{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007353013,0.00007674777,0.0001456931,0.0007287698,0.00005028043,0.00003401166,0.0003973041,0.0001121491,0.00002557982],"category_scores_gemma":[0.002349094,0.00005419412,0.00005654761,0.0004925544,0.0003041324,0.0001454881,0.00005972253,0.000284075,0.00001738224],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006487663,"about_ca_system_score_gemma":0.00005716615,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002830163,"about_ca_topic_score_gemma":0.000009572533,"domain_scores_codex":[0.9986894,0.0000678256,0.000533822,0.000157171,0.00040563,0.0001461408],"domain_scores_gemma":[0.9987127,0.0006202406,0.0002366755,0.0001198721,0.0002864556,0.00002410128],"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":[0.0001944077,0.00007029279,0.002063243,0.00001048761,0.000006745536,0.00009270065,0.0001892229,0.00007605443,0.4695612,0.006024675,0.00001974683,0.5216912],"study_design_scores_gemma":[0.000755692,0.0004291987,0.1097108,0.0007424982,0.00001340322,0.0005160797,0.003394016,0.02165585,0.7908584,0.07121021,0.0005009332,0.0002128703],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9802378,0.00002935293,0.0007697453,0.01832198,0.0004536317,0.0001189957,0.000003254059,0.00002929881,0.00003594884],"genre_scores_gemma":[0.9984431,0.0002052568,0.001145919,0.0001003014,0.00006431869,0.000004411637,3.405313e-7,0.000008024145,0.00002828127],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5214784,"threshold_uncertainty_score":0.2812255,"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005010103,0.0002125567,0.0003010458,0.001081935,0.0001147516,0.00009450901,0.001803405,0.0001840418,0.00001963136],"category_scores_gemma":[0.0002173918,0.0001842773,0.0001760311,0.0004119295,0.00009490371,0.000402276,0.0001912832,0.0005696425,0.00001267613],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001656651,"about_ca_system_score_gemma":0.00007356112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007028195,"about_ca_topic_score_gemma":0.000005220154,"domain_scores_codex":[0.9982154,0.00002099929,0.0005739097,0.0003499279,0.0004889745,0.0003508238],"domain_scores_gemma":[0.9983466,0.00007559275,0.0006120974,0.0002692269,0.0006050561,0.00009137434],"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":[0.0002244791,0.0004161251,0.0002428328,0.00001206974,0.0001562469,0.0002733892,0.0003227899,0.0002179268,0.002923743,0.007046491,0.0001137863,0.9880501],"study_design_scores_gemma":[0.002346186,0.003823652,0.000272209,0.0002342796,0.00002262945,0.004420347,0.0001863285,0.06356257,0.8689614,0.0542979,0.00146964,0.0004028611],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02016373,0.0001027608,0.9705269,0.00643887,0.001348155,0.0001839242,0.0000038078,0.0001731482,0.001058757],"genre_scores_gemma":[0.6815831,0.00001235386,0.3166243,0.0006905753,0.001034083,0.000006665142,0.000001235316,0.00001449504,0.00003319149],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9876472,"threshold_uncertainty_score":0.751461,"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004292779,0.0001855907,0.0002998471,0.001961638,0.0001399245,0.0001616804,0.001635514,0.0002893265,0.00003686498],"category_scores_gemma":[0.000126276,0.0001811924,0.00009894162,0.0005850838,0.0001718271,0.0007152167,0.0002582124,0.0003172701,0.00001713392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001462465,"about_ca_system_score_gemma":0.000112317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005169385,"about_ca_topic_score_gemma":0.00001773483,"domain_scores_codex":[0.998351,0.00002254734,0.0006107537,0.0003506267,0.0003809905,0.0002840398],"domain_scores_gemma":[0.9979399,0.0001014191,0.0004985461,0.0003198386,0.001046948,0.00009332455],"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":[0.000007004208,0.0001231248,0.0001360287,0.000002531811,0.00009459504,0.00004689145,0.00005417845,0.000008216472,0.0124059,0.006416903,0.0001269178,0.9805777],"study_design_scores_gemma":[0.002828685,0.0005963357,0.0001355603,0.0001708955,0.00009478653,0.02013234,0.00174169,0.0802945,0.5306677,0.1432375,0.2193181,0.0007819496],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06907795,0.0005206947,0.9171021,0.0121286,0.0005038129,0.0002632325,0.00001648506,0.0002263269,0.0001607926],"genre_scores_gemma":[0.09716064,0.0001463933,0.9016714,0.0004046099,0.0004856705,0.00002697522,0.000002737946,0.00001941761,0.00008218711],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9797958,"threshold_uncertainty_score":0.7388811,"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003403418,0.0001100327,0.0002146853,0.0007910791,0.00005773204,0.00009284325,0.001958717,0.0001325408,0.00006326356],"category_scores_gemma":[0.0001464567,0.00007338994,0.000118437,0.0004760518,0.0001060866,0.0006253475,0.000326587,0.0002121341,0.00001246393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001623066,"about_ca_system_score_gemma":0.00009590791,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004028304,"about_ca_topic_score_gemma":0.000004744246,"domain_scores_codex":[0.9986679,0.00002116327,0.0004721101,0.0001830467,0.00044745,0.0002083404],"domain_scores_gemma":[0.9983392,0.00006239722,0.0005911736,0.000226818,0.000726276,0.00005411714],