{"id":"W2135433537","doi":"10.1109/89.928919","title":"A maximum a posteriori approach to speaker adaptation using the trended hidden Markov model","year":2001,"lang":"en","type":"article","venue":"IEEE Transactions on Speech and Audio Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Hidden Markov model; Maximum a posteriori estimation; Polynomial; Computer science; Speech recognition; Adaptation (eye); Security token; A priori and a posteriori; Gaussian; Pattern recognition (psychology); Mathematics; Algorithm; Artificial intelligence; Statistics; Maximum likelihood","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":[0.001832936,0.0008252242,0.0007835683,0.0006302447,0.0004692294,0.0006953855,0.001194837,0.0009646951,0.001778853],"category_scores_gemma":[0.005309707,0.0007137236,0.001184525,0.0006449051,0.0004853203,0.001082699,0.0009029773,0.001818321,0.001095833],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003985997,"about_ca_system_score_gemma":0.0009808929,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003462002,"about_ca_topic_score_gemma":0.004111886,"domain_scores_codex":[0.9991116,0.000374558,0.00004366664,0.0002139078,0.000210363,0.00004584764],"domain_scores_gemma":[0.998549,0.0009732594,0.0000692964,0.0001475515,0.0002388204,0.00002210935],"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":[0.0002645403,0.00008555743,0.0008579001,0.0001923752,0.000283573,0.0001703096,0.0002881763,0.5486665,0.02383363,0.01949948,0.002393232,0.4034648],"study_design_scores_gemma":[0.000007903114,0.00003963052,0.000298491,0.000008579917,0.00002546788,0.00005006128,0.00001284629,0.986062,0.003299021,0.008931574,0.001244543,0.00001992438],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00179525,0.00007611202,0.9975604,0.00003240562,0.00001241939,0.00001362107,0.00002227306,0.0002464506,0.000241023],"genre_scores_gemma":[0.1215744,0.0004451406,0.8738481,0.00008404018,0.0001123393,0.0002177667,0.0003144291,0.0002667887,0.003137077],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003462002,"threshold_uncertainty_score":0.009693563,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05320708971129079,"score_gpt":0.2664378542114752,"score_spread":0.2132307645001844,"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."}}