{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":1408,"total_is_capped":false,"direct_labels_cover":2,"predictions_cover":1408,"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":"3f881fb6d4c4","filters":{"topic":"Speech and Audio Processing"}},"results":[{"id":"W2112739286","doi":"10.1109/icassp.2013.6639347","title":"Deep convolutional neural networks for LVCSR","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":1070,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Convolutional neural network; Pooling; Artificial intelligence; Speech recognition; Focus (optics); Vocabulary; Feature (linguistics); Deep neural networks; Artificial neural network; Pattern recognition (psychology)","authors":[{"name":"Tara N. Sainath","is_ca":false},{"name":"Abdelrahman Mohamed","is_ca":true},{"name":"Brian Kingsbury","is_ca":false},{"name":"Bhuvana Ramabhadran","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01317611183544196,"gpt":0.2283655173825606,"spread":0.2151894055471187,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000706135,0.0006787954,0.0004663835,0.000446165,0.0002609138,0.0006365124,0.0006445991,0.0006788456,0.007154326],"category_scores_gemma":[0.001788571,0.0002940558,0.0004010272,0.0007817377,0.0002348472,0.0008133929,0.0004637369,0.001187491,0.002231268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008486422,"about_ca_system_score_gemma":0.0007850384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01048977,"about_ca_topic_score_gemma":0.01589982,"domain_scores_codex":[0.9996916,0.00005837731,0.00001979167,0.00007717498,0.0001205008,0.0000325977],"domain_scores_gemma":[0.9995717,0.0001927324,0.00003861947,0.00006403483,0.0001189458,0.000013928],"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":[0.0001620965,0.00006183166,0.001348672,0.0002767598,0.0000878722,0.0001251242,0.00004645986,0.2000703,0.03197932,0.01615645,0.02077486,0.7289102],"study_design_scores_gemma":[0.00001529478,0.00005346682,0.001546493,0.00005508114,0.00002288795,0.00007461795,0.00001949167,0.9630255,0.01076705,0.01090359,0.01349001,0.00002657242],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0192983,0.006190907,0.9577954,0.0008113713,0.0003241138,0.0000829026,0.001391464,0.004557498,0.009548021],"genre_scores_gemma":[0.4612855,0.004437977,0.5107877,0.0004934167,0.0003615009,0.0002623274,0.005046591,0.0004737134,0.01685129],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01048977,"threshold_uncertainty_score":0.02393359,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2061074721","doi":"10.1007/978-3-540-78612-2","title":"Microphone Array Signal Processing","year":2008,"lang":"en","type":"book","venue":"Springer topics in signal processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":901,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Signal processing; Microphone array; Computer science; SIGNAL (programming language); Array processing; Acoustics; Speech recognition; Microphone; Digital signal processing; Physics; Telecommunications; Computer hardware","authors":[{"name":"Jacob Benesty","is_ca":true},{"name":"Jingdong Chen","is_ca":false},{"name":"Yiteng Huang","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02083511194856587,"gpt":0.243817188674715,"spread":0.2229820767261491,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002765033,0.001361175,0.0009009705,0.0009697912,0.0003205243,0.001181244,0.00091687,0.001225376,0.07211771],"category_scores_gemma":[0.0006664689,0.0004372208,0.0004666699,0.001146981,0.0004031017,0.001026576,0.0008714604,0.00110724,0.08699395],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001966471,"about_ca_system_score_gemma":0.0002769228,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003959049,"about_ca_topic_score_gemma":0.0009683241,"domain_scores_codex":[0.999603,0.00002984978,0.0000160319,0.00007983891,0.0002530125,0.00001823887],"domain_scores_gemma":[0.9997213,0.00005913376,0.0000101294,0.00005705808,0.0001330525,0.00001932058],"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":[0.00006206286,0.00003016064,0.00008129864,0.0003276833,0.00003149609,0.00011796,0.00004229665,0.001640317,0.04769396,0.00667395,0.0901156,0.8531832],"study_design_scores_gemma":[0.00001492111,0.0001630493,0.001086096,0.0001328947,0.00005490614,0.001710771,0.00005351815,0.01871721,0.03982051,0.009406404,0.9287836,0.00005623661],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.001551801,0.01905277,0.8321787,0.0006049071,0.003758804,0.00009804673,0.0006231202,0.004839748,0.1372921],"genre_scores_gemma":[0.01861655,0.01717636,0.2092274,0.0008154477,0.002034877,0.0001336963,0.002041275,0.0009686807,0.7489856],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.07211771,"threshold_uncertainty_score":0.2412578,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2113131123","doi":"10.1109/tsa.2005.860851","title":"New insights into the noise reduction Wiener filter","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":694,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Wiener filter; Noise reduction; Intelligibility (philosophy); Wiener deconvolution; Filter (signal processing); Noise (video); Speech recognition; Distortion (music); Reduction (mathematics); Computer science; Noise measurement; Mathematics; Speech enhancement; Salt-and-pepper noise; Algorithm; Median filter; Artificial intelligence; Telecommunications; Bandwidth (computing); Computer vision; Amplifier","authors":[{"name":"Jingdong Chen","is_ca":false},{"name":"Jacob Benesty","is_ca":true},{"name":"Yiteng Huang","is_ca":false},{"name":"Simon Doclo","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.007253780499054257,"gpt":0.2282763972815397,"spread":0.2210226167824855,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001031712,0.0008948487,0.0009019368,0.001044786,0.0003818623,0.001488051,0.0007520699,0.001713855,0.004814909],"category_scores_gemma":[0.003236559,0.0004119398,0.0007149956,0.0006749986,0.001245161,0.00220983,0.001105304,0.001653248,0.001236086],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006195735,"about_ca_system_score_gemma":0.0006456757,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00107526,"about_ca_topic_score_gemma":0.0006616306,"domain_scores_codex":[0.9992728,0.0001635003,0.00003379488,0.0001249686,0.0003373885,0.00006755937],"domain_scores_gemma":[0.9990539,0.0005108244,0.0001023673,0.00009502665,0.0001981708,0.00003965481],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007476998,0.00005276663,0.000500078,0.0002999859,0.00004875399,0.0002620957,0.0002629966,0.1023458,0.02211879,0.8036198,0.002668971,0.06774503],"study_design_scores_gemma":[0.00001351977,0.00009859815,0.000488607,0.00007446413,0.00002281547,0.0003903882,0.00006191051,0.6853681,0.004437576,0.29134,0.01765646,0.00004757648],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009292799,0.003838229,0.9670358,0.0006952717,0.000281028,0.00002244739,0.00005019082,0.0001465156,0.01863781],"genre_scores_gemma":[0.5317295,0.01542918,0.3992212,0.001082824,0.00171336,0.0001732048,0.0002187421,0.0003711094,0.05006091],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004814909,"threshold_uncertainty_score":0.0161075,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3163652268","doi":"10.1109/icassp39728.2021.9413901","title":"Attention Is All You Need In Speech Separation","year":2021,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":613,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Recurrent neural network; Transformer; Computation; Artificial intelligence; Upsampling; Speech recognition; Artificial neural network; Algorithm; Engineering","authors":[{"name":"Cem Subakan","is_ca":true},{"name":"Mirco Ravanelli","is_ca":true},{"name":"Samuele Cornell","is_ca":false},{"name":"Mirko Bronzi","is_ca":true},{"name":"Jianyuan Zhong","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02245504284799524,"gpt":0.2955110363863656,"spread":0.2730559935383703,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001176412,0.001100404,0.0007726692,0.0004970521,0.0007349776,0.001808155,0.0008183386,0.001809428,0.007157846],"category_scores_gemma":[0.005606715,0.0004758198,0.0005543053,0.000696154,0.001296814,0.004762153,0.002353271,0.002997963,0.004388543],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004911974,"about_ca_system_score_gemma":0.0007788827,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003444873,"about_ca_topic_score_gemma":0.004890559,"domain_scores_codex":[0.9991783,0.0002069611,0.00004189475,0.0002667262,0.0002047482,0.0001012593],"domain_scores_gemma":[0.9985834,0.0007178515,0.00009157679,0.0002418719,0.0002720028,0.00009329583],"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":[0.0009895031,0.0001020761,0.002245706,0.0005705055,0.0001612421,0.0003521984,0.0005145324,0.01706933,0.05014193,0.02123584,0.02820212,0.878415],"study_design_scores_gemma":[0.0001776115,0.0006394172,0.009242048,0.0004196607,0.0004670309,0.001438556,0.001087626,0.428744,0.1036781,0.3194216,0.1344262,0.0002582313],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05327879,0.01215449,0.8931264,0.01396808,0.002058591,0.00009072117,0.0005076876,0.005205812,0.01960946],"genre_scores_gemma":[0.701903,0.01004447,0.2468112,0.007749643,0.002491011,0.0001201511,0.001628203,0.00162655,0.02762575],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007157846,"threshold_uncertainty_score":0.02394533,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2104422351","doi":"10.1109/iros.2003.1248813","title":"Robust sound source localization using a microphone array on a mobile robot","year":2004,"lang":"en","type":"preprint","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":387,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Microphone array; Computer science; Mobile robot; Robot; Acoustic source localization; Sound localization; Omnidirectional antenna; Computer vision; Microphone; Acoustics; Sound (geography); Artificial intelligence; Antenna (radio); Sound pressure","authors":[{"name":"Jean-Marc Valin","is_ca":true},{"name":"François Michaud","is_ca":true},{"name":"Jean Rouat","is_ca":true},{"name":"Dominic Létourneau","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04378815510899821,"gpt":0.2633118744958775,"spread":0.2195237193868793,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002084394,0.0007657486,0.0007471278,0.0003695933,0.0001999088,0.0004271084,0.0007180831,0.001150821,0.002373306],"category_scores_gemma":[0.0008690018,0.0003554359,0.0004142723,0.0002953133,0.0003402297,0.000797347,0.0006408225,0.0005239929,0.002007641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00013107,"about_ca_system_score_gemma":0.0002134955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004224301,"about_ca_topic_score_gemma":0.0005095636,"domain_scores_codex":[0.9996425,0.00008334516,0.00001429617,0.00008946646,0.0001443441,0.0000260766],"domain_scores_gemma":[0.99966,0.0001152135,0.00004580125,0.00004361226,0.0001118377,0.00002359036],"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":[0.0004695269,0.00005487668,0.0006387852,0.0002244453,0.00009064971,0.0003998237,0.00013377,0.02348757,0.7633188,0.001410326,0.00163002,0.2081414],"study_design_scores_gemma":[0.0001916602,0.001691824,0.004129536,0.0000696488,0.0001938543,0.002892886,0.0001682954,0.5738823,0.3901547,0.00314687,0.02326629,0.0002121327],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03293267,0.0004546392,0.962441,0.000104404,0.0001251092,0.00004096092,0.00005248984,0.002190955,0.001657822],"genre_scores_gemma":[0.2421945,0.0004905299,0.7530288,0.0001326432,0.0001499694,0.0001116335,0.0001120462,0.00008945046,0.003690399],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002373306,"threshold_uncertainty_score":0.007939517,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2116635162","doi":"10.1155/asp/2006/26503","title":"Time Delay Estimation in Room Acoustic Environments: An Overview","year":2006,"lang":"en","type":"article","venue":"EURASIP Journal on Advances in Signal Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":368,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Reverberation; Computer science; Sonar; Noise (video); Identification (biology); Ranging; Channel (broadcasting); Radar; Estimation; Acoustics; Telecommunications; Speech recognition; Real-time computing; Artificial intelligence; Engineering; Systems engineering","authors":[{"name":"Jingdong Chen","is_ca":false},{"name":"Jacob Benesty","is_ca":true},{"name":"Yiteng Huang","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01511334718833428,"gpt":0.2898631340188438,"spread":0.2747497868305095,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006951129,0.0009266337,0.0009312957,0.001648237,0.0002390223,0.001499834,0.000705003,0.001613799,0.00157438],"category_scores_gemma":[0.001262734,0.0006036337,0.0005550496,0.002670253,0.000517578,0.002133636,0.0005955299,0.001123147,0.001871405],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003027745,"about_ca_system_score_gemma":0.0004238761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001744356,"about_ca_topic_score_gemma":0.0008706934,"domain_scores_codex":[0.9995702,0.00007707536,0.00004777838,0.0001061739,0.0001754852,0.00002329141],"domain_scores_gemma":[0.9993303,0.0003771824,0.00004043415,0.00003531866,0.0001929935,0.00002381694],"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":[0.0001866448,0.0001177554,0.001393516,0.003211495,0.0001338775,0.0003577524,0.0001966478,0.04549277,0.01839387,0.02711871,0.008183896,0.8952131],"study_design_scores_gemma":[0.00007250719,0.001043336,0.005542036,0.0008970266,0.0003382105,0.004389436,0.0003678768,0.5742239,0.03069821,0.0508928,0.3311906,0.0003440119],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.004257919,0.2053614,0.7846382,0.0003377268,0.0004635631,0.0000472045,0.00007479068,0.000426154,0.004393076],"genre_scores_gemma":[0.09079365,0.4795448,0.4158785,0.0003941263,0.004376875,0.0001671008,0.000496493,0.0001967641,0.008151685],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.001744356,"threshold_uncertainty_score":0.005266786,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2103636088","doi":"10.1109/lsp.2003.813679","title":"Speech probability distribution","year":2003,"lang":"en","type":"article","venue":"IEEE Signal Processing Letters","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":298,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Decorrelation; Generalized gamma distribution; Distribution (mathematics); Marginal distribution; Mathematics; Generalized integer gamma distribution; Speech processing; Speech recognition; Probability