{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":749,"total_is_capped":false,"direct_labels_cover":1,"predictions_cover":749,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"fef9bd4f6705","filters":{"topic":"Speech Recognition and Synthesis"}},"results":[{"id":"W2160815625","doi":"10.1109/msp.2012.2205597","title":"Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups","year":2012,"lang":"en","type":"article","venue":"IEEE Signal Processing Magazine","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10313,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; University of Toronto","funders":"","keywords":"Hidden Markov model; Speech recognition; Computer science; Mixture model; Artificial neural network; Margin (machine learning); Deep neural networks; Pattern recognition (psychology); Frame (networking); Artificial intelligence; Acoustic model; Gaussian; Speech processing; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.2083977889980022,"gpt":0.3405780427773996,"spread":0.1321802537793973,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002976074,0.0001769219,0.0002710969,0.0002554287,0.0002650984,0.0002093916,0.0007222341,0.0001089411,0.00005903529],"category_scores_gemma":[0.000210033,0.0001341379,0.0001006414,0.001008654,0.00008635533,0.0009665369,0.0000953727,0.0004000943,0.00003594335],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005365414,"about_ca_system_score_gemma":0.00007204313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006559229,"about_ca_topic_score_gemma":0.00005128828,"domain_scores_codex":[0.9976826,0.0002659613,0.0005126225,0.0003467459,0.0005027613,0.0006893348],"domain_scores_gemma":[0.9982497,0.0006515458,0.0001466271,0.0002745711,0.0005579449,0.0001196822],"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":[0.00005593251,0.0001211543,0.00004611581,0.0001192773,0.000007951021,0.000006334105,0.0004439196,0.009850288,0.002607016,0.0000173319,0.0003649,0.9863598],"study_design_scores_gemma":[0.0003720014,0.00006175757,0.0001132764,0.0001531942,0.00001312141,0.0000492999,0.00007799613,0.9948729,0.00122985,0.002810339,0.00007454011,0.0001717605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02031341,0.0009115977,0.9765841,0.0005289396,0.0002595892,0.0005153987,0.000003817783,0.00006613872,0.0008169915],"genre_scores_gemma":[0.9534596,0.00001805338,0.04555511,0.000238192,0.0005299222,0.0001112105,0.000006930224,0.00002328987,0.00005775664],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.986188,"threshold_uncertainty_score":0.5469985,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2143612262","doi":"10.1109/icassp.2013.6638947","title":"Speech recognition with deep recurrent neural networks","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8837,"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":"Recurrent neural network; Computer science; Connectionism; TIMIT; Speech recognition; Artificial intelligence; Deep learning; Context (archaeology); Benchmark (surveying); Time delay neural network; Artificial neural network; Hidden Markov model; Pattern recognition (psychology)","retraction":null,"screen_n_in":null,"score":{"opus":0.02127521644955892,"gpt":0.2153082989889602,"spread":0.1940330825394013,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0000998259,0.0001227431,0.0001100183,0.00007610119,0.00007841719,0.0002679776,0.0003163351,0.00004949878,0.001862079],"category_scores_gemma":[0.00001949839,0.00008697183,0.00004476454,0.0002935846,0.00002535213,0.0007312722,0.00006049575,0.0001148165,0.001117346],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001905184,"about_ca_system_score_gemma":0.000009647426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005351136,"about_ca_topic_score_gemma":0.00004821649,"domain_scores_codex":[0.9990389,0.00005567944,0.0001534203,0.0002953965,0.0001961904,0.0002603716],"domain_scores_gemma":[0.9993038,0.00008247193,0.00005153504,0.0002800527,0.0001534831,0.0001286735],"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":[0.000002155371,0.00003375808,0.0001196979,0.00000158102,0.000006339062,0.000006742707,0.00002055794,0.000007122317,0.00001442453,0.0001507641,0.001506453,0.9981304],"study_design_scores_gemma":[0.0003371479,0.0001631914,0.003769328,0.0000215728,0.000007934969,0.0001570127,0.00005935743,0.9898525,0.002360946,0.002104966,0.000829417,0.0003366481],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06591433,0.00004016587,0.8878025,0.001970923,0.0004672232,0.0003925645,5.366709e-7,0.000511274,0.04290046],"genre_scores_gemma":[0.5914597,0.00003334468,0.4050907,0.002441515,0.0001831796,0.0001095492,0.00001049278,0.00001710615,0.0006543544],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9977937,"threshold_uncertainty_score":0.9996604,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2147768505","doi":"10.1109/tasl.2011.2134090","title":"Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3077,"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":"Microsoft Research; University of Toronto; Microsoft","keywords":"Hidden Markov model; Computer science; Speech recognition; Word error rate; Artificial intelligence; Artificial neural network; Context (archaeology); Mixture model; Deep neural networks; Sentence; Generalization; Phone; Deep learning; Pattern recognition (psychology); Vocabulary; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02643442671762116,"gpt":0.2531046896995723,"spread":0.2266702629819512,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005294614,0.0002991415,0.0003100841,0.0002393273,0.0004788661,0.0002428219,0.0003321016,0.000182755,0.0002549924],"category_scores_gemma":[0.00002801077,0.0002819379,0.0001838119,0.0003156143,0.00005020447,0.0007794817,0.0000057619,0.0003134791,0.00002094445],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004389937,"about_ca_system_score_gemma":0.00003968916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005018648,"about_ca_topic_score_gemma":0.0002557664,"domain_scores_codex":[0.9980947,0.0001011318,0.0003633923,0.0006283895,0.0002777333,0.0005346212],"domain_scores_gemma":[0.9990306,0.0001412738,0.0001397245,0.0003220957,0.0001545697,0.0002117269],"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":[0.0001246128,0.0002301331,0.000005735618,0.00006138495,0.00004951068,0.00006603645,0.002243574,0.00002180763,0.0005457756,0.000009297858,0.00002134067,0.9966208],"study_design_scores_gemma":[0.002931606,0.000523607,0.0001702945,0.0002144993,0.0002080128,0.0006830064,0.002468594,0.7359142,0.2548865,0.0007828609,0.0002052653,0.001011625],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02064713,0.001017276,0.9761406,0.0001596678,0.0004126124,0.0005434876,0.00003315259,0.0004184531,0.0006275875],"genre_scores_gemma":[0.9024936,0.00005830904,0.09574365,0.00114744,0.0001134641,0.0001237167,0.00001045963,0.00003602606,0.0002733557],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9956092,"threshold_uncertainty_score":0.9999633,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2102113734","doi":"","title":"Towards End-To-End Speech Recognition with Recurrent Neural Networks","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1855,"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; Word error rate; Trigram; Speech recognition; Connectionism; Language model; Recurrent neural network; Artificial intelligence; Lexicon; Artificial neural network; Word (group theory); Time delay neural network; Natural language processing","retraction":null,"screen_n_in":null,"score":{"opus":0.02874013249881295,"gpt":0.2433709903689867,"spread":0.2146308578701737,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004068828,0.000180029,0.0001847046,0.0001462661,0.0001049211,0.0002415829,0.0004719522,0.00006541959,0.0008809525],"category_scores_gemma":[0.00007702717,0.0001352534,0.0000670964,0.0004731862,0.00002972717,0.0003737988,0.0001163784,0.0001527889,0.0004522608],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003301255,"about_ca_system_score_gemma":0.000024838,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005329136,"about_ca_topic_score_gemma":0.0001038885,"domain_scores_codex":[0.9984757,0.0001265088,0.0002118675,0.000469479,0.0003612265,0.0003552422],"domain_scores_gemma":[0.9990068,0.0001242292,0.00006188249,0.0004145395,0.0001501941,0.0002423735],"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":[0.00001186174,0.00003922889,0.00005935427,0.00000276292,0.000008034753,0.000007127639,0.00004085911,0.00001832447,0.00002551753,0.0006736545,0.001687306,0.997426],"study_design_scores_gemma":[0.001129788,0.001123027,0.006956635,0.0001198168,0.00003943562,0.0003336217,0.00007642042,0.9326965,0.0197171,0.003736935,0.03289049,0.001180263],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03010942,0.00001057001,0.8987174,0.002881951,0.0006594907,0.0002348633,0.000002739758,0.0004097011,0.06697389],"genre_scores_gemma":[0.6809036,0.00001247723,0.3146043,0.003626865,0.00031783,0.00004062855,0.00001500783,0.00001838232,0.0004608608],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9962457,"threshold_uncertainty_score":0.9645811,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2005708641","doi":"10.1109/asru.2013.6707742","title":"Hybrid speech recognition with Deep Bidirectional LSTM","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1794,"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":"TIMIT; Computer science; Word error rate; Speech recognition; Leverage (statistics); Hidden Markov model; Artificial neural network; Recurrent neural network; Artificial intelligence; Deep neural networks; Word (group theory); Vocabulary; Acoustic model; Deep learning; Speech processing","retraction":null,"screen_n_in":null,"score":{"opus":0.01839249538427433,"gpt":0.206168135037918,"spread":0.1877756396536437,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001040131,0.0001063573,0.00009516346,0.0001233321,0.00009508435,0.0002147504,0.0002399069,0.0000282798,0.005670009],"category_scores_gemma":[0.00002973955,0.00007935717,0.00004315297,0.0002101412,0.00002797005,0.0008056699,0.00004115253,0.00007340583,0.006445366],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002582399,"about_ca_system_score_gemma":0.00002925423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001193488,"about_ca_topic_score_gemma":0.00002757868,"domain_scores_codex":[0.9990868,0.00003855579,0.0001319693,0.0002891679,0.0002577376,0.0001957666],"domain_scores_gemma":[0.9993347,0.00008890335,0.00004184015,0.0002250616,0.0002023831,0.0001071017],"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":[0.000002242938,0.00005002552,0.0001406248,0.000002156824,0.00001318108,0.00001048841,0.00001374567,3.143913e-7,0.0003525222,0.0004771296,0.00529702,0.9936405],"study_design_scores_gemma":[0.001829387,0.0005234581,0.02373952,0.00009681722,0.0000369819,0.003068894,0.0002000003,0.09762096,0.7309854,0.1079245,0.03221886,0.001755214],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1685264,0.00001945359,0.5824618,0.002448339,0.0003604653,0.0003365498,0.000002615034,0.000784883,0.2450595],"genre_scores_gemma":[0.2263282,0.00001773282,0.7671171,0.002094597,0.0001464179,0.0001100073,0.00001314186,0.0000156196,0.00415717],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9918854,"threshold_uncertainty_score":0.995239,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1993882792","doi":"10.1109/tasl.2011.2109382","title":"Acoustic Modeling Using Deep Belief Networks","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1746,"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":"University of Pennsylvania","keywords":"TIMIT; Hidden Markov model; Discriminative model; Computer science; Artificial intelligence; Pattern recognition (psychology); Deep belief network; Mixture model; Artificial neural network; Speech recognition; Feature (linguistics); Backpropagation; Feature extraction; Markov model; Generative model; Gaussian; Generative grammar; Machine learning; Markov chain","retraction":null,"screen_n_in":null,"score":{"opus":0.03523967748347272,"gpt":0.249923230056549,"spread":0.2146835525730763,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002364616,0.0002047486,0.0001935345,0.0002131128,0.0004225219,0.0001846962,0.0002624505,0.0001135365,0.0001286251],"category_scores_gemma":[0.000008945613,0.0001923054,0.00007514592,0.0003785461,0.00004404059,0.0005473257,0.000004306778,0.0002684502,0.00001620425],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003901052,"about_ca_system_score_gemma":0.00004820819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007572027,"about_ca_topic_score_gemma":0.00007258936,"domain_scores_codex":[0.9987368,0.00005355815,0.0002378383,0.0004134761,0.0002024656,0.0003558412],"domain_scores_gemma":[0.9993995,0.00004326913,0.00007191679,0.0002518001,0.00007445565,0.000159071],"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":[0.00001619908,0.00009645099,0.000003088209,0.00003051296,0.00001948166,0.00006707281,0.002335843,0.01204807,0.002195393,0.000007682115,0.000001737241,0.9831785],"study_design_scores_gemma":[0.0002215595,0.00003492601,0.00000572782,0.0001033057,0.00004056339,0.0001857429,0.0005484823,0.9775599,0.02093291,0.000116571,0.000003344257,0.0002469279],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02528598,0.0007824803,0.9721779,0.00003085849,0.0002177811,0.0001117378,0.000001686452,0.0002882954,0.001103288],"genre_scores_gemma":[0.8078824,0.00005481129,0.1915515,0.0003602099,0.0000495892,0.000008845283,4.013726e-7,0.00001934045,0.0000728857],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9829316,"threshold_uncertainty_score":0.7841986,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2062227835","doi":"10.1109/icassp.2013.6639346","title":"Improving