{"id":"W2125157818","doi":"","title":"Correcting Errors in Speech Recognition with Articulatory Dynamics","year":2010,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Speech recognition; Vocal tract; Hidden Markov model; Task (project management); Baseline (sea); Dynamics (music); Word error rate; Sentence; Dynamic Bayesian network; Artificial intelligence; Word (group theory); Bayesian probability; 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":[0.0001938843,0.00006147061,0.00006329088,0.00006302921,0.00005436735,0.00007804497,0.0001551615,0.00003675279,0.00003476327],"category_scores_gemma":[0.00002661235,0.00004815797,0.00001090315,0.0002739663,0.00002332333,0.0004247956,0.0000428414,0.000200838,0.00003083058],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000190856,"about_ca_system_score_gemma":0.00004603317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005338646,"about_ca_topic_score_gemma":0.001779712,"domain_scores_codex":[0.9994395,0.00001023185,0.0001004083,0.0001891927,0.0001092163,0.0001514819],"domain_scores_gemma":[0.9996994,0.00002692073,0.00004414514,0.0001526933,0.00003912864,0.00003773087],"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":[0.000002424349,0.00003107974,0.01185571,0.000008279648,0.000001754702,0.00002314412,0.0003525634,0.00002729459,0.001124673,0.0009562783,0.00007727194,0.9855396],"study_design_scores_gemma":[0.0007747991,0.0000837174,0.02406892,0.00014454,0.000006260544,0.0005504804,0.0005469796,0.9105491,0.05410952,0.008309618,0.0002591345,0.0005969011],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.780916,0.00000163461,0.2087173,0.0003490965,0.0002481807,0.00003984217,8.944002e-8,0.00008668777,0.00964118],"genre_scores_gemma":[0.867714,1.274006e-7,0.1316863,0.0004200351,0.00002648242,0.000002413421,9.01285e-7,0.000003864468,0.0001458828],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9849426,"threshold_uncertainty_score":0.1963825,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01179347816073192,"score_gpt":0.2212470218363063,"score_spread":0.2094535436755743,"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."}}