{"id":"W2539922005","doi":"10.1109/nnsp.1992.253696","title":"Maximum mutual information training of a neural predictive-based HMM speech recognition system","year":2003,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Hidden Markov model; Speech recognition; Computer science; Artificial intelligence; Mutual information; Artificial neural network; Pattern recognition (psychology); Scheme (mathematics); Training (meteorology); Machine learning; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001113945,0.0003994705,0.0003876851,0.0002540544,0.0003564779,0.0003809001,0.0008330287,0.0006107786,0.001867843],"category_scores_gemma":[0.002810052,0.0002953913,0.0002677165,0.0001741296,0.0004159476,0.0005163075,0.0005919029,0.0006677185,0.0005162206],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004408546,"about_ca_system_score_gemma":0.0005710002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003118394,"about_ca_topic_score_gemma":0.003185288,"domain_scores_codex":[0.9995223,0.000142007,0.000027818,0.00009595018,0.0001679697,0.00004399577],"domain_scores_gemma":[0.999271,0.0003940663,0.00006018124,0.00008293605,0.0001638697,0.00002793645],"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":[0.0004738496,0.0001666874,0.001344733,0.0001366087,0.00005286121,0.0001339033,0.0002707559,0.4656386,0.06871887,0.004655182,0.001231761,0.4571761],"study_design_scores_gemma":[0.000005479185,0.00005989279,0.0004137624,0.000005156799,0.000008718376,0.0000293903,0.000005508862,0.9843438,0.01447472,0.0003292781,0.0003175373,0.000006855811],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08607814,0.0001317321,0.9069327,0.0001378894,0.00004665902,0.00007125923,0.00002984352,0.002030739,0.004541139],"genre_scores_gemma":[0.8420315,0.00006672218,0.1542072,0.00006008425,0.00002018714,0.000119182,0.00009526408,0.00007209311,0.00332784],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003118394,"threshold_uncertainty_score":0.006248534,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03761875897832177,"score_gpt":0.2209160651004652,"score_spread":0.1832973061221434,"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."}}