deep neural networks for LVCSR using rectified linear units and dropout","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1281,"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; Dropout (neural networks); Artificial neural network; Speech recognition; Artificial intelligence; Sigmoid function; Discriminative model; Deep neural networks; Task (project management); Vocabulary; Deep learning; Mixture model; Hidden Markov model; Time delay neural network; Bayesian probability; Pattern recognition (psychology); Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.0442634602867148,"gpt":0.2510945759761163,"spread":0.2068311156894015,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001419854,0.00009537755,0.0001094183,0.00006280994,0.0001602085,0.0002473006,0.0001915839,0.00005983659,0.00006349308],"category_scores_gemma":[0.0001227201,0.00007995032,0.0000295428,0.0002165709,0.00002322081,0.0004464069,0.00009640434,0.00006802346,0.00001051377],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001333011,"about_ca_system_score_gemma":0.00001461186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000216962,"about_ca_topic_score_gemma":0.0000285139,"domain_scores_codex":[0.9992666,0.00003367453,0.0001452715,0.0002481596,0.00007482206,0.000231501],"domain_scores_gemma":[0.9992913,0.0002047009,0.00004984044,0.0001843452,0.0001715048,0.00009832854],"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":[0.000002750694,0.000009877947,0.0001586846,0.000007468236,0.000007748497,0.000001221591,0.00007644167,0.0001234269,0.00159559,0.000698176,0.0001460475,0.9971726],"study_design_scores_gemma":[0.0001697164,0.00002753993,0.0001228325,0.000004279735,0.000005009479,0.00001892783,0.0000630959,0.9966101,0.002427185,0.0003180912,0.0001122657,0.0001209505],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08331096,0.00003719691,0.9151063,0.0002465244,0.0002822301,0.0002487318,3.169981e-7,0.0001362271,0.0006314968],"genre_scores_gemma":[0.650768,0.000003851861,0.3480042,0.00073773,0.0001397523,0.00002171571,0.000001188758,0.00001132145,0.0003122299],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9970516,"threshold_uncertainty_score":0.3260279,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2747874407","doi":"10.21437/interspeech.2017-1386","title":"Montreal Forced Aligner: Trainable Text-Speech Alignment Using Kaldi","year":2017,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1124,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Computer science; Speech recognition; Natural language processing; Linguistics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.04401314992965729,"gpt":0.2826153983171813,"spread":0.238602248387524,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003147754,0.0001576163,0.0001904603,0.0000791144,0.0006521074,0.0007365605,0.001154824,0.00007229739,0.0003797728],"category_scores_gemma":[0.00006845491,0.0001333815,0.0001142351,0.00006463321,0.00005448173,0.0007618038,0.0002605781,0.00005482676,0.0001804539],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006460335,"about_ca_system_score_gemma":0.00005546538,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001145234,"about_ca_topic_score_gemma":0.0001471,"domain_scores_codex":[0.9986419,0.00003902063,0.0002080984,0.0003998099,0.0003211566,0.0003899845],"domain_scores_gemma":[0.9985608,0.00005050286,0.0001287754,0.001030514,0.00007166461,0.0001577514],"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":[0.000007904634,0.0001126974,0.0002163048,0.0000103472,0.00004884371,0.0001418586,0.0003334622,0.00001293336,0.009439431,0.02843433,0.005293717,0.9559482],"study_design_scores_gemma":[0.002471836,0.0001886413,0.007912846,0.00009378954,0.00006021287,0.0003572469,0.0005324424,0.4718942,0.4481527,0.03384263,0.03310801,0.001385481],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.05874941,0.00003521088,0.4518418,0.002678495,0.0005246354,0.0003443906,0.00000452187,0.0003659739,0.4854556],"genre_scores_gemma":[0.7617482,0.00001445007,0.225095,0.0008416267,0.0001147866,0.00001628764,0.000001233572,0.00001574419,0.01215263],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9545627,"threshold_uncertainty_score":0.7102669,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2107638917","doi":"10.1109/tasl.2006.881693","title":"Joint Factor Analysis Versus Eigenchannels in Speaker Recognition","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":709,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Normalization (sociology); NIST; Speaker recognition; Speech recognition; Computer science; Speaker verification; Gaussian; Joint (building); Session (web analytics); Mixture model; Pattern recognition (psychology); Artificial intelligence; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.0407489263447483,"gpt":0.2811270787352761,"spread":0.2403781523905278,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005038469,0.0001936986,0.0002577322,0.0009560433,0.000174114,0.0001809715,0.0001594837,0.0001129126,0.0003050107],"category_scores_gemma":[0.00002468523,0.0001847497,0.0001343143,0.001530706,0.0000393498,0.0004945417,0.000002714139,0.0002544082,0.00006132271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008387426,"about_ca_system_score_gemma":0.00003985568,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001024889,"about_ca_topic_score_gemma":0.001042329,"domain_scores_codex":[0.9984975,0.00005863392,0.0003345964,0.0004573132,0.0002843284,0.0003676426],"domain_scores_gemma":[0.9993193,0.0001390763,0.00009763881,0.0002161528,0.00007269192,0.0001551251],"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":[0.0000523654,0.0001025893,0.00001797869,0.00001850898,0.00006031465,0.00009585273,0.001916476,0.00002587404,0.002664435,0.000001957474,0.000002572658,0.9950411],"study_design_scores_gemma":[0.002547635,0.0002492324,0.004024476,0.0002258135,0.0003042094,0.0001014954,0.003894184,0.04250968,0.9446577,0.0002842268,0.0001331425,0.001068225],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1861613,0.0002132089,0.8111976,0.0001380639,0.0002208336,0.000119386,0.00001191204,0.0001513123,0.001786457],"genre_scores_gemma":[0.9591091,0.0000521744,0.04037699,0.0002382223,0.00004602881,0.00001009141,0.000003591203,0.0000123501,0.0001514181],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9939728,"threshold_uncertainty_score":0.7533876,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2136879537","doi":"10.1109/tasl.2008.925147","title":"A Study of Interspeaker Variability in Speaker Verification","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":591,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"NIST; Hyperparameter; Channel (broadcasting); Computer science; Word error rate; Task (project management); Joint (building); Speech recognition; Statistics; Function (biology); Error analysis; Pattern recognition (psychology); Artificial intelligence; Mathematics; Engineering; Applied mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02538206399158666,"gpt":0.2646189760404997,"spread":0.2392369120489131,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004543203,0.0001177381,0.000182225,0.000228681,0.0001115007,0.00003675378,0.0001745371,0.00005097907,0.00004838294],"category_scores_gemma":[0.00002653566,0.0001084938,0.00003693393,0.0004855895,0.00005319496,0.0003291435,0.000002574064,0.0001629339,0.000007665747],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003726531,"about_ca_system_score_gemma":0.00004207305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009309202,"about_ca_topic_score_gemma":0.0002510442,"domain_scores_codex":[0.9988912,0.0001523955,0.0002705281,0.0003368611,0.0002004283,0.0001485453],"domain_scores_gemma":[0.9994454,0.00009939809,0.00007974466,0.0002705913,0.0000480947,0.00005676552],"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":[0.00003804536,0.001200703,0.0006156095,0.00003514249,0.00001453992,0.00007188962,0.023717,0.0000292504,0.003329084,0.000006808323,0.000006689965,0.9709352],"study_design_scores_gemma":[0.01007935,0.001819436,0.07528951,0.0008410115,0.0001629973,0.001816748,0.04979117,0.1130386,0.7441034,0.0006293124,0.0002074673,0.002220928],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5679823,0.00003700893,0.4310421,0.00006524957,0.00005469318,0.0001519785,0.000001614359,0.00005576243,0.0006093275],"genre_scores_gemma":[0.9840333,0.0000180625,0.01573977,0.00008192321,0.000009028778,0.00002055272,3.813828e-7,0.000007379836,0.00008955089],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9687143,"threshold_uncertainty_score":0.4424247,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3167533889","doi":"10.48550/arxiv.2106.04624","title":"SpeechBrain: A General-Purpose Speech Toolkit","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":513,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke; McGill University","funders":"","keywords":"Computer science; Scripting language; Python (programming language); Inference; Architecture; Speech processing; Speech recognition; Speech technology; Natural language processing; Artificial intelligence; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.09161433237207015,"gpt":0.1896422480167848,"spread":0.09802791564471466,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003705845,0.0004735086,0.0005469205,0.0004003094,0.0001822325,0.0006191783,0.002723122,0.000473406,0.0007557536],"category_scores_gemma":[0.0001159834,0.0005692933,0.0005284693,0.0009357447,0.000102198,0.0005678798,0.003066885,0.0007389507,0.0005488498],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002551013,"about_ca_system_score_gemma":0.0004249424,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001535114,"about_ca_topic_score_gemma":0.0000798135,"domain_scores_codex":[0.9968985,0.0002845673,0.0003023122,0.001753351,0.0002223101,0.0005389405],"domain_scores_gemma":[0.9969086,0.0001548871,0.0002499586,0.002028847,0.0003297044,0.0003279787],"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":[0.0001564989,0.002271976,0.004624807,0.0007855138,0.001753132,0.06155245,0.001922656,0.02137806,0.003859554,0.4709179,0.02551983,0.4052576],"study_design_scores_gemma":[0.00250103,0.0001771393,0.003425209,0.0007043389,0.0004205251,0.0005242071,0.0006165836,0.8069736,0.03166083,0.1120065,0.03627672,0.004713353],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4423765,0.0001382216,0.5226116,0.0005802608,0.001614218,0.0004429121,0.00002850206,0.0007183857,0.03148945],"genre_scores_gemma":[0.8825709,0.0006066802,0.0947567,0.001445619,0.0003708986,0.000003293912,0.00007122805,0.00005493285,0.0201197],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7855955,"threshold_uncertainty_score":0.9996759,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W100623710","doi":"10.1007/3-540-33486-6_6","title":"Neural Probabilistic Language Models","year":2006,"lang":"en","type":"book-chapter","venue":"Studies in fuzziness and soft computing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":491,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Generalization; Sentence; Curse of dimensionality; Artificial intelligence; Word (group theory); Language model; Natural language processing; Probabilistic logic; Representation (politics); Sequence (biology); Set (abstract data type); Linguistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.06406113222153774,"gpt":0.28941119288099,"spread":0.2253500606594523,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002805903,0.000345754,0.0005941606,0.0001964269,0.0001827346,0.0001049697,0.0003682213,0.0001308193,0.000004901],"category_scores_gemma":[0.00007909731,0.000306416,0.00009243999,0.00007731361,0.0001824131,0.000139349,0.0006721122,0.0002832319,0.000007980156],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006141826,"about_ca_system_score_gemma":0.00002606957,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002334858,"about_ca_topic_score_gemma":0.00004249541,"domain_scores_codex":[0.9983869,0.00003024336,0.0004349553,0.0005997604,0.0002435178,0.0003045942],"domain_scores_gemma":[0.9988773,0.0004550763,0.0001702497,0.0003141897,0.0001352074,0.0000480017],"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":[0.000007709235,0.00004752537,0.00007798458,0.0006780433,0.0001370735,0.0005585744,0.003900859,0.002741684,0.000003369139,0.2241621,0.002159973,0.7655251],"study_design_scores_gemma":[0.0007351064,0.00006934301,0.0002297524,0.001604754,0.00005920057,0.0001265777,0.0004791156,0.7836746,0.00000670839,0.2091078,0.002542676,0.001364367],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.005854535,0.02727105,0.09722345,0.0007637673,0.002655595,0.001039915,0.00002811484,0.0008275007,0.8643361],"genre_scores_gemma":[0.8668099,0.001058679,0.04017885,0.0009828177,0.001456379,0.00004531004,0.0000334612,0.0001614042,0.08927318],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.8609554,"threshold_uncertainty_score":0.9999388,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2121415728","doi":"10.1109/tsa.2004.840940","title":"Eigenvoice modeling with sparse training data","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Speech and Audio Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":472,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Speech recognition; Training set; Set (abstract data type); Adaptation (eye); Limit (mathematics); Training (meteorology); Maximum likelihood; Covariance matrix; Pattern recognition (psychology); Estimation theory; Artificial intelligence; Covariance; Speaker