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001049672,0.00003537931,0.002603303,0.000001250453,0.0002177368,0.0003530963,0.0000345632,0.0004843402,0.01329031,0.01223829,0.0002936297,0.9704376],"study_design_scores_gemma":[0.007631992,0.0008708109,0.002882,0.001993237,0.000323907,0.02738545,0.0003305343,0.2285494,0.296787,0.3300738,0.1012625,0.001909393],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05723243,0.0004774602,0.9231158,0.0179042,0.0009396946,0.00001999984,4.353813e-7,0.00005664142,0.0002532716],"genre_scores_gemma":[0.8751547,0.0001139885,0.1236587,0.0004564685,0.00048576,5.228364e-7,1.170346e-7,0.000007563188,0.0001221352],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9685282,"threshold_uncertainty_score":0.3639817,"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007838304,0.0002431253,0.0004055889,0.002311155,0.00007013221,0.00003606527,0.001231898,0.0004293287,0.002916629],"category_scores_gemma":[0.0003152348,0.0002355838,0.0001683749,0.0007212864,0.0002464298,0.0001759152,0.0003466299,0.001051164,0.001504222],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002325146,"about_ca_system_score_gemma":0.0001737823,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002476476,"about_ca_topic_score_gemma":0.0001221974,"domain_scores_codex":[0.9977152,0.0001015156,0.0008296167,0.0003896076,0.0004255398,0.0005385351],"domain_scores_gemma":[0.9972143,0.00008943929,0.0004746015,0.0003977989,0.00164476,0.0001791604],"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":[0.0006703621,0.0006261935,0.002903451,0.000006375495,0.000624051,0.003199083,0.001724036,6.875035e-7,0.07272698,0.001396111,0.002481866,0.9136408],"study_design_scores_gemma":[0.005328129,0.00336891,0.01362607,0.0003218182,0.0001551981,0.05178235,0.002192749,0.000107628,0.7535781,0.1346527,0.03387162,0.001014762],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9755401,0.000588168,0.001422055,0.001616315,0.00607961,0.0002557175,0.00004059232,0.0000761772,0.01438125],"genre_scores_gemma":[0.9501797,0.0001038357,0.04717435,0.0002264809,0.001111245,0.00001377874,0.000005508885,0.00005293866,0.001132136],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.912626,"threshold_uncertainty_score":0.9992732,"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007617463,0.00009741348,0.0001840328,0.0003180907,0.0001024407,0.0001891478,0.001221454,0.0001690245,0.0001030422],"category_scores_gemma":[0.002423296,0.0000897244,0.0001586447,0.0003002073,0.0005552167,0.0007305861,0.00007844502,0.0001977787,0.00002223911],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002941587,"about_ca_system_score_gemma":0.0001857637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001308077,"about_ca_topic_score_gemma":0.0003812228,"domain_scores_codex":[0.9984671,0.0000229182,0.0004869507,0.0001516523,0.0005958955,0.0002754898],"domain_scores_gemma":[0.9980708,0.0001945659,0.0003487528,0.0001163889,0.001211804,0.00005766744],"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":[0.0001645616,0.000365187,0.03523612,0.000007838581,0.0001589865,0.00004508757,0.0006926043,0.000001493985,0.0004484928,0.05277294,0.006762837,0.9033439],"study_design_scores_gemma":[0.0004756334,0.0001835807,0.0001996232,0.0000324295,0.00001288207,0.0001114142,0.002850471,0.000002255035,0.001073907,0.0762451,0.9187052,0.0001074954],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.947059,0.000311679,0.002403987,0.04063853,0.001403502,0.0003616072,0.00002963048,0.0001425004,0.007649566],"genre_scores_gemma":[0.986572,0.0001003989,0.009612439,0.0001971861,0.0006510587,0.00002375813,0.000004547552,0.00001325553,0.002825368],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9119424,"threshold_uncertainty_score":0.3658855,"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009445513,0.0001482891,0.0003471565,0.0008181737,0.00003536967,0.0000440769,0.001600742,0.0001734349,0.00006613276],"category_scores_gemma":[0.0004425246,0.0001196441,0.0002432143,0.0001976574,0.00008627564,0.0005924415,0.0001856827,0.0002442145,0.00001621596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001611736,"about_ca_system_score_gemma":0.0000802042,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002796408,"about_ca_topic_score_gemma":0.000002171513,"domain_scores_codex":[0.9981272,0.00004945345,0.0005737797,0.0001623588,0.0008202199,0.0002670286],"domain_scores_gemma":[0.9978858,0.0002610164,0.0006272923,0.0002275856,0.0009039968,0.00009431333],"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":[0.000356793,0.0001468851,0.009803661,0.00001355154,0.0003204619,0.00005033211,0.00008281356,0.000005714831,0.009412422,0.01187828,0.001266878,0.9666622],"study_design_scores_gemma":[0.004428855,0.001396549,0.003405634,0.0002439448,0.00007311768,0.004210714,0.00006969796,0.001658959,0.8930755,0.05262996,0.03845209,0.0003549669],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5369667,0.0005248546,0.4508267,0.007830136,0.002676678,0.0002733956,0.00002752642,0.00008328895,0.0007906384],"genre_scores_gemma":[0.9134395,0.00008644439,0.08590204,0.0001277947,0.0003498298,0.000008320448,0.000001938896,0.00001190316,0.00007228641],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9663072,"threshold_uncertainty_score":0.4878946,"