.0002670962,0.0001701967,0.0001083711,0.0004535806,0.0001678248,0.01250667],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007539088,"threshold_uncertainty_score":0.01499045,"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","authors":[{"name":"Deirdre M. Truesdale","is_ca":true},{"name":"Marc D. Pell","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00418898,0.0005440284,0.0005958765,0.001936273,0.003884573,0.00727521,0.001368045,0.005377468,0.007459753],"category_scores_gemma":[0.02713272,0.0003404425,0.0004053517,0.0007765035,0.03591754,0.008778909,0.004708435,0.01215751,0.001754939],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001578858,"about_ca_system_score_gemma":0.001802718,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001941387,"about_ca_topic_score_gemma":0.001492686,"domain_scores_codex":[0.9950041,0.00211426,0.0001624973,0.0006146787,0.001679599,0.0004248807],"domain_scores_gemma":[0.9900592,0.005741372,0.0007650842,0.001088479,0.001233202,0.001112669],"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":[0.0001484695,0.00002366095,0.001624353,0.00009551454,0.00004214848,0.000830169,0.04250044,0.0001317839,0.0007612466,0.8602991,0.06629413,0.02724894],"study_design_scores_gemma":[0.00006584124,0.00006103907,0.001603547,0.0002347809,0.00002480283,0.002276911,0.02000147,0.0003513618,0.0004410001,0.7235048,0.2513534,0.00008111156],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.04490922,0.01459719,0.02536743,0.3273962,0.02457934,0.00005951526,0.0004238334,0.0004820022,0.5621852],"genre_scores_gemma":[0.8662546,0.002228725,0.005020276,0.05953852,0.01066926,0.0001026298,0.0001296365,0.0003510868,0.05570513],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007459753,"threshold_uncertainty_score":0.02495539,"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","authors":[{"name":"Nobuo Suga","is_ca":false},{"name":"Xiaofeng Ma","is_ca":false},{"name":"Enquan Gao","is_ca":false},{"name":"Masashi Sakai","is_ca":false},{"name":"Syed A. Chowdhury","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002658126,0.0001923421,0.000219322,0.000433434,0.0003706409,0.0006093886,0.0002957881,0.0004335379,0.00242707],"category_scores_gemma":[0.0009931499,0.00007397289,0.0001203061,0.0002879737,0.001382481,0.0007883481,0.0003414215,0.0007165171,0.0002580487],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000276771,"about_ca_system_score_gemma":0.0004298183,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001156984,"about_ca_topic_score_gemma":0.001382805,"domain_scores_codex":[0.9999537,0.000007783498,0.000005119666,0.00001311266,0.00001238275,0.000007830419],"domain_scores_gemma":[0.9995174,0.0001759143,0.00004528006,0.00008417782,0.0001119925,0.0000652171],"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":[0.00272776,0.0003935483,0.04300232,0.000716814,0.0001579958,0.001674407,0.0009540736,0.001382321,0.6415806,0.05808762,0.001271963,0.2480507],"study_design_scores_gemma":[0.000229268,0.003322584,0.5497364,0.0002654533,0.0004696683,0.01137699,0.001690697,0.008408287,0.2562034,0.128341,0.03985497,0.0001013328],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9479896,0.02197875,0.01476653,0.002907784,0.0001640261,0.00002596339,0.0002072857,0.00003946829,0.01192062],"genre_scores_gemma":[0.977995,0.01252052,0.004223113,0.0003503597,0.0001787294,0.00002801932,0.0001312981,0.00001988767,0.004553102],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00242707,"threshold_uncertainty_score":0.008119345,"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","authors":[{"name":"Jingdong Chen","is_ca":false},{"name":"Jacob Benesty","is_ca":true},{"name":"Yiteng Huang","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001173134,0.001402183,0.0009815847,0.0008088713,0.000490385,0.0009990314,0.000792262,0.001220158,0.003335325],"category_scores_gemma":[0.003970146,0.0006423264,0.000854822,0.001008127,0.001460407,0.001659464,0.001112352,0.0019572,0.001448621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004231758,"about_ca_system_score_gemma":0.0006022941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001887615,"about_ca_topic_score_gemma":0.002010005,"domain_scores_codex":[0.9990395,0.0003204994,0.00006597776,0.0001467548,0.0003528389,0.00007442498],"domain_scores_gemma":[0.9990452,0.0006644959,0.00004579469,0.00008946973,0.0001375787,0.00001746972],"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":[0.000397033,0.0001076552,0.0002613841,0.0005031996,0.0001375088,0.000123425,0.0002302996,0.2013407,0.02585371,0.1905723,0.009630386,0.5708423],"study_design_scores_gemma":[0.00003835849,0.0001094249,0.0002825093,0.00008212713,0.00006641388,0.0001660641,0.00004607432,0.8243694,0.01009291,0.1501891,0.01450646,0.00005104596],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001718182,0.002275083,0.993397,0.0001871479,0.0001445371,0.000009447052,0.00002019823,0.00008207761,0.002166193],"genre_scores_gemma":[0.139634,0.01086283,0.8302242,0.0004984492,0.001362369,0.0001547667,0.0002502392,0.0002286111,0.01678472],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003335325,"threshold_uncertainty_score":0.01115775,"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","authors":[{"name":"Mohammad Hadi Radfar","is_ca":true},{"name":"Richard M. Dansereau","is_ca":true},{"name":"Abolghasem Sayadiyan","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001093755,0.001154586,0.001482551,0.001188867,0.0003797458,0.001276492,0.0008817964,0.001083399,0.002142713],"category_scores_gemma":[0.002540111,0.000663329,0.001302857,0.0008083162,0.0002940945,0.001671177,0.001398926,0.001022411,0.001831607],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003380866,"about_ca_system_score_gemma":0.0006287702,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008931609,"about_ca_topic_score_gemma":0.002133338,"domain_scores_codex":[0.9993683,0.0001326736,0.00003952556,0.0001165761,0.000283507,0.00005940573],"domain_scores_gemma":[0.9992105,0.0002763553,0.0000634039,0.0001182734,0.0002834015,0.00004817556],"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":[0.001188177,0.0002931536,0.001335866,0.0003242968,0.0002915315,0.0001751076,0.0001496558,0.1200245,0.2392295,0.005657399,0.00199216,0.6293387],"study_design_scores_gemma":[0.0000333051,0.00007877353,0.0009307807,0.00001742932,0.00007129482,0.0001732131,0.00001513697,0.9476447,0.04530817,0.003731842,0.00195579,0.00003957032],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01016941,0.0002159645,0.9877372,0.00005225898,0.00007036494,0.00002271567,0.00005426203,0.0009153449,0.000762375],"genre_scores_gemma":[0.3404439,0.0005933228,0.6537781,0.0001563836,0.000154208,0.00009521589,0.0006867457,0.0005888223,0.003503337],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002142713,"threshold_uncertainty_score":0.007168114,"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","authors":[{"name":"Masaki