recognition; Algorithm; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.095794255220844,"gpt":0.2797844726229301,"spread":0.1839902174020861,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002726736,0.0001901879,0.0001879965,0.0001690448,0.0004653042,0.0003546628,0.0005125126,0.00006532085,0.00003195935],"category_scores_gemma":[0.000005599377,0.0001617532,0.00003005645,0.0003566868,0.00004804187,0.001550951,0.000005577777,0.0002392281,0.00003861698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002682919,"about_ca_system_score_gemma":0.0001330814,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001081001,"about_ca_topic_score_gemma":0.00008380025,"domain_scores_codex":[0.9985489,0.00002995086,0.0002185233,0.0005894941,0.0002953285,0.0003178173],"domain_scores_gemma":[0.9991725,0.00005118871,0.00006399122,0.0004880103,0.00007161476,0.0001526927],"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":[0.00001484614,0.00006165026,0.000001055254,0.00001537318,0.00001530759,0.00001178199,0.0006581083,0.00325511,0.0004572441,0.00001467323,0.00001197543,0.9954829],"study_design_scores_gemma":[0.0004644322,0.00005592065,0.000004579971,0.0001738202,0.00003448621,0.0002031499,0.0003166973,0.9686379,0.02806155,0.0001262747,0.001602705,0.0003185304],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01749291,0.0001897205,0.9787946,0.001346009,0.00007415235,0.000100906,0.00001016485,0.0002581822,0.00173341],"genre_scores_gemma":[0.6683116,0.00008420311,0.3307822,0.0005898212,0.00007045313,0.000008308363,0.000001620514,0.00001475465,0.0001370415],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9951643,"threshold_uncertainty_score":0.6596104,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2188183693","doi":"10.21437/interspeech.2013-744","title":"Exploring convolutional neural network structures and optimization techniques for speech recognition","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":388,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Computer science; Convolutional neural network; Speech recognition; Artificial neural network; Artificial intelligence; Recurrent neural network; Time delay neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.09942673034509407,"gpt":0.2529693359682053,"spread":0.1535426056231112,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001180907,0.00009146586,0.00008749065,0.00006974306,0.0001383837,0.0002005752,0.0001267075,0.00004110316,0.0002426083],"category_scores_gemma":[0.00005051951,0.00008050597,0.00003384018,0.0001249889,0.00002546714,0.001274383,0.00004977857,0.00004409771,0.00001254514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001480689,"about_ca_system_score_gemma":0.00001059299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002444493,"about_ca_topic_score_gemma":0.000002811687,"domain_scores_codex":[0.9993136,0.00002874088,0.0001493345,0.0002270988,0.0001058076,0.0001754309],"domain_scores_gemma":[0.9994818,0.0001357581,0.00004689896,0.0001087819,0.0001659958,0.00006079637],"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":[0.000003328096,0.00000812804,0.00005720579,0.000007154084,0.000007085133,4.067008e-7,0.00002441802,0.0002115222,0.0001839639,0.003652401,0.002010996,0.9938334],"study_design_scores_gemma":[0.0002812362,0.0000967355,0.002308053,0.00002524695,0.000009572294,0.00006327446,0.00005263205,0.8970084,0.02704278,0.07169867,0.001081942,0.0003314496],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01388652,0.00002251554,0.9829663,0.0007905207,0.0002125976,0.0004379144,0.000002828964,0.000346009,0.001334766],"genre_scores_gemma":[0.04555434,0.00004740931,0.9533457,0.0005059658,0.0001931908,0.0002673473,0.0000165021,0.000007342989,0.00006220349],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.993502,"threshold_uncertainty_score":0.3282938,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963403664","doi":"10.21437/interspeech.2016-1446","title":"Towards End-to-End Speech Recognition with Deep Convolutional Neural Networks","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":341,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Institute for Advanced Research; Université de Montréal","funders":"","keywords":"End-to-end principle; Computer science; Speech recognition; Convolutional neural network; Deep learning; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.03436162498600204,"gpt":0.2491030066026894,"spread":0.2147413816166874,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004664594,0.0004756674,0.0004553997,0.0003389994,0.0001526681,0.0004388906,0.001220478,0.0003777322,0.003337984],"category_scores_gemma":[0.00008715614,0.0003407919,0.000214691,0.0003207488,0.0001075623,0.0003941093,0.001061439,0.0005347058,0.0007149164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001797985,"about_ca_system_score_gemma":0.0002488281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001018635,"about_ca_topic_score_gemma":0.0001529085,"domain_scores_codex":[0.9968011,0.0001872962,0.0004569393,0.001179737,0.0007759958,0.0005989544],"domain_scores_gemma":[0.9977834,0.0002349897,0.0002160038,0.0008661639,0.0005113045,0.0003881802],"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":[0.0000388824,0.00006120616,0.00008308882,0.00001592479,0.00007794611,0.00006487328,0.00004426359,0.0001139875,0.00002059851,0.001537913,0.002177414,0.9957639],"study_design_scores_gemma":[0.002431087,0.0006259657,0.01039068,0.001022375,0.0002011937,0.001267631,0.00009493739,0.8698321,0.01236438,0.08674683,0.01069885,0.00432396],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003888024,0.00006163631,0.9373121,0.004494649,0.001550992,0.0005526043,0.00005795111,0.0005705494,0.05151155],"genre_scores_gemma":[0.3964386,0.00007535329,0.5947539,0.004764482,0.001402506,0.0003189176,0.0002029751,0.00007026733,0.001972995],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9914399,"threshold_uncertainty_score":0.9999044,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2901997113","doi":"","title":"Char2Wav: End-to-End Speech Synthesis","year":2017,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":335,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institut National de la Recherche Scientifique; Université de Montréal","funders":"","keywords":"End-to-end principle; Computer science; Speech synthesis; Speech recognition; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.09295328918588806,"gpt":0.3624233461629727,"spread":0.2694700569770846,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003325211,0.0001645955,0.0001643949,0.0003242751,0.0007593175,0.001495697,0.002037018,0.00006336731,0.004040324],"category_scores_gemma":[0.003125869,0.0001675284,0.0001125875,0.0001068603,0.00008818629,0.0007289521,0.0003470157,0.0002789852,0.002615255],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006507093,"about_ca_system_score_gemma":0.00009426342,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002210982,"about_ca_topic_score_gemma":0.00004806055,"domain_scores_codex":[0.9981335,0.0001131951,0.0002634465,0.00057192,0.0006729452,0.0002450409],"domain_scores_gemma":[0.9978911,0.0004387332,0.0002411832,0.0008457612,0.0004083387,0.0001749175],"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":[0.00002338186,0.0001378234,0.006631118,0.00000359071,0.000105229,0.00009531893,0.000867534,0.00009594116,0.00429979,0.2218988,0.001731073,0.7641104],"study_design_scores_gemma":[0.001684199,0.0003893369,0.4363977,0.0007213777,0.0000789178,0.0002966625,0.00187464,0.272077,0.1285068,0.04067498,0.1150485,0.002249939],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.06219863,0.000004218702,0.07413485,0.05760833,0.001842855,0.0003206572,0.00003528175,0.0004374396,0.8034177],"genre_scores_gemma":[0.9703228,0.00002753366,0.01752426,0.0003961497,0.0001789961,0.0001036668,0.00001114344,0.00001368729,0.01142174],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9081242,"threshold_uncertainty_score":0.9995409,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2099621636","doi":"","title":"Vocal Tract Length Perturbation (VTLP) improves speech recognition","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":335,"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; Vocal tract; Normalization (sociology); Convolutional neural network; Spectrogram; Artificial neural network; Test set; Dynamic time warping; Word error rate; TIMIT; Image warping; Artificial intelligence; Pattern recognition (psychology); Hidden Markov model","retraction":null,"screen_n_in":null,"score":{"opus":0.0241960568558066,"gpt":0.2242876426069468,"spread":0.2000915857511402,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001909501,0.000135676,0.000125533,0.0001280839,0.00009962726,0.0003426846,0.0003296562,0.00009381343,0.002343166],"category_scores_gemma":[0.0001362711,0.000110594,0.00008771928,0.0002212595,0.00002552469,0.001584058,0.00005039569,0.0001131992,0.005139957],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003626118,"about_ca_system_score_gemma":0.0000309995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001075793,"about_ca_topic_score_gemma":0.00000766501,"domain_scores_codex":[0.9988604,0.00006464784,0.0002308194,0.0003454972,0.0002559561,0.0002426992],"domain_scores_gemma":[0.9991799,0.0001661344,0.00006627383,0.0002916715,0.000177275,0.0001187712],"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":[0.000001083639,0.00008251918,0.00002620575,0.000003534365,0.000005752305,0.000002649804,0.0000695294,4.41736e-8,0.004399523,0.0007057286,0.003368589,0.9913349],"study_design_scores_gemma":[0.001686939,0.0005854088,0.04752761,0.00007872809,0.0000415867,0.0004484887,0.0007308237,0.2405309,0.52996,0.1583865,0.01826332,0.001759718],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3839311,0.00004819433,0.3286797,0.008211552,0.0009938665,0.0008194505,0.000004411078,0.001231343,0.2760804],"genre_scores_gemma":[0.7033343,0.00003884849,0.2863952,0.002403005,0.0002199818,0.00009333124,0.00001821867,0.00001749494,0.007479699],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9895751,"threshold_uncertainty_score":0.9985688,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2103359087","doi":"","title":"Phone Recognition with the Mean-Covariance Restricted Boltzmann Machine","year":2010,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":275,"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":"TIMIT; Boltzmann machine; Computer science; Covariance; Hidden Markov model; Restricted Boltzmann machine; Speech recognition; Mixture model; Artificial intelligence; Covariance matrix; Pattern recognition (psychology); Algorithm; Artificial neural network; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.01803519807988988,"gpt":0.2190759133437164,"spread":0.2010407152638265,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002398153,0.0001213869,0.0001028057,0.00007393937,0.0001906801,0.0001906731,0.0005930828,0.00005835178,0.0007345024],"category_scores_gemma":[0.00007205134,0.00006753267,0.00003910327,0.0005602447,0.00006106221,0.0003463222,0.00006483474,0.0002708525,0.0007490541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007899986,"about_ca_system_score_gemma":0.00004256955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001165507,"about_ca_topic_score_gemma":0.0007131912,"domain_scores_codex":[0.9990382,0.00006087177,0.0001319271,0.0002962388,0.0002686614,0.0002041636],"domain_scores_gemma":[0.9989732,0.0001938569,0.00007080592,0.0005422967,0.0001431788,0.00007669452],"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":[0.00004954717,0.0001743174,0.000117062,0.000006259807,0.00004776669,0.00004720781,0.0003913259,0.000001585945,0.02422658,0.01178994,0.01510084,0.9480476],"study_design_scores_gemma":[0.005772464,0.0006533781,0.04235618,0.0001149615,0.0001381016,0.001638216,0.0004619315,0.1299054,0.53569,0.03365864,0.2468861,0.002724569],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07910521,0.00003102576,0.801684,0.01852968,0.0007177899,0.0004050687,0.00001208901,0.0007938029,0.09872129],"genre_scores_gemma":[0.6467043,0.00002307235,0.346419,0.00352445,0.0001773212,0.00005753168,0.00001329285,0.00001770695,0.003063296],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.945323,"threshold_uncertainty_score":0.9627824,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2172097686","doi":"10.1109/icassp.2012.6288863","title":"Understanding how Deep Belief Networks perform acoustic modelling","year":2012,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":270,"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":"Deep belief network; TIMIT; Computer science; Hidden Markov model; Artificial intelligence; Artificial neural network; Similarity (geometry); Feature (linguistics); Pattern recognition (psychology); Speech recognition; Feature vector; Visualization; Representation (politics)","retraction":null,"screen_n_in":null,"score":{"opus":0.1542638219167346,"gpt":0.2391786981223847,"spread":0.08491487620565008,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003107303,0.0001076889,0.0001047003,0.00008127094,0.0001972029,0.0002087204,0.000292923,0.00006777603,0.0002264961],"category_scores_gemma":[0.00001537388,0.00009066551,0.00005928898,0.0001767556,0.00001919808,0.0008190137,0.00008380842,0.0001099929,0.00007968699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001000269,"about_ca_system_score_gemma":0.00001132194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003550675,"about_ca_topic_score_gemma":0.000005019744,"domain_scores_codex":[0.9990863,0.00002497252,0.0001004734,0.0001727339,0.0001928522,0.0004227101],"domain_scores_gemma":[0.9993851,0.0001457994,0.00003588126,0.0002382273,0.00002791718,0.0001671158],"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":[0.00001430087,0.0003652952,0.002894316,0.00004695772,0.0001393073,0.00001855082,0.002742902,0.1666138,0.0002594939,0.5051228,0.005332418,0.3164498],"study_design_scores_gemma":[0.00008202136,0.00001058798,0.00003501869,0.00000856034,0.00000728945,0.00001630082,0.0002233806,0.9972193,0.0002237922,0.001781028,0.0002466897,0.000146009],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001327514,0.0001043522,0.9750746,0.0004295871,0.0004280631,0.00006323471,1.449858e-7,0.0002116352,0.02236088],"genre_scores_gemma":[0.8830202,0.00004289324,0.115991,0.0003501867,0.0001801361,0.000004635551,7.383667e-7,0.000007900603,0.0004022517],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8816927,"threshold_uncertainty_score":0.3697232,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1269046860","doi":"10.1201/9781482276237","title":"Speech