{"id":"W2109848220","doi":"10.1109/icassp.2011.5947460","title":"Adapting acoustic and lexical models to dysarthric speech","year":2011,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":80,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Dysarthria; Pronunciation; Speech recognition; Computer science; Vocabulary; Word error rate; Speech production; Lexicon; Artificial intelligence; Audiology; Linguistics","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":[0.0001553831,0.00007661833,0.00009158551,0.00008316983,0.00005234051,0.00006306375,0.0002356047,0.00003498582,0.0002210801],"category_scores_gemma":[0.00002938679,0.00006371195,0.00002355538,0.0001708519,0.00001537333,0.0002812494,0.0001462795,0.00004980226,0.0002804827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007520995,"about_ca_system_score_gemma":0.00001444426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004880402,"about_ca_topic_score_gemma":0.00003197807,"domain_scores_codex":[0.999303,0.00002220827,0.0001144023,0.0002480086,0.0001308777,0.0001815434],"domain_scores_gemma":[0.999533,0.00005666409,0.0000158673,0.0001989918,0.00003795302,0.0001575074],"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":[0.000006835958,0.00006482819,0.0000821891,0.000005399491,0.000009497552,0.00004668034,0.001230783,0.00001766892,0.001207597,0.05429266,0.0008509069,0.942185],"study_design_scores_gemma":[0.0003875516,0.0002386694,0.002171219,0.00004366707,0.00001359113,0.0002454918,0.0004144562,0.8977665,0.02990604,0.06747542,0.0007447672,0.0005926314],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0343896,0.00001517056,0.8606296,0.0002086913,0.0000740595,0.00007320805,3.631195e-7,0.0001658067,0.1044435],"genre_scores_gemma":[0.6097158,0.000004169088,0.3890194,0.0006925795,0.00001615294,0.000002979908,6.318114e-8,0.000003515185,0.0005453652],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9415923,"threshold_uncertainty_score":0.3605131,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1228450209147413,"score_gpt":0.2420656424904895,"score_spread":0.1192206215757482,"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."}}