Naito","is_ca":false},{"name":"Li Deng","is_ca":true},{"name":"Yoshinori Sagisaka","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008310074,0.001179212,0.001418767,0.001262069,0.001265128,0.0008288899,0.00126929,0.001284367,0.005867586],"category_scores_gemma":[0.001698829,0.0006961348,0.001499993,0.0009283707,0.0003702238,0.000802178,0.0007985948,0.001186165,0.006847717],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006452082,"about_ca_system_score_gemma":0.00101468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00961568,"about_ca_topic_score_gemma":0.01639084,"domain_scores_codex":[0.9992099,0.0001845179,0.00005026949,0.0002765326,0.0001853458,0.00009343542],"domain_scores_gemma":[0.9992146,0.0003154245,0.0000475292,0.0001436534,0.0002438481,0.00003491513],"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":[0.0005016603,0.0001209787,0.0006718698,0.0001123543,0.0001892479,0.00007797011,0.0001530492,0.03235062,0.1200829,0.001798646,0.004971536,0.8389693],"study_design_scores_gemma":[0.0000416127,0.000121397,0.004535404,0.00002092458,0.0001497077,0.0002767746,0.0001303646,0.8741155,0.109375,0.004560499,0.006600133,0.00007262154],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01123459,0.0003637761,0.9824827,0.00005147395,0.00004803926,0.00006094122,0.0002490195,0.004816519,0.0006930136],"genre_scores_gemma":[0.1127945,0.0003382906,0.8767862,0.00006745394,0.00007768249,0.000250227,0.002069398,0.001019915,0.006596262],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00961568,"threshold_uncertainty_score":0.019629,"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","authors":[{"name":"Elias Nemer","is_ca":false},{"name":"Rafik Goubran","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005361451,0.0006609115,0.0006466234,0.0006686425,0.0002879257,0.000714705,0.0003457527,0.0007272692,0.002358891],"category_scores_gemma":[0.001766455,0.0002765099,0.0007449473,0.0005075519,0.0004263121,0.001030369,0.0003951024,0.0006988305,0.0008343498],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003793057,"about_ca_system_score_gemma":0.0004756684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007627142,"about_ca_topic_score_gemma":0.002055191,"domain_scores_codex":[0.9997001,0.00007429513,0.00001744699,0.00003913843,0.0001355997,0.00003353733],"domain_scores_gemma":[0.9992288,0.0004206312,0.0000712454,0.00009245674,0.0001611502,0.00002571263],"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":[0.001327113,0.0002116356,0.0009133206,0.0004144151,0.0001514569,0.0002031582,0.0001930488,0.07682367,0.3231341,0.04953032,0.003047785,0.5440501],"study_design_scores_gemma":[0.00005901329,0.000170924,0.00228001,0.00004606864,0.0001179406,0.0003942755,0.00003452926,0.8343133,0.1428057,0.01131793,0.008405898,0.00005442977],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02356914,0.0006799663,0.9726846,0.0001443323,0.00007124922,0.00001940577,0.00003945013,0.0003083591,0.002483505],"genre_scores_gemma":[0.1681732,0.001224511,0.8230682,0.000109039,0.000158941,0.00004735813,0.0001592484,0.000184827,0.006874657],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002358891,"threshold_uncertainty_score":0.007891238,"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","authors":[{"name":"Shari R. Baum","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008988155,0.0002206848,0.0002243103,0.0005961708,0.0001584408,0.000640489,0.0001666811,0.0002980454,0.003779969],"category_scores_gemma":[0.0069349,0.0001978487,0.0001730666,0.0002938258,0.0003593277,0.000567327,0.0003953486,0.0003187168,0.000698294],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001318603,"about_ca_system_score_gemma":0.0001594527,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0010604,"about_ca_topic_score_gemma":0.001416754,"domain_scores_codex":[0.9995474,0.0000939854,0.00005047847,0.0001134982,0.0001375113,0.00005702167],"domain_scores_gemma":[0.994709,0.002623779,0.001029768,0.0006037966,0.0006831088,0.0003505301],"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":[0.005677108,0.0003718339,0.4352057,0.0001422894,0.0002241098,0.001379168,0.00667269,0.0007267925,0.4736224,0.002482382,0.0009568862,0.07253867],"study_design_scores_gemma":[0.00001358983,0.0005757483,0.9878271,0.000008689888,0.00003857717,0.0005998891,0.0004450545,0.0002652863,0.008738969,0.0005072423,0.000963571,0.00001635206],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9960567,0.0003840193,0.0004295942,0.00004239878,0.00003033869,0.000005202142,0.0002027876,0.00001121518,0.002837784],"genre_scores_gemma":[0.9981419,0.0001626122,0.0001782918,0.00001913369,0.00001339457,0.000003949526,0.0001152735,0.00001840522,0.001347039],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003779969,"threshold_uncertainty_score":0.0126453,"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","authors":[{"name":"Vijay Parsa","is_ca":true},{"name":"Donald G. Jamieson","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001779503,0.0004578889,0.0004195777,0.0005811221,0.0002396976,0.0004975852,0.0001822898,0.0003901881,0.0009054375],"category_scores_gemma":[0.02390795,0.0001984391,0.0002574408,0.0002105764,0.0004600256,0.0002808625,0.0004811688,0.0003250427,0.0002345313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002908483,"about_ca_system_score_gemma":0.0002113813,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001269141,"about_ca_topic_score_gemma":0.001901533,"domain_scores_codex":[0.9975129,0.001067257,0.0001809859,0.0002858291,0.000813172,0.0001398516],"domain_scores_gemma":[0.9757317,0.01800508,0.002879958,0.000866381,0.001605922,0.000910911],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.01377072,0.001153767,0.7698121,0.0003436827,0.0004307385,0.002257813,0.003601688,0.001307792,0.1301541,0.00009439671,0.0002335158,0.07683968],"study_design_scores_gemma":[0.00009773519,0.0143709,0.9491232,0.00002604327,0.0003567248,0.003738472,0.001050752,0.002526769,0.0280092,0.0001273414,0.0005240393,0.0000486926],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9994864,0.0001144847,0.0002243709,0.00001007567,0.00000273214,0.000007269195,0.00002238747,0.000005712996,0.0001265695],"genre_scores_gemma":[0.9992648,0.00006972818,0.0004732427,0.00001321857,0.00000598172,0.000005953032,0.000056167,0.000004684144,0.0001062156],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001779503,"threshold_uncertainty_score":0.009410977,"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","authors":[{"name":"Lin Zhong","is_ca":true},{"name":"Rafik