{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":28,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":28,"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":"4f1cdcbff395","filters":{"venue":"International Journal of Speech Technology"}},"results":[{"id":"W4324027600","doi":"10.1007/s10772-023-10027-y","title":"The perception of artificial-intelligence (AI) based synthesized speech in younger and older adults","year":2023,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Hearing Loss and Rehabilitation","field":"Neuroscience","cited_by":53,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Baycrest Hospital; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Intelligibility (philosophy); Speech perception; Computer science; Perception; Speech recognition; Speech processing; Voice activity detection; Speech synthesis; Audiology; Masking (illustration); Psychology; Medicine","authors":[{"name":"Björn Herrmann","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02152581346913179,"gpt":0.3145502182844738,"spread":0.293024404815342,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005357601,0.0003463903,0.000332294,0.0005144902,0.0002067936,0.001244543,0.0001860895,0.0005822584,0.002951873],"category_scores_gemma":[0.004839004,0.0001538089,0.0002278609,0.0001683265,0.0003273208,0.0006456868,0.0006123763,0.0004309901,0.0004777805],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002634741,"about_ca_system_score_gemma":0.0001482067,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006104027,"about_ca_topic_score_gemma":0.005687029,"domain_scores_codex":[0.9997924,0.0000262018,0.00002829024,0.00004794942,0.00006611879,0.0000390653],"domain_scores_gemma":[0.9985044,0.0005440286,0.0003017606,0.000049491,0.0002737497,0.0003266244],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.007348881,0.0009392058,0.7259345,0.0005367828,0.0003305881,0.00214161,0.0693725,0.0005011874,0.1309591,0.0005304132,0.001321143,0.06008401],"study_design_scores_gemma":[0.0000361372,0.0008148658,0.9871964,0.00001653247,0.00005044505,0.0006043874,0.009384739,0.000351373,0.0008914821,0.0002119381,0.0004246455,0.00001709868],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9989983,0.0001303465,0.00005365181,0.00002164734,0.000006787138,0.000005296309,0.00005233704,0.000002085332,0.0007295637],"genre_scores_gemma":[0.9990988,0.00009114264,0.00005804893,0.00004450082,0.000006979926,0.000004612983,0.00006458993,0.00000176905,0.0006295979],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006104027,"threshold_uncertainty_score":0.012137,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2163339323","doi":"10.1007/s10772-011-9116-2","title":"Bayesian on-line spectral change point detection: a soft computing approach for on-line ASR","year":2011,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institut National de la Recherche Scientifique; Université de Moncton; Université du Québec à Montréal","funders":"","keywords":"Computer science; Noise (video); Line (geometry); Speech recognition; Dynamic mode decomposition; Artificial intelligence; Pattern recognition (psychology); Machine learning","authors":[{"name":"Md Fozur Rahman Chowdhury","is_ca":true},{"name":"Sid‐Ahmed Selouani","is_ca":true},{"name":"Douglas O’Shaughnessy","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06346383785389761,"gpt":0.3007303888762885,"spread":0.2372665510223909,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001511,0.001290021,0.002099918,0.001297952,0.0006465332,0.001616708,0.001926725,0.001769592,0.003786809],"category_scores_gemma":[0.005247887,0.000817895,0.0009559373,0.001427272,0.000806731,0.001673588,0.001759118,0.00184855,0.001737837],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006032533,"about_ca_system_score_gemma":0.001055829,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003785459,"about_ca_topic_score_gemma":0.005720092,"domain_scores_codex":[0.9980351,0.0006104523,0.0001314164,0.0002918484,0.0007664159,0.0001646533],"domain_scores_gemma":[0.9971635,0.001499315,0.000288697,0.0002863722,0.0006738942,0.00008822135],"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":[0.000410641,0.0003541892,0.0009023341,0.0001776929,0.0001215,0.0001129252,0.0001200805,0.2375571,0.0286339,0.006722337,0.002068096,0.7228193],"study_design_scores_gemma":[0.000006306856,0.00003427283,0.0002858496,0.00000780995,0.00001128347,0.0000314765,0.00001004746,0.9937103,0.00319066,0.002243612,0.0004577512,0.00001071453],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004597894,0.00007327642,0.993972,0.00008701492,0.00001828856,0.00003841499,0.00003674453,0.0004264367,0.0007499256],"genre_scores_gemma":[0.2883254,0.0002975035,0.7042506,0.0003738356,0.0001592107,0.0002115297,0.0002919414,0.0003289109,0.005761164],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003786809,"threshold_uncertainty_score":0.01266813,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2052003572","doi":"10.1007/s10772-005-2166-6","title":"Aligning Text and Phonemes for Speech Technology Applications Using an EM-Like Algorithm","year":2005,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada; National Research Council Institute for Biodiagnostics","funders":"","keywords":"Computer science; Speech recognition; Speech synthesis; Speech technology; Algorithm; Artificial intelligence; Natural language processing","authors":[{"name":"R.I. Damper","is_ca":false},{"name":"Yannick Marchand","is_ca":true},{"name":"J.-D. S. Marsters","is_ca":false},{"name":"Alex Bazin","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02173062261395104,"gpt":0.3048551054452593,"spread":0.2831244828313083,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001052174,0.001189791,0.0007895868,0.0007732836,0.0006378596,0.001016334,0.001011825,0.001846555,0.007447428],"category_scores_gemma":[0.004700623,0.0005945097,0.001038428,0.001202617,0.0004879997,0.001563687,0.001094081,0.001647498,0.005624262],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000275793,"about_ca_system_score_gemma":0.0008490049,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001441952,"about_ca_topic_score_gemma":0.002115335,"domain_scores_codex":[0.9994305,0.0001601012,0.00004898547,0.0002035052,0.0001121071,0.00004479356],"domain_scores_gemma":[0.9989512,0.0004890775,0.00006472386,0.0001576975,0.0002967943,0.00004040432],"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":[0.0006241585,0.0001559667,0.0007953639,0.00020474,0.0001542477,0.0001918711,0.0001460051,0.08807941,0.07523761,0.009647713,0.004805758,0.8199572],"study_design_scores_gemma":[0.00007546267,0.0001707733,0.0009964156,0.00003270253,0.00008571811,0.0003565903,0.0001055855,0.9047321,0.07089716,0.01046454,0.01203617,0.00004674113],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004090573,0.00004867391,0.9941,0.00005397966,0.00007383529,0.00002950935,0.00004629356,0.0009597861,0.0005973086],"genre_scores_gemma":[0.04557836,0.0001160566,0.9501069,0.0001107992,0.00006088551,0.0001171211,0.0004496025,0.0004391577,0.00302107],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007447428,"threshold_uncertainty_score":0.02491409,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2479628911","doi":"10.1007/s10772-016-9352-6","title":"Audio steganalysis using deep belief networks","year":2016,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Music and Audio Processing","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Moncton","funders":"","keywords":"Steganalysis; Computer science; Artificial intelligence; Support vector machine; Pattern recognition (psychology); Steganography; Deep belief network; Classifier (UML); Mixture model; Speech recognition; Deep learning; Image (mathematics)","authors":[{"name":"Catherine Paulin","is_ca":true},{"name":"Sid‐Ahmed Selouani","is_ca":true},{"name":"Éric