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004106537,0.0001565417,0.0002470798,0.0007885654,0.00006152739,0.0001736732,0.001283558,0.0001796969,0.0001006429],"category_scores_gemma":[0.0001739134,0.0001453355,0.0001497814,0.0003233881,0.00005763377,0.0008721648,0.0001673869,0.0003411738,0.0001038064],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000304832,"about_ca_system_score_gemma":0.0001204269,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003923715,"about_ca_topic_score_gemma":0.000005374685,"domain_scores_codex":[0.9983411,0.00001776305,0.0005571211,0.0002816874,0.0005247849,0.000277486],"domain_scores_gemma":[0.9979651,0.00007982938,0.0006718137,0.000217328,0.001005975,0.00005997632],"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":[0.0001305783,0.0001402659,0.003251357,0.00002173128,0.0001914344,0.0001644078,0.00006805245,0.0001918572,0.08508002,0.005803675,0.001156738,0.9037999],"study_design_scores_gemma":[0.002491893,0.0004679186,0.0007582408,0.0003100605,0.00003008862,0.003129684,0.0002220877,0.002319719,0.7548128,0.2229509,0.01214352,0.0003630842],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.31563,0.0001470572,0.6699391,0.01071779,0.002856176,0.0001624076,0.000006287293,0.0001062189,0.0004349017],"genre_scores_gemma":[0.6106845,0.00008910765,0.3878233,0.0004658403,0.0006013368,0.000005322957,0.00001002086,0.00001995313,0.0003006628],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9034368,"threshold_uncertainty_score":0.592661,"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00114479,0.0001367471,0.0002413018,0.001161593,0.00004845099,0.00005633767,0.001699957,0.0001894709,0.00005109352],"category_scores_gemma":[0.0006574838,0.0001272801,0.00007851654,0.0004915168,0.0001094059,0.0006206023,0.0001314488,0.0005213214,0.00004806688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002603859,"about_ca_system_score_gemma":0.0002110992,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001069542,"about_ca_topic_score_gemma":0.00003316126,"domain_scores_codex":[0.9978483,0.0001400283,0.0005459419,0.0002618666,0.000957247,0.0002465714],"domain_scores_gemma":[0.9986126,0.00006654876,0.0004238038,0.0002775894,0.000541884,0.00007752316],"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":[0.0001533821,0.0005391436,0.04830107,0.000007736735,0.0001702291,0.004556858,0.002557755,0.001013584,0.07548686,0.01478624,0.002357905,0.8500692],"study_design_scores_gemma":[0.01460865,0.004730127,0.008594538,0.0005679797,0.000073362,0.0773701,0.01239037,0.07806627,0.6707118,0.09930039,0.03165881,0.001927572],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9808726,0.0006185736,0.01198083,0.002189975,0.0007693579,0.0001449216,0.000001842128,0.0001046804,0.003317189],"genre_scores_gemma":[0.9886299,0.00008061798,0.01083911,0.00007638238,0.0001765537,0.000005490743,0.000006141633,0.00001155988,0.0001742983],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8481417,"threshold_uncertainty_score":0.519033,"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009784137,0.000125606,0.0002240349,0.001131867,0.00007061364,0.0001009005,0.002636774,0.0001811855,0.00002335919],"category_scores_gemma":[0.0004036686,0.0001239397,0.0001001724,0.0005149069,0.0001311123,0.0006430299,0.0003118519,0.000444137,0.00001840441],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002800936,"about_ca_system_score_gemma":0.0001178464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001214093,"about_ca_topic_score_gemma":0.0001514704,"domain_scores_codex":[0.9984379,0.00001976218,0.0007086261,0.0001968709,0.0003530354,0.0002838098],"domain_scores_gemma":[0.9977721,0.0002104953,0.0005413421,0.0003738806,0.001041169,0.00006104348],"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":[0.00005627302,0.0001838109,0.002087892,0.000004965258,0.00004774866,0.0001554763,0.00007731113,0.00002594408,0.01245676,0.0005478512,0.0003701191,0.9839858],"study_design_scores_gemma":[0.004065647,0.0006125534,0.003050861,0.0004057752,0.0000279009,0.003770971,0.0007781519,0.002952202,0.8012758,0.1208937,0.06168814,0.0004783451],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2176394,0.0008595312,0.7684876,0.01130184,0.0008529912,0.0002478095,0.00003769718,0.0001088037,0.000464276],"genre_scores_gemma":[0.4639674,0.0001498496,0.5354713,0.0001704409,0.0001676499,0.00001342925,0.00002280025,0.000009461645,0.00002763141],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9835075,"threshold_uncertainty_score":0.5054114,"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007168286,0.0001860888,0.000253653,0.000691432,0.00009341835,0.0003371354,0.001062757,0.0002174476,0.000006165611],"category_scores_gemma":[0.0001044694,0.0001515288,0.00008855407,0.0005596077,0.0001165528,0.0003633589,0.0001831139,0.0005325325,0.00001378974],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003306469,"about_ca_system_score_gemma":0.0001530338,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002707528,"about_ca_topic_score_gemma":6.915044e-7,"domain_scores_codex":[0.9981214,0.0000541821,0.0005534857,0.0004137348,0.0005850908,0.0002720419],"domain_scores_gemma":[0.9988575,0.00009722728,0.0003443598,0.0002442301,0.0003841668,0.00007254264],"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":[0.00