Goubran","is_ca":true},{"name":"Richard M. Dansereau","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000878825,0.00129667,0.001474101,0.001411596,0.0006996611,0.001078883,0.0007355367,0.001275253,0.002235427],"category_scores_gemma":[0.003048745,0.0006136505,0.0007605322,0.0006529777,0.0003796937,0.001234315,0.0007398961,0.0008913344,0.002281509],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003803778,"about_ca_system_score_gemma":0.001127321,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003586968,"about_ca_topic_score_gemma":0.008685053,"domain_scores_codex":[0.9993617,0.0001152302,0.00004531836,0.0001662342,0.0002205552,0.0000910891],"domain_scores_gemma":[0.9989339,0.0004691904,0.00006905007,0.0000929446,0.0003856609,0.00004918731],"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":[0.001661524,0.000219141,0.002028145,0.0001781592,0.0001582886,0.0001289617,0.0001217914,0.02294853,0.1945768,0.002310128,0.001151354,0.774517],"study_design_scores_gemma":[0.00008791403,0.0002063199,0.004779548,0.0000332607,0.0002015814,0.0002629619,0.00006037882,0.8184931,0.170608,0.002108193,0.003112038,0.00004671689],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02151656,0.000246951,0.9763757,0.00005400724,0.0000769863,0.00002969298,0.00005988094,0.0007138307,0.0009263884],"genre_scores_gemma":[0.2440206,0.0005519537,0.7487478,0.0001511416,0.0001120882,0.00009529163,0.000440456,0.0002694267,0.005611317],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003586968,"threshold_uncertainty_score":0.007478178,"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","authors":[{"name":"Jacob Benesty","is_ca":true},{"name":"Jingdong Chen","is_ca":false},{"name":"Yiteng Huang","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001968974,0.001351133,0.0007810991,0.0006254445,0.0004149432,0.0009405087,0.0007226945,0.001734102,0.0023518],"category_scores_gemma":[0.00692825,0.0006387551,0.0006998332,0.0009712902,0.001238628,0.002311855,0.001576014,0.001682767,0.0008606751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005684168,"about_ca_system_score_gemma":0.000463649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001585178,"about_ca_topic_score_gemma":0.002345346,"domain_scores_codex":[0.9991379,0.0003397248,0.0000490943,0.0001352844,0.0002811429,0.00005695217],"domain_scores_gemma":[0.9978418,0.001646334,0.00006529529,0.0001639011,0.0002535567,0.00002896204],"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":[0.0005837628,0.00008853119,0.0004236645,0.0002873435,0.0001223602,0.0001670885,0.0003594942,0.2898536,0.03346811,0.3311981,0.003945748,0.3395022],"study_design_scores_gemma":[0.00002545639,0.00007654056,0.0001912413,0.00003168148,0.00003689553,0.0001117658,0.00003717557,0.8368887,0.005169335,0.1522376,0.005149494,0.00004403558],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004750703,0.001032871,0.9922466,0.0001309605,0.00005913312,0.000006411959,0.00001618501,0.00005222368,0.001704876],"genre_scores_gemma":[0.2762733,0.005381166,0.6915883,0.0004235528,0.0005716998,0.0001255082,0.0002141878,0.0002005026,0.02522168],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0023518,"threshold_uncertainty_score":0.01041311,"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","authors":[{"name":"Anna Marczyk","is_ca":false},{"name":"Émilie Belley","is_ca":true},{"name":"Catherine Savard","is_ca":true},{"name":"J. R. Roy","is_ca":true},{"name":"Josée Vaillancourt","is_ca":true},{"name":"Pascale Tremblay","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001051812,0.0003108167,0.0004319347,0.0004604573,0.0003133944,0.001052309,0.0003824016,0.0005343047,0.002181649],"category_scores_gemma":[0.006169957,0.0002031124,0.0002758258,0.0002040793,0.0005649786,0.0008931538,0.0008016301,0.000673219,0.0006703023],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002407971,"about_ca_system_score_gemma":0.0003563618,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003705277,"about_ca_topic_score_gemma":0.003578638,"domain_scores_codex":[0.9997067,0.00007268679,0.00001806941,0.00008944294,0.00007047827,0.00004264474],"domain_scores_gemma":[0.9984419,0.000730603,0.0001219762,0.0002600477,0.0003050134,0.0001404249],"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":[0.001698622,0.0009852536,0.2024679,0.0002104324,0.0002541873,0.0009467851,0.01394409,0.005928037,0.4574025,0.002062666,0.001520443,0.312579],"study_design_scores_gemma":[0.00002424845,0.0006554826,0.9437426,0.00003075678,0.00008161228,0.0007039327,0.004219291,0.02235529,0.02080267,0.005542676,0.001787931,0.00005356839],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9947832,0.0001280448,0.002962055,0.0001182094,0.00001711698,0.00002000369,0.00007714186,0.00003226608,0.001862023],"genre_scores_gemma":[0.9969573,0.0001041323,0.001169366,0.00004157731,0.00001579351,0.00001668302,0.0001307114,0.00002488761,0.001539588],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003705277,"threshold_uncertainty_score":0.007367373,"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","authors":[{"name":"Douglas O’Shaughnessy","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003071441,0.001658642,0.001936902,0.004229004,0.0006211983,0.00268065,0.00241103,0.001875897,0.006330655],"category_scores_gemma":[0.008092635,0.0007803158,0.001261644,0.004275674,0.001036509,0.002530108,0.001262753,0.001764622,0.006820439],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000729746,"about_ca_system_score_gemma":0.001719103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002335262,"about_ca_topic_score_gemma":0.001762646,"domain_scores_codex":[0.9972019,0.0005839787,0.0003104002,0.0006070765,0.001202222,0.00009441325],"domain_scores_gemma":[0.9937783,0.003188047,0.0002443996,0.0004453762,0.002252637,0.00009124727],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007872306,0.00004050029,0.0003110471,0.003021805,0.00009368962,0.00006620371,0.00007706521,0.001108794,0.00580351,0.006036592,0.0149963,0.9683658],"study_design_scores_gemma":[0.00004552128,0.0002299183,0.003932823,0.003469371,0.0004643883,0.001759773,0.0002807665,0.02775485,0.0199136,0.03726897,0.9046577,0.0002224134],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00163581,0.570649,0.4145879,0.001351853,0.002273704,0.0001264609,0.0005625309,0.001185138,0.007627621],"genre_scores_gemma":[0.02248885,0.5620623,0.3910344,0.001826803,0.005941133,0.0003282267,0.001712779,0.0009395864,0.0136659],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.006330655,"threshold_uncertainty_score":0.02117819,"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","authors":[{"name":"Katherine Marcoux","is_ca":false},{"name":"Martin Cooke","is_ca":false},{"name":"Benjamin