Hervet","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01090896686714993,"gpt":0.2630156662380046,"spread":0.2521066993708547,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004618528,0.0006135704,0.0005103423,0.0004604746,0.0002174721,0.0004994991,0.0005380118,0.0006973131,0.001194558],"category_scores_gemma":[0.00158529,0.000389924,0.0004801214,0.0002711704,0.000405884,0.000820905,0.0008859581,0.00121495,0.0002985906],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004340298,"about_ca_system_score_gemma":0.0004942898,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004331659,"about_ca_topic_score_gemma":0.00558308,"domain_scores_codex":[0.9998171,0.00003792496,0.000009303985,0.00003986437,0.00005476246,0.00004121272],"domain_scores_gemma":[0.9992121,0.0004915213,0.00006386168,0.0000620745,0.0001450651,0.00002526608],"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":[0.0002365886,0.00009876129,0.001204316,0.00006129304,0.00009386914,0.00008752603,0.00003751381,0.7481489,0.01420826,0.004894746,0.001051935,0.2298762],"study_design_scores_gemma":[0.000001779196,0.000008313098,0.00004861403,0.000001709955,0.000003316516,0.000005513409,0.000001558732,0.997817,0.001321203,0.0007366564,0.00005296309,0.000001426311],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0559005,0.000458683,0.9407657,0.0003020912,0.00005863402,0.00002521987,0.00005898821,0.0008163514,0.001613841],"genre_scores_gemma":[0.8689856,0.0003217211,0.125695,0.0001431663,0.00004893113,0.000039541,0.0001857401,0.00006113796,0.004519128],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004331659,"threshold_uncertainty_score":0.008612871,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2031495521","doi":"10.1007/s10772-011-9104-6","title":"Using speech rhythm knowledge to improve dysarthric speech recognition","year":2011,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":25,"is_retracted":false,"has_abstract":false,"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; Université de Moncton","funders":"","keywords":"Computer science; Speech recognition; Dysarthria; Intelligibility (philosophy); Rhythm; Hidden Markov model; Classifier (UML); Artificial intelligence; Pattern recognition (psychology); Psychology","authors":[{"name":"Sid‐Ahmed Selouani","is_ca":true},{"name":"Habiba Dahmani","is_ca":true},{"name":"Rim Amami","is_ca":false},{"name":"Habib Hamam","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1036658881049826,"gpt":0.3905004229513346,"spread":0.286834534846352,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002624499,0.0003916968,0.0004218647,0.0002775108,0.0001611238,0.0005503905,0.0002829727,0.0004213377,0.003487509],"category_scores_gemma":[0.002507803,0.0001359362,0.000212173,0.0001586536,0.0001359027,0.0006257199,0.0002868368,0.0004459592,0.0008398836],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009671265,"about_ca_system_score_gemma":0.0002795921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001004614,"about_ca_topic_score_gemma":0.002050838,"domain_scores_codex":[0.9998392,0.00002762496,0.00002365116,0.0000646025,0.00002967771,0.00001533727],"domain_scores_gemma":[0.9992368,0.0004908092,0.00006587597,0.00006455311,0.0001089719,0.00003296182],"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":[0.001347087,0.001556721,0.00666116,0.0002862956,0.0001429723,0.0004070981,0.0002476857,0.004356879,0.29483,0.0003738932,0.001169302,0.688621],"study_design_scores_gemma":[0.001656746,0.008099997,0.2280629,0.0003353063,0.002906078,0.007295568,0.00125797,0.2263296,0.5040854,0.006853974,0.01291029,0.0002061222],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9233896,0.001166837,0.06637714,0.0003590064,0.0001368346,0.000116095,0.0002503454,0.001014584,0.007189523],"genre_scores_gemma":[0.9741825,0.0006255609,0.02216676,0.0001645905,0.00006216871,0.00004207119,0.0003417252,0.00006441194,0.002350106],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003487509,"threshold_uncertainty_score":0.01166683,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1506669403","doi":"10.1023/a:1011323308477","title":"VoiceGrip: A Tool for Programming-by-Voice","year":2001,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Digital Accessibility for Disabilities","field":"Social Sciences","cited_by":22,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"National Research Council Canada","keywords":"Computer science; Programmer; Syntax; Programming language; Usability; Symbol (formal); Code (set theory); Confusion; Range (aeronautics); Speech recognition; Artificial intelligence; Human–computer interaction","authors":[{"name":"Alain Désilets","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01785288856041286,"gpt":0.3474971288228051,"spread":0.3296442402623923,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001822131,0.00348563,0.0015465,0.002474833,0.0007865937,0.002028079,0.002979265,0.001860409,0.1155748],"category_scores_gemma":[0.006137641,0.001374145,0.001656333,0.0008877834,0.0005958433,0.002620813,0.004685564,0.002041834,0.04875373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004170946,"about_ca_system_score_gemma":0.0006749414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001222601,"about_ca_topic_score_gemma":0.001665411,"domain_scores_codex":[0.9986522,0.0002614215,0.000162028,0.0002360197,0.0004861917,0.000202224],"domain_scores_gemma":[0.9970785,0.001711337,0.0001091902,0.0003925207,0.0004266672,0.0002816873],"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":[0.002154074,0.0003643648,0.001615325,0.001889407,0.0002597995,0.001726692,0.001514244,0.002054348,0.03565932,0.006576396,0.4037603,0.5424258],"study_design_scores_gemma":[0.001247404,0.0005918854,0.004442546,0.0008690299,0.0004007219,0.004450751,0.0005479038,0.04772182,0.146892,0.01941812,0.7726915,0.0007263053],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"software","genre_gemma":"methods","genre_scores_codex":[0.004020841,0.0003097732,0.3594983,0.0001729443,0.0003696534,0.0008419557,0.005794845,0.6133876,0.01560405],"genre_scores_gemma":[0.09356262,0.00117572,0.4505068,0.001791334,0.0004304937,0.005668478,0.03512049,0.2918348,0.1199093],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.1155748,"threshold_uncertainty_score":0.3866361,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1963733617","doi":"10.1007/s10772-012-9146-4","title":"Speaker-independent ASR for Modern Standard Arabic: effect of regional accents","year":2012,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Speech recognition; Hidden Markov model; Arabic; Stress (linguistics); Modern Standard Arabic; Natural language processing; Artificial intelligence; Linguistics","authors":[{"name":"Ghania Droua-Hamdani","is_ca":false},{"name":"Sid‐Ahmed Selouani","is_ca":true},{"name":"Malika Boudraa","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02049470695497841,"gpt":0.304830386805333,"spread":0.2843356798503546,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009314899,0.0009597995,0.0006335953,0.0003247899,0.0003886718,0.0007722515,0.0004250768,0.0006727576,0.006791135],"category_scores_gemma":[0.004594365,0.0002704095,0.0003668789,0.0003485848,0.0003152827,0.0009825237,0.0005740728,0.0009130224,0.003282369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001545896,"about_ca_system_score_gemma":0.0004091963,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001576945,"about_ca_topic_score_gemma":0.00266878,"domain_scores_codex":[0.9993099,0.0002465539,0.00005133557,0.0001482212,0.0001568588,0.00008703492],"domain_scores_gemma":[0.995302,0.002943571,0.000153242,0.0003716691,0.00107972,0.0001498258],"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":[0.007342673,0.0002378065,0.001839537,0.0004492147,0.0001383575,0.0004328134,0.0004133982,0.01055659,0.7722173,0.0007597771,0.001902992,0.2037095],"study_design_scores_gemma":[0.0002730701,0.003048181,0.03718201,0.0001083541,0.0008923093,0.00262049,0.0006283313,0.1954034,0.7488014,0.001374609,0.009476407,0.0001914835],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8844714,0.001601448,0.09667365,0.0003131721,0.0003603979,0.00009493879,0.0009633867,0.002155718,0.01336587],"genre_scores_gemma":[0.9436872,0.00092983,0.04426977,0.0001672952,0.0001399166,0.00006768337,0.001556577,0.0008939435,0.00828776],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006791135,"threshold_uncertainty_score":0.02271867,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2982012035","doi":"10.1007/s10772-019-09642-5","title":"Maximum