Processing","year":2018,"lang":"en","type":"book","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":239,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Université du Québec à Montréal","funders":"","keywords":"Speech recognition; Computer science; Natural language processing","retraction":null,"screen_n_in":null,"score":{"opus":0.0272552053198968,"gpt":0.2467195160514359,"spread":0.2194643107315391,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000166537,0.000172664,0.0001881817,0.0001448931,0.0000770879,0.0002716725,0.000841357,0.0001978105,0.001957658],"category_scores_gemma":[0.00002677153,0.0001445329,0.0000874714,0.00008395059,0.00004788817,0.0002100111,0.0001693597,0.0001329684,0.005687085],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006450869,"about_ca_system_score_gemma":0.0003908776,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001196807,"about_ca_topic_score_gemma":0.000005191399,"domain_scores_codex":[0.9989225,0.00001612433,0.0001732263,0.0004016317,0.00030398,0.0001824852],"domain_scores_gemma":[0.9991875,0.00004662549,0.00009498173,0.0004363968,0.0001556588,0.00007881502],"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":[2.844536e-7,0.000006076278,1.378061e-7,0.00001523078,0.000005236035,0.00001791543,0.00001715169,1.669275e-9,0.000002907173,0.008011482,0.3225252,0.6693983],"study_design_scores_gemma":[0.00004999029,0.00002079649,0.000002985709,0.000109567,0.000006818148,0.00006363713,0.000001585125,0.001293223,0.0009318386,0.05026722,0.9469854,0.0002668896],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[4.266015e-7,0.00006386782,0.1468065,0.0002778372,0.0002643065,0.00007507874,0.000001115525,0.0003666103,0.8521443],"genre_scores_gemma":[0.000002610029,0.000009543915,0.2091728,0.001131263,0.0003432176,0.000003486709,0.000003222376,0.0000134198,0.7893205],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.6691315,"threshold_uncertainty_score":0.9989547,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2132037657","doi":"10.1109/icassp.2011.5947700","title":"Learning a better representation of speech soundwaves using restricted boltzmann machines","year":2011,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":229,"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":"Cepstrum; Speech recognition; Computer science; Mel-frequency cepstrum; Linear predictive coding; Boltzmann machine; Restricted Boltzmann machine; Representation (politics); Artificial intelligence; Speech coding; Pattern recognition (psychology); Artificial neural network; Feature extraction","retraction":null,"screen_n_in":null,"score":{"opus":0.07598615674813156,"gpt":0.2849837548539779,"spread":0.2089975981058464,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001082853,0.00008017486,0.0001273152,0.0001799707,0.00006949467,0.00004629922,0.0002582915,0.00004203966,0.0003569821],"category_scores_gemma":[0.0001338579,0.00006902261,0.00006371013,0.0004229106,0.00003029679,0.0003782194,0.00009109051,0.00007691366,0.00003773375],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001003962,"about_ca_system_score_gemma":0.00001772979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004551654,"about_ca_topic_score_gemma":0.00001136541,"domain_scores_codex":[0.9991367,0.0001020831,0.0002205412,0.0002189473,0.0001887266,0.0001330186],"domain_scores_gemma":[0.9994141,0.00008807412,0.0001140833,0.0002427587,0.0001003551,0.00004064319],"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":[0.00002325241,0.0001119302,0.06314261,0.00002050016,0.0000612131,0.00004666313,0.002719283,0.00001310465,0.04853439,0.003344656,0.0002776803,0.8817047],"study_design_scores_gemma":[0.0006551478,0.0001829651,0.1251838,0.00006293895,0.00004020578,0.0001534187,0.0005694138,0.2876958,0.5673507,0.01711977,0.000480499,0.0005052941],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7208279,0.000008825077,0.2526343,0.0001009755,0.0001072502,0.00007589275,3.863569e-7,0.0001436255,0.02610077],"genre_scores_gemma":[0.5655645,0.000005041177,0.4337256,0.00009507201,0.00003787461,0.000001865996,0.000001332226,0.000006181275,0.0005625382],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8811994,"threshold_uncertainty_score":0.3908704,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1556470778","doi":"","title":"Prosodylab-aligner: A tool for forced alignment of laboratory speech","year":2011,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":228,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":false},"ca_institutions":"McGill University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Computer science; Hidden Markov model; Unix; Scripting language; Speech recognition; Operating system; Process (computing); Computer graphics (images); Software","retraction":null,"screen_n_in":null,"score":{"opus":0.02785983580016489,"gpt":0.2188774394414399,"spread":0.191017603641275,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002223141,0.0001148423,0.0001579789,0.0001682183,0.00007453654,0.00004097386,0.0004640346,0.00008784898,0.0001469591],"category_scores_gemma":[0.0001668793,0.0001176422,0.0000607432,0.0002362731,0.0000437773,0.0001188928,0.00002818171,0.00004462274,0.00003535335],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001224255,"about_ca_system_score_gemma":0.0006355367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001596502,"about_ca_topic_score_gemma":0.0009996244,"domain_scores_codex":[0.9990371,0.0000218485,0.000230996,0.0002241347,0.0001503583,0.0003355344],"domain_scores_gemma":[0.9989009,0.00006296746,0.0000812575,0.0004033313,0.0002674858,0.0002840399],"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":[0.00005842448,0.0003648993,0.001948435,0.0005048794,0.0003145191,0.0003710918,0.005342745,0.00002689796,0.2149309,0.1914515,0.1549429,0.4297428],"study_design_scores_gemma":[0.003397741,0.001194271,0.01313653,0.0002803511,0.0003036034,0.00009586182,0.001123074,0.06995209,0.7981355,0.03039292,0.07931206,0.002676039],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.125463,0.00009387691,0.8519852,0.0004805618,0.001360569,0.001553837,0.0008300007,0.0001934349,0.01803951],"genre_scores_gemma":[0.6825685,0.000008838217,0.315399,0.001231136,0.00006937145,0.00006355424,0.000007088523,0.00001941334,0.0006331311],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5832046,"threshold_uncertainty_score":0.479731,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2084514013","doi":"10.1109/msp.2009.932166","title":"Developments and directions in speech recognition and understanding, Part 1 [DSP Education]","year":2009,"lang":"en","type":"article","venue":"IEEE Signal Processing Magazine","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":227,"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":"Computer science; Set (abstract data type); Focus (optics); Field (mathematics); Data science; Speech processing; Digital signal processing; Speech recognition","retraction":null,"screen_n_in":null,"score":{"opus":0.06475663745855617,"gpt":0.2729375041776006,"spread":0.2081808667190444,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002419027,0.0001232971,0.0001258782,0.0002659811,0.0001729007,0.0002701892,0.0001010192,0.00005590283,0.00002604962],"category_scores_gemma":[0.00003054895,0.0001206337,0.00001375427,0.0004553094,0.00004194084,0.0006580491,0.00001720398,0.0001083844,0.000037432],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008083587,"about_ca_system_score_gemma":0.000205494,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005174031,"about_ca_topic_score_gemma":0.00003043551,"domain_scores_codex":[0.999076,0.00004026051,0.0002113704,0.0003289755,0.000158183,0.0001852309],"domain_scores_gemma":[0.999634,0.00004593029,0.00007454961,0.00007479693,0.00007519831,0.00009557866],"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":[0.000005282739,0.00009240721,0.0003156615,0.00001648735,0.000002697195,0.000005606366,0.0002067974,1.968853e-7,0.001238184,0.0001104877,0.0006299036,0.9973763],"study_design_scores_gemma":[0.005264725,0.00086392,0.1733716,0.004633491,0.0001314767,0.002287316,0.001471059,0.02494906,0.07672463,0.6433948,0.06283494,0.004073024],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4775688,0.003085946,0.3330736,0.01016345,0.001394743,0.001247319,0.00001862697,0.001095215,0.1723523],"genre_scores_gemma":[0.9342061,0.0001900841,0.06372764,0.0009692683,0.00009521849,0.0000151309,0.000007935136,0.000009362049,0.0007793027],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9933032,"threshold_uncertainty_score":0.4919299,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2964187693","doi":"10.1109/icassp.2018.8462688","title":"Deep Residual Learning for Small-Footprint Keyword Spotting","year":2018,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":227,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Keyword spotting; Computer science; Residual; Convolutional neural network; Deep learning; Footprint; Memory footprint; Benchmark (surveying); Artificial intelligence; Spotting; Machine learning; Speech recognition; Algorithm; Cartography","retraction":null,"screen_n_in":null,"score":{"opus":0.04154259823274774,"gpt":0.2640082849263389,"spread":0.2224656866935912,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004389965,0.00008724374,0.00009872248,0.00008103303,0.0002403683,0.0001639684,0.0003982715,0.0000459548,0.0001751225],"category_scores_gemma":[0.0003452814,0.00007699701,0.00005884938,0.0001532757,0.00003492016,0.00008730525,0.0001409629,0.00007543112,0.0002731074],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001766652,"about_ca_system_score_gemma":0.00002546378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001528034,"about_ca_topic_score_gemma":0.00004936984,"domain_scores_codex":[0.9991183,0.00004479012,0.0001621718,0.0002944797,0.000117772,0.0002625301],"domain_scores_gemma":[0.9992498,0.0002599815,0.00005304314,0.0002178709,0.0001445885,0.00007471046],"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":[0.000007756544,0.00001937345,0.0004424587,0.000005756944,0.00001124766,0.000002633699,0.0003355568,0.000006301837,0.0009498247,0.02059416,0.000223745,0.9774012],"study_design_scores_gemma":[0.001205193,0.0006628312,0.008610711,0.00007027026,0.00002134848,0.00006798679,0.0008102995,0.514668,0.3284133,0.01670033,0.1278835,0.0008861953],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0326277,0.00000834525,0.9115483,0.0007730432,0.000228317,0.0001174358,8.836763e-8,0.0003276812,0.05436911],"genre_scores_gemma":[0.3253387,0.000002344914,0.6703811,0.0004422787,0.000326429,0.00002004643,7.250401e-7,0.000009640082,0.003478793],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.976515,"threshold_uncertainty_score":0.3510334,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2112582577","doi":"10.1109/tasl.2007.894527","title":"Speaker and Session Variability in GMM-Based Speaker Verification","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":227,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"NIST; Computer science; Speaker recognition; Speech recognition; Session (web analytics); Set (abstract data type); Statistic; Pattern recognition (psychology); Artificial intelligence; Speaker diarisation; Factor (programming language); Feature (linguistics); Statistics; Mathematics; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.01295308220622218,"gpt":0.2605477096187157,"spread":0.2475946274124935,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001315303,0.000161855,0.0001653428,0.0002685488,0.0001832532,0.0001589102,0.0001322261,0.0001082042,0.00007621456],"category_scores_gemma":[0.00004018613,0.0001476082,0.00003670782,0.0004684351,0.00006659441,0.0004118353,0.000002488733,0.0002303043,0.00001280793],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006003976,"about_ca_system_score_gemma":0.00005992299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005419949,"about_ca_topic_score_gemma":0.0001813788,"domain_scores_codex":[0.9986907,0.0001073364,0.0002655813,0.000455952,0.0002173576,0.0002631053],"domain_scores_gemma":[0.9992757,0.0002203385,0.00007445329,0.0002482387,0.00005311141,0.0001281506],"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":[0.00003647326,0.0001387215,0.0002293225,0.00005204498,0.000003447501,0.0000303324,0.0008241988,0.00001435299,0.009569786,0.00001405683,0.000004907499,0.9890823],"study_design_scores_gemma":[0.002332906,0.0001441388,0.02529149,0.0005402766,0.00004676487,0.0002159962,0.001382958,0.1408985,0.8269771,0.0006315889,0.0006210352,0.0009172293],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1819227,0.0001249125,0.8160593,0.0003891807,0.0001005078,0.0001440604,0.000002784209,0.0001221778,0.001134405],"genre_scores_gemma":[0.9241261,0.0000194684,0.07525355,0.0004559355,0.00002261722,0.000008462847,0.000001452295,0.00001085084,0.0001015848],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9881651,"threshold_uncertainty_score":0.6019288,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1993409002","doi":"10.1109/icassp.2013.6639211","title":"Fast