V. Tucker","is_ca":true},{"name":"Mirjam Ernestus","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007937287,0.0003367595,0.0003770496,0.0003413554,0.000177972,0.0006637568,0.000142711,0.0003686793,0.002808815],"category_scores_gemma":[0.004674443,0.0001424659,0.000185674,0.00008098679,0.0003926819,0.000716115,0.0009862639,0.000353797,0.000425378],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001218595,"about_ca_system_score_gemma":0.0001591568,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006023134,"about_ca_topic_score_gemma":0.001187252,"domain_scores_codex":[0.9996911,0.00006370477,0.00003283152,0.00006075634,0.0001191505,0.00003248233],"domain_scores_gemma":[0.9983454,0.001043501,0.0001100324,0.0001256795,0.0002100558,0.0001652814],"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":[0.004864017,0.0001590821,0.0207561,0.0003174627,0.000103173,0.0004165712,0.002190389,0.0003851225,0.9270811,0.0004214792,0.0001830091,0.04312238],"study_design_scores_gemma":[0.0001407449,0.003477155,0.862004,0.00005785675,0.000242113,0.002052492,0.003264853,0.003348284,0.121807,0.001453818,0.002081493,0.00007011565],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9966003,0.0001754022,0.00102662,0.00002353445,0.000009232999,0.00001101953,0.00004024709,0.00001948538,0.002094143],"genre_scores_gemma":[0.9982673,0.00007647004,0.0008375603,0.00003019773,0.000006912786,0.00001744215,0.0000780882,0.00001398699,0.0006721644],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002808815,"threshold_uncertainty_score":0.009396374,"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","authors":[{"name":"Brady Laska","is_ca":true},{"name":"Miodrag Bolić","is_ca":true},{"name":"Rafik Goubran","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005878082,0.0008074059,0.0006286926,0.0004634979,0.0003581864,0.0008482501,0.0003788641,0.0009452493,0.004734703],"category_scores_gemma":[0.001719074,0.0003513848,0.0005017694,0.000556351,0.0002937162,0.0007772186,0.0006204945,0.0009878569,0.002685205],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002996697,"about_ca_system_score_gemma":0.0009162251,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002372836,"about_ca_topic_score_gemma":0.002449421,"domain_scores_codex":[0.9995498,0.0000566977,0.00002286952,0.00008330263,0.0002512563,0.00003602379],"domain_scores_gemma":[0.9993713,0.0001451148,0.00003467721,0.00009357804,0.0003352239,0.00002004109],"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":[0.0006576634,0.0001696064,0.001095989,0.0002215243,0.00006889631,0.0002335797,0.00008762722,0.03341838,0.1515966,0.008099025,0.007975412,0.7963758],"study_design_scores_gemma":[0.00006326106,0.000284368,0.00516535,0.00004935081,0.0001210234,0.0007466094,0.00005860297,0.7801723,0.1794199,0.002503077,0.03136532,0.00005079031],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01205955,0.0006913686,0.9796926,0.0003133996,0.0005839033,0.00008035031,0.0001096116,0.0008122775,0.005656946],"genre_scores_gemma":[0.239801,0.002214617,0.7119303,0.0005734654,0.0003888495,0.0001628298,0.0006991464,0.0003656621,0.0438641],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004734703,"threshold_uncertainty_score":0.01583916,"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","authors":[{"name":"Huijun Ding","is_ca":false},{"name":"Tan Lee","is_ca":false},{"name":"Ing Yann Soon","is_ca":false},{"name":"Chai Kiat Yeo","is_ca":false},{"name":"Peng Dai","is_ca":true},{"name":"Dan Guo","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002576012,0.0007842582,0.0006021879,0.001810486,0.0002787279,0.0009274437,0.0004691037,0.0007553732,0.00243285],"category_scores_gemma":[0.00809373,0.0001849808,0.0004096793,0.0009666484,0.000302217,0.0007417755,0.000636834,0.000536992,0.0006546339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002968903,"about_ca_system_score_gemma":0.0003907987,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008822638,"about_ca_topic_score_gemma":0.00184121,"domain_scores_codex":[0.9971907,0.0006292408,0.0002838949,0.0002429053,0.001572152,0.00008120859],"domain_scores_gemma":[0.9941487,0.001962464,0.0008889086,0.0002977763,0.002454234,0.0002478785],"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":[0.007409317,0.001161264,0.1124617,0.003406767,0.0008683651,0.0003824554,0.000966701,0.005451837,0.4696187,0.001655125,0.002959228,0.3936586],"study_design_scores_gemma":[0.0005613089,0.01150424,0.6695083,0.000677986,0.001607672,0.003718412,0.001389442,0.03342126,0.2633668,0.002018287,0.01189228,0.0003340971],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.671097,0.01178352,0.2953502,0.0001639333,0.0002897415,0.001546737,0.006368599,0.0006103694,0.01278987],"genre_scores_gemma":[0.869709,0.004528298,0.1159876,0.0002186698,0.0002502203,0.001082668,0.003736018,0.0002073782,0.004280193],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002576012,"threshold_uncertainty_score":0.01362342,"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","authors":[{"name":"Douglas O’Shaughnessy","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001089282,0.0007422667,0.0006479525,0.004813586,0.0004428956,0.002274727,0.0008190274,0.001408066,0.004863557],"category_scores_gemma":[0.001964314,0.0004776487,0.0005017173,0.004244186,0.0007342663,0.003585266,0.0008579636,0.00138423,0.0033121],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001004635,"about_ca_system_score_gemma":0.001056543,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001593455,"about_ca_topic_score_gemma":0.002230302,"domain_scores_codex":[0.9995172,0.0000754498,0.00007956451,0.0001182418,0.0001772845,0.00003218163],"domain_scores_gemma":[0.9982154,0.001066417,0.0001411528,0.00004807116,0.0004387358,0.00009017865],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007042496,0.00007722993,0.001600827,0.006040354,0.00004597549,0.0001435174,0.0002478044,0.0009618174,0.002362891,0.008581885,0.01975116,0.9601161],"study_design_scores_gemma":[0.000008153355,0.0002312158,0.005937958,0.005189606,0.0001026195,0.001765583,0.0006265095,0.002495973,0.001568055,0.01013358,0.971836,0.0001046756],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.001505511,0.9805234,0.006670725,0.002015452,0.0009398519,0.00002425769,0.0001139518,0.000149574,0.00805722],"genre_scores_gemma":[0.008353126,0.9738401,0.01033016,0.000999273,0.001796094,0.00004642814,0.0003388785,0.00004714511,0.004248784],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.004863557,"threshold_uncertainty_score":0.01627022,"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","authors":[{"name":"Nitin Mohan Sharma","is_ca":false},{"name":"Prasant Kumar Mahapatra","is_ca":false},{"name":"Vaibhav