entropy PLDA for robust speaker recognition under speech coding distortion","year":2019,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Speech recognition; TIMIT; Robustness (evolution); Artificial intelligence; Pattern recognition (psychology); Hidden Markov model","authors":[{"name":"Ahmed Krobba","is_ca":false},{"name":"Mohamed Debyeche","is_ca":false},{"name":"Sid‐Ahmed Selouani","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02108643474596907,"gpt":0.263887749614766,"spread":0.242801314868797,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009164679,0.0007188253,0.000711413,0.0004177036,0.0003248531,0.0007216653,0.0005218292,0.0005425895,0.002109045],"category_scores_gemma":[0.002217771,0.0003528753,0.0004567134,0.0004051698,0.0003444548,0.0009642651,0.0008080119,0.0007715542,0.000960287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000283221,"about_ca_system_score_gemma":0.0005359683,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001188926,"about_ca_topic_score_gemma":0.001859074,"domain_scores_codex":[0.9994809,0.0001819323,0.00004431532,0.00009746309,0.0001471827,0.00004830081],"domain_scores_gemma":[0.9991767,0.0004705055,0.00006072044,0.0001148484,0.0001543284,0.00002281544],"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":[0.0009576768,0.0001233189,0.0009465584,0.0002530821,0.0001161223,0.0002940587,0.0001117903,0.1161888,0.1317678,0.008962232,0.002894556,0.7373841],"study_design_scores_gemma":[0.00001233718,0.00009253761,0.001090408,0.00001465387,0.00002179837,0.0001294622,0.00001474574,0.9639952,0.03038583,0.002531706,0.00169089,0.00002034888],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01762271,0.0005876019,0.9801328,0.0001076111,0.00004567361,0.00002524853,0.0001421785,0.0007009908,0.0006351287],"genre_scores_gemma":[0.4456637,0.0009202362,0.5462569,0.0001244794,0.0001295715,0.0001253587,0.0009594162,0.0002386451,0.00558172],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002109045,"threshold_uncertainty_score":0.007055461,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2018093467","doi":"10.1007/s10772-009-9039-3","title":"Synthetic speech in foreign language learning: an evaluation by learners","year":2008,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Natural (archaeology); Active listening; Speech synthesis; Comprehension; Speech recognition; Natural language processing; Foreign language; Linguistics; Artificial intelligence; Psychology; Communication","authors":[{"name":"Min Kang","is_ca":false},{"name":"Harumi Kashiwagi","is_ca":false},{"name":"Jutta Treviranus","is_ca":true},{"name":"Makoto Kaburagi","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01774191416063589,"gpt":0.287508369161797,"spread":0.269766455001161,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006369673,0.001135102,0.00115769,0.000890533,0.0005885126,0.001341575,0.0008102179,0.001609798,0.002979253],"category_scores_gemma":[0.02071265,0.0002508752,0.0006939989,0.0003856963,0.0007718752,0.001241512,0.00186906,0.0006532961,0.001288999],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004502956,"about_ca_system_score_gemma":0.0006820581,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00113357,"about_ca_topic_score_gemma":0.0008251776,"domain_scores_codex":[0.9951264,0.003294321,0.0003339292,0.0003621266,0.0007448766,0.0001383977],"domain_scores_gemma":[0.9811473,0.01200085,0.0004969353,0.001412008,0.003041288,0.00190167],"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":[0.07240538,0.03125343,0.09350332,0.005202436,0.001374675,0.003205071,0.05337587,0.03021689,0.1012928,0.00178354,0.006150648,0.6002359],"study_design_scores_gemma":[0.009578382,0.2148719,0.3528445,0.00100817,0.003203247,0.01067726,0.05605473,0.1079906,0.1975565,0.004838627,0.04050051,0.0008755053],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9918175,0.000277228,0.004653205,0.00007090984,0.00006816134,0.000307449,0.0003853278,0.0002019317,0.002218265],"genre_scores_gemma":[0.9866678,0.0005285582,0.007134277,0.00009250675,0.00007397689,0.0005600231,0.001395661,0.0001038082,0.003443404],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006369673,"threshold_uncertainty_score":0.0336864,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2085830557","doi":"10.1007/s10772-009-9025-9","title":"A noise-robust front-end for distributed speech recognition in mobile communications","year":2007,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Speech recognition; Front and back ends; Formant; Mel-frequency cepstrum; GSM; Speech processing; Cepstrum; Noise (video); Task (project management); Artificial intelligence; Feature extraction; Telecommunications","authors":[{"name":"Djamel Addou","is_ca":false},{"name":"Sid‐Ahmed Selouani","is_ca":true},{"name":"Kaoukeb Kifaya","is_ca":true},{"name":"Malika Boudraa","is_ca":false},{"name":"Bachir Boudraa","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02978584671247504,"gpt":0.3092272312638119,"spread":0.2794413845513368,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005792323,0.0009026246,0.001047003,0.0005875573,0.0006554301,0.001005225,0.001169604,0.001774281,0.00489393],"category_scores_gemma":[0.001208011,0.0004019007,0.0005233879,0.0004257287,0.0002865037,0.0008271174,0.0007182026,0.0009147143,0.005921063],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003384312,"about_ca_system_score_gemma":0.000426232,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009897368,"about_ca_topic_score_gemma":0.002101951,"domain_scores_codex":[0.9993155,0.00009520468,0.00003248292,0.0001136224,0.0003791456,0.00006400218],"domain_scores_gemma":[0.999303,0.0002311463,0.00003046916,0.00009857916,0.0003005117,0.00003627521],"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":[0.001795689,0.0003245188,0.0005528027,0.0002028427,0.0001063237,0.0003669587,0.00009599156,0.009566078,0.5628316,0.003002762,0.006282269,0.4148721],"study_design_scores_gemma":[0.0001545296,0.0006787048,0.001392766,0.00005091684,0.0001574945,0.001066189,0.0000450957,0.4693901,0.5068362,0.002392388,0.01776061,0.0000749188],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02093657,0.0005033545,0.9716558,0.0001508885,0.0001800557,0.00007539974,0.0001230219,0.004355894,0.00201903],"genre_scores_gemma":[0.270538,0.0005210087,0.7059007,0.0008360972,0.0003427567,0.0002136298,0.0008413203,0.0004694638,0.02033698],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00489393,"threshold_uncertainty_score":0.01637185,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4400357331","doi":"10.1007/s10772-024-10120-w","title":"Pathological voice classification system based on CNN-BiLSTM network using speech enhancement and multi-stream approach","year":2024,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Speech recognition; Artificial intelligence; Voice activity detection; Natural language processing; Speech processing","authors":[{"name":"Soumeya Belabbas","is_ca":false},{"name":"Djamel Addou","is_ca":false},{"name":"Sid‐Ahmed