{"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,"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","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005402551,0.0007394771,0.0005086479,0.0003133033,0.0002536988,0.0004917633,0.001687372,0.0007769361,0.002501511],"category_scores_gemma":[0.00153387,0.0004941287,0.0005412256,0.0003877989,0.0003055956,0.001191418,0.0007305618,0.001933341,0.00107255],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007601764,"about_ca_system_score_gemma":0.0009559336,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007518476,"about_ca_topic_score_gemma":0.02138541,"domain_scores_codex":[0.9996786,0.00007865491,0.00001941365,0.0001115022,0.00007642763,0.00003542179],"domain_scores_gemma":[0.9995771,0.0001831806,0.00003111435,0.00007630474,0.000110842,0.00002145998],"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":[0.000216901,0.0001577714,0.001560718,0.0001241886,0.00009306375,0.0001280724,0.00008988482,0.6963683,0.0251768,0.01086662,0.004675195,0.2605426],"study_design_scores_gemma":[0.000002948923,0.00001410471,0.0001425975,0.000003593974,0.000005418377,0.00001479494,0.000002966377,0.9952232,0.002444667,0.001664389,0.0004769564,0.000004298496],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01591547,0.0005193853,0.9801224,0.0001349295,0.00007814744,0.00003435438,0.000239563,0.00167253,0.00128327],"genre_scores_gemma":[0.5965258,0.0007011815,0.3934449,0.0003093461,0.00009234325,0.0002660953,0.0013868,0.0002139815,0.00705944],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007518476,"threshold_uncertainty_score":0.01494944,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02643442671762116,"score_gpt":0.2531046896995723,"score_spread":0.2266702629819512,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}