Gandhi","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001489309,0.0007149915,0.0008588441,0.001995246,0.0003074264,0.0008275959,0.0003638019,0.0004943105,0.001906301],"category_scores_gemma":[0.003073712,0.0001306201,0.0009544475,0.001438468,0.0001758471,0.0007865502,0.0003062945,0.0004257748,0.0005304769],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001946767,"about_ca_system_score_gemma":0.0003886344,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002359119,"about_ca_topic_score_gemma":0.002208106,"domain_scores_codex":[0.9994352,0.0001085872,0.00008611561,0.0001193683,0.0001406269,0.0001100326],"domain_scores_gemma":[0.9972522,0.001851795,0.0001138083,0.00009139044,0.0006427703,0.00004808077],"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":[0.00199064,0.000264132,0.009749277,0.0005027195,0.0002888373,0.000134279,0.0001848569,0.004445999,0.1057603,0.0003229667,0.001219307,0.8751366],"study_design_scores_gemma":[0.0002950931,0.004638969,0.3857629,0.0002684361,0.002473789,0.001942679,0.001344129,0.3491689,0.2435557,0.001537176,0.008770163,0.0002420588],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7086526,0.006993659,0.2772272,0.0002581166,0.0002600889,0.0002105208,0.001514998,0.00174643,0.003136436],"genre_scores_gemma":[0.87664,0.002678705,0.1151507,0.00005745105,0.0001166057,0.0001785775,0.002881063,0.0001752628,0.002121541],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002359119,"threshold_uncertainty_score":0.007876337,"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","authors":[{"name":"Peter Birkholz","is_ca":false},{"name":"Daniel Pape","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006063741,0.0005503894,0.0004531531,0.0002826947,0.0004788362,0.001899384,0.000879047,0.001863061,0.003940089],"category_scores_gemma":[0.002684952,0.0004827867,0.0006332838,0.00017446,0.0006604695,0.001799692,0.0004783173,0.001075213,0.0005477517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006292456,"about_ca_system_score_gemma":0.0007152337,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0115771,"about_ca_topic_score_gemma":0.006198204,"domain_scores_codex":[0.9998574,0.00003959295,0.000006182727,0.00005417916,0.00001833988,0.00002424843],"domain_scores_gemma":[0.9992681,0.0004466955,0.00007654057,0.00004714134,0.00009201263,0.00006945067],"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":[0.0001364951,0.00007114038,0.001725911,0.00002694358,0.0000317479,0.00008332119,0.0001062676,0.9822264,0.005203246,0.006377138,0.0002146333,0.003796885],"study_design_scores_gemma":[0.000008948703,0.0000142302,0.0001818273,0.000002520018,0.00001121679,0.000006721318,0.00001286121,0.9986264,0.000264984,0.0007606611,0.0001041876,0.000005498875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6265081,0.0002586654,0.3560531,0.001395657,0.0002622879,0.00006759781,0.0001664816,0.0004617794,0.01482626],"genre_scores_gemma":[0.9877483,0.00006298852,0.009084431,0.00006043502,0.00002110155,0.00002147155,0.00003915091,0.0000661052,0.002896197],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0115771,"threshold_uncertainty_score":0.02301943,"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)","authors":[{"name":"Matthew S. Craig","is_ca":true},{"name":"Pascal van Lieshout","is_ca":true},{"name":"Willy Wong","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005805165,0.0003141859,0.0003675962,0.0003274828,0.000280761,0.0005725941,0.0006440016,0.0008295873,0.004604512],"category_scores_gemma":[0.001728331,0.0001991123,0.0002130616,0.0002899076,0.0002046354,0.0004448368,0.0002561962,0.000331791,0.001702071],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000159209,"about_ca_system_score_gemma":0.0004581354,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008680686,"about_ca_topic_score_gemma":0.001068447,"domain_scores_codex":[0.9996705,0.00009285245,0.00001537958,0.00008256051,0.0001152013,0.0000234495],"domain_scores_gemma":[0.9990968,0.0004155303,0.00002985539,0.00006221198,0.0003326868,0.00006303591],"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":[0.0009966025,0.00008446146,0.002834994,0.0001804821,0.00002927633,0.0001122238,0.00007498022,0.000275889,0.9025387,0.0002580068,0.0008847491,0.09172959],"study_design_scores_gemma":[0.0002907256,0.002584033,0.03981557,0.000125976,0.0002946756,0.004328914,0.0002304927,0.03544055,0.9016452,0.0004209019,0.01472668,0.00009619827],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4000064,0.001743549,0.5836981,0.0004770689,0.0005570477,0.000685595,0.001128292,0.002713239,0.008990713],"genre_scores_gemma":[0.7361107,0.001391826,0.2528595,0.0005315389,0.0003094717,0.0006724993,0.0006787871,0.0003202093,0.007125496],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004604512,"threshold_uncertainty_score":0.01540363,"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","authors":[{"name":"Sebastian Möller","is_ca":false},{"name":"Hervé Bourlard","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006912885,0.0008150606,0.0007856853,0.0006007121,0.0004362822,0.0006797175,0.0008302614,0.001336176,0.002928092],"category_scores_gemma":[0.005278864,0.000484685,0.0005825917,0.0005627204,0.0004747891,0.0009241751,0.0004121621,0.0005508912,0.0005224693],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009495953,"about_ca_system_score_gemma":0.0005080795,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008289681,"about_ca_topic_score_gemma":0.003111568,"domain_scores_codex":[0.9995265,0.0001924026,0.00001729257,0.00004602434,0.0001293322,0.00008848187],"domain_scores_gemma":[0.9961913,0.002905967,0.0002247732,0.0001248561,0.0005110434,0.00004214089],"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":[0.0001156523,0.00002492839,0.000408416,0.00003315009,0.00001178282,0.00006059324,0.00002993601,0.9934502,0.002543942,0.00104286,0.0001322549,0.002146335],"study_design_scores_gemma":[0.00000839614,0.00006342556,0.0002077539,0.000004127815,0.00001431308,0.00002199142,0.00001005165,0.9982564,0.001139065,0.0001767889,0.00009223023,0.00000551762],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7951549,0.0006133482,0.1827206,0.0004401731,0.0000592107,0.0001445275,0.0004626988,0.00113114,0.01927326],"genre_scores_gemma":[0.9948265,0.0001139352,0.003713296,0.0000207283,0.000009935819,0.00002993209,0.00008221852,0.00003983316,0.00116349],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008289681,"threshold_uncertainty_score":0.01648289,"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","authors":[{"name":"Chao Pan","is_ca":false},{"name":"Jingdong Chen","is_ca":false},{"name":"Jacob