Selouani","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03711003070019565,"gpt":0.3019843318947205,"spread":0.2648743011945248,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003307652,0.0006604808,0.0005229147,0.0006678681,0.0002201185,0.0004913828,0.0005094995,0.0006930683,0.002504704],"category_scores_gemma":[0.0004704913,0.000174027,0.0004136539,0.0001976513,0.0001251851,0.0004748835,0.0004594616,0.0003828671,0.001307937],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002103266,"about_ca_system_score_gemma":0.0003959991,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002161674,"about_ca_topic_score_gemma":0.004864424,"domain_scores_codex":[0.9998133,0.0000162491,0.00001369222,0.00006714783,0.00006138546,0.00002823934],"domain_scores_gemma":[0.9998266,0.0000266981,0.00001141988,0.00001544072,0.000100717,0.00001914982],"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":[0.0008345084,0.0002048366,0.0160994,0.0002458323,0.0001377774,0.001104867,0.00007508645,0.008493412,0.1886444,0.0005622431,0.005867397,0.7777303],"study_design_scores_gemma":[0.00008799595,0.0005866573,0.05159295,0.00008466346,0.0004228952,0.004663361,0.0001745258,0.7945331,0.1391512,0.001809165,0.006806041,0.0000874158],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2765184,0.003124188,0.7016551,0.0006788142,0.0009271121,0.0003607736,0.001331932,0.007758022,0.007645568],"genre_scores_gemma":[0.8666736,0.001315726,0.1185967,0.0003527979,0.0002732718,0.0001580486,0.001544856,0.0001955904,0.01088937],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002504704,"threshold_uncertainty_score":0.008379102,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2015313388","doi":"10.1007/s10772-014-9224-x","title":"Dialogue POMDP components (Part II): learning the reward function","year":2014,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval","funders":"","keywords":"Partially observable Markov decision process; Computer science; Reinforcement learning; Markov decision process; Context (archaeology); Artificial intelligence; Function (biology); Process (computing); Bellman equation; Machine learning; Markov process; Markov chain; Markov model; Mathematical optimization; Mathematics","authors":[{"name":"Hamidreza Chinaei","is_ca":true},{"name":"Brahim Chaib-draa","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0121418797332161,"gpt":0.2309892475912225,"spread":0.2188473678580064,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001477143,0.001027873,0.001128046,0.0003120274,0.000428394,0.001825099,0.00162563,0.00141272,0.01457134],"category_scores_gemma":[0.00714266,0.0007765064,0.0006933609,0.0003107325,0.0006595586,0.002063914,0.001744034,0.002621439,0.002030648],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000931944,"about_ca_system_score_gemma":0.00193108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00431527,"about_ca_topic_score_gemma":0.003610569,"domain_scores_codex":[0.9992594,0.0001897971,0.00003864049,0.0002495947,0.0001620586,0.0001005701],"domain_scores_gemma":[0.9988332,0.0006058007,0.00005570961,0.0001946852,0.0002223561,0.00008824966],"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":[0.001207897,0.000402938,0.003186737,0.00051843,0.0001735122,0.00020435,0.0005211631,0.3205005,0.02178867,0.05622165,0.007973084,0.5873011],"study_design_scores_gemma":[0.00007420477,0.0001712512,0.001161754,0.00004813558,0.00004682429,0.00005246509,0.00004672063,0.9512985,0.01252555,0.03045222,0.004086839,0.0000356071],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01748937,0.000236401,0.9759453,0.0002595134,0.0001189754,0.000255304,0.000274823,0.001366075,0.004054229],"genre_scores_gemma":[0.5295138,0.0003040998,0.4580461,0.0002002034,0.000114979,0.0006686873,0.0007899718,0.0004900264,0.009872055],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01457134,"threshold_uncertainty_score":0.04874599,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2022504354","doi":"10.1007/s10772-013-9203-7","title":"A novel sub-band adaptive filtering for acoustic echo cancellation based on empirical mode decomposition algorithm","year":2013,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Hilbert–Huang transform; Algorithm; Microphone; Echo (communications protocol); Adaptive filter; Transfer function; SIGNAL (programming language); Mode (computer interface); Noise (video); Speech recognition; Filter (signal processing); Artificial intelligence; Telecommunications","authors":[{"name":"Xiaochuan He","is_ca":true},{"name":"Rafik Goubran","is_ca":true},{"name":"Peter Liu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01989133890375423,"gpt":0.3417703319344523,"spread":0.3218789930306981,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003441287,0.000714139,0.0007594191,0.00047508,0.0002895427,0.0005360551,0.0007762138,0.0008177715,0.003000512],"category_scores_gemma":[0.000676039,0.0003202091,0.0006859517,0.0005942616,0.000224837,0.0008325347,0.0005368794,0.0008064493,0.001680467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001574047,"about_ca_system_score_gemma":0.0004761125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001025269,"about_ca_topic_score_gemma":0.001979176,"domain_scores_codex":[0.9996436,0.0000598781,0.00002238693,0.00006477405,0.0001838112,0.00002560397],"domain_scores_gemma":[0.9996872,0.0001051276,0.00002110761,0.00003986173,0.0001291242,0.00001752351],"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":[0.0003261504,0.0001413957,0.0004645007,0.0001903058,0.0001249995,0.0001106531,0.00006911802,0.02528919,0.3170388,0.00755924,0.002615949,0.6460698],"study_design_scores_gemma":[0.00003784068,0.0001842038,0.0007631083,0.00002060828,0.00005962994,0.0003989574,0.00001812409,0.9342129,0.05199138,0.00167192,0.01059439,0.00004684739],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002393068,0.0001779932,0.9966586,0.00002548577,0.00004443021,0.00001373515,0.00001311807,0.0001929537,0.00048069],"genre_scores_gemma":[0.03820086,0.0003773341,0.9581895,0.00008090384,0.00006211684,0.00007090354,0.0001128991,0.00005488828,0.002850596],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003000512,"threshold_uncertainty_score":0.01003766,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W586724576","doi":"10.1007/s10772-015-9280-x","title":"Mobile spoken dialogue system using parser dependencies and ontology","year":2015,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Moncton; Université du Québec à Montréal","funders":"","keywords":"Computer science; Parsing; Sentence; Natural language processing; Mobile phone; Android (operating system); Artificial intelligence; Spoken language; Dependency (UML)","authors":[{"name":"Mohammed Sidi Yakoub","is_ca":true},{"name":"Sid‐Ahmed Selouani","is_ca":true},{"name":"Roger Nkambou","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02908544527401479,"gpt":0.2784860737345201,"spread":0.2494006284605053,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006752174,0.0006262372,0.001082182,0.0008057024,0.0006020935,0.001223801,0.0008366346,0.0006482376,0.006386256],"category_scores_gemma":[0.001430452,0.0005314261,0.0006419081,0.0004831729,0.0002038565,0.001979273,0.00110894,0.0007802065,0.00293809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003866584,"about_ca_system_score_gemma":0.001356774,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004807733,"about_ca_topic_score_gemma":0.004737088,"domain_scores_codex":[0.9996152,0.00006440964,0.00004504243,0.0001557567,0.00008742544,0.00003209593],"domain_scores_gemma":[0.9994003,0.0002457227,0.00003113282,0.00009043908,0.0001927326,0.00003975968],"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":[0.001790363,0.0004487844,0.003782302,0.0009250576,0.0003113407,0.001379212,0.001688535,0.01149629,0.1967026,0.01510287,0.03916004,0.7272126],"study_design_scores_gemma":[0.0004183719,0.0004597886,0.004875418,0.0001492915,0.0007364178,0.001450817,0.0009880105,0.6964095,0.1769751,0.01787431,0.09935196,0.0003110749],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05472217,0.0005237845,0.838863,0.0002235634,0.0002242885,0.0002508203,0.003800729,0.096251,0.005140667],"genre_scores_gemma":[0.4660218,0.000291845,0.511058,0.0002465284,0.00007622319,0.000350855,0.009092656,0.003120411,0.009741642],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006386256,"threshold_uncertainty_score":0.02136415,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2158112478","doi":"10.1007/s10772-008-9007-3","title":"VoiceMarks: restructuring hierarchical voice menus for improving navigation","year":2006,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Ticket; Human–computer interaction; Process (computing); Schedule; Interface (matter); User interface; Telephony; Multimedia; Telecommunications; Computer network","authors":[{"name":"Pourang Irani","is_ca":true},{"name":"Peer Shajahan","is_ca":true},{"name":"Christel Kemke","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.006951465877085184,"gpt":0.2531112935043907,"spread":0.2461598276273055,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006956642,0.001732402,0.001078887,0.001008882,0.0006364787,0.00120639,0.002773563,0.001481542,0.02194441],"category_scores_gemma":[0.005619483,0.0009698129,0.0007253714,0.0008722325,0.0004842962,0.002822651,0.002152931,0.001224669,0.004559311],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000285152,"about_ca_system_score_gemma":0.0007522276,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003134654,"about_ca_topic_score_gemma":0.004689755,"domain_scores_codex":[0.9993019,0.0001080797,0.00006246151,0.000159432,0.0002806213,0.00008745005],"domain_scores_gemma":[0.9969332,0.001479611,0.0001782926,0.0006700171,0.0005415053,0.0001973993],"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":[0.001979883,0.0005064749,0.002134138,0.000577061,0.00008072113,0.000421636,0.0006785021,0.007878907,0.1206102,0.003926868,0.03607687,0.8251287],"study_design_scores_gemma":[0.001353363,0.001801385,0.005676449,0.0002801266,0.000605601,0.001311281,0.0009884557,0.5201091,0.3447733,0.02080042,0.101879,0.0004215947],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05636932,0.0005868045,0.7687687,0.0001735211,0.0003813628,0.0002406788,0.001231741,0.1690091,0.003238829],"genre_scores_gemma":[0.2920172,0.0003950565,0.6798258,0.0003242036,0.0001634479,0.0003366433,0.003319121,0.01124178,0.01237673],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02194441,"threshold_uncertainty_score":0.07341135,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2016053816","doi":"10.1007/s10772-012-9186-9","title":"MCRA noise estimation for KLT-VRE-based speech enhancement","year":2013,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Speech recognition; Noise (video); Estimation; Speech enhancement; Artificial intelligence; Pattern recognition (psychology); Noise reduction","authors":[{"name":"Adda Saadoune","is_ca":true},{"name":"Abderrahmane Amrouche","is_ca":false},{"name":"Sid‐Ahmed Selouani","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.00989396939828999,"gpt":0.2753188794034044,"spread":0.2654249100051144,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007756219,0.00118721,0.0007641522,0.0008407997,0.0003903818,0.0007695892,0.0006882597,0.001274833,0.005177603],"category_scores_gemma":[0.002001641,0.0003605768,0.0006737984,0.0004697884,0.000289256,0.00103514,0.0008457308,0.0009729572,0.003566538],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002385938,"about_ca_system_score_gemma":0.0005666661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001754171,"about_ca_topic_score_gemma":0.00385235,"domain_scores_codex":[0.999254,0.000150071,0.0000484126,0.0001191604,0.0003507281,0.00007768671],"domain_scores_gemma":[0.9991295,0.000337705,0.00005401162,0.00009015506,0.0003520965,0.00003663804],"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":[0.001102974,0.0001901259,0.0012308,0.0004339757,0.0001122685,0.0002580118,0.0001392946,0.02032612,0.4701912,0.001745185,0.002252704,0.5020173],"study_design_scores_gemma":[0.00005010028,0.0003240295,0.004058638,0.0001390381,0.0001768674,0.0009335517,0.0001047585,0.5444552,0.4300447,0.001001582,0.01862231,0.00008925517],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01866625,0.00121286,0.9746997,0.0001727315,0.0001723308,0.00006684704,0.0001680344,0.001496565,0.003344633],"genre_scores_gemma":[0.2909395,0.001597266,0.6938124,0.0003882847,0.0001470142,0.0001399368,0.001030293,0.0005084263,0.01143679],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005177603,"threshold_uncertainty_score":0.01732087,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2134558312","doi":"10.1007/s10772-012-9157-1","title":"The CARES corpus: a database of older adult actor simulated emergency dialogue for developing a personal emergency response system","year":2012,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Social Robot Interaction and HRI","field":"Psychology","cited_by":4,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Rehabilitation Institute; University of Toronto","funders":"Canadian Institutes of Health Research; University of Toronto; Toronto Rehabilitation Institute","keywords":"Computer science; Emergency response; Human–computer interaction; Multimedia; World Wide Web; Database; Natural language processing; Medical emergency; Medicine","authors":[{"name":"Victoria Young","is_ca":true},{"name":"Alex Mihailidis","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03739795723703559,"gpt":0.3822370290246715,"spread":0.344839071787636,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00104675,0.001521487,0.0007976301,0.002455117,0.000957397,0.001134986,0.001511382,0.002324683,0.01570044],"category_scores_gemma":[0.006089718,0.0003567441,0.0006305198,0.001688451,0.000641897,0.001128744,0.00168957,0.001036036,0.008979673],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006769458,"about_ca_system_score_gemma":0.001256067,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01022976,"about_ca_topic_score_gemma":0.01764302,"domain_scores_codex":[0.9991018,0.0003244005,0.0001344384,0.0002028731,0.0001678721,0.00006872575],"domain_scores_gemma":[0.9975303,0.001311667,0.0001356218,0.000331959,0.0004721934,0.0002183045],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.003135739,0.002129857,0.0170811,0.009924881,0.0006056817,0.005861538,0.007798238,0.00662068,0.03539844,0.003786835,0.6915376,0.2161194],"study_design_scores_gemma":[0.001167456,0.0007473404,0.09530591,0.001598558,0.0006180386,0.006251581,0.007800463,0.01913683,0.02495452,0.004000166,0.8378934,0.0005256615],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.2199256,0.003811295,0.02402091,0.0008733115,0.0007467755,0.001588999,0.7219898,0.009638702,0.01740456],"genre_scores_gemma":[0.1334104,0.0009357687,0.02365207,0.0004072074,0.0001440247,0.001998474,0.8302736,0.0009484091,0.008230018],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01570044,"threshold_uncertainty_score":0.0525232,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2061284695","doi":"10.1007/s10772-013-9189-1","title":"Computational auditory models in predicting noise reduction performance for wideband telephony applications","year":2013,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Computer science; Speech recognition; Noise (video); Wideband; Noise reduction; Reliability (semiconductor); Wideband audio; Reduction (mathematics); Telephony; Quality (philosophy); Artificial intelligence; Speech coding; Telecommunications; Mathematics","authors":[{"name":"Nazanin Pourmand","is_ca":true},{"name":"Vijay Parsa","is_ca":true},{"name":"Angela