speaker adaptation of hybrid NN/HMM model for speech recognition based on discriminative learning of speaker code","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":224,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Speech recognition; Computer science; TIMIT; Hidden Markov model; Speaker diarisation; Adaptation (eye); Speaker recognition; Discriminative model; Artificial intelligence; Artificial neural network; Pattern recognition (psychology)","retraction":null,"screen_n_in":null,"score":{"opus":0.06434906411656907,"gpt":0.2616561921307978,"spread":0.1973071280142288,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003393628,0.0001605264,0.0002496037,0.0002309085,0.00006601556,0.00005035784,0.0002506618,0.00004341212,0.0003972967],"category_scores_gemma":[0.0002858671,0.0001396303,0.0001458687,0.0001840781,0.00005438626,0.0005575129,0.00003742019,0.00009945053,0.0001050704],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003564876,"about_ca_system_score_gemma":0.00005945603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008424727,"about_ca_topic_score_gemma":0.00002821451,"domain_scores_codex":[0.9985911,0.00009767435,0.0003998048,0.0003481985,0.0003564114,0.0002068453],"domain_scores_gemma":[0.9984005,0.0004095711,0.0002729438,0.0002486951,0.000596322,0.00007194113],"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":[0.00005557026,0.0003251071,0.00005771143,0.00006759682,0.00002608653,0.000001688263,0.0008193885,0.01197062,0.003827452,0.001506455,0.0008301522,0.9805122],"study_design_scores_gemma":[0.0004899175,0.0001924668,0.0002875574,0.00007076332,0.00001499101,0.000002375628,0.0004773827,0.8385168,0.1563506,0.003408264,0.00003837376,0.0001504356],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07350665,0.000002521044,0.9139122,0.0004337323,0.00007254207,0.0004928307,0.00003506648,0.00007169387,0.01147274],"genre_scores_gemma":[0.6598601,0.00000294191,0.3389899,0.0001732495,0.00001623742,0.00004799789,0.00003597292,0.00001232922,0.0008611751],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9803618,"threshold_uncertainty_score":0.5693957,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2141778357","doi":"10.21437/interspeech.2010-304","title":"Investigation of full-sequence training of deep belief networks for speech recognition","year":2010,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":213,"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; Training (meteorology); Speech recognition; Sequence (biology); Artificial intelligence; Natural language processing","retraction":null,"screen_n_in":null,"score":{"opus":0.08245940770069941,"gpt":0.2678514967899197,"spread":0.1853920890892203,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000538206,0.00008434751,0.0001608902,0.0001136939,0.00004553222,0.00002605716,0.00030095,0.00009976496,0.0001277437],"category_scores_gemma":[0.0002495228,0.00007944139,0.00007799933,0.0002729689,0.00008594988,0.0003453089,0.00003104948,0.00009733804,0.000006933292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006495889,"about_ca_system_score_gemma":0.00004559041,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001688515,"about_ca_topic_score_gemma":0.0001072706,"domain_scores_codex":[0.9991207,0.00003179996,0.0003255511,0.0002092496,0.0001591158,0.0001535959],"domain_scores_gemma":[0.998894,0.0003237624,0.0001936266,0.0002302748,0.0002886257,0.00006976115],"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":[0.000006391063,0.0000115672,0.0000897506,0.00001557578,0.000007865406,4.36596e-7,0.000278725,0.000005180521,0.1303285,0.003495653,0.00005581076,0.8657045],"study_design_scores_gemma":[0.0004256602,0.00018108,0.0008492841,0.00005314701,0.00001672805,0.00004486329,0.0001531744,0.3228397,0.6324756,0.04262456,0.000122525,0.0002137281],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2323066,0.00000645982,0.764337,0.0002597278,0.0003001934,0.0002011735,0.000004922095,0.00006576775,0.002518117],"genre_scores_gemma":[0.4904674,0.000004173178,0.5092999,0.0001318529,0.00004682933,0.00001600662,0.000009575258,0.000004407423,0.00001990319],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8654908,"threshold_uncertainty_score":0.3239526,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2064364374","doi":"10.1109/icassp.2013.6639151","title":"PLDA for speaker verification with utterances of arbitrary duration","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":205,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"NIST; Computer science; Speaker verification; Covariance; Speech recognition; Classifier (UML); Speaker recognition; Duration (music); Speech processing; Artificial intelligence; Pattern recognition (psychology); Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.01382047087280255,"gpt":0.2059364721303044,"spread":0.1921160012575018,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005576915,0.00004087764,0.00005690563,0.00003549803,0.00002539087,0.00004864551,0.0001265526,0.00001642533,0.0001687932],"category_scores_gemma":[0.00001069739,0.00002835837,0.00002040731,0.00008822271,0.0000149969,0.0004980108,0.000006026847,0.00001377185,0.00005746843],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004079574,"about_ca_system_score_gemma":0.0000149132,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002830392,"about_ca_topic_score_gemma":0.00000924572,"domain_scores_codex":[0.9996128,0.00001050454,0.0001144896,0.000115838,0.00008489821,0.00006148905],"domain_scores_gemma":[0.9996291,0.00005152663,0.00005483716,0.0001444091,0.00009965233,0.00002052004],"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":[0.00002926936,0.0001700005,0.002734408,0.00006258037,0.00004117897,5.304689e-7,0.0006046642,0.000005028826,0.03657632,0.0888043,0.006697182,0.8642746],"study_design_scores_gemma":[0.0009052384,0.0003001912,0.07849468,0.00005151714,0.00001221312,0.00001706743,0.0002194223,0.1132954,0.7808867,0.01854105,0.006931928,0.0003446234],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1356091,0.000007449828,0.848493,0.001584458,0.00005782738,0.0002745158,9.935045e-7,0.00005769836,0.01391492],"genre_scores_gemma":[0.6707506,0.000003004064,0.3285094,0.0003098012,0.00001473358,0.00005833642,0.000002681496,0.000002298674,0.0003490532],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8639299,"threshold_uncertainty_score":0.1848167,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1990505856","doi":"10.1109/icassp.2014.6854321","title":"Deep mixture density networks for acoustic modeling in statistical parametric speech synthesis","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":193,"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":"Naturalness; Parametric statistics; Computer science; Speech synthesis; Artificial neural network; Speech recognition; Probability density function; Layer (electronics); Deep neural networks; Mixture model; Statistical model; Artificial intelligence; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.02765918503457674,"gpt":0.2498129052068847,"spread":0.222153720172308,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007314714,0.0001549413,0.0002744335,0.0002420541,0.00009033376,0.0001473861,0.0004327386,0.0001400365,0.00007527889],"category_scores_gemma":[0.002133135,0.0001355934,0.0000733651,0.0005271453,0.00002239161,0.0001614807,0.00008196736,0.0001459015,0.00004502795],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004849803,"about_ca_system_score_gemma":0.00002388021,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005618233,"about_ca_topic_score_gemma":0.0002267961,"domain_scores_codex":[0.9985265,0.0001243893,0.0002872464,0.0004450915,0.0002173098,0.0003995242],"domain_scores_gemma":[0.9964512,0.00290771,0.00004348454,0.0003533176,0.0001081201,0.0001361437],"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":[0.00002051609,0.0001125682,0.0003334563,0.0000248102,0.00001531195,0.00001522267,0.00002834406,0.03919595,0.00003565282,0.0129351,0.0004418647,0.9468412],"study_design_scores_gemma":[0.0001651063,0.00002595943,0.0003223513,0.00001564509,0.00001466631,0.00001530615,0.00001500349,0.9892396,0.0004348662,0.009512761,0.00004618543,0.0001925747],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007316679,0.00002007109,0.9907631,0.000228796,0.0001888536,0.0002156126,0.000001667702,0.0001354295,0.001129747],"genre_scores_gemma":[0.5902571,0.000007613695,0.4092905,0.0003301768,0.00004963795,0.00002869945,0.000001591946,0.000007601499,0.0000270766],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9500436,"threshold_uncertainty_score":0.5529337,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W217970951","doi":"","title":"Roles of Pre-Training and Fine-Tuning in Context-Dependent DBN-HMMs for Real-World Speech Recognition","year":2010,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":193,"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":"Hidden Markov model; Computer science; Artificial intelligence; Speech recognition; Context (archaeology); Deep belief network; Vocabulary; Deep learning; Pattern recognition (psychology)","retraction":null,"screen_n_in":null,"score":{"opus":0.0420777987342523,"gpt":0.2835390570334626,"spread":0.2414612582992103,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000763245,0.0001332696,0.0002556066,0.0004024435,0.0001186861,0.0004245667,0.0002246209,0.00008703562,0.000004729096],"category_scores_gemma":[0.0002113834,0.000123273,0.00004269633,0.0003022582,0.00003645549,0.003209876,0.00004246485,0.0001693522,0.00000484223],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002272735,"about_ca_system_score_gemma":0.0000696218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001503054,"about_ca_topic_score_gemma":0.000627518,"domain_scores_codex":[0.9986246,0.00004144628,0.0006912945,0.0001680928,0.000268557,0.000206017],"domain_scores_gemma":[0.998879,0.0001659506,0.0004416089,0.0001582487,0.0002912193,0.00006403793],"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":[0.00001615478,0.00001307343,0.0004046288,0.0003089892,0.000005102698,6.750821e-7,0.00350159,0.00003468509,0.001725116,0.0003881677,0.00003337425,0.9935684],"study_design_scores_gemma":[0.00165567,0.0001393284,0.003347272,0.000954856,0.00002043242,0.0001572047,0.003941684,0.9532833,0.03164655,0.00103197,0.003318684,0.00050308],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9327809,0.0001477271,0.0603407,0.0002795796,0.0009138031,0.001014206,0.00003007015,0.0002641313,0.004228856],"genre_scores_gemma":[0.9893546,0.000006568281,0.01028796,0.00009001032,0.000059843,0.00008711599,0.00002071331,0.000007024084,0.000086209],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9930654,"threshold_uncertainty_score":0.5026926,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2076794394","doi":"10.1109/asru.2011.6163900","title":"Making Deep Belief Networks effective for large vocabulary continuous speech recognition","year":2011,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":192,"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; Vocabulary; Artificial intelligence; Natural language processing; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.04830958816975836,"gpt":0.2643455917612188,"spread":0.2160360035914604,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005977419,0.0001740242,0.0002234626,0.0001253518,0.0001819804,0.0001024714,0.0003968972,0.0001333057,0.0004575745],"category_scores_gemma":[0.0001287039,0.0001590639,0.0001545416,0.000237562,0.00001929086,0.0004476813,0.000115258,0.0001186396,0.000236265],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003325354,"about_ca_system_score_gemma":0.00001439577,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001390432,"about_ca_topic_score_gemma":0.00005485161,"domain_scores_codex":[0.9986274,0.0001032402,0.0002392598,0.0004419291,0.0001509727,0.0004372312],"domain_scores_gemma":[0.9989771,0.0003178732,0.0001032087,0.00031433,0.0002009359,0.0000864978],"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":[0.00003071526,0.0001422658,0.0002496431,0.000009844843,0.00003878753,0.00002517524,0.0002703959,3.109945e-7,0.00003855557,0.003809429,0.0008080166,0.9945769],"study_design_scores_gemma":[0.006592719,0.001929206,0.02198635,0.0004512249,0.0002406039,0.0005954406,0.0009449878,0.6969224,0.1383718,0.1102279,0.01879123,0.002946146],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003666086,0.00008333469,0.9520586,0.00006620299,0.0005374809,0.0007541736,0.000005647375,0.0003778688,0.0424506],"genre_scores_gemma":[0.4754765,0.00001629314,0.5218537,0.001838188,0.0002027143,0.0002566983,0.0000163726,0.00002473016,0.0003148471],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9916307,"threshold_uncertainty_score":0.6486439,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2036242736","doi":"10.1109/icassp.2013.6638952","title":"A deep convolutional neural network using heterogeneous pooling for trading acoustic invariance with phonetic confusion","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":188,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Computer science; Word error rate; Speech recognition; Pooling; Convolutional neural network; TIMIT; Artificial intelligence; Dropout (neural networks); Deep learning; Artificial neural network; Hidden Markov model; Pattern recognition (psychology); Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.03207903847495538,"gpt":0.2313530530693191,"spread":0.1992740145943637,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001207194,0.000146062,0.0001663284,0.0000565278,0.0002679234,0.0002301759,0.0002815456,0.00005261008,0.000292583],"category_scores_gemma":[0.00003160375,0.0001190004,0.000060531,0.0002059014,0.0000432714,0.0003345381,0.00005273641,0.0000685991,0.00003000575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004418596,"about_ca_system_score_gemma":0.00005173636,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005419262,"about_ca_topic_score_gemma":0.00003003511,"domain_scores_codex":[0.9988477,0.0000428021,0.0002047791,0.0003317058,0.0001860578,0.0003870176],"domain_scores_gemma":[0.9991992,0.0002713804,0.00008101507,0.0001909968,0.0001369365,0.0001205025],"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":[0.0001561053,0.0002979954,0.001164795,0.0001456654,0.0002491642,0.00009471588,0.000878106,0.6869699,0.07857637,0.01227973,0.001551208,0.2176362],"study_design_scores_gemma":[0.0003852696,0.00006924124,0.0003254412,0.00003669956,0.00001432629,0.000259199,0.00001996796,0.995303,0.001336793,0.002026483,0.00003265871,0.0001909677],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1329963,0.00007070028,0.8657231,0.0001789187,0.0002369028,0.0003811899,7.256913e-7,0.0001182105,0.0002940477],"genre_scores_gemma":[0.6900868,0.000001633815,0.308955,0.0007574912,0.0001097124,0.00003913824,0.000001605464,0.000009776363,0.00003880907],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5570906,"threshold_uncertainty_score":0.4852695,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2125964738","doi":"10.1109/icassp.2011.5947401","title":"Large vocabulary continuous speech recognition with context-dependent DBN-HMMS","year":2011,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":182,"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":"Hidden Markov model; Computer science; Speech recognition; Word error rate; Mixture model; Artificial intelligence; Context (archaeology); Vocabulary; Phone; Pattern recognition (psychology); Sentence","retraction":null,"screen_n_in":null,"score":{"opus":0.03873870180704939,"gpt":0.2173281653530459,"spread":0.1785894635459966,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0004110294,0.0002011354,0.0002538336,0.0001419684,0.000118866,0.000124379,0.0005281487,0.00009655349,0.002876805],"category_scores_gemma":[0.00004083712,0.0001541033,0.0001002599,0.000239409,0.00004244676,0.0006554207,0.0001183069,0.000147751,0.002145872],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002905951,"about_ca_system_score_gemma":0.00004930666,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001580064,"about_ca_topic_score_gemma":0.0002487314,"domain_scores_codex":[0.9983485,0.0000930692,0.0002626186,0.0004993215,0.0003899103,0.0004065858],"domain_scores_gemma":[0.9989167,0.00006815117,0.00009451789,0.0005391151,0.0002084967,0.0001730232],"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":[0.00005725509,0.0004490482,0.0012672,0.00001023303,0.0001053643,0.0003861002,0.0009402154,2.47706e-8,0.0002189618,0.003607533,0.002377335,0.9905807],"study_design_scores_gemma":[0.008849259,0.002354049,0.01556924,0.0003238616,0.0002289254,0.002975082,0.006052717,0.004009959,0.8762734,0.02971529,0.05034386,0.003304374],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1110591,0.0001647968,0.6135224,0.0003000859,0.0005108547,0.0005798393,0.00002200338,0.001004395,0.2728365],"genre_scores_gemma":[0.8621283,0.00002824447,0.1318634,0.00215437,0.00006532809,0.00004412537,0.00001038495,0.00002323544,0.003682611],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9872764,"threshold_uncertainty_score":0.9986311,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2989571531","doi":"10.1109/sped.2019.8906599","title":"FoR: A Dataset for Synthetic Speech Detection","year":2019,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":169,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Computer science; Speech recognition; Artificial intelligence; Natural language processing","retraction":null,"screen_n_in":null,"score":{"opus":0.02481780576436919,"gpt":0.2639481081266526,"spread":0.2391303023622834,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002148156,0.00006214403,0.00008315202,0.00006241952,0.00004986102,0.0000818887,0.0002814422,0.00003570029,0.0001660132],"category_scores_gemma":[0.00007209044,0.0000526136,0.00005945665,0.00008148648,0.000006160402,0.0002089381,0.00003657753,0.00002135559,0.0004716318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001502512,"about_ca_system_score_gemma":0.00001361575,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007228404,"about_ca_topic_score_gemma":0.00002301739,"domain_scores_codex":[0.9994123,0.00001164686,0.00009931066,0.000245524,0.00008310378,0.0001481423],"domain_scores_gemma":[0.9992871,0.0002483911,0.00002887758,0.0003508302,0.00004584797,0.00003899339],"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":[0.00001570528,0.00003732248,0.00001519565,0.00002724221,0.00001229988,4.485088e-7,0.00001702728,8.6271e-7,0.007395199,0.00581796,0.0130118,0.973649],"study_design_scores_gemma":[0.0006418684,0.0002019258,0.00005844301,0.0000117267,0.00001114721,0.0000361244,0.00003464519,0.1511707,0.3819898,0.009282066,0.4563312,0.0002303031],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003962292,0.000004774166,0.9914281,0.0004731939,0.0003901935,0.000554185,0.0002224963,0.00009889796,0.002865816],"genre_scores_gemma":[0.280052,0.000005011217,0.7133036,0.001849726,0.0001114753,0.000259518,0.0001922683,0.00001889942,0.004207509],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9734187,"threshold_uncertainty_score":0.6062029,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1749856071","doi":"","title":"A new algorithm for the alignment of phonetic sequences","year":2000,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":167,"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; Similarity (geometry); Algorithm; Basis (linear algebra); Scheme (mathematics); Sequence (biology); Phonology; Multiple sequence alignment; Artificial intelligence; Speech recognition; Sequence alignment; Mathematics; Image (mathematics); Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.02299981020833271,"gpt":0.2477532114839289,"spread":0.2247534012755962,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001082321,0.00004250349,0.00005931057,0.00001577718,0.00003974009,0.00003379015,0.0003503413,0.00001410744,0.002170802],"category_scores_gemma":[0.000005308919,0.00002442856,0.00005034275,0.00009843112,0.00001740734,0.00006378964,0.00001424092,0.0000131404,0.00007654703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005756086,"about_ca_system_score_gemma":0.00003491951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001246616,"about_ca_topic_score_gemma":0.00000699949,"domain_scores_codex":[0.9995682,0.00001236997,0.00009917906,0.0001059683,0.0001241027,0.0000902001],"domain_scores_gemma":[0.999576,0.0001754193,0.00001935211,0.0001766146,0.00001837001,0.00003426348],"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":[5.652091e-7,0.000008115039,0.000001133126,6.982835e-7,0.000007047801,2.685395e-7,0.00009025643,0.000002339877,0.00008762752,0.001109647,0.003124005,0.9955683],"study_design_scores_gemma":[0.0008792391,0.0002650536,0.000808879,0.00003123504,0.00003228477,0.00004167444,0.0002606266,0.5517417,0.2238406,0.03409684,0.1876896,0.0003122519],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000286914,0.00009271494,0.9863688,0.001958852,0.00008174398,0.0001427862,0.000001622609,0.00003510059,0.01103146],"genre_scores_gemma":[0.0105967,0.00008765461,0.9763611,0.0007732111,0.00004765426,0.00002232937,2.829449e-7,0.000002632436,0.01210843],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9952561,"threshold_uncertainty_score":0.9987413,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2123798005","doi":"10.1109/icassp.2010.5495646","title":"Multilingual acoustic modeling for speech recognition based on subspace Gaussian Mixture Models","year":2010,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":160,"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":"Subspace topology; Computer science; Phone; Gaussian; Mixture model; Speech recognition; Set (abstract data type); Language model; Artificial intelligence; Acoustic model; Space (punctuation); Hidden Markov model; Natural language processing; Pattern recognition (psychology); Speech processing; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.04797919133278814,"gpt":0.2764242881821557,"spread":0.2284450968493676,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004127781,0.0002080482,0.0001814518,0.0002107022,0.0001810037,0.0001941427,0.0004431274,0.0001964431,0.0001600793],"category_scores_gemma":[0.0002554482,0.0001800428,0.0001471685,0.0002083339,0.00002111371,0.0004200199,0.0000340876,0.0002804894,0.0001021577],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002291958,"about_ca_system_score_gemma":0.00009164342,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002248266,"about_ca_topic_score_gemma":0.000189249,"domain_scores_codex":[0.9985311,0.00003705748,0.0002331747,0.0005422023,0.0003035287,0.0003529551],"domain_scores_gemma":[0.9986911,0.0003346988,0.00006308531,0.0004938963,0.0002488419,0.000168398],"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":[0.00007507773,0.0002866925,0.000004544442,0.00003629785,0.00001522996,0.00001702024,0.0001896961,0.01951184,0.02080236,0.001307637,0.00060509,0.9571485],"study_design_scores_gemma":[0.0005239919,0.00005966036,0.000002340027,0.00002670211,0.00001177944,0.00001113875,0.00003978732,0.9110518,0.07773715,0.0101746,0.0001086077,0.0002524492],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04771985,0.000002774935,0.9412403,0.001162444,0.0005957349,0.0005251132,0.00001948675,0.0003817787,0.008352594],"genre_scores_gemma":[0.5557336,0.000001408834,0.442945,0.0008885824,0.0001172392,0.0000599417,0.00001485087,0.00001592248,0.0002235452],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9568961,"threshold_uncertainty_score":0.734193,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2137743578","doi":"10.1109/34.845379","title":"Training hidden Markov models with multiple observations-a combinatorial method","year":2000,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":150,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Polytechnique Montréal; Université Laval; SNC-Lavalin (Canada)","funders":"Natural Sciences and Engineering Research Council of Canada; Guangxi University; East China Institute of Technology","keywords":"Hidden Markov model; Computer science; Artificial intelligence; Markov chain; Lagrange multiplier; Generality; Handwriting; Independence (probability theory); Machine learning; Function (biology); Maximization; Pattern recognition (psychology); Algorithm; Mathematics; Mathematical optimization; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.06005585691777636,"gpt":0.2821406138225669,"spread":0.2220847569047905,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003248538,0.0002392522,0.0003629132,0.0003897201,0.0002883438,0.0001968624,0.0004155757,0.00007424955,0.0007189052],"category_scores_gemma":[0.000004558187,0.0001979027,0.0002132384,0.001210967,0.00005009749,0.0004686539,0.000002754001,0.0002376214,0.00003072151],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000279866,"about_ca_system_score_gemma":0.00003005442,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001131846,"about_ca_topic_score_gemma":0.001095866,"domain_scores_codex":[0.9982935,0.000166223,0.0003601315,0.0005752897,0.0003466858,0.0002581631],"domain_scores_gemma":[0.9988309,0.0003821563,0.00007775506,0.0004592969,0.00009014766,0.0001597675],"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":[0.00002689675,0.0001306334,0.0001301929,0.000004503069,0.0003601096,0.000009229564,0.0005573534,0.01038158,0.00003932579,0.0001693954,0.000003906467,0.9881869],"study_design_scores_gemma":[0.0002545113,0.0001218209,0.0006389078,0.00002502487,0.0003810089,0.00002597388,0.0001052207,0.9764352,0.0197282,0.001812085,0.0001273236,0.0003446957],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004376739,0.00001984084,0.9940422,0.0004556229,0.0001232009,0.0001418072,0.00003803956,0.0001361391,0.0006664431],"genre_scores_gemma":[0.8832632,0.0001413795,0.1156475,0.0005434065,0.00001969405,0.00004286923,0.000005837075,0.0000128648,0.0003232168],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9878422,"threshold_uncertainty_score":0.807024,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2115599677","doi":"10.1109/jstsp.2010.2081790","title":"Diarization of Telephone Conversations Using Factor Analysis","year":2010,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Signal Processing","topic":"Speech Recognition and Synthesis","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":"Computer Research Institute of Montréal","funders":"Johns Hopkins University","keywords":"Speaker diarisation; Computer science; Cluster analysis; Speech recognition; Word error rate; Speaker recognition; NIST; Channel (broadcasting); Hierarchical clustering; Bayes' theorem; Exploit; Artificial intelligence; Pattern recognition (psychology); Telecommunications; Bayesian