distribution; Multivariate statistics; Gaussian; Gamma distribution; Multivariate normal distribution; Joint probability distribution; Discrete cosine transform; Computer science; Random variable; Statistics; Artificial intelligence; Mathematical analysis; Physics","authors":[{"name":"Saeed Gazor","is_ca":true},{"name":"Wei Zhang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01804183266396142,"gpt":0.2324819737331489,"spread":0.2144401410691875,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001096615,0.0006513598,0.0006450524,0.001471011,0.0005070217,0.001674234,0.0009298908,0.001034955,0.009285551],"category_scores_gemma":[0.007683611,0.0002568445,0.0006118069,0.001102773,0.001135003,0.001954084,0.000832328,0.0009036603,0.003853337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007090711,"about_ca_system_score_gemma":0.0006507108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002280955,"about_ca_topic_score_gemma":0.0009478241,"domain_scores_codex":[0.9990433,0.0001403403,0.00004309495,0.0003398379,0.0003420341,0.00009137394],"domain_scores_gemma":[0.9966762,0.001923063,0.0002227849,0.0004380555,0.0006662111,0.00007375969],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004071935,0.0001071668,0.01017886,0.0004011884,0.0001124811,0.001961958,0.0006869553,0.2805085,0.03928886,0.4360327,0.01168015,0.218634],"study_design_scores_gemma":[0.00002283381,0.0001103602,0.006292876,0.00004629085,0.0000487045,0.002253625,0.0001475461,0.8388487,0.008904944,0.1314682,0.01176033,0.0000956923],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02923572,0.0006026632,0.9565365,0.000470883,0.0000895088,0.00007363439,0.0007941393,0.0009978932,0.01119912],"genre_scores_gemma":[0.8832145,0.002328311,0.0896928,0.0003141263,0.000374661,0.0002583479,0.002306276,0.0003675416,0.0211435],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009285551,"threshold_uncertainty_score":0.0310632,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2168729028","doi":"10.1109/tasl.2009.2025790","title":"On Optimal Frequency-Domain Multichannel Linear Filtering for Noise Reduction","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":288,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Noise reduction; Noise (video); Reduction (mathematics); Distortion (music); Filter (signal processing); Wiener filter; Computer science; Algorithm; Frequency domain; Mathematics; Speech recognition; Artificial intelligence; Telecommunications","authors":[{"name":"Mehrez Souden","is_ca":true},{"name":"Jacob Benesty","is_ca":true},{"name":"Sofiène Affes","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01224379360348507,"gpt":0.2637650849999195,"spread":0.2515212913964344,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001543211,0.001449082,0.0009612985,0.0007242164,0.0003205072,0.0009371151,0.0007667698,0.001323793,0.002846127],"category_scores_gemma":[0.002694011,0.0005399761,0.001062108,0.001229487,0.001132768,0.001728423,0.0009226183,0.001329154,0.0008832988],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009102373,"about_ca_system_score_gemma":0.0009535385,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001927775,"about_ca_topic_score_gemma":0.002045922,"domain_scores_codex":[0.9989183,0.000343822,0.00007530169,0.0002022694,0.00037785,0.00008249059],"domain_scores_gemma":[0.999017,0.0006870426,0.00006343237,0.00007658193,0.0001419992,0.00001391934],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00009722447,0.0001232244,0.0003164086,0.0007238589,0.0001185478,0.0001186074,0.0001476952,0.4925045,0.02080523,0.2527906,0.003277891,0.2289762],"study_design_scores_gemma":[0.00001610598,0.0001173969,0.0002137183,0.00007205844,0.00003746059,0.0001035631,0.00002484706,0.9180626,0.009924776,0.06094228,0.01043386,0.0000514363],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0009462495,0.0008971411,0.9962667,0.0000843539,0.00002849847,0.00001301065,0.00001702254,0.00003987516,0.001707245],"genre_scores_gemma":[0.1150773,0.01106653,0.8628175,0.0005032963,0.0004881028,0.000188455,0.0002664095,0.0001839733,0.009408385],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002846127,"threshold_uncertainty_score":0.009521246,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2135817141","doi":"10.1109/tsa.2004.833008","title":"Time-Delay Estimation via Linear Interpolation and Cross Correlation","year":2004,"lang":"en","type":"article","venue":"IEEE Transactions on Speech and Audio Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":243,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Reverberation; Multilateration; Cross-correlation; Computer science; Microphone; Multipath propagation; Algorithm; Noise (video); Interpolation (computer graphics); SIGNAL (programming language); Linear interpolation; Speech recognition; Acoustics; Mathematics; Artificial intelligence; Telecommunications; Pattern recognition (psychology)","authors":[{"name":"Jacob Benesty","is_ca":true},{"name":"Jun Chen","is_ca":false},{"name":"Yuli Huang","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.00977493263216831,"gpt":0.2592749246945659,"spread":0.2494999920623976,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009391968,0.0008023282,0.0005341196,0.001130531,0.0003224172,0.0006962012,0.0008653183,0.000630002,0.001735595],"category_scores_gemma":[0.003552416,0.0003548874,0.000633362,0.00146056,0.0003904032,0.0009381155,0.0009964828,0.001123117,0.0007820987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004401126,"about_ca_system_score_gemma":0.00114351,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00558165,"about_ca_topic_score_gemma":0.004875625,"domain_scores_codex":[0.9994602,0.0001141125,0.0000276613,0.0001320555,0.000216607,0.00004945629],"domain_scores_gemma":[0.9987283,0.0005850436,0.0001531469,0.0001487839,0.0003497699,0.00003495176],"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":[0.0002135164,0.00009086967,0.002076574,0.0001676528,0.0001039396,0.0001964845,0.0001478526,0.4632329,0.02667249,0.01666992,0.002121609,0.4883062],"study_design_scores_gemma":[0.000005577347,0.00003318065,0.0003847108,0.000008234362,0.00001041224,0.00008355149,0.000009689393,0.9904149,0.006056963,0.001402814,0.001573908,0.00001605376],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006660045,0.0001741338,0.9922536,0.00002546041,0.00002278875,0.00001129145,0.00002161797,0.0003429293,0.0004881139],"genre_scores_gemma":[0.1944244,0.0005513509,0.8008049,0.00005108392,0.00006615481,0.00007365204,0.0002939159,0.0001835803,0.003551073],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00558165,"threshold_uncertainty_score":0.01109833,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2000916836","doi":"10.1109/89.902276","title":"An adaptive KLT approach for speech enhancement","year":2001,"lang":"en","type":"article","venue":"IEEE Transactions on Speech and Audio Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":235,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Speech enhancement; Speech recognition; Noise (video); Computer science; Speech processing; White noise; Additive white Gaussian noise; Residual; Background noise; Colors of noise; Distortion (music); Mathematics; Artificial intelligence; Noise reduction; Algorithm; Telecommunications","authors":[{"name":"A. Rezayee","is_ca":true},{"name":"Saeed Gazor","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0278643172740081,"gpt":0.2735090793971463,"spread":0.2456447621231382,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004629183,0.0007296977,0.0005198315,0.0007440879,0.0002657289,0.0005898561,0.0006896963,0.0006557532,0.002078975],"category_scores_gemma":[0.0009670551,0.0002483186,0.0006885913,0.0005719202,0.0004379277,0.0008595167,0.0006135628,0.0007517397,0.001308603],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003030722,"about_ca_system_score_gemma":0.0004103679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008711552,"about_ca_topic_score_gemma":0.001368324,"domain_scores_codex":[0.9995084,0.00007657913,0.00002993704,0.0001027159,0.0002499982,0.00003239295],"domain_scores_gemma":[0.9996955,0.00009743718,0.00002743288,0.00003528197,0.0001320033,0.00001228741],"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":[0.000199089,0.00007506512,0.0004037103,0.0001660612,0.00006520696,0.0001566409,0.0001320803,0.05082987,0.2024493,0.01043239,0.001615354,0.7334752],"study_design_scores_gemma":[0.00002840018,0.0002158452,0.0008845259,0.00001991648,0.00005633854,0.0006063598,0.00004327236,0.8977051,0.08075202,0.005864569,0.01377593,0.00004776431],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001977151,0.0001975784,0.9968891,0.00003264851,0.0000251283,0.0000152254,0.00000878919,0.0002576773,0.0005967661],"genre_scores_gemma":[0.08430077,0.0006371111,0.9094498,0.0001243682,0.00008878113,0.00007807832,0.0001226441,0.0001249397,0.005073483],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002078975,"threshold_uncertainty_score":0.006954908,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2804619907","doi":"10.1145/3197517.3201292","title":"Visemenet","year":2018,"lang":"en","type":"article","venue":"ACM Transactions on Graphics","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":227,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Massachusetts; National Science Foundation","keywords":"Computer science; Computer facial animation; Viseme; Animation; Speech recognition; Motion (physics); Artificial intelligence; Motion capture; Synchronization (alternating current); Face (sociological concept); Computer animation; Speech synthesis; Computer graphics (images); Speech technology","authors":[{"name":"Yang Zhou","is_ca":false},{"name":"Zhan Xu","is_ca":false},{"name":"Chris Landreth","is_ca":true},{"name":"Evangelos Kalogerakis","is_ca":false},{"name":"Subhransu Maji","is_ca":false},{"name":"Karan Singh","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02182020117249972,"gpt":0.2660231279796109,"spread":0.2442029268071111,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001901401,0.001697092,0.0004700589,0.0009497915,0.000425478,0.001518441,0.001876544,0.001251233,0.06896371],"category_scores_gemma":[0.0008879898,0.0004585867,0.0007338042,0.0007462526,0.0002899053,0.002411589,0.001415793,0.001388834,0.02514182],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007249311,"about_ca_system_score_gemma":0.0006575405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005989714,"about_ca_topic_score_gemma":0.01624356,"domain_scores_codex":[0.9997781,0.00001766727,0.000009772483,0.000119086,0.00004449304,0.00003092186],"domain_scores_gemma":[0.9998863,0.0000240006,0.000007298956,0.00003685732,0.00002964165,0.0000159233],"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":[0.0005164667,0.0002184513,0.001139036,0.0006330134,0.0001572472,0.0003804408,0.0001081709,0.02011381,0.0217973,0.01800973,0.2802603,0.6566659],"study_design_scores_gemma":[0.0001535234,0.0003555627,0.001872877,0.0001790138,0.0001235812,0.0007191139,0.0001917121,0.3916874,0.04922708,0.04341967,0.5119753,0.00009518883],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.05764337,0.004524761,0.4180222,0.001829653,0.00361164,0.0005130939,0.07159074,0.2521358,0.1901288],"genre_scores_gemma":[0.2864982,0.002126344,0.3915715,0.002941011,0.0003679871,0.0007264282,0.1651426,0.007865113,0.1427609],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.06896371,"threshold_uncertainty_score":0,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2054040518","doi":"10.1109/97.889636","title":"Wavelet speech enhancement based on the Teager energy operator","year":2001,"lang":"en","type":"article","venue":"IEEE Signal Processing Letters","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":194,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Energy operator; Speech enhancement; Wavelet; Speech recognition; Energy (signal processing); Computer science; Noise (video); A priori and a posteriori; Artificial intelligence; Pattern recognition (psychology); Noise measurement; Wavelet transform; Noise reduction; Mathematics; Statistics","authors":[{"name":"Mohammed Bahoura","is_ca":true},{"name":"Jean Rouat","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01549480607661621,"gpt":0.2246815998051548,"spread":0.2091867937285386,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004911085,0.0004622421,0.0004735676,0.0003502215,0.0001241614,0.0004567311,0.000481139,0.0005047904,0.001341107],"category_scores_gemma":[0.0007564205,0.0002161773,0.0004854221,0.0002931595,0.0003330428,0.0009137518,0.0005283603,0.0007329663,0.0005839836],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001139275,"about_ca_system_score_gemma":0.0001772648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001928243,"about_ca_topic_score_gemma":0.0002553938,"domain_scores_codex":[0.9998041,0.00004343163,0.0000111701,0.00004013377,0.00008467466,0.00001660725],"domain_scores_gemma":[0.9996697,0.0001362028,0.00003856687,0.00004886993,0.00008418478,0.00002257951],"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":[0.0004160865,0.00007865109,0.0003339903,0.0001846832,0.00004861439,0.0002075511,0.0001148173,0.01944851,0.6221696,0.01311944,0.0007589355,0.3431191],"study_design_scores_gemma":[0.0000579626,0.0005250849,0.001531147,0.00002834305,0.00006973631,0.0008239269,0.0000328369,0.6664359,0.3167683,0.004960434,0.008708481,0.00005780103],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0159855,0.0003612407,0.9826985,0.00004336991,0.00004997581,0.0000185571,0.00001061747,0.0002445421,0.0005876892],"genre_scores_gemma":[0.2153985,0.001142681,0.7784564,0.0001132916,0.0001133687,0.00006239688,0.00006989052,0.0001321751,0.004511297],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001341107,"threshold_uncertainty_score":0.004486442,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3197912330","doi":"10.21437/interspeech.2021-599","title":"MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement","year":2021,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":190,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Speech enhancement; Computer science; Speech recognition; Artificial intelligence; Noise reduction","authors":[{"name":"Szu‐Wei Fu","is_ca":false},{"name":"Cheng Yu","is_ca":false},{"name":"Tsun-An Hsieh","is_ca":false},{"name":"Peter Plantinga","is_ca":false},{"name":"Mirco Ravanelli","is_ca":true},{"name":"Xugang Lu","is_ca":false},{"name":"Yu