007512679,0.0003629213,0.003081065,0.0001068987,0.0001703039,0.00181036,0.0001015771,0.001459531,0.0676735,0.01587429,0.0003100168,0.9089744],"study_design_scores_gemma":[0.0007938203,0.0003802808,0.0004638853,0.0009936019,0.00003541955,0.004878587,0.0002668042,0.8793615,0.1079054,0.002731817,0.001899039,0.0002898348],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1226533,0.000971377,0.8706538,0.003152891,0.00141548,0.0001253074,0.00000257022,0.0002281899,0.000797124],"genre_scores_gemma":[0.6005708,0.00003296175,0.3989262,0.0001209828,0.0003100552,0.000003648445,0.000001557272,0.000008627851,0.00002511643],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9086846,"threshold_uncertainty_score":0.6179165,"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001020264,0.0001278046,0.0002140376,0.0005407439,0.000172164,0.0001108421,0.002210932,0.0001486557,0.00002015025],"category_scores_gemma":[0.0005681587,0.00009043097,0.0001226695,0.0003284289,0.0001104382,0.000343515,0.0004222135,0.0005680202,0.00009507399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008958462,"about_ca_system_score_gemma":0.0000574381,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003744574,"about_ca_topic_score_gemma":0.00001402943,"domain_scores_codex":[0.9983177,0.000113314,0.0005220455,0.0001922729,0.0006307104,0.0002239559],"domain_scores_gemma":[0.9983395,0.0001342863,0.0005779582,0.000303365,0.000585362,0.00005955364],"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":[0.0002357017,0.0002487753,0.01787568,0.000008288701,0.0005571417,0.0002564986,0.0004661209,0.0005704037,0.02606458,0.2707057,0.01723238,0.6657787],"study_design_scores_gemma":[0.00172188,0.001302117,0.005123965,0.0001363903,0.0000275207,0.003293004,0.0001441236,0.003039317,0.01393683,0.08650152,0.8844827,0.0002906403],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5561238,0.0004550967,0.3638945,0.0556067,0.01773783,0.0002116076,0.000003179053,0.0003906203,0.005576635],"genre_scores_gemma":[0.9933823,0.00003619267,0.004629279,0.0004045625,0.001208655,0.000003440711,0.000003529545,0.00000905379,0.0003229858],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8672503,"threshold_uncertainty_score":0.4108499,"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001607772,0.0001359134,0.0001848199,0.0007032868,0.00007295926,0.0001487625,0.000839095,0.0001377407,0.00001307065],"category_scores_gemma":[0.0001058536,0.000123372,0.00009113991,0.0002404257,0.00004943876,0.0005171514,0.00005980972,0.0002625061,0.000009907029],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002755107,"about_ca_system_score_gemma":0.0001516236,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001180403,"about_ca_topic_score_gemma":0.000007051632,"domain_scores_codex":[0.9987633,0.00001136462,0.0003872877,0.00022224,0.0004050071,0.0002108211],"domain_scores_gemma":[0.9983399,0.0001361166,0.0003942501,0.0001461619,0.000922932,0.00006067063],"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":[0.0000654914,0.0001471346,0.0001636273,0.000005954617,0.00006231922,0.00004357163,0.00005156305,0.01684603,0.3866087,0.0001388278,0.0005660632,0.5953008],"study_design_scores_gemma":[0.000829599,0.0003310569,0.0001607931,0.000110322,0.000006903643,0.000289596,0.0000188536,0.4941426,0.4959581,0.007905412,0.0001419032,0.0001048556],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0436263,0.00003741183,0.948161,0.007212384,0.000630215,0.0001503424,0.000009389947,0.00006966652,0.0001032801],"genre_scores_gemma":[0.5466498,0.00000561312,0.4527747,0.0003451043,0.0001923849,0.0000121359,0.000002231817,0.000007501819,0.00001052514],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5951959,"threshold_uncertainty_score":0.5030965,"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006347808,0.0001358599,0.0003172464,0.0007707799,0.0000368979,0.0001002556,0.001421367,0.0002136123,0.000002679181],"category_scores_gemma":[0.0002204865,0.000116282,0.00006436795,0.0002498435,0.0001315155,0.0004710948,0.0003722869,0.0002550818,0.00002140269],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002591072,"about_ca_system_score_gemma":0.0002626671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001348055,"about_ca_topic_score_gemma":0.00004823829,"domain_scores_codex":[0.9984827,0.00005883444,0.000523517,0.0002099214,0.0004955283,0.0002294776],"domain_scores_gemma":[0.9982297,0.00005271834,0.0004555621,0.0002464061,0.0008819017,0.0001337201],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"case_report","study_design_scores_codex":[0.0005429697,0.0004557042,0.1159052,0.00008733042,0.001387358,0.01712373,0.004302188,0.0008265605,0.04044711,0.4658716,0.005421596,0.3476287],"study_design_scores_gemma":[0.01712116,0.006441587,0.003907423,0.001317259,0.0002292002,0.3768311,0.01891128,0.03920465,0.1812623,0.205778,0.1464905,0.002505598],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8807015,0.002402867,0.1084328,0.001274626,0.005604409,0.0001698865,0.000007958247,0.0001781021,0.001227928],"genre_scores_gemma":[0.9503083,0.00003348065,0.04915652,0.00006335302,0.0003863409,0.000003933204,9.421356e-7,0.000007973013,0.00003917191],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3597073,"threshold_uncertainty_score":0.4741841,"