probability","retraction":null,"screen_n_in":null,"score":{"opus":0.02582700289371216,"gpt":0.2748875302374324,"spread":0.2490605273437203,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002670704,0.00008259673,0.0002524602,0.0007486649,0.00006334091,0.00008768441,0.0003020754,0.00008730608,0.00006096669],"category_scores_gemma":[0.0001447933,0.00007574035,0.00008238725,0.002388179,0.00003851406,0.000600995,0.0000138202,0.0003168962,5.574376e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003949958,"about_ca_system_score_gemma":0.0003165596,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001294921,"about_ca_topic_score_gemma":0.00003185515,"domain_scores_codex":[0.9988521,0.00006000403,0.0005295904,0.000113531,0.0003150819,0.0001296681],"domain_scores_gemma":[0.9983171,0.0001045184,0.0005589525,0.00009086099,0.0008702298,0.00005834655],"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":[0.00001678293,0.0002073649,0.02918863,0.00004174437,0.0001743309,0.00002110495,0.001658796,0.001608432,0.7891133,0.0001678499,0.000008339171,0.1777933],"study_design_scores_gemma":[0.0005358754,0.00006819001,0.03219612,0.00009394866,0.0001673107,0.00007514875,0.00008025519,0.4514744,0.513439,0.001618123,0.00004480012,0.000206862],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4986351,0.0000211133,0.5010766,0.00008187309,0.00009780111,0.00002385333,8.003159e-7,0.000007547234,0.0000552337],"genre_scores_gemma":[0.902378,0.000006244931,0.09744916,0.00003270761,0.0001188904,3.302086e-7,4.952951e-7,0.000004152143,0.00001003892],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.449866,"threshold_uncertainty_score":0.3088602,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2112021726","doi":"10.1109/taslp.2014.2346313","title":"Fast Adaptation of Deep Neural Network Based on Discriminant Codes for Speech Recognition","year":2014,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":139,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"University of Science and Technology of China","keywords":"Computer science; Speech recognition; TIMIT; Normalization (sociology); Adaptation (eye); Artificial neural network; Artificial intelligence; Speaker recognition; Pattern recognition (psychology); Word error rate; Hidden Markov model","retraction":null,"screen_n_in":null,"score":{"opus":0.02681299895984912,"gpt":0.2610017309285276,"spread":0.2341887319686785,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000426369,0.0002307242,0.0002852806,0.0002325087,0.0003568034,0.0001627947,0.0002863296,0.0001070005,0.00004354782],"category_scores_gemma":[0.0001076568,0.000206259,0.0001263486,0.0003675963,0.00006549773,0.0003740453,0.000004541018,0.0001745881,0.00000980958],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003252941,"about_ca_system_score_gemma":0.00003783945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003752575,"about_ca_topic_score_gemma":0.0001939096,"domain_scores_codex":[0.9984644,0.0001122676,0.0003367709,0.0004580916,0.0002973338,0.000331153],"domain_scores_gemma":[0.9987566,0.0004220583,0.000194131,0.0003500535,0.0001598476,0.0001173385],"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":[0.0001042079,0.0001366535,0.000008567584,0.0001252147,0.00001069364,0.000005004461,0.0006026553,0.003037183,0.001531391,0.000009951091,0.00001253539,0.9944159],"study_design_scores_gemma":[0.000924801,0.0004441584,0.0001605906,0.0002870611,0.00006626725,0.00003346598,0.0006661433,0.8807871,0.1152522,0.0009689324,0.00009304905,0.0003161836],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03578917,0.0001063626,0.962364,0.000552687,0.0002579727,0.0003226584,0.00002754918,0.0001577269,0.0004218609],"genre_scores_gemma":[0.6780998,0.00001042187,0.3211658,0.0004896244,0.0001021704,0.00004978945,0.00001611384,0.00001962879,0.00004675044],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9940997,"threshold_uncertainty_score":0.8411,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2398971481","doi":"10.21437/interspeech.2015-95","title":"The reddots data collection for speaker recognition","year":2015,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","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":"VoiceAge (Canada); Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Speech recognition; Speaker recognition; Data collection; Natural language processing; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.285855109260436,"gpt":0.3252087216737488,"spread":0.03935361241331276,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008201186,0.00005400089,0.00005273244,0.00003449978,0.0001958936,0.0002346731,0.0006312935,0.00003018113,0.00002518041],"category_scores_gemma":[0.0005619041,0.00003531504,0.00002327578,0.0002060233,0.00001826683,0.0004590258,0.0001364939,0.00003286788,0.0002692759],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002669546,"about_ca_system_score_gemma":0.00007278808,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001994552,"about_ca_topic_score_gemma":0.0001011869,"domain_scores_codex":[0.9993081,0.00004866878,0.0001224952,0.0002329296,0.0001545801,0.0001332247],"domain_scores_gemma":[0.9988465,0.0002663113,0.00004090759,0.0005843577,0.0001908854,0.00007099775],"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":[0.00001329319,0.00001788885,0.000008513854,0.000001007759,0.000007753501,5.330426e-7,0.00004446095,1.112965e-7,0.00002832621,0.001490964,0.2950691,0.7033181],"study_design_scores_gemma":[0.0007545487,0.000111051,0.0001885409,0.000009683736,0.00001241471,0.00004589964,0.0002423997,0.1993348,0.007404094,0.05721924,0.7344713,0.0002060493],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005949394,0.00004109348,0.9318139,0.006431657,0.001011588,0.0003293327,0.00001067499,0.0002114849,0.05955534],"genre_scores_gemma":[0.02151197,0.000108143,0.9485435,0.002201212,0.0005259875,0.0001697319,0.0001487782,0.00002257647,0.02676808],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.703112,"threshold_uncertainty_score":0.3461087,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2008066109","doi":"10.1016/j.specom.2009.04.006","title":"Tools and Technologies for Computer-Aided Speech and Language Therapy","year":2009,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":133,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Pronunciation; Speech recognition; Population; Dysarthria; Set (abstract data type); Speech technology; Articulation (sociology); Domain (mathematical analysis); Speech processing; Speech corpus; Natural language processing; Speech synthesis; Linguistics; Audiology; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.03613621209312245,"gpt":0.287530217985311,"spread":0.2513940058921886,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003778731,0.0001197486,0.0001582697,0.0001184616,0.0001834044,0.0002963725,0.0006702747,0.0000924326,0.00000350308],"category_scores_gemma":[0.0001004475,0.0001086779,0.00003407129,0.0001783451,0.00007255808,0.0004244907,0.0001668176,0.0001090811,0.000006260069],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001742898,"about_ca_system_score_gemma":0.00001326355,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001035914,"about_ca_topic_score_gemma":0.000008903427,"domain_scores_codex":[0.9992449,0.00006641619,0.0001720906,0.0002455338,0.0001123406,0.0001587053],"domain_scores_gemma":[0.9986256,0.0003242698,0.00008244895,0.0008530842,0.00008060039,0.00003397893],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000006374274,0.00003612979,0.00004266059,0.000003452777,0.000006321788,0.000001325418,0.0002664836,1.225135e-7,0.003367946,0.006180189,0.0002531927,0.9898358],"study_design_scores_gemma":[0.004841542,0.001587212,0.04260873,0.0002834401,0.00003426604,0.0005027884,0.002107626,0.05544677,0.6391944,0.2009033,0.05091089,0.001579057],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6891873,0.008743736,0.2578022,0.03442496,0.0001435172,0.001749422,0.0000260164,0.002186286,0.005736556],"genre_scores_gemma":[0.366828,0.002180407,0.6302824,0.0005946833,0.00001734405,0.00002248766,0.00001382004,0.000005870767,0.00005497511],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9882568,"threshold_uncertainty_score":0.4431754,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2109886035","doi":"10.1109/icassp.2016.7472618","title":"End-to-end attention-based large vocabulary speech recognition","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":124,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Computer science; Hidden Markov model; Recurrent neural network; Speech recognition; Decoding methods; Vocabulary; Sequence (biology); Pooling; Artificial intelligence; Character (mathematics); Language model; Process (computing); Pattern recognition (psychology); Artificial neural network; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.03520127758503985,"gpt":0.2663043535830252,"spread":0.2311030759979854,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009400473,0.0004565143,0.0004547439,0.0006456989,0.0001730486,0.0004482972,0.001403332,0.0004356206,0.006774079],"category_scores_gemma":[0.0002100452,0.0003816348,0.0004287359,0.0003386169,0.00003928691,0.0003162272,0.001011658,0.0004167266,0.008813525],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001585513,"about_ca_system_score_gemma":0.000319923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004832787,"about_ca_topic_score_gemma":0.00006294052,"domain_scores_codex":[0.9964646,0.000255365,0.000575304,0.001315938,0.0007738587,0.0006149127],"domain_scores_gemma":[0.9972631,0.0003371029,0.0002362938,0.001393853,0.0004136615,0.0003559413],"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":[0.00001619125,0.0002700356,0.0003434989,0.00007965991,0.00007819768,0.0001057536,0.00003614506,0.00000118415,0.001006412,0.001274076,0.01402768,0.9827611],"study_design_scores_gemma":[0.007212972,0.0006484445,0.02527181,0.005724936,0.0004498568,0.0002870476,0.0001801727,0.07030804,0.4177328,0.2745286,0.187609,0.01004631],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008313604,0.00003578897,0.9217717,0.007686906,0.002112836,0.0007185619,0.0002774925,0.0009256444,0.05815744],"genre_scores_gemma":[0.2383082,0.00006209214,0.7377222,0.0117028,0.00105101,0.0005285342,0.0005862279,0.0001150406,0.00992391],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9727148,"threshold_uncertainty_score":0.9998636,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4291746033","doi":"10.3390/app12094419","title":"Automatic Speech Recognition (ASR) Systems for Children: A Systematic Literature Review","year":2022,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":124,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Moncton","funders":"","keywords":"Speech recognition; Computer science; Task (project management); Speech technology; Field (mathematics); Process (computing); Speech processing; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02825174921800579,"gpt":0.2559027336825049,"spread":0.2276509844644991,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003068878,0.0001845041,0.0004506835,0.0002465764,0.000943297,0.0005420791,0.001361026,0.00003676836,0.0001041584],"category_scores_gemma":[0.0001611596,0.0001481212,0.000136683,0.001782178,0.00006912838,0.0003660145,0.0001928079,0.0001372843,0.0001089468],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006328703,"about_ca_system_score_gemma":0.00009229525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003356044,"about_ca_topic_score_gemma":6.260048e-7,"domain_scores_codex":[0.9975089,0.0002368496,0.0005130036,0.0005959859,0.0008012702,0.0003440287],"domain_scores_gemma":[0.9986847,0.0004131806,0.0002994425,0.0004267203,0.00008886879,0.00008711305],"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":[0.00001450692,0.00068417,0.00006330006,0.1633694,0.0002612291,0.00006326629,0.002150269,0.00005582569,0.0009757009,0.093632,0.07949761,0.6592327],"study_design_scores_gemma":[0.005234964,0.002729354,0.000590475,0.2329885,0.001271301,0.01342202,0.005579991,0.6322641,0.009286805,0.07794252,0.01077597,0.00791397],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"methods","genre_scores_codex":[0.0631846,0.5344242,0.2239673,0.01418936,0.01182435,0.06807246,0.0008885911,0.00716965,0.07627945],"genre_scores_gemma":[0.4155877,0.01565513,0.5105351,0.02181147,0.0007598614,0.03377897,0.0003001619,0.0001173103,0.001454326],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6513187,"threshold_uncertainty_score":0.7255173,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2015633636","doi":"10.1109/icassp.2014.6854823","title":"I-vector-based speaker adaptation of deep neural networks for French broadcast audio transcription","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":119,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Speech recognition; Computer science; Speaker diarisation; Word error rate; Transcription (linguistics); Feature vector; Hidden Markov model; Artificial neural network; Artificial intelligence; Speaker recognition; Acoustic model; Vector quantization; Pattern recognition (psychology); Speech processing","retraction":null,"screen_n_in":null,"score":{"opus":0.02772913931601576,"gpt":0.2293340230087177,"spread":0.2016048836927019,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002520087,0.00009968226,0.0001429147,0.00008353911,0.00005878402,0.00005278408,0.0002339065,0.00006089713,0.0001284209],"category_scores_gemma":[0.0000481758,0.0000881977,0.0001230344,0.0001844641,0.0000242183,0.0002248338,0.000008619801,0.00004630386,0.000009342182],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001465372,"about_ca_system_score_gemma":0.00001130377,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005850014,"about_ca_topic_score_gemma":0.0001569336,"domain_scores_codex":[0.9991374,0.00007179943,0.0002287783,0.0002268275,0.0001614603,0.0001737585],"domain_scores_gemma":[0.9993014,0.0001977018,0.00008214496,0.0002210581,0.0001370624,0.00006064656],"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":[0.00001281474,0.00006085529,0.0001209168,0.00001545841,0.000008712835,2.89597e-7,0.0001403727,0.01018468,0.001667193,0.004777859,0.0002296559,0.9827812],"study_design_scores_gemma":[0.0004883284,0.0001246851,0.003014132,0.000006871755,0.000009959331,0.000001761714,0.00001784527,0.9906013,0.004143672,0.0003565682,0.001123875,0.0001110068],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007863239,0.00002613584,0.9896209,0.0004235755,0.0003545502,0.0001907742,0.000001600768,0.0001062629,0.001412936],"genre_scores_gemma":[0.8271446,0.000001098606,0.1723234,0.0003408456,0.00007584228,0.00002107599,0.000009558611,0.000006346655,0.00007729334],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9826702,"threshold_uncertainty_score":0.3596598,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1846073453","doi":"10.1109/icassp.2000.859138","title":"Towards