{"id":"W2182621190","doi":"10.1016/j.bbe.2015.11.004","title":"Fully automated speaker identification and intelligibility assessment in dysarthria disease using auditory knowledge","year":2015,"lang":"en","type":"article","venue":"Journal of Applied Biomedicine","topic":"Voice and Speech Disorders","field":"Medicine","cited_by":56,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada; Université de Moncton","keywords":"Dysarthria; Intelligibility (philosophy); Speech recognition; Computer science; Mixture model; Mel-frequency cepstrum; Support vector machine; Speaker identification; Context (archaeology); Artificial intelligence; Speaker recognition; Feature extraction; Audiology; Medicine","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001438382,0.0001431913,0.0004182363,0.0004524706,0.00002698355,0.00001797634,0.00007646977,0.0000741699,0.00002765762],"category_scores_gemma":[0.0001553118,0.0001064,0.00004948746,0.0004157936,0.0001706132,0.0001114199,0.00003416908,0.000288443,0.000008696164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002804488,"about_ca_system_score_gemma":0.0006335517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009328411,"about_ca_topic_score_gemma":0.00001030191,"domain_scores_codex":[0.9984131,0.00003649997,0.0007609494,0.0001862075,0.0004268064,0.0001764112],"domain_scores_gemma":[0.9986728,0.00004894868,0.0003422087,0.0001987267,0.0002849661,0.0004523025],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.01170786,0.007812041,0.1784795,0.002163721,0.0008123966,0.001451942,0.01017918,0.0003703541,0.6038685,0.0007642985,0.07717952,0.1052106],"study_design_scores_gemma":[0.01860051,0.001203931,0.9154955,0.001205439,0.0008055384,0.0002978026,0.007988679,0.03127495,0.001844426,0.002446257,0.01839861,0.0004383096],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9945526,0.0009106502,0.0008580208,0.001692749,0.0006345668,0.0003209476,0.000002347142,0.00003652332,0.0009916299],"genre_scores_gemma":[0.9978896,0.000108921,0.001206145,0.0001669592,0.0005442006,0.000002493229,0.0000127741,0.00001466135,0.00005425672],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.737016,"threshold_uncertainty_score":0.4338865,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03901766970372088,"score_gpt":0.3682898045092549,"score_spread":0.329272134805534,"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."}}