{"id":"W2031495521","doi":"10.1007/s10772-011-9104-6","title":"Using speech rhythm knowledge to improve dysarthric speech recognition","year":2011,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":25,"is_retracted":false,"has_abstract":false,"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal; Université de Moncton","funders":"","keywords":"Computer science; Speech recognition; Dysarthria; Intelligibility (philosophy); Rhythm; Hidden Markov model; Classifier (UML); Artificial intelligence; Pattern recognition (psychology); Psychology","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007838304,0.0002431253,0.0004055889,0.002311155,0.00007013221,0.00003606527,0.001231898,0.0004293287,0.002916629],"category_scores_gemma":[0.0003152348,0.0002355838,0.0001683749,0.0007212864,0.0002464298,0.0001759152,0.0003466299,0.001051164,0.001504222],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002325146,"about_ca_system_score_gemma":0.0001737823,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002476476,"about_ca_topic_score_gemma":0.0001221974,"domain_scores_codex":[0.9977152,0.0001015156,0.0008296167,0.0003896076,0.0004255398,0.0005385351],"domain_scores_gemma":[0.9972143,0.00008943929,0.0004746015,0.0003977989,0.00164476,0.0001791604],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006703621,0.0006261935,0.002903451,0.000006375495,0.000624051,0.003199083,0.001724036,6.875035e-7,0.07272698,0.001396111,0.002481866,0.9136408],"study_design_scores_gemma":[0.005328129,0.00336891,0.01362607,0.0003218182,0.0001551981,0.05178235,0.002192749,0.000107628,0.7535781,0.1346527,0.03387162,0.001014762],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9755401,0.000588168,0.001422055,0.001616315,0.00607961,0.0002557175,0.00004059232,0.0000761772,0.01438125],"genre_scores_gemma":[0.9501797,0.0001038357,0.04717435,0.0002264809,0.001111245,0.00001377874,0.000005508885,0.00005293866,0.001132136],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.912626,"threshold_uncertainty_score":0.9992732,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1036658881049826,"score_gpt":0.3905004229513346,"score_spread":0.286834534846352,"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."}}