Tsao","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01889896437997837,"gpt":0.277745182418337,"spread":0.2588462180383586,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001859011,0.002296372,0.0011335,0.0009219254,0.0003476082,0.0008017229,0.001693123,0.001386003,0.006146219],"category_scores_gemma":[0.004161123,0.0004282187,0.0009386645,0.0005209272,0.0005008605,0.001635937,0.001671558,0.001649278,0.002984101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006057295,"about_ca_system_score_gemma":0.0006490861,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002771897,"about_ca_topic_score_gemma":0.006425837,"domain_scores_codex":[0.9989876,0.0003588439,0.00005376997,0.0002728353,0.0002348719,0.00009203752],"domain_scores_gemma":[0.9989871,0.000382495,0.00003976637,0.0002921115,0.0002618361,0.00003659675],"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":[0.0006688562,0.0002758514,0.001791704,0.0005329709,0.0003408373,0.0002532166,0.0001125622,0.09568132,0.03442585,0.004021854,0.03118492,0.8307101],"study_design_scores_gemma":[0.000135717,0.0006545094,0.002585988,0.00007981073,0.0001139628,0.0006231065,0.00007001456,0.9023221,0.04971916,0.007497192,0.03609857,0.00009986898],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05657217,0.00356184,0.887041,0.0005506711,0.0008261288,0.0005016474,0.002834309,0.03464142,0.01347084],"genre_scores_gemma":[0.2838871,0.0009415851,0.6750144,0.001197026,0.0001896728,0.0008140079,0.01283925,0.002815732,0.02230125],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006146219,"threshold_uncertainty_score":0.02056116,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3161950572","doi":"10.1109/icassp39728.2021.9413740","title":"TSTNN: Two-Stage Transformer Based Neural Network for Speech Enhancement in the Time Domain","year":2021,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":186,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Encoder; Computer science; Transformer; Speech recognition; Artificial neural network; Speech enhancement; Benchmark (surveying); Time domain; Pattern recognition (psychology); Artificial intelligence; Noise reduction; Computer vision; Engineering; Voltage","authors":[{"name":"Kai Wang","is_ca":true},{"name":"Bengbeng He","is_ca":true},{"name":"Wei‐Ping Zhu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01613232171435938,"gpt":0.2649973294156781,"spread":0.2488650077013187,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004237488,0.0007644268,0.00042886,0.0002779218,0.0001724434,0.0004374586,0.001147645,0.000685823,0.002585863],"category_scores_gemma":[0.0007355655,0.0002487665,0.0006060849,0.0002943489,0.0003158868,0.001005857,0.0006706838,0.001016861,0.001213773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003950901,"about_ca_system_score_gemma":0.0005464238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003240319,"about_ca_topic_score_gemma":0.00672214,"domain_scores_codex":[0.9998388,0.00002524215,0.00001059738,0.00004284329,0.00005558183,0.00002695138],"domain_scores_gemma":[0.9998111,0.00006245932,0.00001535147,0.0000244222,0.00007265314,0.00001395695],"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":[0.0005933584,0.0001845175,0.001209109,0.000261544,0.0001841584,0.0002604339,0.0001033545,0.201522,0.1057181,0.00706423,0.005248894,0.6776503],"study_design_scores_gemma":[0.00001142191,0.000113482,0.0002616358,0.00001278372,0.00004084255,0.0001239461,0.00001306992,0.9702637,0.02464557,0.002094724,0.002404926,0.00001392377],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02064491,0.0008672901,0.9736603,0.0001261087,0.0001689777,0.00005672927,0.0001447694,0.001654707,0.002676237],"genre_scores_gemma":[0.59358,0.001263063,0.3891406,0.000442229,0.00008910622,0.000152467,0.001092741,0.0002488862,0.01399084],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003240319,"threshold_uncertainty_score":0.008650541,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2128604088","doi":"10.1109/tsa.2003.818031","title":"Incorporating the human hearing properties in the signal subspace approach for speech enhancement","year":2003,"lang":"en","type":"article","venue":"IEEE Transactions on Speech and Audio Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":171,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Speech recognition; Speech enhancement; Computer science; Signal subspace; Noise (video); Spectrogram; Noise reduction; Residual; Colors of noise; Subspace topology; Filter (signal processing); Artificial intelligence; Algorithm; Computer vision","authors":[{"name":"F. Jabloun","is_ca":true},{"name":"Benoı̂t Champagne","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04549423966659918,"gpt":0.264615521974624,"spread":0.2191212823080248,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003631875,0.0005648311,0.0003603335,0.0003027857,0.0001871996,0.0004266967,0.0002441204,0.0005556873,0.001995727],"category_scores_gemma":[0.0006798014,0.0002013846,0.0005405328,0.0002724043,0.0003328492,0.0008342257,0.0003276009,0.0004108854,0.001025173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008463814,"about_ca_system_score_gemma":0.0002652854,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003972455,"about_ca_topic_score_gemma":0.0008388362,"domain_scores_codex":[0.9998577,0.00005346571,0.000008450925,0.00001854322,0.00005344889,0.000008488321],"domain_scores_gemma":[0.9998042,0.0001016985,0.00001157122,0.00003311524,0.00004353614,0.000005989078],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001994317,0.0000951621,0.0003680762,0.000258198,0.00006016653,0.000280279,0.0001586173,0.08580533,0.4519422,0.01788746,0.000867618,0.4420775],"study_design_scores_gemma":[0.00002614269,0.0006423569,0.001013364,0.00003118947,0.00006381241,0.001487559,0.00007736367,0.7922491,0.1775798,0.01217186,0.01458217,0.00007534271],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005253729,0.0001625012,0.99368,0.00003809961,0.00001997902,0.00001430388,0.000009518229,0.0002532347,0.0005686007],"genre_scores_gemma":[0.1443982,0.001096294,0.8510427,0.000073806,0.00006021561,0.00005615828,0.00009345928,0.0000910809,0.003087987],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001995727,"threshold_uncertainty_score":0.006676316,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2600579021","doi":"10.1109/taslp.2017.2689681","title":"On the Design of Frequency-Invariant Beampatterns With Uniform Circular Microphone Arrays","year":2017,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Audio Speech and Language Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":170,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"China Scholarship Council","keywords":"Directivity; Microphone; Superposition principle; Acoustics; White noise; Invariant (physics); Loudspeaker; Harmonics; Computer science; Mathematics; Control theory (sociology); Physics; Mathematical analysis; Telecommunications; Artificial intelligence","authors":[{"name":"Gongping Huang","is_ca":true},{"name":"Jacob Benesty","is_ca":true},{"name":"Jingdong Chen","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02053196319033007,"gpt":0.2443639679900176,"spread":0.2238320047996875,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007932286,0.0007047434,0.0003800113,0.000322538,0.0001514378,0.0004921549,0.0004799346,0.0004605613,0.00161264],"category_scores_gemma":[0.00273746,0.0004157448,0.000352647,0.0005013788,0.0006288116,0.0006879481,0.000626842,0.0004136571,0.0007030449],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002489082,"about_ca_system_score_gemma":0.0003612137,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003682676,"about_ca_topic_score_gemma":0.0005184655,"domain_scores_codex":[0.9993699,0.0002166565,0.00003685245,0.0001163494,0.0002196757,0.00004059789],"domain_scores_gemma":[0.9991854,0.0004201062,0.0000882966,0.00009503852,0.0001830562,0.00002807124],"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":[0.0002769877,0.00007138492,0.0008562209,0.0004708494,0.00007674898,0.0002018452,0.0002977346,0.2855172,0.1917083,0.0726027,0.002508776,0.4454112],"study_design_scores_gemma":[0.00004130724,0.0002328905,0.0005426517,0.00004321912,0.00003375717,0.0003926655,0.00005842859,0.915196,0.05576973,0.01627586,0.01136989,0.00004348061],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001696493,0.00007100864,0.9973007,0.00002029198,0.000007956904,0.000008826063,0.000007809807,0.00004882815,0.0008381194],"genre_scores_gemma":[0.1076663,0.00075411,0.8885213,0.0001341651,0.00007614396,0.0001100978,0.00008423893,0.00009699883,0.002556682],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00161264,"threshold_uncertainty_score":0.005394816,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2042809187","doi":"10.2307/3316063","title":"The historical functional linear model","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":151,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Bivariate analysis; Mathematics; Acceleration; Covariate; Function (biology); Basis (linear algebra); Functional data analysis; Applied mathematics; Calibration; Domain (mathematical analysis); Regression analysis; Linear regression; Basis function; Linear model; Statistics; Mathematical analysis; Geometry; Physics","authors":[{"name":"Nicole Malfait","is_ca":true},{"name":"J. O. Ramsay","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03208348061610872,"gpt":0.2109072855509716,"spread":0.1788238049348629,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003900034,0.001091405,0.0008477023,0.001473264,0.0006966292,0.00179986,0.002827387,0.00208973,0.01563054],"category_scores_gemma":[0.008530946,0.0006092919,0.001199788,0.001554946,0.001783796,0.002887127,0.001424649,0.002046951,0.00297473],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002255064,"about_ca_system_score_gemma":0.001365118,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01643316,"about_ca_topic_score_gemma":0.01013135,"domain_scores_codex":[0.9981287,0.0008468721,0.00006627002,0.0005595729,0.0002105087,0.0001880357],"domain_scores_gemma":[0.9969051,0.00180939,0.0003292183,0.0002449482,0.0005789782,0.0001323051],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001086769,0.00007458836,0.006486208,0.0002278379,0.0001677013,0.0002690408,0.0004974505,0.3836278,0.0004961391,0.5246037,0.01094557,0.07249522],"study_design_scores_gemma":[0.00002283809,0.00008164014,0.00177796,0.00007428614,0.00005188265,0.000219289,0.00009044827,0.7262611,0.0001869093,0.2510931,0.02009545,0.00004510037],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02449941,0.00201656,0.944244,0.004053009,0.000292925,0.00006276184,0.001937592,0.000431083,0.02246273],"genre_scores_gemma":[0.8267976,0.002719991,0.1055619,0.001170474,0.0006652336,0.0004574464,0.002735112,0.000274941,0.05961734],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01643316,"threshold_uncertainty_score":0.05228937,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2036042055","doi":"10.1093/scan/nsu168","title":"Engaged listeners: shared neural processing of powerful political speeches","year":2015,"lang":"en","type":"article","venue":"Social Cognitive and Affective Neuroscience","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":146,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"National Institute of Mental Health","keywords":"Psychology; Politics; Communication; Cognitive psychology; Political science; Law","authors":[{"name":"Ralf Schmälzle","is_ca":false},{"name":"Frank E. K. Häcker","is_ca":false},{"name":"Christopher J. Honey","is_ca":true},{"name":"Uri Hasson","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07407495775601558,"gpt":0.320296329765696,"spread":0.2462213720096804,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005082231,0.0002880586,0.0002322223,0.0003039855,0.0002241046,0.0008650376,0.0001524757,0.0004806281,0.002382086],"category_scores_gemma":[0.002989239,0.0002417575,0.0002021635,0.0001617443,0.0006375086,0.0008254164,0.001038943,0.000487031,0.0002317668],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001160864,"about_ca_system_score_gemma":0.0001113834,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002171857,"about_ca_topic_score_gemma":0.0004546684,"domain_scores_codex":[0.9997138,0.00005938945,0.0000101787,0.00009426148,0.0000718341,0.0000505165],"domain_scores_gemma":[0.999423,0.0002727268,0.0001185561,0.00005396389,0.00004230886,0.00008949221],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.001140621,0.0001011895,0.01726249,0.0001963267,0.0001475824,0.0004813733,0.00607312,0.0004508094,0.9219507,0.001272973,0.0002858436,0.05063699],"study_design_scores_gemma":[0.0001103043,0.001116152,0.9133808,0.0000657955,0.0002497155,0.001503622,0.003937751,0.00443466,0.06413543,0.009309675,0.001693564,0.00006249016],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9925114,0.0001594903,0.003506203,0.00009277825,0.00001776453,0.00001278982,0.0000436581,0.00002590441,0.003630016],"genre_scores_gemma":[0.9982389,0.00007460237,0.00105213,0.00004208018,0.00002313901,0.00001572529,0.00003387938,0.00001427921,0.0005053005],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002382086,"threshold_uncertainty_score":0.007968903,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2100555417","doi":"10.1109/tsa.2003.815518","title":"A soft voice activity detector based on a laplacian-gaussian model","year":2003,"lang":"en","type":"article","venue":"IEEE Transactions on Speech and Audio Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":141,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Speech recognition; Hidden Markov model; Computer science; Noise (video); Discrete cosine transform; Gaussian; Posterior probability; Detector; Probability distribution; Bayesian probability; Pattern recognition (psychology); Mathematics; Artificial intelligence; Statistics","authors":[{"name":"Saeed Gazor","is_ca":true},{"name":"Wei Zhang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01821155687566045,"gpt":0.2488104677728221,"spread":0.2305989108971617,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009163311,0.0005790011,0.001027905,0.0009435171,0.0002643696,0.001004967,0.001150841,0.001006141,0.0015051],"category_scores_gemma":[0.002366951,0.0003603991,0.0006736009,0.0005583711,0.0005754491,0.001355773,0.00083384,0.0008663945,0.0008030797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005112033,"about_ca_system_score_gemma":0.0005900709,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001840861,"about_ca_topic_score_gemma":0.001980227,"domain_scores_codex":[0.9992642,0.0001653434,0.00003241333,0.0001784873,0.0002925458,0.00006699112],"domain_scores_gemma":[0.9990442,0.0005858412,0.00005844174,0.00006868667,0.0001946571,0.00004809914],"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":[0.0005737302,0.0001882091,0.004332872,0.0002496879,0.0002072849,0.0003746977,0.0001654588,0.1957909,0.07481424,0.02419837,0.003757159,0.6953474],"study_design_scores_gemma":[0.00001312759,0.00005526627,0.0005838284,0.000005697992,0.00001733539,0.000168727,0.000009189828,0.989854,0.005208374,0.003042235,0.001018975,0.00002322362],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006184169,0.0002132505,0.992373,0.00006513816,0.00004330728,0.0000220412,0.00003643591,0.0004466902,0.0006159724],"genre_scores_gemma":[0.5598485,0.0006526265,0.4331001,0.0004332405,0.0001583067,0.0001460891,0.0003631708,0.0001065881,0.005191373],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001840861,"threshold_uncertainty_score":0.005035102,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2153038597","doi":"10.1109/msp.2014.2358871","title":"Objective