Weaver","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.009768127122746243,"gpt":0.2514530187062966,"spread":0.2416848915835504,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000390347,0.0005278805,0.0003720032,0.000397018,0.0002354564,0.0006583783,0.0004519777,0.0006979992,0.0009507373],"category_scores_gemma":[0.002758866,0.0003110417,0.0003913996,0.0002170163,0.0001858231,0.0004978236,0.0003092681,0.0005752334,0.0003928817],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002983496,"about_ca_system_score_gemma":0.0004545271,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009143298,"about_ca_topic_score_gemma":0.009577746,"domain_scores_codex":[0.9998953,0.0000313637,0.000006693656,0.00001672896,0.00003302595,0.00001690322],"domain_scores_gemma":[0.999077,0.0007045615,0.00004804708,0.00003089988,0.0001150974,0.00002453368],"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":[0.0001742012,0.00007670093,0.001140194,0.00002049976,0.00002383258,0.00003038864,0.00002134502,0.970592,0.003642416,0.0004179195,0.0002183161,0.02364211],"study_design_scores_gemma":[0.000001744035,0.00001491057,0.0001844401,0.000001130658,0.000004535514,0.000004415997,0.00000306172,0.9991798,0.0004506603,0.000129657,0.00002340167,0.000002161891],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6330516,0.0006774978,0.3612526,0.0003052629,0.0001160653,0.00005096817,0.0001923935,0.001002898,0.00335069],"genre_scores_gemma":[0.9840338,0.0001408573,0.01447628,0.00002999142,0.00001900351,0.00002593373,0.00007539813,0.00002574006,0.001172947],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009143298,"threshold_uncertainty_score":0.01818013,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2901429777","doi":"10.1007/s10772-018-09564-8","title":"Evaluating noise suppression methods for recovering the Lombard speech from vocal output in an external noise field","year":2018,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"QUIET; Computer science; Noise (video); Noise reduction; Headphones; Acoustics; Background noise; Microphone; Speech recognition; Intelligibility (philosophy); Speech perception; Speech enhancement; Perception; Sound pressure; Telecommunications; Physics; Artificial intelligence; Psychology","authors":[{"name":"Ghazaleh Vaziri","is_ca":true},{"name":"Christian Giguère","is_ca":true},{"name":"Hilmi R. Dajani","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0534927076411623,"gpt":0.4276633464048619,"spread":0.3741706387636995,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001612092,0.001159115,0.0007875481,0.0008554331,0.0003792027,0.000712319,0.0005823231,0.001330181,0.001323639],"category_scores_gemma":[0.005033276,0.0002840339,0.0005681041,0.0003996081,0.0004572373,0.0007571197,0.0006367083,0.0004347757,0.0005329514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003304714,"about_ca_system_score_gemma":0.0006988985,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003378587,"about_ca_topic_score_gemma":0.003957998,"domain_scores_codex":[0.9993532,0.0001604659,0.00005339304,0.0001117573,0.0002595583,0.00006163921],"domain_scores_gemma":[0.996466,0.002432714,0.0001595351,0.0001338053,0.0006928701,0.0001149481],"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":[0.007634364,0.0008999615,0.005151076,0.001053632,0.0004751413,0.0002311285,0.0002669009,0.1294153,0.3209914,0.0006567411,0.000519671,0.5327047],"study_design_scores_gemma":[0.0001508818,0.002134096,0.007528652,0.00003492746,0.0003245941,0.0002531247,0.0001893576,0.8421642,0.1462851,0.0002888671,0.0006006414,0.00004559254],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5897242,0.002914651,0.4037841,0.0001268975,0.0001227342,0.0001806309,0.000137596,0.0007481395,0.002260957],"genre_scores_gemma":[0.8053404,0.001276936,0.1891112,0.00007775638,0.00007233613,0.0001125643,0.0003997443,0.0001561884,0.003452906],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003378587,"threshold_uncertainty_score":0.00852567,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2011408835","doi":"10.1007/s10772-014-9244-6","title":"Dialogue POMDP components (part I): learning states and observations","year":2014,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval","funders":"","keywords":"Partially observable Markov decision process; Computer science; Artificial intelligence; Context (archaeology); Machine learning; Process (computing); Set (abstract data type); Markov model; Markov chain","authors":[{"name":"Hamid R. Chinaei","is_ca":true},{"name":"Brahim Chaib-draa","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01849621693690926,"gpt":0.2416316221646863,"spread":0.2231354052277771,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008844829,0.0008223816,0.000584896,0.0003325827,0.0003640309,0.001846338,0.001060202,0.0009048609,0.01285506],"category_scores_gemma":[0.006144981,0.0006188284,0.00076288,0.0004098815,0.0007621443,0.002240956,0.001190018,0.001640752,0.002506791],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007272318,"about_ca_system_score_gemma":0.001291804,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004901627,"about_ca_topic_score_gemma":0.002867171,"domain_scores_codex":[0.9994375,0.0001272287,0.00003801298,0.0002101336,0.0001400044,0.00004715104],"domain_scores_gemma":[0.9990358,0.0005275487,0.00006410496,0.0001611018,0.0001679695,0.00004356425],"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":[0.0008020483,0.0004131982,0.0123099,0.000881561,0.0001926789,0.0004603313,0.002180857,0.1930715,0.03228014,0.1025109,0.00933334,0.6455636],"study_design_scores_gemma":[0.00006122309,0.0003243757,0.01328877,0.0001937338,0.0001422559,0.00025141,0.0004614173,0.8087056,0.04761576,0.1023609,0.02649376,0.0001009094],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02252946,0.0002792068,0.9646601,0.0002346744,0.00009341889,0.0003558385,0.001079655,0.001752659,0.009014952],"genre_scores_gemma":[0.49863,0.0005240998,0.4822893,0.0001332282,0.00009297261,0.0008609987,0.00251772,0.0005091499,0.01444252],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01285506,"threshold_uncertainty_score":0.04300445,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1976677479","doi":"10.1007/s10772-015-9276-6","title":"Feature selection for robust automatic speech recognition: a temporal offset approach","year":2015,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Speech recognition; Offset (computer science); Pattern recognition (psychology); Mel-frequency cepstrum; Feature selection; Artificial intelligence; Noise (video); Selection (genetic algorithm); Feature (linguistics); Feature extraction","authors":[{"name":"Ludovic Trottier","is_ca":true},{"name":"Philippe Giguère","is_ca":true},{"name":"Brahim Chaib-draa","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05480987488323085,"gpt":0.2838900785927865,"spread":0.2290802037095557,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005744324,0.0005721557,0.0008006396,0.0006603738,0.0003788589,0.0005704214,0.0005883424,0.0004203437,0.002293342],"category_scores_gemma":[0.001339682,0.0002363014,0.0007345921,0.0008635893,0.0002476563,0.0006228049,0.0005830406,0.0006450554,0.0008628293],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002076739,"about_ca_system_score_gemma":0.0006517355,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001546012,"about_ca_topic_score_gemma":0.002119605,"domain_scores_codex":[0.9996305,0.00006847889,0.0000286229,0.00007928431,0.0001384445,0.00005469796],"domain_scores_gemma":[0.9995184,0.0001839707,0.00004084207,0.00006587406,0.00016903,0.00002180278],"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":[0.0005947057,0.0001650101,0.001106233,0.0001153135,0.00009550109,0.0001431668,0.00004367608,0.02226563,0.1478152,0.004022931,0.001963198,0.8216694],"study_design_scores_gemma":[0.00005414532,0.0004625075,0.00831192,0.00002451931,0.0001855012,0.000387765,0.00006756776,0.8821193,0.09584852,0.004802709,0.007682308,0.00005323379],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01740421,0.0004812525,0.9807582,0.00007095226,0.00006628854,0.00002769243,0.00008819967,0.0004875657,0.0006156943],"genre_scores_gemma":[0.4023228,0.0009724121,0.5879244,0.0001366715,0.00023277,0.0001901909,0.0009617,0.0004242281,0.006834802],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002293342,"threshold_uncertainty_score":0.007672012,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4318350603","doi":"10.1007/s10772-023-10018-z","title":"Plain-to-clear speech video conversion for enhanced intelligibility","year":2023,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"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 