Benesty","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002330688,0.001763331,0.00110475,0.002320315,0.0003417004,0.00191572,0.0008851582,0.00115294,0.002610977],"category_scores_gemma":[0.008922973,0.0004230513,0.0006455456,0.002094481,0.0014608,0.003657954,0.00209555,0.001240957,0.002133982],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004232305,"about_ca_system_score_gemma":0.0003402465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009365411,"about_ca_topic_score_gemma":0.001266542,"domain_scores_codex":[0.9967387,0.0009905483,0.0002438457,0.0005886626,0.001304301,0.0001339947],"domain_scores_gemma":[0.9934012,0.003348233,0.0005215131,0.001279929,0.001305681,0.0001433378],"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":[0.001274138,0.0002373841,0.01291816,0.0007531937,0.0003780476,0.001125341,0.0004580186,0.05199174,0.1525303,0.04621834,0.003630034,0.7284853],"study_design_scores_gemma":[0.00005525206,0.002659217,0.0505368,0.0004872879,0.0007654181,0.01069046,0.0007972988,0.7085378,0.1468273,0.05226531,0.02604952,0.0003283924],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05091032,0.004960908,0.9290777,0.0002653671,0.0002508488,0.00009761677,0.0002909827,0.0007197827,0.01342654],"genre_scores_gemma":[0.7191605,0.007246336,0.2575138,0.0004091211,0.001324712,0.0001265281,0.001105974,0.0005664203,0.01254658],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002610977,"threshold_uncertainty_score":0.012326,"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","authors":[{"name":"Liang Xie","is_ca":true},{"name":"Yakun Zhang","is_ca":true},{"name":"Hao Yuan","is_ca":false},{"name":"Meishan Zhang","is_ca":true},{"name":"Xingyu Zhang","is_ca":true},{"name":"Changyan Zheng","is_ca":false},{"name":"Yan Ye","is_ca":true},{"name":"Erwei Yin","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001894611,0.0004660711,0.0002433363,0.000338294,0.0001643635,0.0002970689,0.0002080276,0.0002987529,0.003256275],"category_scores_gemma":[0.0004213925,0.0001189099,0.000286908,0.0003584559,0.0001424765,0.0003581879,0.0002509357,0.0002317118,0.0009069951],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001212732,"about_ca_system_score_gemma":0.0003064265,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002666323,"about_ca_topic_score_gemma":0.004855982,"domain_scores_codex":[0.9999093,0.00001601508,0.000006532357,0.00003115997,0.0000224314,0.00001460945],"domain_scores_gemma":[0.9999127,0.00003202402,0.000005838045,0.000009563938,0.00003124527,0.000008596761],"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":[0.0004018474,0.00007489174,0.003229121,0.0001430087,0.0000530312,0.000249642,0.00007409042,0.003583329,0.3292934,0.000778118,0.001629359,0.6604903],"study_design_scores_gemma":[0.00009628507,0.0007028366,0.1030967,0.00005969571,0.0003265839,0.001344345,0.0002920872,0.5053349,0.3792677,0.002178551,0.007234354,0.00006596575],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.398503,0.001983638,0.5807033,0.0003182469,0.0004428568,0.0002298441,0.001300307,0.002139042,0.01437975],"genre_scores_gemma":[0.8877364,0.0006595736,0.09926107,0.00009521968,0.0001114871,0.0001046139,0.001026529,0.00009555972,0.01090953],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003256275,"threshold_uncertainty_score":0.01089329,"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","authors":[{"name":"Shumit Saha","is_ca":true},{"name":"Keerthana Viswanathan","is_ca":true},{"name":"Anamika Saha","is_ca":true},{"name":"Azadeh Yadollahi","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002081406,0.0005989893,0.0004384809,0.0004492155,0.0004394877,0.0005043487,0.0003709223,0.0007746329,0.0009447685],"category_scores_gemma":[0.003248699,0.0003999801,0.000320469,0.0001914985,0.000786222,0.0005896954,0.0003378975,0.0004444839,0.0002777027],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001012096,"about_ca_system_score_gemma":0.0003774588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001986426,"about_ca_topic_score_gemma":0.002474636,"domain_scores_codex":[0.9993662,0.0003283445,0.00002938772,0.0001302954,0.00007942559,0.00006631499],"domain_scores_gemma":[0.9977884,0.001421866,0.00009319623,0.0001789694,0.0002726796,0.000244899],"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":[0.03765466,0.006560623,0.3785148,0.0002187567,0.0002249971,0.00075864,0.002630731,0.0007934244,0.5116587,0.0001447483,0.0002166719,0.06062324],"study_design_scores_gemma":[0.0008445735,0.06931897,0.8841865,0.00001612117,0.0003669194,0.001086396,0.002368662,0.004810141,0.03604646,0.0001256308,0.0007727986,0.00005683308],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9967312,0.00010205,0.002583764,0.00001196106,0.00001734905,0.0001961666,0.00007448039,0.000008429346,0.0002747447],"genre_scores_gemma":[0.9962768,0.00008201536,0.003017376,0.0000417022,0.00003047131,0.0001988861,0.00008743996,0.000009051149,0.0002561637],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002081406,"threshold_uncertainty_score":0.01100767,"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","authors":[{"name":"Phil Howson","is_ca":false},{"name":"Irfana Madathodiyil","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002690344,0.0003120084,0.0005608986,0.001128184,0.001191125,0.004805285,0.001194253,0.001312178,0.01084684],"category_scores_gemma":[0.009757781,0.0005671192,0.0005005245,0.0006505043,0.00440265,0.008704568,0.004253292,0.002349658,0.0008593263],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008455829,"about_ca_system_score_gemma":0.0009144673,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002895921,"about_ca_topic_score_gemma":0.001899301,"domain_scores_codex":[0.9985923,0.0002278081,0.00005471849,0.0006939739,0.00033184,0.00009923],"domain_scores_gemma":[0.990303,0.004519928,0.0007253074,0.002256717,0.001593348,0.0006016962],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001125691,0.0003665898,0.04122203,0.0004864146,0.000163595,0.0003460887,0.01538694,0.001289806,0.06404667,0.6856071,0.002759932,0.1871992],"study_design_scores_gemma":[0.0001853139,0.0004901657,0.2179288,0.0003332756,0.0001878976,0.001284287,0.01337697,0.02543698,0.01709719,0.691233,0.03224236,0.0002037232],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7757607,0.00156678,0.05574259,0.005989479,0.0003491317,0.00008574849,0.000244598,0.000220094,0.1600408],"genre_scores_gemma":[0.9874011,0.0003730433,0.007920986,0.0007134226,0.0002072546,0.00004610894,0.0001021717,0.0002052767,0.003030615],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01084684,"threshold_uncertainty_score":0.03628623,"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","authors":[{"name":"Fan Zhang","is_ca":false},{"name":"Chao Pan","is_ca":false},{"name":"Jingdong Chen","is_ca":false},{"name":"Jacob