Quality and Intelligibility Prediction for Users of Assistive Listening Devices: Advantages and limitations of existing tools","year":2015,"lang":"en","type":"article","venue":"IEEE Signal Processing Magazine","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":138,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University; Institut National de la Recherche Scientifique","funders":"National Institute on Deafness and Other Communication Disorders","keywords":"Reverberation; Intelligibility (philosophy); Active listening; Computer science; Speech perception; Speech recognition; Cochlear implant; Hearing aid; Perception; Sound quality; Audiology; Acoustics; Psychology; Medicine","authors":[{"name":"Tiago H. Falk","is_ca":true},{"name":"Vijay Parsa","is_ca":false},{"name":"João Felipe Santos","is_ca":true},{"name":"Kathryn H. Arehart","is_ca":false},{"name":"Oldooz Hazrati","is_ca":false},{"name":"Rainer Hüber","is_ca":false},{"name":"James M. Kates","is_ca":false},{"name":"Susan Scollie","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.195169606849618,"gpt":0.3647818179845549,"spread":0.169612211134937,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002953717,0.002343018,0.0010401,0.002964105,0.0002779289,0.002259711,0.001209577,0.001047076,0.001807698],"category_scores_gemma":[0.01715311,0.0004724348,0.0005809236,0.001266978,0.0004303376,0.001940672,0.001233431,0.0009637888,0.00112366],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003246698,"about_ca_system_score_gemma":0.0004509737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002453315,"about_ca_topic_score_gemma":0.00283349,"domain_scores_codex":[0.997596,0.0004741513,0.0002902653,0.0004499311,0.001113126,0.00007655502],"domain_scores_gemma":[0.9885536,0.00610391,0.001561313,0.0009250144,0.002585388,0.0002707282],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0008339504,0.0003858743,0.06955767,0.001064627,0.0002895677,0.0001621023,0.0003382356,0.02028543,0.00868162,0.00130571,0.003254452,0.8938408],"study_design_scores_gemma":[0.0001807465,0.002946554,0.1817223,0.001463799,0.000705164,0.001777414,0.001495594,0.7323905,0.05045447,0.009378545,0.01682524,0.0006597057],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2366364,0.01594114,0.7244189,0.0006300077,0.0002407341,0.0004602479,0.003635125,0.00707135,0.0109662],"genre_scores_gemma":[0.7540836,0.005458488,0.2321146,0.0002597079,0.0003137488,0.0004404307,0.003523552,0.0003021516,0.003503785],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002964105,"threshold_uncertainty_score":0.01562095,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1981446207","doi":"10.1155/s1110865703212014","title":"The Fusion of Distributed Microphone Arrays for Sound Localization","year":2003,"lang":"en","type":"article","venue":"EURASIP Journal on Advances in Signal Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":138,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Microphone; Computer science; Noise-canceling microphone; Acoustic source localization; Microphone array; Acoustics; SIGNAL (programming language); Noise (video); Speech recognition; Sound (geography); Telecommunications; Artificial intelligence; Physics; Sound pressure","authors":[{"name":"Parham Aarabi","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01377679451943762,"gpt":0.2795702934340798,"spread":0.2657934989146422,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008893018,0.000997102,0.001024249,0.000851252,0.0002671001,0.0006994525,0.001000753,0.000995021,0.00187743],"category_scores_gemma":[0.002727455,0.0005228215,0.0007661128,0.0008599558,0.0004164866,0.001368271,0.001683511,0.0008307758,0.001364433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002314012,"about_ca_system_score_gemma":0.0003350881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003241292,"about_ca_topic_score_gemma":0.0005206889,"domain_scores_codex":[0.9989383,0.0002216651,0.00004349512,0.0002049915,0.0005453228,0.00004628631],"domain_scores_gemma":[0.9994043,0.0001940996,0.0000592551,0.00009997654,0.0002189874,0.00002344008],"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":[0.0003521311,0.00006276336,0.000740703,0.0004324444,0.0001561144,0.0003944284,0.0002331444,0.06379116,0.2342229,0.01185404,0.002174508,0.6855857],"study_design_scores_gemma":[0.00006442488,0.0004260997,0.001461401,0.0000693532,0.0001313143,0.001372608,0.00008626578,0.8428192,0.1202711,0.0131952,0.01998699,0.0001160328],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002879448,0.000326617,0.9955445,0.00004339992,0.00005395035,0.00001416739,0.00002134224,0.0003191522,0.0007975227],"genre_scores_gemma":[0.1757315,0.0009492455,0.8197447,0.0001349838,0.0001892769,0.00009018514,0.000178936,0.0001164083,0.002864926],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00187743,"threshold_uncertainty_score":0.006280601,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1593114658","doi":"10.48550/arxiv.1312.4314","title":"Learning Factored Representations in a Deep Mixture of Experts","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":137,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"MNIST database; Parallelizable manifold; Computer science; Artificial intelligence; Layer (electronics); Class (philosophy); Machine learning; Deep learning; Space (punctuation); Algorithm","authors":[{"name":"David Eigen","is_ca":false},{"name":"Marc’Aurelio Ranzato","is_ca":false},{"name":"Ilya Sutskever","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0519460007582218,"gpt":0.2001051598742186,"spread":0.1481591591159968,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001200311,0.00119202,0.0008338741,0.0006713258,0.0002956083,0.0009000195,0.001174027,0.001380799,0.002508595],"category_scores_gemma":[0.003162945,0.000786704,0.001212076,0.0005757764,0.0008583512,0.002901652,0.001483787,0.001975943,0.0008515993],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008911255,"about_ca_system_score_gemma":0.0006986987,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005523539,"about_ca_topic_score_gemma":0.0070478,"domain_scores_codex":[0.9994835,0.0001652731,0.0000176278,0.0001823896,0.00007084769,0.00008031349],"domain_scores_gemma":[0.9992937,0.0003441799,0.00006227405,0.0001147272,0.0001253382,0.00005981035],"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":[0.0003524787,0.00009916011,0.00222446,0.00007992915,0.0001582129,0.0001350646,0.0002317037,0.791155,0.01179631,0.02936769,0.004285135,0.1601148],"study_design_scores_gemma":[0.000007179409,0.0000182805,0.00008353345,0.000005280821,0.000008247758,0.00001901417,0.000008851398,0.9884536,0.001130352,0.009853871,0.0004064266,0.000005440777],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04218943,0.000320305,0.954144,0.0003258603,0.00004300142,0.00002662673,0.0001493428,0.001142515,0.001658896],"genre_scores_gemma":[0.7320677,0.0002999336,0.2598183,0.000361819,0.00007874097,0.00008717394,0.000553177,0.0001755536,0.006557639],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005523539,"threshold_uncertainty_score":0.01098275,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4319596491","doi":"10.3390/electronics12040839","title":"Speech Emotion Recognition Based on Multiple Acoustic Features and Deep Convolutional Neural Network","year":2023,"lang":"en","type":"article","venue":"Electronics","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":136,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Mel-frequency cepstrum; Speech recognition; Computer science; Convolutional neural network; Feature (linguistics); Optimal distinctiveness theory; Pattern recognition (psychology); Artificial intelligence; Jitter; Feature extraction; Artificial neural network","authors":[{"name":"Kishor Bhangale","is_ca":false},{"name":"Mohanaprasad Kothandaraman","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01374466518818066,"gpt":0.2307959788309115,"spread":0.2170513136427309,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003026683,0.0007661241,0.0004576356,0.000530638,0.0001959772,0.0004092121,0.0004491487,0.0003859769,0.001269539],"category_scores_gemma":[0.0005562195,0.0002163022,0.0004309942,0.0003026518,0.0001492654,0.000588808,0.000519946,0.0006680303,0.0006340886],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004017758,"about_ca_system_score_gemma":0.0002829212,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005469516,"about_ca_topic_score_gemma":0.007925728,"domain_scores_codex":[0.9997787,0.00002535156,0.00001432026,0.00007213183,0.00007083151,0.00003873681],"domain_scores_gemma":[0.9998336,0.00003445473,0.0000160682,0.00001583189,0.00008940125,0.00001067433],"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":[0.0005106234,0.0002023205,0.003337311,0.000120213,0.0001301102,0.0001736186,0.00008134785,0.04135742,0.1174208,0.001234079,0.004586086,0.8308461],"study_design_scores_gemma":[0.000009180528,0.00008336758,0.003860016,0.00001226622,0.00005941716,0.00008608848,0.00002879535,0.9704348,0.02333616,0.0006622578,0.001410317,0.00001741318],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1845416,0.003164633,0.8006275,0.0004090905,0.00039619,0.0001096727,0.0005884637,0.003460158,0.00670273],"genre_scores_gemma":[0.8926023,0.001167724,0.09721356,0.0001976747,0.00009933064,0.00007897187,0.001213741,0.00006866634,0.007358116],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005469516,"threshold_uncertainty_score":0.01087534,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2100820878","doi":"10.1109/iros.2004.1389723","title":"Enhanced robot audition based on microphone array source separation with post-filter","year":2005,"lang":"en","type":"preprint","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":136,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Microphone array; Computer science; Filter (signal processing); Microphone; Robot; Noise-canceling microphone; Source separation; Acoustics; Separation (statistics); Speech recognition; Artificial intelligence; Computer vision; Physics; Sound pressure; Telecommunications","authors":[{"name":"Jean-Marc Valin","is_ca":true},{"name":"Jean Rouat","is_ca":true},{"name":"F. Michaud","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01035412407496789,"gpt":0.2456421257564639,"spread":0.235288001681496,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002573085,0.0005226795,0.000472414,0.000278852,0.0001373084,0.0004460391,0.0006099031,0.0007324175,0.003570769],"category_scores_gemma":[0.0006669384,0.0002410325,0.0003565526,0.0002382714,0.0002570915,0.0006018095,0.0005251367,0.0003793825,0.001438566],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001183398,"about_ca_system_score_gemma":0.0002270949,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003753983,"about_ca_topic_score_gemma":0.0006322158,"domain_scores_codex":[0.9996833,0.00005751822,0.00001200244,0.00006011541,0.0001572244,0.00002987682],"domain_scores_gemma":[0.9996688,0.000115879,0.0000284736,0.00005117409,0.0001202468,0.00001535148],"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":[0.0006521328,0.00009170268,0.000653458,0.0002302582,0.00005212714,0.0002111705,0.0000828468,0.01120252,0.6627132,0.00121151,0.0008498901,0.3220492],"study_design_scores_gemma":[0.0001586062,0.00128688,0.007504685,0.00003965778,0.0001584513,0.002454253,0.00005704917,0.3945022,0.5731443,0.00146986,0.01912036,0.0001037237],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06342715,0.0004691021,0.9312459,0.00009416758,0.000135934,0.00006771398,0.00006320322,0.002031489,0.002465392],"genre_scores_gemma":[0.3428119,0.0004150901,0.6500581,0.0001020115,0.0001132,0.00008559033,0.0001635327,0.0001121071,0.006138476],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003570769,"threshold_uncertainty_score":0.01194543,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2098651198","doi":"10.1109/tsmcb.2004.826398","title":"Enhanced Sound Localization","year":2004,"lang":"en","type":"article","venue":"IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":133,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Microphone; Reverberation; Acoustic source localization; Directivity; Acoustics; Orientation (vector space); Sound localization; Ranging; Microphone array; Computer science; Sound (geography); Noise-canceling microphone; Mathematics; Physics; Sound pressure; Telecommunications; Geometry","authors":[{"name":"B. Mungamuru","is_ca":true},{"name":"Parham Aarabi","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01668988838778912,"gpt":0.2359552121620396,"spread":0.2192653237742505,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005907186,0.001095227,0.001148555,0.001302505,0.0003431874,0.001326734,0.001517854,0.001261066,0.004860011],"category_scores_gemma":[0.002565395,0.0004848442,0.001024606,0.000967062,0.0006422422,0.002139449,0.002147132,0.001087466,0.002652797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003701618,"about_ca_system_score_gemma":0.000687453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006818784,"about_ca_topic_score_gemma":0.000988791,"domain_scores_codex":[0.9990677,0.0001344991,0.00004472881,0.0002103155,0.000480135,0.00006257104],"domain_scores_gemma":[0.9989964,0.0002820407,0.0001126161,0.0002271201,0.0003505023,0.00003131047],"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":[0.0002400868,0.00007942966,0.0007125073,0.0004537809,0.000119803,0.0003696676,0.0001473599,0.06485381,0.1182001,0.02717871,0.004498082,0.7831467],"study_design_scores_gemma":[0.00007740022,0.0003655948,0.0009421008,0.00007393635,0.0001102108,0.002096695,0.00008478057,0.8712357,0.07306172,0.0156341,0.03621729,0.0001005983],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00149667,0.0001407967,0.996991,0.00002953903,0.00004938311,0.00001585641,0.00002059397,0.0004891083,0.0007669898],"genre_scores_gemma":[0.06816901,0.0005251678,0.924665,0.0001454121,0.0001147369,0.00009582349,0.0001909798,0.0001909354,0.005902918],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004860011,"threshold_uncertainty_score":0.01625836,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2119901478","doi":"10.1109/tasl.2007.901310","title":"Soft