{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004541156,0.0001148649,0.0001661211,0.0002379755,0.00006849312,0.00008814504,0.00021283,0.00007232759,0.0001390496],"category_scores_gemma":[0.0001762786,0.0001042378,0.00008481453,0.0003720105,0.00002864769,0.001182763,0.00001699827,0.00007919383,0.0001583934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004970922,"about_ca_system_score_gemma":0.00009764945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001264791,"about_ca_topic_score_gemma":0.000003098804,"domain_scores_codex":[0.9988068,0.0001364699,0.0003795552,0.0001594372,0.0003223149,0.0001954619],"domain_scores_gemma":[0.9991938,0.0001358027,0.0001616447,0.0002175744,0.0002110847,0.00008008075],"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":[0.00002264194,0.00004778493,0.0001048419,0.0000752972,0.00001712724,0.000006542117,0.0007309434,0.00003988749,0.0002707494,0.003184701,0.0002203898,0.9952791],"study_design_scores_gemma":[0.002096681,0.0004432042,0.001108853,0.0002216012,0.00003544116,0.0002522127,0.004360473,0.7253712,0.2615455,0.002019278,0.002023981,0.0005215322],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08152104,0.000005540033,0.8248501,0.0001094846,0.0003772796,0.0002729653,0.00001707279,0.000369463,0.09247708],"genre_scores_gemma":[0.8788907,6.988156e-7,0.1208034,0.0002230841,0.00001640217,0.00002032368,0.00001321762,0.000004540702,0.0000276049],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9947575,"threshold_uncertainty_score":0.4250696,"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."}}