{"id":"W1548001769","doi":"10.1109/icslp.1996.607801","title":"Optimal filtering and smoothing for speech recognition using a stochastic target model","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Vocal tract; Smoothing; Hidden Markov model; Computer science; Speech recognition; Piecewise linear function; Trajectory; Speech production; Markov process; Kalman filter; Optimal control; Algorithm; Mathematics; Artificial intelligence; Mathematical optimization; Computer vision","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":[0.0001290452,0.00009958192,0.0001016571,0.00007670589,0.0001899731,0.0002673034,0.0001581921,0.00003811529,0.00001960626],"category_scores_gemma":[0.00004380613,0.00009660044,0.00002828728,0.0001087535,0.00001617663,0.0008797098,0.00009516107,0.00006171855,0.000004707748],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002138987,"about_ca_system_score_gemma":0.00001277562,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003738297,"about_ca_topic_score_gemma":5.733648e-7,"domain_scores_codex":[0.9992296,0.000006271361,0.0001317601,0.000280713,0.0001038526,0.0002478172],"domain_scores_gemma":[0.9996777,0.00004080042,0.00004831195,0.0001164434,0.00005006381,0.0000667128],"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":[0.00001321127,0.00007262651,0.00001451628,0.0001233057,0.00002180028,0.00001315527,0.001932646,0.1865835,0.0738816,0.0001731623,0.0003294415,0.736841],"study_design_scores_gemma":[0.0002255196,0.00002567395,0.000001045688,0.00004318808,0.000004320432,0.00004946477,0.0000268844,0.9531972,0.04290865,0.003368027,0.000008659556,0.0001413585],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0938721,0.00009715017,0.9050791,0.0001428387,0.00006043978,0.0001090383,0.000001987563,0.0001173528,0.0005200233],"genre_scores_gemma":[0.2270289,0.000001755136,0.7726734,0.0001541939,0.00004391293,0.000005599212,7.766067e-7,0.000007587063,0.00008386235],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7666137,"threshold_uncertainty_score":0.3939252,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0764197902726713,"score_gpt":0.2639901566829519,"score_spread":0.1875703664102806,"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."}}