Mask Methods for Single-Channel Speaker Separation","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":122,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Spectrogram; Computer science; SIGNAL (programming language); Speech recognition; Binary number; Channel (broadcasting); Masking (illustration); Source separation; Speech enhancement; Speech processing; Algorithm; Pattern recognition (psychology); Artificial intelligence; Mathematics; Telecommunications; Noise reduction","authors":[{"name":"Aarthi M. Reddy","is_ca":true},{"name":"Bhiksha Raj","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0249877122083876,"gpt":0.338796042543846,"spread":0.3138083303354585,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007229979,0.000897027,0.0006524281,0.000851231,0.0004402519,0.0008144411,0.0009989167,0.0008766694,0.00507943],"category_scores_gemma":[0.00270405,0.0003718921,0.0005898434,0.0006873528,0.0006325301,0.001198721,0.001117859,0.001160739,0.00253094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003978041,"about_ca_system_score_gemma":0.0006748012,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001546393,"about_ca_topic_score_gemma":0.001700083,"domain_scores_codex":[0.9994276,0.0001186563,0.00002197757,0.0000835338,0.000313364,0.00003484233],"domain_scores_gemma":[0.999172,0.0004902885,0.00006013064,0.0001073896,0.0001423763,0.00002789372],"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":[0.0004964418,0.00006241463,0.0002963208,0.0003425784,0.00008628125,0.0001171932,0.0001748823,0.1208082,0.04698643,0.03722503,0.004382018,0.7890222],"study_design_scores_gemma":[0.0000352302,0.00007442693,0.000389332,0.00003134918,0.00002703554,0.00020789,0.00003592996,0.9311491,0.02240516,0.036592,0.009017881,0.00003467564],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002151676,0.0005195223,0.9960068,0.00005171192,0.00003959083,0.00002283018,0.00003889787,0.000342641,0.0008263239],"genre_scores_gemma":[0.07865454,0.001264867,0.9144138,0.00009767563,0.000161156,0.0001444131,0.0002210488,0.0001762627,0.004866268],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00507943,"threshold_uncertainty_score":0.01699233,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2139129402","doi":"10.1109/robot.2004.1307286","title":"Localization of simultaneous moving sound sources for mobile robot using a frequency- domain steered beamformer approach","year":2004,"lang":"en","type":"preprint","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":117,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Mobile robot; Robot; Acoustic source localization; Frequency domain; Probabilistic logic; Computer vision; Complement (music); Artificial intelligence; Range (aeronautics); Beamforming; Acoustics; Sound (geography); Engineering; Telecommunications","authors":[{"name":"Jean-Marc Valin","is_ca":true},{"name":"François Michaud","is_ca":true},{"name":"Brahim Hadjou","is_ca":true},{"name":"Jean Rouat","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02598173886488693,"gpt":0.2722140111097762,"spread":0.2462322722448892,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003303587,0.0006723009,0.0004733994,0.0003555303,0.0001530982,0.0004072531,0.0004562065,0.0008247516,0.002361574],"category_scores_gemma":[0.0007037692,0.0003888087,0.0004276164,0.0003388518,0.0003739067,0.0006974489,0.000612552,0.0003964656,0.001401241],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001203718,"about_ca_system_score_gemma":0.000357822,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005328671,"about_ca_topic_score_gemma":0.001167525,"domain_scores_codex":[0.9997798,0.00006032453,0.00001027361,0.00004967501,0.00008335446,0.00001673386],"domain_scores_gemma":[0.9997267,0.00008933076,0.00003548936,0.00003530906,0.00009576117,0.00001728233],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003724488,0.00006737015,0.0005199422,0.0001907557,0.000147074,0.0004136304,0.0002917361,0.1048595,0.5867736,0.005284606,0.001893239,0.299186],"study_design_scores_gemma":[0.0001245095,0.0004170804,0.0008167197,0.00002989289,0.0000950827,0.0008332281,0.0001367642,0.8626203,0.1202336,0.005594144,0.009032671,0.00006605504],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006404826,0.00007495734,0.9927273,0.0000481616,0.00002338433,0.000008756947,0.00000897071,0.0003627659,0.0003408239],"genre_scores_gemma":[0.1272667,0.0003171076,0.8687383,0.00008879363,0.00005242187,0.00006340616,0.00007088973,0.00006233985,0.003339944],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002361574,"threshold_uncertainty_score":0.007900238,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2109124605","doi":"10.1109/tpami.2003.1206512","title":"A graphical model for audiovisual object tracking","year":2003,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":115,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Graphical model; Artificial intelligence; Video tracking; Computer vision; Exploit; Object (grammar); Tracking (education); Inference; Process (computing); Statistical model; Data modeling; Bayesian inference; Bayesian probability","authors":[{"name":"Matthew J. Beal","is_ca":true},{"name":"Nebojša Jojić","is_ca":false},{"name":"Hagai Attias","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03213946701149374,"gpt":0.2976170625537154,"spread":0.2654775955422217,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019099,0.001190547,0.001175286,0.002415437,0.0005298321,0.002482099,0.003455658,0.002313147,0.005866498],"category_scores_gemma":[0.008724744,0.001023298,0.001849105,0.003020892,0.001285144,0.003357957,0.001597918,0.002025489,0.002572552],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001907033,"about_ca_system_score_gemma":0.001283544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01189446,"about_ca_topic_score_gemma":0.01115256,"domain_scores_codex":[0.998546,0.0004222691,0.00007924832,0.0004691671,0.000351136,0.0001321673],"domain_scores_gemma":[0.9967659,0.00191289,0.0003955284,0.0003412902,0.0004709719,0.0001134291],"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":[0.0001655712,0.00007247217,0.001848582,0.0001978766,0.0001470945,0.0003986486,0.0002338705,0.6565737,0.004127393,0.2417756,0.007448323,0.08701102],"study_design_scores_gemma":[0.00002154124,0.00001826278,0.0002378014,0.00001719952,0.00002834807,0.00009318032,0.00001064201,0.9247214,0.0004343103,0.07052256,0.003869871,0.00002487252],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001307696,0.000149096,0.996651,0.0001832564,0.00003007377,0.00001892436,0.0003767718,0.0004851923,0.0007981278],"genre_scores_gemma":[0.3158563,0.001683462,0.662593,0.0005412014,0.0003362258,0.0006538955,0.003873337,0.0005453036,0.01391726],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01189446,"threshold_uncertainty_score":0.02365047,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2888493610","doi":"10.1109/taslp.2018.2862826","title":"Insights Into Frequency-Invariant Beamforming With Concentric Circular Microphone Arrays","year":2018,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Audio Speech and Language Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":113,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"Israel Science Foundation; National Natural Science Foundation of China","keywords":"Beamforming; Directivity; Invariant (physics); Microphone; Loudspeaker; Computer science; Acoustics; Physics; Telecommunications","authors":[{"name":"Gongping Huang","is_ca":false},{"name":"Jingdong Chen","is_ca":false},{"name":"Jacob Benesty","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.008513987475283591,"gpt":0.2308448052122166,"spread":0.222330817736933,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001023853,0.001101859,0.0005418952,0.0004982575,0.0002385453,0.0008241499,0.0006558116,0.0009680244,0.002463695],"category_scores_gemma":[0.003349226,0.0005579566,0.0005808964,0.0004514114,0.0009662313,0.001525969,0.0009439092,0.0008496289,0.0009839428],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004796994,"about_ca_system_score_gemma":0.0004569227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005660699,"about_ca_topic_score_gemma":0.0005281405,"domain_scores_codex":[0.9991778,0.0002721107,0.00003506373,0.0001560643,0.0002916122,0.00006744494],"domain_scores_gemma":[0.9987653,0.000727146,0.0001697635,0.0001030638,0.0001849237,0.00004975929],"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":[0.0001588659,0.00005303745,0.0006186776,0.0003632432,0.00006177898,0.0006633041,0.0003895006,0.395343,0.08428489,0.3734973,0.003092476,0.1414738],"study_design_scores_gemma":[0.00002230799,0.0001191118,0.0004973726,0.00003929298,0.0000180034,0.0006435708,0.0001043982,0.8689359,0.01147497,0.1075224,0.01056705,0.00005562333],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002763154,0.0001942338,0.9937567,0.00009745837,0.00002646202,0.000009292022,0.00002143998,0.00006058142,0.003070776],"genre_scores_gemma":[0.233682,0.002500427,0.7538104,0.0003501494,0.0003466292,0.0001488989,0.0001728206,0.0001576301,0.008831082],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002463695,"threshold_uncertainty_score":0.008241892,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2002786446","doi":"10.1121/1.4898429","title":"On the design and implementation of linear differential microphone arrays","year":2014,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":110,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Microphone array; Directivity; Computer science; Microphone; Beamforming; Acoustics; White noise; Noise (video); Short-time Fourier transform; SIGNAL (programming language); Sound pressure; Fourier transform; Mathematics; Telecommunications; Fourier analysis; Physics","authors":[{"name":"Jingdong Chen","is_ca":false},{"name":"Jacob Benesty","is_ca":true},{"name":"Chao Pan","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01230584599860526,"gpt":0.2558567051470595,"spread":0.2435508591484542,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004779627,0.0005501785,0.0002799109,0.0003187696,0.000208643,0.0007791856,0.001040968,0.0006835262,0.002988062],"category_scores_gemma":[0.001520856,0.0004074294,0.0002979298,0.0003247469,0.0003798576,0.0006336579,0.0005616939,0.0005660604,0.001703036],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003831495,"about_ca_system_score_gemma":0.000349335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003387817,"about_ca_topic_score_gemma":0.0005129268,"domain_scores_codex":[0.9993169,0.0001578136,0.00004273811,0.00009903842,0.0003406195,0.00004282509],"domain_scores_gemma":[0.9994047,0.0001637354,0.00006872587,0.00007162469,0.0002706335,0.00002053413],"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":[0.0001996859,0.00008039793,0.001076156,0.001079861,0.00006549441,0.0004814076,0.0003624554,0.08780262,0.3574869,0.0705993,0.00385541,0.4769103],"study_design_scores_gemma":[0.00006853786,0.0009104647,0.001035569,0.0002352575,0.00007124343,0.001444468,0.0001177698,0.5229983,0.3203751,0.01031251,0.1423478,0.00008282869],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00226259,0.0003761016,0.9913501,0.00007546986,0.00004598906,0.0000479273,0.00001531466,0.000349601,0.005476832],"genre_scores_gemma":[0.14067,0.001316827,0.8489315,0.0001604512,0.00006855586,0.0001796768,0.00009470875,0.00007281557,0.008505323],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002988062,"threshold_uncertainty_score":0.009996116,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2119000949","doi":"10.1109/tsa.2005.858512","title":"On the importance of phase in human speech recognition","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":108,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Active listening; Phase (matter); Word error rate; Speech recognition; Computer science; Word (group theory); Mean squared error; Perception; Statistics; Noise (video); Pattern recognition (psychology); Mathematics; Artificial intelligence; Psychology; Physics; Communication","authors":[{"name":"Guangji Shi","is_ca":true},{"name":"Maryam M. Shanechi","is_ca":true},{"name":"Parham Aarabi","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01647496210812098,"gpt":0.2745142636396765,"spread":0.2580393015315555,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003495773,0.0006788349,0.0005285774,0.000805266,0.0002897821,0.001209947,0.0003854973,0.001015818,0.00113813],"category_scores_gemma":[0.03847237,0.0003545489,0.0003676271,0.0006264401,0.0009687971,0.002342984,0.0007183295,0.0005143091,0.0004809232],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002006654,"about_ca_system_score_gemma":0.0002111303,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000392805,"about_ca_topic_score_gemma":0.0002881349,"domain_scores_codex":[0.9962184,0.001325756,0.0003037739,0.0005958397,0.001407764,0.0001485111],"domain_scores_gemma":[0.9435699,0.04921792,0.003103052,0.001514086,0.002325744,0.0002692383],"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":[0.004677888,0.000296615,0.04633727,0.001275978,0.0003117194,0.001207431,0.001310627,0.07198013,0.4430881,0.002630101,0.00044692,0.4264373],"study_design_scores_gemma":[0.0001301218,0.006959277,0.2413271,0.0001703489,0.0006369051,0.008360268,0.0008285845,0.2678124,0.4555278,0.01343068,0.004351604,0.0004648834],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6789847,0.003879432,0.3138052,0.0002780673,0.0001275439,0.0000844136,0.0001605953,0.0003704197,0.002309699],"genre_scores_gemma":[0.9667248,0.00114004,0.03111362,0.00008939103,0.0001172192,0.00003684512,0.0001943134,0.000115428,0.0004683912],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003495773,"threshold_uncertainty_score":0.01848763,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2922332774","doi":"10.1109/icassp.2019.8683175","title":"Non-intrusive Speech Quality Assessment Using Neural Networks","year":2019,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":108,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"PESQ; Mean opinion score; Computer science; Mean squared error; Artificial neural network; Speech recognition; Quality (philosophy); Correlation; Quality of experience; Artificial intelligence; Machine learning; Speech enhancement; Quality of service; Statistics; Noise reduction; Telecommunications; Mathematics","authors":[{"name":"Anderson