{"id":"W2163376162","doi":"10.1109/icassp.1997.596213","title":"Speaker adaptation experiments using nonstationary-state hidden Markov models: a MAP approach","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Hidden Markov model; Polynomial; Adaptation (eye); Computer science; Gaussian; Speech recognition; Pattern recognition (psychology); State (computer science); Algorithm; Artificial intelligence; 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":[0.0001254734,0.0001333758,0.0001163687,0.000146226,0.0001173465,0.0001693224,0.0003015856,0.00003905616,0.0006510869],"category_scores_gemma":[0.000007287487,0.0001243874,0.00006035005,0.0002362533,0.00002533159,0.001038901,0.00005625418,0.00005684521,0.0003044276],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005871444,"about_ca_system_score_gemma":0.00002115729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005511344,"about_ca_topic_score_gemma":0.000002766912,"domain_scores_codex":[0.9987764,0.00007478416,0.0002258091,0.0003561086,0.0003425878,0.0002243254],"domain_scores_gemma":[0.9994259,0.00004473465,0.00006918194,0.0002817637,0.00008414628,0.00009423262],"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":[0.00001431323,0.0006163299,0.00004697269,0.00002382223,0.00007574322,0.00003818156,0.009881041,0.002903521,0.001081951,0.01407384,0.00657912,0.9646652],"study_design_scores_gemma":[0.000241013,0.00001114242,0.00002430834,0.000008316262,0.000003748525,0.00002270199,0.0003770112,0.9950351,0.001020528,0.002695546,0.0003861967,0.0001743934],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005054025,0.00008490859,0.9088752,0.0002002405,0.0001331396,0.0001685158,0.000002675521,0.000168805,0.08531249],"genre_scores_gemma":[0.180672,0.00001701255,0.8154055,0.0003791183,0.00002608061,0.00002061953,0.000004883885,0.00001089491,0.003463838],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9921316,"threshold_uncertainty_score":0.7128944,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1370463160265479,"score_gpt":0.2604941524964074,"score_spread":0.1234478364698595,"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."}}