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004644615,0.000122466,0.0002000022,0.0006878707,0.00006668804,0.0001377107,0.001558816,0.0001711224,0.000003315829],"category_scores_gemma":[0.0002821579,0.0001112749,0.0001180227,0.0002598654,0.00007200184,0.0004862243,0.0001820487,0.0003020821,0.000009263946],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001699755,"about_ca_system_score_gemma":0.0001353773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001062308,"about_ca_topic_score_gemma":0.00002069205,"domain_scores_codex":[0.9984344,0.00002508747,0.0006110314,0.0002169188,0.0004743726,0.0002382159],"domain_scores_gemma":[0.9983263,0.0001338185,0.0005516156,0.000222381,0.0007179693,0.00004792761],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002172857,0.0001318859,0.00287915,0.00004387751,0.0001577442,0.0007813558,0.0001214545,0.0002618278,0.2004986,0.2379392,0.002156347,0.5548112],"study_design_scores_gemma":[0.002884327,0.0006393311,0.002962797,0.0002124353,0.00002894144,0.008662566,0.0001039039,0.008816002,0.3578443,0.5881464,0.02925006,0.000448919],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4787377,0.0003436853,0.5062305,0.009362458,0.004172309,0.0002238346,0.00001043188,0.000168351,0.0007506863],"genre_scores_gemma":[0.8487534,0.000003724316,0.1499139,0.00006009822,0.001167821,0.000007031382,0.000005438988,0.000009709761,0.00007887012],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5543624,"threshold_uncertainty_score":0.4537659,"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003385924,0.000153921,0.0002215376,0.0008407919,0.00007117983,0.0002359557,0.001862505,0.0001398506,0.0001165906],"category_scores_gemma":[0.0003288907,0.0001362852,0.0001218258,0.0003331422,0.000076652,0.0008470313,0.0001413919,0.0002471309,0.00009086724],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001852664,"about_ca_system_score_gemma":0.0001999644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009399851,"about_ca_topic_score_gemma":0.000003485846,"domain_scores_codex":[0.9983395,0.00001361036,0.0005883451,0.0002322492,0.0005584691,0.0002677959],"domain_scores_gemma":[0.9975036,0.00009150636,0.0006195641,0.0002540952,0.00145893,0.00007226517],"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":[0.0000240296,0.0001320083,0.0005131642,0.00001137158,0.00006941082,0.00005756204,0.0000311925,0.0001682759,0.06267606,0.001928222,0.002663014,0.9317257],"study_design_scores_gemma":[0.001131041,0.0003147283,0.0002251339,0.0001203631,0.000009864285,0.0003994457,0.0000270508,0.01424452,0.9021384,0.07533997,0.005886765,0.0001626743],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09264034,0.0001390984,0.8716668,0.03384253,0.001144755,0.0002070724,0.000001950588,0.00009594494,0.000261524],"genre_scores_gemma":[0.4412776,0.00001397364,0.5578227,0.0005504243,0.0001851458,0.00002021676,0.000002498369,0.000008746184,0.0001187101],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.931563,"threshold_uncertainty_score":0.5557548,"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007611246,0.0001646503,0.0002782145,0.0005236366,0.0001357091,0.00001281928,0.0007221475,0.0002349052,0.0004281756],"category_scores_gemma":[0.001464566,0.0001270808,0.0002357132,0.0002824497,0.0001030704,0.0002002731,0.00008951272,0.000368727,0.00003584247],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002393644,"about_ca_system_score_gemma":0.0001197035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008019287,"about_ca_topic_score_gemma":0.00005747004,"domain_scores_codex":[0.998001,0.0001458145,0.0009819998,0.0001509466,0.0003908281,0.0003293647],"domain_scores_gemma":[0.9961044,0.0004071103,0.001042584,0.0001865765,0.00219075,0.00006860259],"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":[0.03032968,0.001657151,0.159654,0.0002200462,0.008431888,0.000401221,0.03081247,0.00002231899,0.1567574,0.3936338,0.08769663,0.1303835],"study_design_scores_gemma":[0.02323966,0.003662491,0.114513,0.002846188,0.001161877,0.01071031,0.2478224,0.001064815,0.1424898,0.007164588,0.4423462,0.002978694],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9647874,0.001683668,0.006009745,0.006168011,0.02062454,0.0002986248,0.0001171335,0.00006318595,0.0002476685],"genre_scores_gemma":[0.9971651,0.0002217225,0.0009774518,0.00005611339,0.0008951921,0.00002278118,0.00001279362,0.00002619972,0.0006226425],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3864692,"threshold_uncertainty_score":0.5182205,"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002680656,0.0001019249,0.0001553656,0.0008366195,0.0000742166,0.0001080664,0.00105641,0.0001107124,0.000008618798],"category_scores_gemma":[0.00006741563,0.00009828065,0.00005599725,0.0003684607,0.00007517279,0.001453207,0.0001066226,0.0002716154,0.00001082863],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001681935,"about_ca_system_score_gemma":0.0001631322,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007293851,"about_ca_topic_score_gemma":0.000001555451,"domain_scores_codex":[0.9987277,0.00001006172,0.0005319019,0.0001953624,0.0003497256,0.0001852395],"domain_scores_gemma":[0.9982734,0.00006933574,0.0004397698,0.0001315721,0.001042559,0.00004333982],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002940483,0.0001