R. Avila","is_ca":true},{"name":"Hannes Gamper","is_ca":false},{"name":"Chandan K. Reddy","is_ca":false},{"name":"Ross Cutler","is_ca":false},{"name":"Ivan Tashev","is_ca":false},{"name":"Johannes Gehrke","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03097023443026254,"gpt":0.3260866942796873,"spread":0.2951164598494248,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009765336,0.001015445,0.0004365085,0.0006493218,0.0001947905,0.0006227597,0.0004862123,0.0006517448,0.0007901938],"category_scores_gemma":[0.002710352,0.0001934606,0.000369516,0.0003207469,0.00022548,0.0006685433,0.0006007199,0.0006288643,0.0002958127],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000596712,"about_ca_system_score_gemma":0.0002593738,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006211206,"about_ca_topic_score_gemma":0.007429603,"domain_scores_codex":[0.9994646,0.0001440517,0.00003342012,0.0001472716,0.0001530085,0.00005773279],"domain_scores_gemma":[0.9989354,0.0004901384,0.0001297977,0.00004939752,0.0003555046,0.00003976439],"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":[0.001106844,0.0005424694,0.01091094,0.0001873016,0.0003036241,0.0002175402,0.0001315163,0.4805269,0.03475083,0.0005654219,0.002055868,0.4687008],"study_design_scores_gemma":[0.000006151113,0.00007880463,0.002474569,0.000009231978,0.00002138349,0.00001882334,0.00001655759,0.9925711,0.004476725,0.0002069992,0.0001113618,0.000008288949],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6809027,0.00223751,0.3091832,0.0003489497,0.0001967118,0.0001080689,0.0004044002,0.001533512,0.00508492],"genre_scores_gemma":[0.9779763,0.000227644,0.01953184,0.00006473527,0.00003787003,0.00002782239,0.000330357,0.00002241184,0.001781103],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006211206,"threshold_uncertainty_score":0.01235008,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2111070087","doi":"10.1109/tasl.2007.904233","title":"Single-Channel Speech Separation Using Soft Mask Filtering","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":108,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Wiener filter; Filter (signal processing); Binary number; Channel (broadcasting); Computer science; Minimum mean square error; Gaussian; Algorithm; Noise (video); Mean squared error; Signal-to-noise ratio (imaging); Speech enhancement; Mathematics; Speech recognition; Statistics; Artificial intelligence; Physics; Telecommunications; Computer vision","authors":[{"name":"Richard M. Dansereau","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02335064070139286,"gpt":0.2833091741114335,"spread":0.2599585334100406,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004164173,0.0006134374,0.0008064305,0.0005582298,0.0003614739,0.000784312,0.0006174137,0.001027087,0.002060294],"category_scores_gemma":[0.001350716,0.0002684606,0.0006034462,0.0005173906,0.0003380381,0.001061474,0.0007201082,0.0005076705,0.001379925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002729586,"about_ca_system_score_gemma":0.000489662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000841343,"about_ca_topic_score_gemma":0.001375075,"domain_scores_codex":[0.9995969,0.00004747692,0.00002631921,0.00008023778,0.0002199563,0.00002907068],"domain_scores_gemma":[0.9996361,0.0001663608,0.00004303646,0.00006087688,0.00007492426,0.00001873923],"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":[0.0005336251,0.00009019629,0.000812652,0.0002760304,0.000117156,0.0002371515,0.0001462401,0.03511374,0.2733926,0.009031956,0.001384796,0.6788639],"study_design_scores_gemma":[0.00003549818,0.0002282154,0.001749893,0.00003664825,0.00008762673,0.0009349449,0.00003737518,0.7328698,0.2481874,0.009628604,0.006137016,0.00006699738],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01631098,0.0003104249,0.9819064,0.00005238521,0.00004875803,0.00002011157,0.00004090189,0.0004218238,0.0008883008],"genre_scores_gemma":[0.2270777,0.0005299356,0.7679122,0.0001099528,0.00007488696,0.00007198691,0.0001906137,0.0000815591,0.003951118],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002060294,"threshold_uncertainty_score":0.006892383,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2147271331","doi":"10.1109/tsmcb.2004.830345","title":"Phase-Based Dual-Microphone Robust Speech Enhancement","year":2004,"lang":"en","type":"article","venue":"IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":104,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Speech recognition; Reverberation; Microphone; Speech enhancement; Word error rate; Beamforming; Multilateration; Noise (video); SIGNAL (programming language); Pattern recognition (psychology); Artificial intelligence; Acoustics; Noise reduction; Telecommunications; Physics","authors":[{"name":"Parham Aarabi","is_ca":true},{"name":"Guang Shi","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02311683342707415,"gpt":0.246703202702189,"spread":0.2235863692751149,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005114651,0.0007433504,0.0006100921,0.0004413314,0.0001912744,0.0005165302,0.0008830745,0.0008137957,0.003002181],"category_scores_gemma":[0.001162763,0.0003555055,0.0004380961,0.0002720093,0.000250725,0.000771606,0.0007778729,0.0006066236,0.002475726],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001775834,"about_ca_system_score_gemma":0.0003107005,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002377148,"about_ca_topic_score_gemma":0.0004460249,"domain_scores_codex":[0.9995486,0.00005901319,0.00002737219,0.00009877478,0.0002312907,0.0000349222],"domain_scores_gemma":[0.9995278,0.0001155756,0.0000548752,0.00006852268,0.000209697,0.00002349607],"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":[0.0005883938,0.0001089284,0.000458916,0.0001771009,0.00004006056,0.0001406478,0.00006203856,0.01327135,0.5913645,0.004381751,0.001318361,0.3880881],"study_design_scores_gemma":[0.00006506102,0.0003980768,0.00101109,0.00002038856,0.00006345971,0.001375763,0.00002179132,0.2946967,0.6883116,0.001384569,0.01260212,0.00004946325],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01374808,0.0002851876,0.9835824,0.0000578174,0.00007414759,0.00003693305,0.00004311985,0.000739064,0.001433163],"genre_scores_gemma":[0.1267926,0.0003569618,0.866205,0.0001120514,0.00006555401,0.00006465364,0.000172004,0.00009349683,0.006137648],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003002181,"threshold_uncertainty_score":0.01004326,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2140651276","doi":"10.1109/tasl.2006.883253","title":"Single-Ended Speech Quality Measurement Using Machine Learning Methods","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":103,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"PESQ; Computer science; Speech recognition; Support vector machine; Mean opinion score; Random forest; Artificial intelligence; Classifier (UML); Multiplicative function; Machine learning; Pattern recognition (psychology); Speech enhancement; Noise reduction; Mathematics; Engineering","authors":[{"name":"Tiago H. Falk","is_ca":true},{"name":"W.-Y. Chan","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04909807463381612,"gpt":0.3245484020317244,"spread":0.2754503273979083,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001026191,0.0008051662,0.0007459717,0.0007975104,0.0002933477,0.001086422,0.0009599458,0.0008500585,0.001699896],"category_scores_gemma":[0.003616151,0.0003249091,0.0004893118,0.0003936043,0.000366068,0.001145763,0.0007297603,0.0006812552,0.001265734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003908667,"about_ca_system_score_gemma":0.0003527765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004711746,"about_ca_topic_score_gemma":0.0006714205,"domain_scores_codex":[0.9986334,0.0002635737,0.00008451737,0.0003267542,0.0006443245,0.00004734543],"domain_scores_gemma":[0.9985589,0.0005390045,0.0001911127,0.0002421053,0.0004166129,0.00005227841],"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":[0.0004336293,0.0002264455,0.002966068,0.0002055074,0.0001252962,0.0001277921,0.0001125229,0.07195655,0.102531,0.003111984,0.001213073,0.8169901],"study_design_scores_gemma":[0.0000318508,0.0002799525,0.00206133,0.00001990619,0.00002549797,0.0002938525,0.00001861434,0.9309391,0.06238729,0.002021265,0.00187482,0.00004658253],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01320525,0.00007959048,0.985087,0.00002763054,0.0000210192,0.00004955048,0.00003540294,0.0009883437,0.0005062458],"genre_scores_gemma":[0.2773327,0.0001130344,0.7203197,0.0000696013,0.00003486777,0.0001532771,0.0002228735,0.0001061798,0.001647813],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001699896,"threshold_uncertainty_score":0.0056867,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2507780144","doi":"10.1109/mcas.2016.2583681","title":"Recent Developments in Speech Enhancement in the Short-Time Fourier Transform Domain","year":2016,"lang":"en","type":"article","venue":"IEEE Circuits and Systems Magazine","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":95,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Université de Sherbrooke; Concordia University","funders":"","keywords":"Short-time Fourier transform; Speech enhancement; Estimator; Computer science; Spectral density estimation; Wiener filter; Noise (video); Gaussian noise; Speech recognition; Fourier transform; Frequency domain; Algorithm; Spectral density; Noise reduction; Artificial intelligence; Mathematics; Fourier analysis; Statistics; Telecommunications; Computer vision","authors":[{"name":"Mahdi Parchami","is_ca":true},{"name":"Wei‐Ping Zhu","is_ca":true},{"name":"Benoı̂t Champagne","is_ca":true},{"name":"Éric Plourde","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02387619114841635,"gpt":0.2448962645437055,"spread":0.2210200733952891,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001546844,0.0009338421,0.0008684703,0.001724249,0.0002669473,0.001208649,0.0007651537,0.001169431,0.003807021],"category_scores_gemma":[0.002495446,0.0005033541,0.0005742714,0.002578272,0.0007151632,0.002465769,0.0008928066,0.001435385,0.002295614],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003255525,"about_ca_system_score_gemma":0.0005544704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005464118,"about_ca_topic_score_gemma":0.0005550904,"domain_scores_codex":[0.9992914,0.0001384942,0.00006889519,0.0001974188,0.0002631667,0.00004063421],"domain_scores_gemma":[0.9964664,0.002307739,0.0001555757,0.0001929401,0.0008028156,0.00007454302],"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":[0.000171145,0.00008362156,0.0004195598,0.003062626,0.00006111662,0.0001910298,0.0002117023,0.004112451,0.023473,0.01594788,0.004147944,0.948118],"study_design_scores_gemma":[0.00004535255,0.0009623025,0.004113247,0.001738785,0.0003601811,0.003413515,0.0005139775,0.07324589,0.08925654,0.02716407,0.7989365,0.000249593],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.01000041,0.5065366,0.4574295,0.001858331,0.001394262,0.0000781061,0.0001346967,0.0005231106,0.02204513],"genre_scores_gemma":[0.07796749,0.5752501,0.3234515,0.001357505,0.006372273,0.0001207876,0.0005511218,0.0002754455,0.01465376],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.003807021,"threshold_uncertainty_score":0.01273572,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2139231522","doi":"10.1109/icapr.2009.80","title":"Bangla Speech Recognition System Using LPC and ANN","year":2009,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":93,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"La Cité Collégiale","funders":"","keywords":"Speech recognition; Computer science; Linear predictive coding; Cepstrum; Speech processing; Voice activity detection; Speech coding; Mel-frequency cepstrum; Artificial intelligence; Pattern recognition (psychology); Vector quantization; Artificial neural network; Feature extraction; Feature vector","authors":[{"name":"Anup Kumar Paul","is_ca":true},{"name":"Dipankar Das","is_ca":false},{"name":"Md. Mustafa Kamal","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02663728876712292,"gpt":0.24343624757153,"spread":0.216798958804407,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003784223,0.0005618415,0.000615549,0.0006353829,0.0004876544,0.0009805131,0.0006986114,0.000687746,0.006426833],"category_scores_gemma":[0.0008412849,0.0002917156,0.0004217511,0.0005630756,0.0002348522,0.0007017225,0.0003468091,0.0005282772,0.004494109],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004708857,"about_ca_system_score_gemma":0.0004107424,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005331384,"about_ca_topic_score_gemma":0.004063614,"domain_scores_codex":[0.9994728,0.00005133723,0.00005695828,0.0001615317,0.0002194065,0.00003805419],"domain_scores_gemma":[0.999587,0.0000755396,0.00002680376,0.0000403353,0.0002532709,0.00001709345],"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":[0.0004822314,0.000191522,0.003238965,0.000601416,0.0001604435,0.0006873792,0.0002506202,0.05981888,0.1308854,0.002576258,0.01039482,0.7907121],"study_design_scores_gemma":[0.00004479824,0.0003285902,0.006822756,0.0001138832,0.0001370742,0.0009291316,0.000123714,0.8807744,0.06760637,0.001690259,0.04131099,0.000118105],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08134063,0.002088963,0.84914,0.0005187608,0.0006453115,0.0004741183,0.001131869,0.02246067,0.04219957],"genre_scores_gemma":[0.5420069,0.001524277,0.3946761,0.0003851463,0.0001794672,0.0004990546,0.002567031,0.0004043359,0.0577577],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006426833,"threshold_uncertainty_score":0.02149993,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4311167834","doi":"10.1109/taslp.2022.3205757","title":"Deep Learning-Based Non-Intrusive Multi-Objective Speech Assessment Model With Cross-Domain Features","year":2022,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Audio Speech and Language Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":92,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Microsoft (Canada)","funders":"National Science and Technology Council; Academia Sinica","keywords":"PESQ; Computer science; Intelligibility (philosophy); Speech recognition; Artificial neural network; Mean opinion score; Artificial intelligence; Machine learning; Metric (unit); Speech enhancement; Noise reduction; Engineering","authors":[{"name":"Ryandhimas E. Zezario","is_ca":false},{"name":"Szu‐Wei Fu","is_ca":true},{"name":"Fei Chen","is_ca":false},{"name":"Chiou‐Shann Fuh","is_ca":false},{"name":"Hsin‐Min Wang","is_ca":false},{"name":"Yu