language independent acoustic modeling","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":111,"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":"Universidade Federal de Alagoas; Rice University","keywords":"Computer science; Czech; Discriminative model; Hidden Markov model; Acoustic model; Language model; Speech recognition; Natural language processing; Mandarin Chinese; Artificial intelligence; Adaptation (eye); Speech processing; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.04217330464563866,"gpt":0.2469683376392459,"spread":0.2047950329936072,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00009487994,0.0000650243,0.00006955599,0.00006762113,0.00004574112,0.0001014807,0.0003423202,0.00002967361,0.00151296],"category_scores_gemma":[0.00003617745,0.00005371076,0.00004088276,0.0001469402,0.000005480505,0.0001969793,0.00008057144,0.00006170118,0.0009967739],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002771906,"about_ca_system_score_gemma":0.000006596516,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004413397,"about_ca_topic_score_gemma":0.0000225462,"domain_scores_codex":[0.9993403,0.00001841824,0.0001009567,0.000178872,0.0002085808,0.000152881],"domain_scores_gemma":[0.9996249,0.0000199418,0.00001401638,0.0002420658,0.00002912877,0.00006996161],"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":[6.673025e-7,0.00008458357,0.00002217696,0.000005737728,0.00001269329,0.00007236211,0.001038063,0.0007040499,0.001344683,0.005420912,0.001169466,0.9901246],"study_design_scores_gemma":[0.00008666043,0.000008244181,0.0000327066,0.00000310706,0.000002216298,0.0000227316,0.00009878854,0.9968617,0.002367149,0.0002991361,0.0001286949,0.00008885139],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02860954,0.00005941703,0.8819358,0.0005028206,0.0001226588,0.00004200916,5.217506e-7,0.0002610952,0.08846613],"genre_scores_gemma":[0.9390146,0.00001495234,0.05876527,0.0006929221,0.00003578654,0.000004653426,2.487542e-7,0.000004030548,0.001467601],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9961576,"threshold_uncertainty_score":0.9997811,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2167191127","doi":"10.1109/icassp.1989.266415","title":"A comparison of several acoustic representations for speech recognition with degraded and undegraded speech","year":2003,"lang":"en","type":"article","venue":"International Conference on Acoustics, Speech, and Signal Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":109,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"","keywords":"Speech recognition; Cepstrum; Mel-frequency cepstrum; Computer science; Weighting; Noise (video); Filter (signal processing); Filter bank; Pattern recognition (psychology); Mathematics; Artificial intelligence; Feature extraction; Acoustics","retraction":null,"screen_n_in":null,"score":{"opus":0.1034577501804792,"gpt":0.3427565667719608,"spread":0.2392988165914816,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003272082,0.0002529319,0.0003472191,0.0002915036,0.0002260047,0.0004009448,0.0002981034,0.0001160877,0.0001100952],"category_scores_gemma":[0.0002875671,0.0002266784,0.00005411427,0.0002076783,0.0001945798,0.0004969682,0.00004330405,0.0002142599,0.000004524756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004920146,"about_ca_system_score_gemma":0.0002021509,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002616599,"about_ca_topic_score_gemma":0.00003254113,"domain_scores_codex":[0.9981011,0.00007925168,0.0004722827,0.0005574941,0.0005242187,0.0002656188],"domain_scores_gemma":[0.9981411,0.0003759021,0.000329916,0.0001614663,0.0008513931,0.0001402308],"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":[0.0003609279,0.0006856981,0.002236552,0.0002954062,0.0001801319,0.00005741455,0.001262284,0.0001953864,0.04958961,0.01605208,0.0003434296,0.9287411],"study_design_scores_gemma":[0.002860837,0.0008441822,0.001836114,0.0008054633,0.0001755974,0.0004799555,0.003271317,0.8128352,0.1036616,0.07219441,0.0001745675,0.0008607252],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09952361,0.00007561113,0.8930845,0.0007522169,0.0001882954,0.000441611,0.00006997891,0.00009432064,0.005769856],"genre_scores_gemma":[0.7847447,0.00004716525,0.2146803,0.0001790591,0.00005278606,0.00002357869,0.0000314838,0.00001524532,0.0002257248],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9278803,"threshold_uncertainty_score":0.9243675,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3210530853","doi":"10.1109/icassp43922.2022.9746484","title":"A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion","year":2022,"lang":"en","type":"article","venue":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":107,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ubisoft (Canada)","funders":"","keywords":"Computer science; Speech recognition","retraction":null,"screen_n_in":null,"score":{"opus":0.07575626700609553,"gpt":0.3305673919311458,"spread":0.2548111249250503,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007773428,0.0003463835,0.0005210258,0.0004037429,0.0006236124,0.000420675,0.0009886975,0.0001158948,0.0004753947],"category_scores_gemma":[0.0002887125,0.000352157,0.0001002948,0.0004490312,0.0002168363,0.000421047,0.0004801189,0.0005978709,0.000005541852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001433145,"about_ca_system_score_gemma":0.0003160367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004032718,"about_ca_topic_score_gemma":0.000008437909,"domain_scores_codex":[0.9969674,0.0001546307,0.0006810739,0.0008330672,0.0009502504,0.0004135715],"domain_scores_gemma":[0.9975572,0.0005546723,0.0005670912,0.0002834561,0.0008075549,0.0002300379],"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":[0.0008809923,0.0007123147,0.0005985901,0.0003119206,0.0002209614,0.00008678042,0.001298102,0.0002094104,0.236731,0.004796318,0.006305875,0.7478477],"study_design_scores_gemma":[0.001331668,0.0008682678,0.0001500018,0.0001114045,0.0000694652,0.0001226331,0.001902609,0.9682258,0.01889936,0.004030991,0.003771796,0.0005160128],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1359567,0.0005758097,0.8463379,0.007157706,0.002295551,0.001408559,0.001519498,0.0003415402,0.004406833],"genre_scores_gemma":[0.9754838,0.00008396478,0.02238268,0.0006140259,0.0001484493,0.00008501425,0.00009757699,0.00003088861,0.001073607],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9680164,"threshold_uncertainty_score":0.9998931,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2151936436","doi":"10.1109/tasl.2010.2072499","title":"Articulatory Knowledge in the Recognition of Dysarthric Speech","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":105,"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":"Vocal tract; Discriminative model; Dysarthria; Speech recognition; Computer science; Speech production; Manner of articulation; Generative grammar; Artificial intelligence; Natural language processing; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.01747474294777467,"gpt":0.2601078714734097,"spread":0.242633128525635,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006211798,0.0001399805,0.0001629538,0.0002704214,0.0001508434,0.0001124966,0.0002687574,0.00009608842,0.0001006819],"category_scores_gemma":[0.00002448338,0.0001062061,0.00006493639,0.0006058851,0.00008539064,0.0003489258,0.000002440863,0.0003999569,0.00004477305],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001230791,"about_ca_system_score_gemma":0.00006352256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002723886,"about_ca_topic_score_gemma":0.0004447727,"domain_scores_codex":[0.9989461,0.0001025928,0.0002526501,0.0002780168,0.000209663,0.0002109548],"domain_scores_gemma":[0.9993301,0.0001781877,0.0000847429,0.000267761,0.00007641885,0.00006276715],"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":[0.000008119324,0.0001920651,0.00001292274,0.00003836989,0.000005090474,0.00002555281,0.002605185,0.000001578871,0.0229799,0.00001530221,0.00001432912,0.9741016],"study_design_scores_gemma":[0.001034828,0.0001361703,0.001461826,0.0002631654,0.00004571804,0.0005849483,0.002910548,0.01640869,0.9753495,0.0009621477,0.0003834613,0.0004589765],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7598599,0.0004029015,0.2351243,0.0003819436,0.0002835112,0.0002202483,0.000006587151,0.0001112707,0.003609348],"genre_scores_gemma":[0.9726697,0.00002998331,0.02687233,0.0002721137,0.00004215398,0.00002342084,9.120265e-7,0.000009791057,0.00007963199],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9736426,"threshold_uncertainty_score":0.433096,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3206189675","doi":"10.1109/icassp43922.2022.9747814","title":"Large-Scale Self-Supervised Speech Representation Learning for Automatic Speaker Verification","year":2022,"lang":"en","type":"article","venue":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":102,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Generalizability theory; Computer science; Speech recognition; Word error rate; Speaker recognition; Artificial intelligence; Representation (politics); Artificial neural network; Scale (ratio); Feature (linguistics); Pattern recognition (psychology); Machine learning; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.0517667352431102,"gpt":0.3075118367600685,"spread":0.2557451015169583,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001268903,0.000387335,0.0004158143,0.000497583,0.001138796,0.0009149078,0.001139939,0.0001303504,0.002280774],"category_scores_gemma":[0.0002805972,0.0004215977,0.0001757487,0.0005865452,0.00008197835,0.0006909479,0.0003248943,0.0007746368,0.00007071548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003448308,"about_ca_system_score_gemma":0.0003323498,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001935069,"about_ca_topic_score_gemma":0.000007875948,"domain_scores_codex":[0.9956914,0.0003185476,0.0007503577,0.001128938,0.001551735,0.0005590103],"domain_scores_gemma":[0.9977696,0.0004130426,0.0005150227,0.0004122565,0.0006603603,0.0002297243],"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":[0.0003298735,0.001527078,0.0009077172,0.0002445513,0.0002667115,0.0002017168,0.004040523,0.001639841,0.08344477,0.00520104,0.008806953,0.8933892],"study_design_scores_gemma":[0.00112663,0.0003428824,0.0004090668,0.00006620648,0.00006133707,0.0001789931,0.002469466,0.9826756,0.003558284,0.004618881,0.003977077,0.0005156475],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1322812,0.0001250367,0.8490936,0.005613015,0.00192185,0.001210901,0.0002562636,0.0009461328,0.008551979],"genre_scores_gemma":[0.9063435,0.0001067145,0.08928773,0.0009742996,0.0003264602,0.0003628111,0.0002522927,0.00005593717,0.002290325],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9810357,"threshold_uncertainty_score":0.9998236,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2063689849","doi":"10.1109/iscslp.2012.6423452","title":"Investigation of deep neural networks (DNN) for large vocabulary continuous speech recognition: Why DNN surpasses GMMS in acoustic modeling","year":2012,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Computer science; Speech recognition; Artificial neural network; Vocabulary; Context (archaeology); Mel-frequency cepstrum; Word error rate; Artificial intelligence; Task (project management); Reduction (mathematics); Deep neural networks; Hidden Markov model; Logarithm; Pattern recognition (psychology); Feature extraction; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.05066265927163722,"gpt":0.2545038198180309,"spread":0.2038411605463937,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009144932,0.0001787531,0.0002962467,0.0002085619,0.00008397001,0.00008084323,0.0003263968,0.0001278802,0.00006574961],"category_scores_gemma":[0.0002800436,0.0001711579,0.000106733,0.0004617057,0.00002670749,0.001104626,0.00008788508,0.0001418308,0.00001448901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000420742,"about_ca_system_score_gemma":0.00002695574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004691264,"about_ca_topic_score_gemma":0.0002232823,"domain_scores_codex":[0.9983262,0.0001333,0.0004943685,0.0003023375,0.0002343706,0.0005093906],"domain_scores_gemma":[0.9986672,0.0005131535,0.0001389588,0.0002799341,0.000245413,0.0001553038],"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":[0.0001064118,0.0003992509,0.03643407,0.0002156611,0.00009500178,0.00001838326,0.00147318,0.01261907,0.002550016,0.001498726,0.0024064,0.9421839],"study_design_scores_gemma":[0.0005286934,0.000049324,0.000767538,0.00003471342,0.00002026299,0.00002204804,0.0001794144,0.991209,0.005422439,0.001493381,0.00004348996,0.000229666],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2386157,0.0001360441,0.7597689,0.0002953662,0.0003965321,0.0003236912,0.000005599627,0.0001078248,0.0003503208],"genre_scores_gemma":[0.9012222,0.00001832539,0.09740314,0.0009894428,0.0002339919,0.00005736174,0.00003492455,0.00001620969,0.00002445832],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.97859,"threshold_uncertainty_score":0.6979614,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}