533926,0.005096209,0.00002115866,0.00007262567,0.00001245615,0.0002321196,0.03827256,0.02508502,0.003114206,0.001246985,0.9266639],"study_design_scores_gemma":[0.00260932,0.0003420718,0.004104342,0.0003299775,0.00001439374,0.002741729,0.0003598219,0.3225617,0.1705374,0.4917199,0.004282964,0.0003963289],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3467234,0.000149968,0.6461827,0.005808624,0.0006763263,0.0002163518,0.000001829669,0.00006470294,0.0001760612],"genre_scores_gemma":[0.7435564,0.00003962876,0.2558143,0.00007046564,0.0004121572,0.00005690014,0.000002119337,0.000006812242,0.00004132046],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9262675,"threshold_uncertainty_score":0.4007769,"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001758732,0.0001788937,0.0002851177,0.0006097078,0.0001210743,0.0002691734,0.003064629,0.0002158872,0.00004003519],"category_scores_gemma":[0.001458617,0.0001331601,0.0001234207,0.0003316636,0.0001186302,0.0009124519,0.0004910775,0.0005843984,0.000009031238],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001485099,"about_ca_system_score_gemma":0.000169448,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004634731,"about_ca_topic_score_gemma":0.00004322513,"domain_scores_codex":[0.9979442,0.0001254186,0.0007202434,0.0003586265,0.0005300653,0.0003214757],"domain_scores_gemma":[0.9974669,0.0005295207,0.0005971015,0.0004008489,0.000932588,0.00007300541],"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":[0.0001265677,0.00004855261,0.00228841,0.000002226445,0.00002841307,0.00006009173,0.0002114519,0.00003781358,0.1896797,0.0001829588,0.000104252,0.8072296],"study_design_scores_gemma":[0.001100486,0.0007593477,0.001331415,0.0002888394,0.00001353581,0.0005143685,0.0001297759,0.02553003,0.8920302,0.07592379,0.00220856,0.0001696986],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4530793,0.0002097115,0.5380644,0.00664218,0.001784836,0.00009775726,0.000002238221,0.00004119777,0.00007834695],"genre_scores_gemma":[0.3538692,0.00002176213,0.6446534,0.0004826743,0.0009185776,0.000006305458,8.693737e-7,0.00001142148,0.00003574164],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8070599,"threshold_uncertainty_score":0.5694894,"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000497671,0.0001045645,0.000203968,0.0005641246,0.00006947244,0.0001196884,0.001098662,0.0001053179,0.000006832442],"category_scores_gemma":[0.000462371,0.0000935503,0.00005269419,0.0002298916,0.00009360532,0.0004001347,0.0002557283,0.000316152,0.00002247835],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005023282,"about_ca_system_score_gemma":0.00004075106,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005125562,"about_ca_topic_score_gemma":0.00001825417,"domain_scores_codex":[0.998786,0.00005897107,0.0004408668,0.0001660229,0.0003744622,0.0001736701],"domain_scores_gemma":[0.9986984,0.0001484463,0.0003972089,0.0001650679,0.0005187172,0.00007219689],"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":[0.00008864605,0.0002542544,0.1941665,0.00001908277,0.0004751762,0.0004364357,0.0006681437,0.0006003429,0.0481122,0.3239417,0.005476837,0.4257607],"study_design_scores_gemma":[0.004566984,0.001453525,0.06164915,0.000401346,0.00003878068,0.006422997,0.0004182909,0.02675566,0.03694387,0.2990374,0.5615426,0.0007693489],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8241432,0.000300736,0.1547632,0.0171497,0.002771141,0.00007988347,0.000004446675,0.0001579486,0.0006297681],"genre_scores_gemma":[0.9671596,0.0001497654,0.03190873,0.0002449859,0.0004052151,0.000002305037,0.000007747974,0.000007777478,0.0001138264],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5560658,"threshold_uncertainty_score":0.381487,"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008538262,0.0001850346,0.0003185566,0.00124632,0.00006445705,0.0001784077,0.001433479,0.0003029805,0.00003902267],"category_scores_gemma":[0.0007487368,0.0001653172,0.0001845884,0.0006621903,0.00007793523,0.0007403006,0.0001313994,0.0004193358,0.00005174612],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002686353,"about_ca_system_score_gemma":0.0002831256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000767473,"about_ca_topic_score_gemma":0.00001098947,"domain_scores_codex":[0.9982233,0.00005618457,0.0004954202,0.0002819191,0.0006975232,0.0002456539],"domain_scores_gemma":[0.9966002,0.00009577879,0.0006075789,0.0002016444,0.002363004,0.0001317896],"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":[0.0000563809,0.0001914351,0.0006021734,0.000009706159,0.0001732096,0.00008819615,0.0000622904,0.00001268216,0.0003790312,0.001292437,0.02712698,0.9700055],"study_design_scores_gemma":[0.009997305,0.002418492,0.0004220284,0.0004949339,0.000184668,0.07194811,0.001798494,0.3562468,0.1450534,0.2188795,0.1911398,0.001416543],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05682033,0.0002124956,0.8928671,0.04373778,0.002916737,0.0004592279,0.00003179001,0.0004922154,0.002462263],"genre_scores_gemma":[0.04264664,0.00002109129,0.9559304,0.0003404811,0.0006254974,0.0000250758,0.00002006951,0.00001773979,0.0003729925],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9685889,"threshold_uncertainty_score":0.674144,"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