{"id":"W2900035714","doi":"10.1080/17549507.2018.1508499","title":"Automatic prediction of intelligible speaking rate for individuals with ALS from speech acoustic and articulatory samples","year":2018,"lang":"en","type":"article","venue":"International Journal of Speech-Language Pathology","topic":"Voice and Speech Disorders","field":"Medicine","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Institute on Deafness and Other Communication Disorders; National Institutes of Health; American Speech-Language-Hearing Foundation","keywords":"Speech recognition; Intelligibility (philosophy); Tongue; Mean squared error; Computer science; Word error rate; Speech error; Support vector machine; Speech production; Artificial intelligence; Pattern recognition (psychology); Mathematics; Statistics; 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":[0.0006124524,0.0001488114,0.0004142465,0.0003740889,0.00003306131,0.00002694318,0.0001715593,0.0001072622,0.000289037],"category_scores_gemma":[0.000633323,0.0001130362,0.00009506147,0.00009284545,0.0002167206,0.0001796705,0.00004569528,0.0001747682,0.00000685249],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005150503,"about_ca_system_score_gemma":0.0001160549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005276956,"about_ca_topic_score_gemma":0.00007398733,"domain_scores_codex":[0.9985818,0.000059179,0.000619573,0.0001843507,0.0003776811,0.0001774586],"domain_scores_gemma":[0.9982244,0.0002969547,0.0005660501,0.0001451562,0.0006789018,0.00008854838],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001351917,0.000476101,0.2621041,0.0001661946,0.001801227,0.00191715,0.0109558,0.00005221746,0.5607514,0.0001500236,0.0006562187,0.1596176],"study_design_scores_gemma":[0.01335254,0.005689796,0.468013,0.002320679,0.001741797,0.01306234,0.01348755,0.004277028,0.4711429,0.004559617,0.001874926,0.0004778535],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9840864,0.0005066199,0.01387381,0.0005850208,0.0004258955,0.0002284245,0.0001238441,0.00001992755,0.0001500733],"genre_scores_gemma":[0.9610078,0.00007210447,0.03765162,0.0003627095,0.0008010697,0.000003992615,0.00003787339,0.00002228881,0.00004048911],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2059089,"threshold_uncertainty_score":0.4609483,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02020683450282267,"score_gpt":0.3090213836923736,"score_spread":0.2888145491895509,"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."}}