Benesty","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002150939,0.001000509,0.001381769,0.0007875631,0.0004711407,0.001478013,0.001885956,0.001463252,0.0029879],"category_scores_gemma":[0.01002573,0.001009442,0.0009710583,0.0007866976,0.0006014343,0.001747683,0.001093227,0.002621685,0.002323127],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004160189,"about_ca_system_score_gemma":0.0008948134,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004294842,"about_ca_topic_score_gemma":0.006159831,"domain_scores_codex":[0.9982779,0.0003932958,0.0001575672,0.0004010452,0.0006693117,0.0001009539],"domain_scores_gemma":[0.9964283,0.002064683,0.0001355728,0.0003134573,0.0009931849,0.00006491157],"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":[0.0003656627,0.0001248292,0.000920684,0.0003122656,0.0001621223,0.0002168598,0.0001665587,0.2347785,0.02584751,0.01974688,0.004585285,0.7127728],"study_design_scores_gemma":[0.00002546066,0.0000471152,0.0004127255,0.00003188841,0.00004512594,0.0001485331,0.000008846194,0.9839189,0.007574576,0.004848059,0.002908541,0.00003032069],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001262346,0.0001451613,0.9979888,0.00003835404,0.00005028929,0.00001731714,0.00002619532,0.0001874987,0.0002840431],"genre_scores_gemma":[0.09124564,0.0006070885,0.9028878,0.0001514589,0.0002754993,0.0002127116,0.0003067603,0.0002655699,0.004047482],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004294842,"threshold_uncertainty_score":0.01137537,"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","authors":[{"name":"Joan A. Sereno","is_ca":false},{"name":"Allard Jongman","is_ca":false},{"name":"Yue Wang","is_ca":true},{"name":"Paul Tupper","is_ca":true},{"name":"Dawn M. Behne","is_ca":false},{"name":"Jetic Gū","is_ca":true},{"name":"Haoyao Ruan","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004316054,0.0001900196,0.0001529909,0.0001010937,0.00006960469,0.0004359311,0.0001307414,0.0002866701,0.003123936],"category_scores_gemma":[0.004733053,0.0001523245,0.0001618832,0.00002702713,0.0001503268,0.0003588779,0.0003680952,0.000268975,0.0004142004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008072025,"about_ca_system_score_gemma":0.0001277671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004408592,"about_ca_topic_score_gemma":0.0005158256,"domain_scores_codex":[0.9997218,0.00006291291,0.00003356027,0.00007253409,0.00008852618,0.00002053818],"domain_scores_gemma":[0.9979949,0.001106625,0.0003138594,0.0001455849,0.0002421128,0.0001969161],"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":[0.00125814,0.0001342002,0.005100183,0.0001131819,0.00001456333,0.00009822792,0.0004351903,0.0001643706,0.9723625,0.00004038446,0.00008630391,0.02019276],"study_design_scores_gemma":[0.0001227465,0.005997141,0.7722947,0.00006385466,0.0001129824,0.000855607,0.001124305,0.006519661,0.2106002,0.0005099317,0.001744701,0.00005412906],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.996636,0.00008381093,0.002170588,0.00002701625,0.00001016371,0.00001144053,0.00002208274,0.00004656523,0.0009922495],"genre_scores_gemma":[0.9975135,0.00007295111,0.001574018,0.00003563506,0.000007085902,0.00001213268,0.00004345198,0.00001391946,0.0007272739],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003123936,"threshold_uncertainty_score":0.0104506,"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","authors":[{"name":"Yan Pan","is_ca":false},{"name":"Jian Zhou","is_ca":false},{"name":"Huabin Wang","is_ca":false},{"name":"Wenming Zheng","is_ca":false},{"name":"Liang Tao","is_ca":false},{"name":"Hon Keung Kwan","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000972644,0.0007722327,0.0006367369,0.0003994297,0.0002280859,0.0005466916,0.0007225037,0.0009715081,0.002019031],"category_scores_gemma":[0.002830882,0.0002652093,0.000458388,0.0004360232,0.0005796106,0.00105213,0.001559826,0.001053689,0.001002315],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002760602,"about_ca_system_score_gemma":0.0004874711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001416642,"about_ca_topic_score_gemma":0.002037437,"domain_scores_codex":[0.9994701,0.0001346578,0.00002033011,0.00009882393,0.0002317826,0.00004441241],"domain_scores_gemma":[0.9991543,0.0004471047,0.00006091692,0.0001218179,0.0001657929,0.00005012012],"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":[0.0005418092,0.0002023193,0.001192645,0.0001802056,0.00009781485,0.0001873288,0.0001264929,0.5043858,0.08893061,0.01579294,0.002956335,0.3854056],"study_design_scores_gemma":[0.000005429762,0.00005295231,0.0002533074,0.000006636879,0.0000150622,0.00007293445,0.00001186146,0.9864175,0.009795674,0.002560333,0.0007994089,0.000008858997],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01638199,0.0001971117,0.9815258,0.0001136229,0.00008542106,0.0000177066,0.0000397958,0.0003077459,0.001330907],"genre_scores_gemma":[0.6596422,0.0007109996,0.3291404,0.0003469262,0.0001906282,0.00007071791,0.0003496132,0.0002948846,0.00925373],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002019031,"threshold_uncertainty_score":0.006754279,"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","authors":[{"name":"Johannes Heim","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005017085,0.0005977993,0.00065988,0.0006060211,0.0003742365,0.002474486,0.0007481182,0.0006754214,0.005465953],"category_scores_gemma":[0.03856648,0.0006105591,0.0005643613,0.0004471162,0.001445769,0.002393062,0.001921973,0.001063259,0.0004614072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003529874,"about_ca_system_score_gemma":0.0001852676,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005858791,"about_ca_topic_score_gemma":0.0006560773,"domain_scores_codex":[0.995475,0.002342201,0.0003703014,0.0007358436,0.0009143309,0.0001623997],"domain_scores_gemma":[0.9337655,0.05578228,0.005123747,0.003381319,0.001393118,0.0005540489],"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":[0.01076987,0.000709885,0.1059642,0.001545683,0.0007684806,0.0004607681,0.01313224,0.001828911,0.782065,0.00578725,0.0004231394,0.0765445],"study_design_scores_gemma":[0.0002172626,0.002052486,0.9039784,0.0001722896,0.0004684273,0.000505218,0.003749819,0.00596325,0.07347972,0.007714209,0.001529236,0.0001695926],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9810109,0.0004208926,0.01197041,0.0001121423,0.00003300005,0.0001267869,0.0002591418,0.00007747913,0.005989257],"genre_scores_gemma":[0.9925337,0.000101815,0.006231942,0.0001137313,0.00001435088,0.0001391003,0.0002062621,0.0001433893,0.0005157164],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005465953,"threshold_uncertainty_score":0.02653319,"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","authors":[{"name":"Vincent Hughes","is_ca":false},{"name":"Carmen