{"id":"W4392638861","doi":"10.1109/jtehm.2024.3375323","title":"Improving Dysarthric Speech Segmentation With Emulated and Synthetic Augmentation","year":2024,"lang":"en","type":"article","venue":"IEEE Journal of Translational Engineering in Health and Medicine","topic":"Voice and Speech Disorders","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Brain Institute; Toronto Rehabilitation Institute; University of Toronto; University Health Network","funders":"National Institute on Deafness and Other Communication Disorders; Science and Engineering Research Council; Toronto Rehabilitation Institute; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Associated Medical Services; Parkinson Canada; Weston Brain Institute; ALS Society of Canada; AGE-WELL; Mitacs; Sunnybrook Research Institute","keywords":"Speech recognition; Computer science; Segmentation; Artificial intelligence; Natural language processing","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":[0.0003791652,0.00008923224,0.0002160345,0.0003711241,0.00002210272,0.000008772126,0.00001357604,0.00003293494,0.00001057781],"category_scores_gemma":[0.00003331624,0.00006391988,0.0000162306,0.0001959808,0.00002669891,0.0001396426,8.924199e-7,0.0002058669,2.372649e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003995036,"about_ca_system_score_gemma":0.0001681827,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004695009,"about_ca_topic_score_gemma":0.00001001869,"domain_scores_codex":[0.9991313,0.00001293148,0.0003941861,0.00009539889,0.000246275,0.0001199631],"domain_scores_gemma":[0.9995811,0.0001076685,0.00006499232,0.00002950629,0.00004630328,0.0001704502],"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":[0.00243274,0.0002281597,0.03067115,0.01757676,0.0004471436,0.0009301203,0.0174414,0.04673706,0.06880803,0.0008711161,0.0003176563,0.8135387],"study_design_scores_gemma":[0.04092243,0.01657601,0.1330662,0.03551412,0.0007329035,0.01469034,0.003851426,0.7462803,0.003259624,0.0006233595,0.003673621,0.000809698],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9504099,0.01635017,0.02312052,0.009599438,0.0002244303,0.0002517885,0.000001288379,0.00002103761,0.00002143947],"genre_scores_gemma":[0.9938147,0.001555274,0.004188611,0.0002300075,0.0001692052,0.000002168206,0.000007489458,0.00001366802,0.0000188693],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.812729,"threshold_uncertainty_score":0.2606577,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01228067549499672,"score_gpt":0.2878225791137894,"score_spread":0.2755419036187927,"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."}}