Tsao","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.009114245931778077,"gpt":0.2788869952743462,"spread":0.2697727493425682,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008535873,0.001076146,0.0006814295,0.0004535105,0.0001821115,0.0006384645,0.001171868,0.0007297443,0.001193304],"category_scores_gemma":[0.001458648,0.0003907845,0.0007191854,0.0003203196,0.000283644,0.0009900079,0.0009728415,0.00141117,0.0005504852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006299473,"about_ca_system_score_gemma":0.0006210595,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005168619,"about_ca_topic_score_gemma":0.00622923,"domain_scores_codex":[0.9995986,0.00007918039,0.00002378107,0.000149474,0.00009984427,0.00004914931],"domain_scores_gemma":[0.9995128,0.0001573021,0.00005918878,0.00003540457,0.0001985226,0.00003682019],"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":[0.0003671258,0.0003044961,0.006068703,0.0001181126,0.0002600635,0.0002168675,0.000146949,0.6014997,0.01545057,0.002483046,0.002898268,0.3701861],"study_design_scores_gemma":[0.000003431281,0.00002930158,0.0004792355,0.000003628322,0.00001346864,0.00001537568,0.000004081697,0.9979526,0.0008878512,0.0004527266,0.000152692,0.000005673115],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07480105,0.0009600863,0.919956,0.000274724,0.0001006103,0.00007549387,0.0002494183,0.001214155,0.002368482],"genre_scores_gemma":[0.9197966,0.0003131401,0.07185683,0.0002555027,0.00005953373,0.0001411324,0.0006509529,0.00007104464,0.00685518],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005168619,"threshold_uncertainty_score":0.01027709,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2028124797","doi":"10.1016/j.specom.2012.08.007","title":"Multitaper MFCC and PLP features for speaker verification using i-vectors","year":2012,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":91,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Computer Research Institute of Montréal; Institut National de la Recherche Scientifique","funders":"National Institute of Standards and Technology","keywords":"Multitaper; Mel-frequency cepstrum; Computer science; NIST; Speech recognition; Pattern recognition (psychology); Cepstrum; Speaker recognition; Artificial intelligence; Feature extraction","authors":[{"name":"Jahangir Alam","is_ca":true},{"name":"Tomi Kinnunen","is_ca":false},{"name":"Patrick Kenny","is_ca":true},{"name":"Pierre Ouellet","is_ca":true},{"name":"Douglas O’Shaughnessy","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03390941946555964,"gpt":0.2998207171212208,"spread":0.2659112976556612,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006205595,0.0008454508,0.000673186,0.0009052348,0.0004476138,0.0006890895,0.0006981821,0.0009408582,0.008409541],"category_scores_gemma":[0.001920444,0.0002970834,0.000549058,0.0007724473,0.0001981853,0.001206433,0.0007493768,0.0007075911,0.006367714],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001609732,"about_ca_system_score_gemma":0.000481638,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001633215,"about_ca_topic_score_gemma":0.002725732,"domain_scores_codex":[0.9993823,0.0001371816,0.00005699903,0.0001172361,0.0002271194,0.00007923795],"domain_scores_gemma":[0.9991406,0.0002609389,0.00006564814,0.0001652935,0.000326277,0.00004124333],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008391078,0.0001218214,0.0006279353,0.0001657283,0.00004409647,0.00008726698,0.00004650228,0.00316787,0.2133023,0.0009559232,0.003361669,0.7772799],"study_design_scores_gemma":[0.0001427442,0.000774202,0.01357831,0.0001034659,0.0002794371,0.0008954371,0.0001768461,0.3657354,0.5995418,0.001725338,0.0169152,0.0001317978],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0710517,0.001897294,0.9137853,0.0002267672,0.0002148627,0.0001599411,0.001314508,0.00588133,0.005468351],"genre_scores_gemma":[0.4398955,0.001366983,0.5414621,0.0001367663,0.0001710847,0.0002752524,0.004607956,0.0005263121,0.01155788],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008409541,"threshold_uncertainty_score":0.02813268,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2560525638","doi":"10.3758/s13428-016-0830-1","title":"Chronset: An automated tool for detecting speech onset","year":2016,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":90,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"The Scarborough Hospital","funders":"","keywords":"Multitaper; Computer science; Speech recognition; Measure (data warehouse); Artificial intelligence; Natural language processing; Data mining","authors":[{"name":"Frédéric Roux","is_ca":false},{"name":"Blair C. Armstrong","is_ca":true},{"name":"Manuel Carreiras","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2584792315470756,"gpt":0.5748492312116953,"spread":0.3163699996646197,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001574746,0.002112932,0.001353887,0.005456818,0.0004846927,0.001089725,0.001826173,0.001287537,0.02208981],"category_scores_gemma":[0.007853742,0.0007389298,0.0008900338,0.001981279,0.0002825398,0.001203574,0.001596993,0.0009259264,0.01237325],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004574657,"about_ca_system_score_gemma":0.000950336,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001844854,"about_ca_topic_score_gemma":0.003524731,"domain_scores_codex":[0.9985853,0.0001663982,0.000163219,0.0004942009,0.0005240886,0.00006675875],"domain_scores_gemma":[0.9955872,0.00199229,0.0006797609,0.0005060293,0.0009931494,0.0002414778],"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":[0.001803668,0.0003601049,0.009954029,0.001861911,0.0003406393,0.0004743141,0.0004589481,0.004234981,0.09615938,0.003407254,0.1660731,0.7148716],"study_design_scores_gemma":[0.0005572612,0.0009405434,0.06673171,0.0003830475,0.000326738,0.003187406,0.0006055015,0.4444288,0.1995637,0.0156793,0.266882,0.0007140652],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01923936,0.0006931552,0.7631987,0.0001353826,0.000426463,0.0005890852,0.03622976,0.1746431,0.004845013],"genre_scores_gemma":[0.09293769,0.0004785647,0.836405,0.0002559382,0.0002889147,0.002823013,0.04851402,0.008879529,0.009417244],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02208981,"threshold_uncertainty_score":0.07389778,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2130121545","doi":"10.1109/tsp.2008.2010596","title":"On Spatial Aliasing in Microphone Arrays","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Signal Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":89,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Aliasing; Narrowband; Wideband; Microphone array; Acoustics; Computer science; Broadband; Bandlimiting; Microphone; Direction finding; Direction of arrival; Spatial filter; Algorithm; Mathematics; Fourier transform; Filter (signal processing); Telecommunications; Optics; Physics; Antenna (radio); Mathematical analysis; Loudspeaker; Computer vision; Artificial intelligence","authors":[{"name":"Jacek Dmochowski","is_ca":true},{"name":"Jacob Benesty","is_ca":true},{"name":"Sofiène Affes","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02176814778197394,"gpt":0.2386615811167431,"spread":0.2168934333347692,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001240436,0.0008437636,0.000535864,0.0006663548,0.0004565587,0.001194968,0.0006639672,0.001410476,0.002249284],"category_scores_gemma":[0.01022045,0.0005698492,0.000595295,0.001197171,0.001045445,0.002138328,0.001089073,0.001145773,0.001103356],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000520276,"about_ca_system_score_gemma":0.0003893867,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00143463,"about_ca_topic_score_gemma":0.001276617,"domain_scores_codex":[0.9981013,0.0006584201,0.00008941308,0.000186526,0.0008733762,0.00009113982],"domain_scores_gemma":[0.9962258,0.002624857,0.0002165337,0.0002905192,0.000600455,0.00004187186],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003203093,0.00005188478,0.001407041,0.0005107613,0.0001238458,0.001550908,0.0006908181,0.4402847,0.04390329,0.2094841,0.004403569,0.2972687],"study_design_scores_gemma":[0.0000136705,0.00009027016,0.0005277172,0.00006814442,0.0000275331,0.0008127631,0.0000956492,0.9229355,0.01300268,0.05068863,0.01169434,0.00004309689],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003571583,0.001198591,0.990088,0.0001087447,0.00009400471,0.00001297977,0.00001345662,0.0001397588,0.004772861],"genre_scores_gemma":[0.4646384,0.01226726,0.5058447,0.0006767981,0.001187131,0.000166407,0.0001925523,0.0003639849,0.01466274],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002249284,"threshold_uncertainty_score":0.00752455,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2019338151","doi":"10.1121/1.1787525","title":"Measurements of directional properties of reverberant sound fields in rooms using a spherical microphone array","year":2004,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":88,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute for Microstructural Sciences; University of Waterloo","funders":"University of Waterloo","keywords":"Acoustics; Reverberation; Sound energy; Microphone; Reverberation room; Microphone array; Anisotropy; Isotropy; Impulse (physics); Attenuation; Physics; Optics; Sound pressure; Sound (geography)","authors":[{"name":"Bradford N. Gover","is_ca":true},{"name":"James G. Ryan","is_ca":true},{"name":"Michael R. Stinson","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03633421389483735,"gpt":0.251627352135803,"spread":0.2152931382409656,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005322103,0.0007204971,0.0006388083,0.0007444247,0.0002094267,0.000487975,0.0004785433,0.0004222704,0.001046118],"category_scores_gemma":[0.001305166,0.0004868042,0.0005011893,0.0004178832,0.0004079856,0.0004311935,0.0005652401,0.0004801869,0.0006455871],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001909244,"about_ca_system_score_gemma":0.0002325085,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006847943,"about_ca_topic_score_gemma":0.001222579,"domain_scores_codex":[0.9995078,0.00008228519,0.00002164784,0.000148177,0.000175897,0.00006422056],"domain_scores_gemma":[0.9990829,0.000275311,0.00009933975,0.00007521763,0.0003427219,0.0001244021],"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":[0.0004703578,0.00004303367,0.0055299,0.00009223622,0.000042055,0.00008226465,0.0003546131,0.001123307,0.9778194,0.00009044875,0.00007277527,0.01427958],"study_design_scores_gemma":[0.00009526002,0.001712659,0.1216596,0.00001947682,0.0002116322,0.001272176,0.0004863319,0.01712821,0.8554982,0.000236207,0.001483841,0.0001964843],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9589655,0.0002463093,0.03936056,0.00002309326,0.00002067034,0.00002505698,0.0001980934,0.0003413234,0.0008192693],"genre_scores_gemma":[0.9707196,0.0002286279,0.02801858,0.00002889085,0.00001631489,0.00003158306,0.0002874748,0.00007224032,0.0005965971],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001046118,"threshold_uncertainty_score":0.003499627,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2155213659","doi":"10.1109/lsp.2006.884038","title":"Time Delay Estimation via Minimum Entropy","year":2007,"lang":"en","type":"article","venue":"IEEE Signal Processing Letters","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":88,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Multilateration; Computer science; Algorithm; Reverberation; Entropy (arrow of time); Additive white Gaussian noise; Gaussian; Speech recognition; White noise; Mathematics; Telecommunications; Acoustics","authors":[{"name":"Jacob Benesty","is_ca":true},{"name":"Yiteng Huang","is_ca":false},{"name":"Jingdong Chen","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.008847824756960781,"gpt":0.2346610019047672,"spread":0.2258131771478064,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006157917,0.0005832913,0.000814846,0.0009428536,0.0002669267,0.0007909521,0.0005524795,0.0006331079,0.001572373],"category_scores_gemma":[0.003616367,0.0004216416,0.0004332702,0.0007222143,0.0005029296,0.001451877,0.000932792,0.0006380889,0.0004226938],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004881767,"about_ca_system_score_gemma":0.0005630787,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001053452,"about_ca_topic_score_gemma":0.0007639141,"domain_scores_codex":[0.9996471,0.0001052751,0.00002101714,0.00007439663,0.000122217,0.00002996797],"domain_scores_gemma":[0.9990104,0.0006898823,0.0001064032,0.00006122012,0.0001033464,0.00002870763],"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":[0.0001560721,0.00002965083,0.0009642286,0.0001444727,0.00005594251,0.0001344371,0.00006521768,0.7700758,0.0111205,0.05729089,0.001664277,0.1582985],"study_design_scores_gemma":[0.00000650831,0.0000126254,0.0002085484,0.000006291734,0.000004441321,0.00003584203,0.000003258725,0.9832783,0.001804268,0.01416326,0.0004672246,0.000009423149],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006744727,0.0001727238,0.9920937,0.00007888838,0.00001478014,0.000009194219,0.000035024,0.0001147191,0.0007362523],"genre_scores_gemma":[0.524829,0.0008897785,0.4689546,0.00008086755,0.0001813299,0.000112431,0.0004468184,0.0001608243,0.004344318],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001572373,"threshold_uncertainty_score":0.00526011,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2885194458","doi":"10.1177/0956797618779083","title":"Familiar Voices Are More Intelligible, Even if They Are Not Recognized as Familiar","year":2018,"lang":"en","type":"article","venue":"Psychological Science","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":83,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Industry Canada","keywords":"Psychology; Intelligibility (philosophy); Perception; Vocal tract; Cognitive psychology; Speech perception; Communication; Speech recognition; Computer science","authors":[{"name":"Emma Holmes","is_ca":false},{"name":"Ysabel Domingo","is_ca":false},{"name":"Ingrid