{"id":"W1603639024","doi":"10.1109/icassp.2003.1198920","title":"Variational inference and learning for segmental switching state space models of hidden speech dynamics","year":2003,"lang":"en","type":"article","venue":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Inference; Computer science; Dynamics (music); State space; Speech recognition; Artificial intelligence; Space (punctuation); State (computer science); Algorithm; Mathematics; Physics; Acoustics","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":[0.003045043,0.0009190299,0.001026793,0.0006880341,0.0005256199,0.0009515864,0.001774975,0.00124072,0.00230301],"category_scores_gemma":[0.009094624,0.0009930596,0.001213168,0.0006242076,0.001334231,0.001966242,0.001504701,0.002228386,0.0004304003],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001296269,"about_ca_system_score_gemma":0.001164502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006777887,"about_ca_topic_score_gemma":0.00721397,"domain_scores_codex":[0.9992195,0.000369141,0.00003938979,0.0001669238,0.0001463828,0.00005851128],"domain_scores_gemma":[0.9964724,0.003053417,0.000136568,0.0001223047,0.0001546121,0.00006067171],"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":[0.00003981894,0.00002345557,0.0003915645,0.00008840438,0.00006341585,0.00004678155,0.0001063914,0.8415912,0.0009431941,0.1167487,0.0008069379,0.03915008],"study_design_scores_gemma":[0.000002462428,0.000004148048,0.00003226699,0.000003132335,0.000002446168,0.0000050974,0.000003480763,0.9789158,0.000154414,0.02057883,0.0002943113,0.000003634543],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00222616,0.0001778175,0.9970685,0.00007461204,0.00001058763,0.0000100161,0.0000241198,0.00006416753,0.0003440658],"genre_scores_gemma":[0.3009969,0.001024776,0.6906991,0.0001791619,0.0001446464,0.0002731759,0.0006438572,0.000300457,0.005737871],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006777887,"threshold_uncertainty_score":0.01610386,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03233964176221436,"score_gpt":0.2818868902001562,"score_spread":0.2495472484379418,"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."}}