Llamas","is_ca":false},{"name":"Thomas Kettig","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001098252,0.0004149877,0.000438132,0.0007192447,0.0003479394,0.0008218497,0.0003551851,0.0008635613,0.006349981],"category_scores_gemma":[0.003631914,0.0001778552,0.0004409571,0.0003017906,0.0004475479,0.0006086616,0.0004711835,0.0002490463,0.001528314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002146324,"about_ca_system_score_gemma":0.0002514681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001701582,"about_ca_topic_score_gemma":0.002675948,"domain_scores_codex":[0.9991032,0.0003486115,0.00005911061,0.0002466315,0.0001543818,0.00008811068],"domain_scores_gemma":[0.9983589,0.0009333114,0.00004759064,0.0001659745,0.0004363481,0.00005788503],"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":[0.008967731,0.0001574444,0.008196811,0.0005102518,0.0002413486,0.0007937321,0.0007514661,0.005852772,0.7638856,0.0008251068,0.001029381,0.2087883],"study_design_scores_gemma":[0.0004543682,0.00242313,0.1872699,0.00008252404,0.0007631492,0.005862872,0.00163182,0.120372,0.6705999,0.001253681,0.009119364,0.0001674003],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9142551,0.001130197,0.07640118,0.0000805869,0.0002979682,0.00009016684,0.0009224908,0.001212845,0.005609506],"genre_scores_gemma":[0.981405,0.00017352,0.01516293,0.00003817921,0.00004815747,0.00002887364,0.0006920042,0.0002562164,0.002195143],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006349981,"threshold_uncertainty_score":0.0212428,"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)","authors":[{"name":"Eija Aalto","is_ca":true},{"name":"Hana Ben Asker","is_ca":false},{"name":"Lucie Ménard","is_ca":true},{"name":"Walcir Cardoso","is_ca":true},{"name":"Catherine Laporte","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07907268,0.002213852,0.01647157,0.01916821,0.00170794,0.006580623,0.003727,0.003922646,0.004557656],"category_scores_gemma":[0.241719,0.001941012,0.01550333,0.01705203,0.002985601,0.005823393,0.006266722,0.002548545,0.0003780149],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.009683765,"about_ca_system_score_gemma":0.0334449,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008718606,"about_ca_topic_score_gemma":0.02901842,"domain_scores_codex":[0.8947703,0.04405404,0.04453315,0.00544024,0.009370058,0.001832205],"domain_scores_gemma":[0.7928709,0.1571375,0.03328661,0.004488551,0.01081809,0.001398293],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.000277338,0.0000255998,0.001460298,0.9683645,0.01689681,0.0000788319,0.001009241,0.00007572092,0.0001409526,0.0002912593,0.000779512,0.01059987],"study_design_scores_gemma":[0.0008038813,0.0002280739,0.004393834,0.8725888,0.1110496,0.0002173944,0.002203227,0.0001659132,0.0002022925,0.0008028952,0.00726725,0.00007683805],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.006505448,0.9795222,0.00210639,0.001184733,0.0003768912,0.008239947,0.001578417,0.00003185196,0.0004540296],"genre_scores_gemma":[0.138753,0.8010714,0.01464145,0.003573369,0.000358002,0.03973819,0.001336482,0.00006906877,0.000458964],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9209273,"threshold_uncertainty_score":0.4181813,"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)","authors":[{"name":"Junrui Ni","is_ca":false},{"name":"Liming Wang","is_ca":true},{"name":"Yang Zhang","is_ca":false},{"name":"Kaizhi Qian","is_ca":false},{"name":"Heting Gao","is_ca":false},{"name":"Mark Hasegawa‐Johnson","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001346695,0.001655477,0.001463188,0.0008860074,0.0006551541,0.002121523,0.001655398,0.001967185,0.005234666],"category_scores_gemma":[0.004251966,0.001040435,0.001430884,0.0007507156,0.0007378102,0.002339576,0.002203764,0.00280195,0.01210689],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004268444,"about_ca_system_score_gemma":0.001484286,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003137919,"about_ca_topic_score_gemma":0.005803899,"domain_scores_codex":[0.9984329,0.0004430867,0.0000979027,0.0005131711,0.0003890675,0.000123734],"domain_scores_gemma":[0.9967728,0.00139839,0.0001126954,0.0007580997,0.0008728578,0.00008518793],"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":[0.0003396388,0.0001728493,0.0009656724,0.0003062762,0.0001640626,0.0001727566,0.0001881142,0.03075035,0.1553551,0.01467913,0.008715241,0.7881908],"study_design_scores_gemma":[0.00004334112,0.0001692018,0.001553719,0.00006692796,0.0001436669,0.0004685615,0.0001105795,0.8325859,0.1251815,0.02041745,0.01919761,0.00006160209],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003543015,0.0002181922,0.990738,0.0001101968,0.0001130619,0.00003282159,0.0002054464,0.003706092,0.001333106],"genre_scores_gemma":[0.09837645,0.0005565032,0.8796084,0.0004461844,0.0002673657,0.0002075288,0.003117009,0.001268972,0.01615169],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005234666,"threshold_uncertainty_score":0.01751167,"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)","authors":[{"name":"Ayden M. Cauchi","is_ca":true},{"name":"Jaina Negandhi","is_ca":true},{"name":"Sharon L. Cushing","is_ca":true},{"name":"Karen A. Gordon","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005615982,0.0009727033,0.0005875338,0.001709353,0.0005524284,0.0007105475,0.001125567,0.001867679,0.003118549],"category_scores_gemma":[0.01332334,0.000338532,0.0006826021,0.0004950605,0.0006238388,0.001364137,0.0005341717,0.0007920665,0.002093977],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003618604,"about_ca_system_score_gemma":0.0006056862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001634919,"about_ca_topic_score_gemma":0.001937794,"domain_scores_codex":[0.9960497,0.001782572,0.0003754498,0.0004296711,0.001178025,0.0001846262],"domain_scores_gemma":[0.9901205,0.005803197,0.0002452732,0.0004996156,0.00301814,0.0003132242],"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":[0.009315752,0.004216913,0.233703,0.0004348037,0.0002163425,0.001735979,0.001038706,0.00150301,0.5734915,0.0007765312,0.001079317,0.1724882],"study_design_scores_gemma":[0.0008019017,0.07433543,0.3523943,0.00009717388,0.0009025349,0.01292063,0.001701326,0.03822835,0.510478,0.0008799444,0.007110106,0.0001503291],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9252547,0.001794809,0.06262998,0.0003430305,0.0002706233,0.0009055012,0.0004554243,0.0003318953,0.008013943],"genre_scores_gemma":[0.9654916,0.0005251421,0.02859531,0.0003473332,0.0001407747,0.0003952805,0.0005054531,0.00007943582,0.003919697],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005615982,"threshold_uncertainty_score":0.02970052,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}