{"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,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Speech recognition; Vocabulary; Artificial intelligence; Natural language processing; Linguistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"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"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04830958816975836,"score_gpt":0.2643455917612188,"score_spread":0.2160360035914604,"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."}}