of Canada; Simon Fraser University","keywords":"Computer science; Intelligibility (philosophy); Speech recognition; Image warping; Perception; Artificial intelligence; Psychology","authors":[{"name":"Shubam Sachdeva","is_ca":true},{"name":"Haoyao Ruan","is_ca":true},{"name":"Ghassan Hamarneh","is_ca":true},{"name":"Dawn M. Behne","is_ca":false},{"name":"Allard Jongman","is_ca":false},{"name":"Joan A. Sereno","is_ca":false},{"name":"Yue Wang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01663494020198911,"gpt":0.3090252094865346,"spread":0.2923902692845454,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000312092,0.0004713788,0.0002024073,0.0003215855,0.000113651,0.0004072531,0.000276585,0.0003249571,0.003347678],"category_scores_gemma":[0.001635281,0.0001293201,0.0002235485,0.0001507162,0.0002461364,0.0004750279,0.000439867,0.0003738428,0.0005691994],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008682053,"about_ca_system_score_gemma":0.0001297799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002348436,"about_ca_topic_score_gemma":0.0003563656,"domain_scores_codex":[0.999858,0.00002959382,0.00001659018,0.00003206031,0.00004811542,0.00001559309],"domain_scores_gemma":[0.9993966,0.0002974033,0.00005322814,0.00007984922,0.0001315186,0.00004143653],"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":[0.000316948,0.00009190913,0.0004758523,0.0002129709,0.000011862,0.0001483763,0.0001023173,0.002112463,0.9423221,0.0004805354,0.0002976856,0.05342697],"study_design_scores_gemma":[0.00004966223,0.001111962,0.007865658,0.00003107048,0.0000511606,0.000544506,0.0001041044,0.02828211,0.9574602,0.0003678168,0.004098875,0.00003297732],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6876065,0.0006375097,0.30463,0.0001362415,0.0001645433,0.0003011719,0.0005445897,0.001512795,0.00446693],"genre_scores_gemma":[0.8086301,0.0004798068,0.1865517,0.0001196158,0.0000486987,0.0002438465,0.0004922712,0.0002604411,0.003173502],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003347678,"threshold_uncertainty_score":0.01119906,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3007770218","doi":"10.1007/s10772-020-09688-w","title":"Low-complexity disordered speech quality estimation","year":2020,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec en Outaouais; Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Speech recognition; Quality (philosophy); Estimation; Artificial intelligence","authors":[{"name":"Yousef S. Ettomi Ali","is_ca":true},{"name":"Vijay Parsa","is_ca":true},{"name":"Phillip Doyle","is_ca":true},{"name":"Soulaimane Berkane","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03829898257176356,"gpt":0.3238917484867665,"spread":0.2855927659150029,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003080721,0.0005743451,0.0004632145,0.0005150747,0.0001996889,0.0005302492,0.0003413421,0.0005006123,0.001629043],"category_scores_gemma":[0.001822897,0.0001909741,0.0002818502,0.0002908724,0.0001782526,0.0005095187,0.0004856849,0.0004572311,0.000622305],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000180588,"about_ca_system_score_gemma":0.0003832797,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002530591,"about_ca_topic_score_gemma":0.003266639,"domain_scores_codex":[0.9997092,0.00005274148,0.00002106279,0.00005697256,0.0001229491,0.00003698807],"domain_scores_gemma":[0.9994721,0.0002385015,0.00004182693,0.00006276058,0.0001556682,0.00002917377],"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":[0.002038263,0.0002420729,0.0106188,0.000424502,0.0001191312,0.0007118582,0.0001760769,0.04792586,0.3302895,0.002623079,0.001681666,0.6031492],"study_design_scores_gemma":[0.00004700071,0.0002748042,0.01978672,0.00002807242,0.00009004601,0.0009094312,0.00006670981,0.9063671,0.06910307,0.001209838,0.002078999,0.00003821095],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1755307,0.0006766398,0.8203096,0.0001368548,0.00007569479,0.00006132553,0.0003045927,0.0008887898,0.002015837],"genre_scores_gemma":[0.8397583,0.0004224525,0.1568683,0.00006888637,0.00005814832,0.00003509846,0.0006241169,0.0000829488,0.002081865],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002530591,"threshold_uncertainty_score":0.005449712,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2072245166","doi":"10.1007/s10772-005-2168-4","title":"Post Recognition Speech Localization","year":2005,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Phrase; Speech recognition; SIGNAL (programming language); Speech processing; Multilateration; Word (group theory); Artificial intelligence; Pattern recognition (psychology); Acoustics; Mathematics","authors":[{"name":"Sam Mavandadi","is_ca":true},{"name":"Parham Aarabi","is_ca":true},{"name":"Keyvan Mohajer","is_ca":false},{"name":"Maryam M. Shanechi","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01544005197725855,"gpt":0.2639430521250483,"spread":0.2485030001477898,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004161278,0.001573437,0.0008839445,0.001262604,0.0009813055,0.002220438,0.0008330683,0.001467887,0.0753638],"category_scores_gemma":[0.001022132,0.0004591483,0.0006218152,0.0007133078,0.0004145528,0.001321738,0.001197927,0.0009568498,0.07170521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004316439,"about_ca_system_score_gemma":0.0009685328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001664786,"about_ca_topic_score_gemma":0.003404635,"domain_scores_codex":[0.9993708,0.0000501901,0.00002719301,0.000211193,0.0002369277,0.0001037856],"domain_scores_gemma":[0.9992365,0.0001140534,0.00004125959,0.0002246511,0.0003360207,0.00004765528],"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":[0.0007466071,0.000129846,0.0008554319,0.0001888335,0.00003271453,0.0002793304,0.00007844881,0.000733297,0.4483379,0.002603237,0.01141822,0.5345961],"study_design_scores_gemma":[0.00005765078,0.0004553961,0.007499203,0.00005106285,0.0001119992,0.001560805,0.0001200626,0.02823733,0.8710956,0.001637397,0.08912019,0.000053336],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05919622,0.001329557,0.8359259,0.0006838277,0.001616219,0.0004616035,0.00311606,0.03532991,0.06234072],"genre_scores_gemma":[0.3623419,0.001183765,0.3520243,0.001295234,0.000779735,0.000535836,0.01050508,0.003369854,0.2679644],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0753638,"threshold_uncertainty_score":0.252117,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4378231186","doi":"10.1007/s10772-023-10030-3","title":"Mouth2Audio: intelligible audio synthesis from videos with distinctive vowel articulation","year":2023,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"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 of Canada; Simon Fraser University","keywords":"Computer science; Speech recognition; Formant; Spectrogram; Manner of articulation; Landmark; Vowel; Articulation (sociology); Artificial intelligence","authors":[{"name":"Saurabh Garg","is_ca":true},{"name":"Haoyao Ruan","is_ca":true},{"name":"Ghassan Hamarneh","is_ca":true},{"name":"Dawn M. Behne","is_ca":false},{"name":"Allard Jongman","is_ca":false},{"name":"Joan A. Sereno","is_ca":false},{"name":"Yue