007953327,0.0001475728,0.0002635168,0.001380326,0.00008301856,0.0001295386,0.002452308,0.0001644591,0.00003075909],"category_scores_gemma":[0.001073389,0.0001362628,0.0001453247,0.001015601,0.00008439102,0.0004707624,0.0004839892,0.0003152281,0.0002162524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001868041,"about_ca_system_score_gemma":0.0001451774,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003745694,"about_ca_topic_score_gemma":0.000004239607,"domain_scores_codex":[0.9982079,0.00001845902,0.0005590857,0.0003309869,0.0005562542,0.0003273475],"domain_scores_gemma":[0.9978582,0.0002001837,0.0003706813,0.0002991488,0.001166495,0.0001053289],"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":[0.0002075062,0.00007182764,0.0004942792,0.00001793613,0.0001108308,0.0002947275,0.0002253805,0.00008585022,0.2050649,0.003853953,0.005778504,0.7837943],"study_design_scores_gemma":[0.0006242272,0.0003638425,0.0001409444,0.00009390997,0.000005574655,0.0003698582,0.0001422104,0.0006171866,0.9238337,0.04009324,0.03357654,0.0001387922],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5341864,0.00006816676,0.4323524,0.03021704,0.002298436,0.0001942858,0.000006658061,0.0003185687,0.0003580385],"genre_scores_gemma":[0.7956652,0.00007413237,0.2028391,0.0006891958,0.0003644809,0.000006970185,0.000002618371,0.00001575364,0.000342549],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7836555,"threshold_uncertainty_score":0.5556637,"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003742287,0.0001498065,0.0002833465,0.0003937859,0.00006488679,0.0001750045,0.002476576,0.0001356441,0.00005842766],"category_scores_gemma":[0.0008634717,0.0001381251,0.0001184637,0.0005914504,0.0001431242,0.0008244732,0.000371155,0.000457958,0.00006602907],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000968486,"about_ca_system_score_gemma":0.0001555539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008335094,"about_ca_topic_score_gemma":0.00000589792,"domain_scores_codex":[0.9980585,0.0000392794,0.0007081537,0.0002600418,0.0007167226,0.000217327],"domain_scores_gemma":[0.9981275,0.00005839833,0.0007148446,0.0002227429,0.0007657852,0.0001107739],"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":[0.0000535787,0.0001116044,0.002049382,0.00001812475,0.00007450658,0.0003286507,0.0002263112,0.0001017286,0.03381133,0.01408133,0.0006012202,0.9485422],"study_design_scores_gemma":[0.001408574,0.0002779364,0.002087394,0.00009879944,0.00001075205,0.001124642,0.0001662068,0.005885327,0.7979011,0.1873441,0.003397375,0.0002977869],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3196304,0.0001511932,0.5851815,0.09358549,0.0006784578,0.00006573751,0.000004028248,0.0001955383,0.0005076582],"genre_scores_gemma":[0.6732583,0.00002643279,0.3255761,0.0008802302,0.0002340145,9.978269e-7,0.000001805104,0.000007257375,0.00001484425],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9482445,"threshold_uncertainty_score":0.5632581,"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000407607,0.0001323105,0.0001935006,0.001339902,0.0000530575,0.0001267293,0.001475883,0.0001877424,0.0003910308],"category_scores_gemma":[0.000483252,0.0001236287,0.0001256095,0.0004534543,0.00007490777,0.0009103169,0.0001532567,0.0002962497,0.000461404],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000179689,"about_ca_system_score_gemma":0.0000979588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007665699,"about_ca_topic_score_gemma":0.00001992591,"domain_scores_codex":[0.9983664,0.00003853336,0.0005971957,0.0002004393,0.0006096445,0.000187755],"domain_scores_gemma":[0.9972453,0.00007201037,0.0004712348,0.0002148298,0.001925251,0.00007143352],"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":[0.0000203372,0.0001013127,0.000224182,0.00000140054,0.00006524965,0.0002222957,0.00004449047,0.00000896611,0.005128833,0.003166239,0.000931942,0.9900848],"study_design_scores_gemma":[0.001843537,0.0004241313,0.0004187759,0.0001895083,0.00003447391,0.01627783,0.0002580335,0.008722926,0.7235506,0.0641517,0.183653,0.0004754754],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1805073,0.0003513648,0.710793,0.09687752,0.003174028,0.0001944842,0.00002148336,0.000453489,0.007627262],"genre_scores_gemma":[0.5422353,0.0002896435,0.4538623,0.002316343,0.0009797737,0.00000412475,0.000009248794,0.00001809226,0.0002852451],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9896093,"threshold_uncertainty_score":0.5930569,"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002850462,0.0001508924,0.0002441568,0.001001964,0.00007070367,0.0001680979,0.001462999,0.0001207214,0.00003973979],"category_scores_gemma":[0.0004870816,0.0001187052,0.0000817923,0.0009942516,0.0001155443,0.0006971493,0.0002668372,0.0003153616,0.0001476147],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001441806,"about_ca_system_score_gemma":0.0001196487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002302739,"about_ca_topic_score_gemma":0.00002149561,"domain_scores_codex":[0.9983831,0.00002504579,0.0004421145,0.0002660478,0.0006442301,0.0002394323],"domain_scores_gemma":[0.9981897,0.0002344537,0.0005034496,0.0002493322,0.0007569366,0.00006616097],"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":[0.0001587786,0.0001157999,0.01