S. Johnsrude","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04582410819481825,"gpt":0.3623059346435138,"spread":0.3164818264486955,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006595794,0.0003466172,0.0003343889,0.0002678143,0.0002352098,0.0007362875,0.0001750527,0.0004364571,0.006374929],"category_scores_gemma":[0.002293316,0.0002125069,0.0001769316,0.00009058393,0.0004860536,0.0006280533,0.0007922424,0.0003366261,0.0008377758],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008279317,"about_ca_system_score_gemma":0.00009362093,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001671507,"about_ca_topic_score_gemma":0.0005170765,"domain_scores_codex":[0.9995284,0.00008743151,0.00005154796,0.0001495912,0.0001241722,0.00005879925],"domain_scores_gemma":[0.9988989,0.0003320042,0.0002939658,0.0001404726,0.0001229628,0.0002116408],"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":[0.001607902,0.0002896187,0.01860943,0.0002093501,0.00008989578,0.0006800445,0.00231669,0.00006299116,0.9485513,0.0002160827,0.0001754778,0.02719128],"study_design_scores_gemma":[0.0001990047,0.006227137,0.7786287,0.00007499489,0.0002771265,0.006025299,0.006116248,0.0006731188,0.1942911,0.001951359,0.005448713,0.00008709895],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9970677,0.0001817721,0.001257624,0.00003465262,0.00001924153,0.00001969516,0.00003757269,0.00002461677,0.001356976],"genre_scores_gemma":[0.9961941,0.00008880948,0.001682611,0.00006332876,0.00001817994,0.00003123669,0.00007072377,0.00002009903,0.001830995],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006374929,"threshold_uncertainty_score":0.02132624,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4283818626","doi":"10.1609/aaai.v36i2.20102","title":"SyncTalkFace: Talking Face Generation with Precise Lip-Syncing via Audio-Lip Memory","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":83,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Leverage (statistics); Speech recognition; Synchronization (alternating current); Visualization; Artificial intelligence; Sound quality; Audio visual; Representation (politics); Face (sociological concept); Computer vision; Multimedia; Channel (broadcasting)","authors":[{"name":"Se Jin Park","is_ca":true},{"name":"Minsu Kim","is_ca":true},{"name":"Joanna Hong","is_ca":true},{"name":"Jeongsoo Choi","is_ca":true},{"name":"Yong Man Ro","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05082625186549095,"gpt":0.260706983795317,"spread":0.209880731929826,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003638528,0.0005571693,0.0005256843,0.000340346,0.000208647,0.000633618,0.001320109,0.0007717211,0.006694633],"category_scores_gemma":[0.0009927333,0.0002579444,0.0004655928,0.0001724474,0.000270044,0.0007850848,0.001058087,0.0005954879,0.001675209],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002349502,"about_ca_system_score_gemma":0.0003084063,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001123208,"about_ca_topic_score_gemma":0.00152174,"domain_scores_codex":[0.999799,0.00002908357,0.000007547427,0.00006933909,0.00007115747,0.00002394335],"domain_scores_gemma":[0.9998128,0.00007051056,0.00001190878,0.00005077169,0.00003396854,0.00002008271],"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":[0.000747395,0.0001735309,0.0006980574,0.0002391667,0.00008929997,0.0005433687,0.0002404335,0.06236721,0.144778,0.007182825,0.009255465,0.7736853],"study_design_scores_gemma":[0.00005787447,0.0001796127,0.0005970383,0.00002723003,0.00004055181,0.0006647552,0.00006718685,0.9114525,0.07410073,0.004410353,0.008364643,0.00003756856],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04306816,0.0008087325,0.9417372,0.0002181686,0.0002383171,0.0001354238,0.0002694844,0.005615606,0.007908934],"genre_scores_gemma":[0.6290631,0.0004440563,0.3544019,0.0004143659,0.0001391334,0.0001855449,0.0007857013,0.0006643934,0.01390187],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006694633,"threshold_uncertainty_score":0.02239579,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2128977628","doi":"10.1109/aspaa.2007.4392978","title":"Broadband Music: Opportunities and Challenges for Multiple Source Localization","year":2007,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":79,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Broadband; Narrowband; Computer science; Multiple signal classification; Beamforming; Subspace topology; Microphone; SIGNAL (programming language); Signal subspace; Parameterized complexity; Microphone array; Algorithm; Acoustics; Speech recognition; Artificial intelligence; Telecommunications; Physics; Noise (video)","authors":[{"name":"Jacek Dmochowski","is_ca":true},{"name":"Jacob Benesty","is_ca":true},{"name":"Sofiène Affes","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1047535433927906,"gpt":0.2617795992806458,"spread":0.1570260558878552,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001764294,0.0007109698,0.0009523074,0.0009050131,0.0007527059,0.002204491,0.001227174,0.002286311,0.003655554],"category_scores_gemma":[0.00365228,0.0004393064,0.0004326284,0.001453518,0.001858852,0.003829668,0.001951419,0.001686217,0.002024321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004020534,"about_ca_system_score_gemma":0.0006745569,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004734974,"about_ca_topic_score_gemma":0.0008945687,"domain_scores_codex":[0.9993324,0.000236306,0.00002411714,0.00008576139,0.0002718991,0.00004958171],"domain_scores_gemma":[0.9980122,0.00115975,0.00009625782,0.00019151,0.0004208176,0.0001194423],"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":[0.0002295907,0.00006552227,0.001192218,0.0006550752,0.00006652313,0.0005109373,0.0003887179,0.03226858,0.0217291,0.1747497,0.0117456,0.7563984],"study_design_scores_gemma":[0.0001164527,0.0003636053,0.0009603529,0.000362718,0.0000666363,0.002319033,0.001284024,0.3499188,0.01223923,0.5118197,0.120361,0.0001885362],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008166968,0.02345838,0.951165,0.009677789,0.0004768122,0.00002444854,0.00005568068,0.0006568497,0.006318088],"genre_scores_gemma":[0.2208718,0.03896622,0.726544,0.00180064,0.003055043,0.0001300271,0.0002326923,0.0002099311,0.008189782],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003655554,"threshold_uncertainty_score":0.01222903,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2489919266","doi":"10.1007/978-981-10-1046-0","title":"Fundamentals of Differential Beamforming","year":2016,"lang":"en","type":"book","venue":"Springer briefs in electrical and computer engineering","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Beamforming; Differential (mechanical device); Microphone; Computer science; Microphone array; Acoustics; Engineering; Telecommunications; Physics; Aerospace engineering","authors":[{"name":"Jacob Benesty","is_ca":true},{"name":"Jingdong Chen","is_ca":false},{"name":"Chao Pan","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.00485740277940988,"gpt":0.1859106297270694,"spread":0.1810532269476595,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002890154,0.001027167,0.0006698566,0.001336937,0.0003705597,0.001425906,0.000857205,0.001041541,0.03496685],"category_scores_gemma":[0.000650548,0.0004105287,0.0003984038,0.001664007,0.0008341022,0.001281065,0.0011679,0.001601307,0.02814002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004157983,"about_ca_system_score_gemma":0.0005334566,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002493754,"about_ca_topic_score_gemma":0.0003931333,"domain_scores_codex":[0.9996979,0.00003526971,0.00001710862,0.00006022464,0.0001627607,0.00002663247],"domain_scores_gemma":[0.9997738,0.00007565236,0.0000138483,0.00003974709,0.0000757345,0.00002124597],"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":[0.00004056604,0.00003217778,0.000183123,0.0004139186,0.00001900657,0.0001225927,0.0001391088,0.00544567,0.01842989,0.1850999,0.06378212,0.726292],"study_design_scores_gemma":[0.00001046026,0.00007375728,0.0005912816,0.0002392363,0.00001655555,0.0008893286,0.0000629436,0.01427242,0.006876532,0.1394583,0.8374633,0.00004597759],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.001409002,0.04230068,0.7247317,0.001238652,0.004241703,0.00005617516,0.0003096093,0.001110182,0.2246023],"genre_scores_gemma":[0.06442909,0.07759799,0.3335402,0.001617776,0.005962454,0.0002850986,0.001262976,0.0007662724,0.5145382],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.03496685,"threshold_uncertainty_score":0.1169758,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2127707623","doi":"10.1109/tim.2009.2024697","title":"Temporal Dynamics for Blind Measurement of Room Acoustical Parameters","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Instrumentation and Measurement","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Reverberation; Estimator; Speech recognition; Modulation (music); Energy (signal processing); Computer science; Natural sounds; Cepstrum; Noise (video); Artificial intelligence; Pattern recognition (psychology); Acoustics; Mathematics; Physics; Statistics","authors":[{"name":"Tiago H. Falk","is_ca":true},{"name":"Wai-Yip Chan","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04796652431332021,"gpt":0.2738247761681069,"spread":0.2258582518547866,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009161413,0.0006698671,0.000556751,0.0008003436,0.0003262793,0.0008748982,0.0005629958,0.0008571441,0.001988122],"category_scores_gemma":[0.004703401,0.0002596324,0.0003869119,0.0007280099,0.0004788488,0.001521485,0.001147226,0.0007320731,0.001285093],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003501548,"about_ca_system_score_gemma":0.0008059999,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001020842,"about_ca_topic_score_gemma":0.001550854,"domain_scores_codex":[0.9989315,0.0002556142,0.00005679344,0.0002465769,0.0004428094,0.00006668725],"domain_scores_gemma":[0.998695,0.0004760659,0.0001892062,0.0002309345,0.000354089,0.00005487023],"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":[0.001222077,0.0001110482,0.001962638,0.0004146135,0.0001054261,0.0002147843,0.0002037012,0.07451595,0.2733597,0.03163732,0.00226375,0.6139889],"study_design_scores_gemma":[0.00003045061,0.0002431207,0.004055274,0.0000845773,0.00007013838,0.0006951972,0.00006766158,0.8649957,0.1039611,0.01377463,0.01192134,0.0001008529],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0109846,0.0004506621,0.9864696,0.00005784991,0.00005829152,0.00002647062,0.0001035147,0.0003885925,0.001460466],"genre_scores_gemma":[0.3508231,0.001688202,0.6411243,0.0002310063,0.0002245603,0.0001917142,0.0007398119,0.0002223287,0.004754907],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001988122,"threshold_uncertainty_score":0.006650925,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2115560088","doi":"10.1109/tbme.2006.889191","title":"Acoustic Analysis and Detection of Hypernasality Using a Group Delay Function","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Biomedical Engineering","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"All India Institute of Speech and Hearing","keywords":"Formant; Speech recognition; Acoustics; Vowel; Measure (data warehouse); Speech processing; Computer science; Physics","authors":[{"name":"P. Vijayalakshmi","is_ca":false},{"name":"M. Ramasubba Reddy","is_ca":false},{"name":"Douglas O’Shaughnessy","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.008955212916931557,"gpt":0.2225912738224138,"spread":0.2136360609054823,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003809644,0.0006822753,0.0004141118,0.001396126,0.0002434509,0.0004945747,0.0004334575,0.0005178457,0.00203251],"category_scores_gemma":[0.001016625,0.0001777551,0.0003770158,0.0005779645,0.0004235592,0.0005901013,0.0003653787,0.0003834751,0.000811994],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002250963,"about_ca_system_score_gemma":0.0002892929,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004782683,"about_ca_topic_score_gemma":0.0006823682,"domain_scores_codex":[0.9996704,0.00005514094,0.00001715147,0.00007756847,0.0001529903,0.00002678078],"domain_scores_gemma":[0.9995053,0.0002443596,0.00007703281,0.00004543619,0.00009712142,0.00003071019],"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":[0.0002788668,0.00006694028,0.002169033,0.000199749,0.00004929436,0.0001702787,0.0001469239,0.002070416,0.8709704,0.0005838838,0.0001610132,0.1231332],"study_design_scores_gemma":[0.00009194299,0.001373949,0.05145486,0.00005811022,0.0002186225,0.00275748,0.0004327437,0.1342879,0.797561,0.001560593,0.01004597,0.000156795],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.327496,0.0009658387,0.6677059,0.00008864394,0.0001171574,0.0001386656,0.0002014267,0.0008342328,0.002452044],"genre_scores_gemma":[0.5878801,0.0009200701,0.4084141,0.00007860854,0.00008155416,0.0001597717,0.0002909053,0.0001301003,0.002044643],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00203251,"threshold_uncertainty_score":0.006799459,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2032556581","doi":"10.1121/1.2108861","title":"Measuring the acoustic effects of compression amplification on speech in noise","year":2006,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"National Institute on Deafness and Other Communication Disorders","keywords":"QUIET; Acoustics; Noise (video); Background noise; Computer science; Speech recognition; Dynamic range; Physics; Artificial intelligence","authors":[{"name":"Pamela E. Souza","is_ca":false},{"name":"Lorienne M. Jenstad","is_ca":true},{"name":"Kumiko T. Boike","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01244227588007775,"gpt":0.2360477618239906,"spread":0.2236054859439129,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003327216,0.0003670777,0.0002487667,0.0003305599,0.0002572481,0.0003005037,0.000263147,0.0003946796,0.001148968],"category_scores_gemma":[0.001742315,0.0001692556,0.0001311912,0.0001887298,0.0004307361,0.0003924587,0.0003984008,0.0003336587,0.000362189],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002018708,"about_ca_system_score_gemma":0.000198368,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004290129,"about_ca_topic_score_gemma":0.0005837142,"domain_scores_codex":[0.9994264,0.000101514,0.0000240527,0.00007965233,0.000315665,0.0000526525],"domain_scores_gemma":[0.9990913,0.0005361834,0.00007166535,0.0000519432,0.0001949352,0.00005395133],"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":[0.0002994018,0.00002891948,0.0008427238,0.0000509006,0.000006679763,0.00008008132,0.00007552928,0.0003096249,0.9856873,0.0000762795,0.00002345293,0.01251913],"study_design_scores_gemma":[0.00001120861,0.0006722739,0.008406437,0.000007137223,0.00003081909,0.0004331627,0.00006531698,0.003414995,0.9862186,0.00008644393,0.000641113,0.00001262892],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9779002,0.0005541396,0.01909925,0.00004085102,0.00004220521,0.00004811306,0.0000425994,0.00009977962,0.002172895],"genre_scores_gemma":[0.9805049,0.000530803,0.01742877,0.00005826643,0.00004934022,0.00003998682,0.00007401407,0.00002536699,0.001288586],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001148968,"threshold_uncertainty_score":0.003843665,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}