Wang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.009332505270161847,"gpt":0.2516490338928938,"spread":0.242316528622732,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003623043,0.0008194661,0.0004718798,0.0005269389,0.0001836145,0.0006000875,0.0004658747,0.000744897,0.01603915],"category_scores_gemma":[0.0009159148,0.0001815444,0.0002575834,0.0002890641,0.0001973786,0.000411289,0.0007350207,0.0003202604,0.002492446],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001244913,"about_ca_system_score_gemma":0.0001994901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000776972,"about_ca_topic_score_gemma":0.001874512,"domain_scores_codex":[0.9997992,0.00002995598,0.0000109117,0.00004622735,0.00008658168,0.00002711394],"domain_scores_gemma":[0.9997943,0.00009476554,0.000008249465,0.00002666899,0.00004875722,0.00002730961],"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":[0.003034633,0.0001252532,0.0008024006,0.0006529271,0.00007065848,0.0007508974,0.0001913971,0.005037567,0.5721171,0.001956093,0.01092339,0.4043376],"study_design_scores_gemma":[0.0008570378,0.001654393,0.007710631,0.0001278205,0.0001169011,0.00223728,0.0002910107,0.2062376,0.7202672,0.002150293,0.05821449,0.0001353723],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.239103,0.001944444,0.7051635,0.0003843819,0.001014264,0.0005244021,0.008740818,0.02363711,0.01948804],"genre_scores_gemma":[0.5264291,0.0008605495,0.4280856,0.0002526491,0.0003611635,0.0004702439,0.01274555,0.002854085,0.02794107],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01603915,"threshold_uncertainty_score":0.05365622,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2799838911","doi":"10.1007/s10772-018-9507-8","title":"Gain optimization for millimeter wave reflectarray antennas based on a phase gradient approach","year":2018,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Advanced Antenna and Metasurface Technologies","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Extremely high frequency; Linear phase; Bandwidth (computing); Phase (matter); Base station; Unit (ring theory); Antenna (radio); Millimeter; Electronic engineering; Telecommunications; Optics; Physics; Mathematics; Engineering","authors":[{"name":"Rania R. Elsharkawy","is_ca":false},{"name":"Moataza A. Hindy","is_ca":false},{"name":"Abdel-Razik Sebak","is_ca":true},{"name":"Adel Saleeb","is_ca":false},{"name":"El‐Sayed M. El‐Rabaie","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02695181452873003,"gpt":0.2978482421224721,"spread":0.2708964275937421,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001632105,0.0005299005,0.0003652324,0.0002121409,0.0001210489,0.0005291727,0.0003921491,0.0005266706,0.001812415],"category_scores_gemma":[0.0003592247,0.0002455775,0.0003603827,0.0002761205,0.0002198613,0.0004293022,0.0003586607,0.0003355778,0.0007097077],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002939361,"about_ca_system_score_gemma":0.0002683587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003795888,"about_ca_topic_score_gemma":0.0008228904,"domain_scores_codex":[0.9998922,0.00002444301,0.000002466239,0.00001177396,0.00005494009,0.00001406608],"domain_scores_gemma":[0.9999266,0.0000304624,0.00001176209,0.000007321672,0.00001976904,0.000004068569],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003606101,0.0001502394,0.0008614463,0.0002198036,0.00009134364,0.0001272518,0.0001524968,0.6242268,0.2052052,0.06346237,0.003053847,0.1020886],"study_design_scores_gemma":[0.0000240426,0.00007293138,0.0002414468,0.000007883052,0.00001290765,0.0000582045,0.00002436497,0.9812944,0.01339026,0.00289963,0.001961549,0.00001239338],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06757108,0.0003465695,0.9096383,0.0003487136,0.00005102296,0.00003716863,0.0000631616,0.0002719482,0.02167215],"genre_scores_gemma":[0.6599581,0.0005268766,0.3262611,0.0001690055,0.00005491295,0.0001265004,0.0001345092,0.000306101,0.01246289],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001812415,"threshold_uncertainty_score":0.006063163,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4388380244","doi":"10.1007/s10772-023-10059-4","title":"Attention-based factorized TDNN for a noise-robust and spoof-aware speaker verification system","year":2023,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Spoofing attack; Speech recognition; Speaker verification; Encoder; Speaker recognition; Artificial neural network; Context (archaeology); Mel-frequency cepstrum; Artificial intelligence; Word error rate; Frame (networking); Pattern recognition (psychology); Feature extraction; Telecommunications","authors":[{"name":"Zhor Benhafid","is_ca":false},{"name":"Sid‐Ahmed Selouani","is_ca":false},{"name":"Abderrahmane Amrouche","is_ca":false},{"name":"Mohammed Sidi Yakoub","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02756174976548047,"gpt":0.2720836184628326,"spread":0.2445218686973522,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005493155,0.0005609195,0.0006070452,0.0004133502,0.0004188452,0.000442681,0.0007791077,0.000672729,0.00277902],"category_scores_gemma":[0.0007316875,0.0002149396,0.000499081,0.000315154,0.0001971828,0.0006561039,0.0005208225,0.0006452064,0.001012621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004280411,"about_ca_system_score_gemma":0.0006929262,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009221364,"about_ca_topic_score_gemma":0.01299119,"domain_scores_codex":[0.9996701,0.00004534048,0.00002436888,0.0001097832,0.0000883696,0.00006203257],"domain_scores_gemma":[0.9996021,0.00008574382,0.00002374575,0.00003191801,0.0002336643,0.00002278973],"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":[0.0009929306,0.0001768036,0.001233626,0.0001276971,0.00008661102,0.0001439487,0.00006582738,0.02713189,0.1990796,0.0008085289,0.002787631,0.7673649],"study_design_scores_gemma":[0.00002391918,0.0002638889,0.002444819,0.00001994069,0.00009328317,0.0002567802,0.00002927809,0.9287469,0.0651812,0.000554322,0.0023512,0.00003443846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09631404,0.001448474,0.8951883,0.0002616114,0.0004662087,0.00009307338,0.0002778443,0.002987362,0.002962997],"genre_scores_gemma":[0.8156336,0.0006064271,0.1767054,0.0002514447,0.0001483577,0.00007733767,0.0004477671,0.0001069902,0.006022633],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009221364,"threshold_uncertainty_score":0.0183354,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3013233519","doi":"10.1007/s10772-020-09697-9","title":"Correction to: Low-complexity disordered speech quality estimation","year":2020,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec en Outaouais; Western University","funders":"","keywords":"Mistake; Spelling; Computer science; Estimation; Quality (philosophy); Speech recognition; Artificial intelligence; Linguistics; Epistemology; Philosophy; Law; Management","authors":[{"name":"Yousef S. Ettomi Ali","is_ca":true},{"name":"Vijay Parsa","is_ca":true},{"name":"Philip C. Doyle","is_ca":true},{"name":"Soulaimane Berkane","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03186906875116981,"gpt":0.3246419416956319,"spread":0.2927728729444621,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00154257,0.002105599,0.002779742,0.002583321,0.001927462,0.002263603,0.002684441,0.009685124,0.09592108],"category_scores_gemma":[0.03721905,0.001125141,0.001262261,0.001559298,0.001407355,0.001653823,0.00184551,0.007399202,0.05136156],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001327093,"about_ca_system_score_gemma":0.001210756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00397128,"about_ca_topic_score_gemma":0.006087271,"domain_scores_codex":[0.9979381,0.0002121498,0.0005721409,0.0003525108,0.0007189348,0.0002061697],"domain_scores_gemma":[0.9790101,0.005737016,0.001124506,0.002510876,0.01054705,0.001070508],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005757498,0.00005541102,0.0004694753,0.0007085121,0.00008299313,0.008456113,0.0001718418,0.0002956251,0.002489678,0.001473307,0.9194998,0.06572155],"study_design_scores_gemma":[0.0002666353,0.0002189858,0.00529659,0.0004435403,0.00009334177,0.01801421,0.0003233181,0.003642076,0.006873189,0.003381494,0.9612356,0.0002109886],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"other","genre_scores_codex":[0.001764047,0.001014748,0.007581469,0.0215666,0.9629441,0.00008497302,0.001232174,0.001990214,0.001821696],"genre_scores_gemma":[0.1815332,0.008291119,0.05987097,0.05233886,0.4162238,0.0007376591,0.006163382,0.00743884,0.2674021],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.09592108,"threshold_uncertainty_score":0.3208879,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}