938266,0.000006945577,0.0005636278,0.001914331,0.0005799265,0.000857681,0.04748267,0.002747024,0.001304133,0.9248864],"study_design_scores_gemma":[0.0005555872,0.0001659148,0.009741265,0.0002847901,0.00003345281,0.0007839574,0.0003086752,0.003262282,0.9078937,0.07458425,0.002147195,0.0002389387],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6299495,0.0001052573,0.3529836,0.01555821,0.000686691,0.00006583567,0.000008379939,0.0002979674,0.0003444795],"genre_scores_gemma":[0.9127269,0.00004541699,0.08674057,0.0001129681,0.0002553866,0.000006857828,0.000002904837,0.00001296673,0.00009603897],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9246475,"threshold_uncertainty_score":0.4840658,"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002047626,0.0001701495,0.0002469528,0.001005632,0.00004155874,0.00002113817,0.0004563137,0.0001898978,0.00002743408],"category_scores_gemma":[0.0002805197,0.0001441889,0.000119232,0.0002780184,0.0001799108,0.0001235235,0.00002735565,0.0002756362,0.00000462663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001563199,"about_ca_system_score_gemma":0.00002274681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":5.613073e-7,"about_ca_topic_score_gemma":0.000001267346,"domain_scores_codex":[0.9989449,0.000009025289,0.0004052865,0.0001594302,0.0002463456,0.0002349652],"domain_scores_gemma":[0.9989236,0.00004847876,0.0001827786,0.0001875988,0.000620247,0.00003730584],"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":[0.001276787,0.0007951572,0.0001176909,0.0000531131,0.0007826992,0.0002419285,0.0002404026,0.1962851,0.3956676,0.004520303,0.002663927,0.3973554],"study_design_scores_gemma":[0.002581525,0.001435306,0.000004311921,0.00009988216,0.00003278741,0.000287932,0.0002377358,0.6516125,0.3320474,0.003457292,0.007990222,0.0002131427],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1018325,0.0001852762,0.8945724,0.001379695,0.001020255,0.0001824761,0.00002372778,0.0003231747,0.0004805259],"genre_scores_gemma":[0.6582069,0.00008238435,0.3413807,0.00009220578,0.0001691733,0.00001184309,0.000008274299,0.00002479866,0.00002376287],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5563744,"threshold_uncertainty_score":0.5879853,"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004611604,0.0001206776,0.0002165888,0.001173589,0.00007047164,0.0001216444,0.0008685119,0.0001488878,0.00001924782],"category_scores_gemma":[0.0002633495,0.0001099089,0.0001263124,0.0004724281,0.00006282541,0.0002712327,0.00008216001,0.0001566538,0.00005577456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000140732,"about_ca_system_score_gemma":0.00009189431,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000533599,"about_ca_topic_score_gemma":0.000003883126,"domain_scores_codex":[0.9986997,0.00002797986,0.000464781,0.0002281562,0.0004041685,0.0001751861],"domain_scores_gemma":[0.9982157,0.0001934228,0.0004020664,0.0002019441,0.0009264555,0.00006036548],"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":[0.0002484701,0.0001948172,0.01023126,0.0001068065,0.0004986131,0.0005348059,0.000126955,0.0001115598,0.04920394,0.04741565,0.003613088,0.887714],"study_design_scores_gemma":[0.01849742,0.001511048,0.05176797,0.002071849,0.0002695077,0.007869053,0.003746283,0.5049473,0.2740705,0.03552781,0.09776163,0.001959623],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2943845,0.00005611041,0.6832986,0.01892824,0.002364073,0.0002768076,0.00003792006,0.0004654143,0.0001883597],"genre_scores_gemma":[0.9213557,0.0000366927,0.07812569,0.0001034307,0.0001934659,0.00002199406,0.00001199674,0.00001424553,0.0001368013],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8857544,"threshold_uncertainty_score":0.4481954,"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003652135,0.0001440456,0.0002577172,0.0004902278,0.00007114357,0.0001779779,0.001882966,0.0001027768,0.00004435356],"category_scores_gemma":[0.0015773,0.0001377907,0.0001016817,0.0007889681,0.00007828502,0.0006954095,0.0003297931,0.0004449971,0.00009304528],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001424872,"about_ca_system_score_gemma":0.0001448293,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002110914,"about_ca_topic_score_gemma":0.00001807,"domain_scores_codex":[0.9981626,0.00003897941,0.0006514487,0.0002741241,0.0006657485,0.0002070913],"domain_scores_gemma":[0.9981924,0.00007581103,0.0005587066,0.0002007264,0.0008367049,0.0001356286],"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":[0.00007487811,0.00008723344,0.001997113,0.00001010808,0.00005008824,0.000145861,0.0002796671,0.0003775801,0.03454795,0.003075128,0.003348662,0.9560058],"study_design_scores_gemma":[0.001344439,0.0005561989,0.005543935,0.0002073346,0.00001310518,0.001438536,0.0002695248,0.01839743,0.8956306,0.07045826,0.005733466,0.0004071767],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2489387,0.00006091339,0.6742802,0.0733834,0.002566144,0.00008212612,0.000002643982,0.0001912789,0.0004946509],"genre_scores_gemma":[0.7198383,0.00001265925,0.2785529,0.001244507,0.0002987486,0.000001728181,0.00000178128,0.000007925086,0.00004148541],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9555985,"threshold_uncertainty_score":0.5618944,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}