{"id":"W4307993093","doi":"10.32920/21428724.v1","title":"A Joint Time-Frequency and Matrix Decomposition Feature Extraction Methodology for Pathological Voice Classification","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Voice and Speech Disorders","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Non-negative matrix factorization; Computer science; Speech recognition; Matrix decomposition; SIGNAL (programming language); Feature extraction; Abnormality; Pattern recognition (psychology); Artificial intelligence; Joint (building); Feature (linguistics); 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009097565,0.0006801906,0.0006062184,0.001917722,0.0003584985,0.0006313563,0.0004745662,0.0006725034,0.001684229],"category_scores_gemma":[0.001858929,0.0001853303,0.0009435536,0.001324922,0.0004012105,0.0007495489,0.0004787616,0.0007059634,0.001017077],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002653127,"about_ca_system_score_gemma":0.0005591143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001800079,"about_ca_topic_score_gemma":0.002000942,"domain_scores_codex":[0.9993393,0.0001135922,0.00006814732,0.000164708,0.0002603139,0.000053932],"domain_scores_gemma":[0.9992917,0.0001714871,0.0001006121,0.00009340679,0.0003126196,0.00003016374],"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":[0.0001171175,0.0001150493,0.001824636,0.0001240286,0.00006242101,0.0001219225,0.00008341995,0.007959038,0.1172133,0.003007861,0.002889052,0.8664821],"study_design_scores_gemma":[0.00003458931,0.0003985605,0.0142816,0.00004442953,0.0001025411,0.001205078,0.0001167851,0.8997878,0.06226738,0.006530042,0.01513482,0.00009642896],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004630591,0.0001546446,0.9944488,0.00005222007,0.00003973015,0.00004252528,0.00007352855,0.0003297226,0.0002283473],"genre_scores_gemma":[0.08387603,0.0002830913,0.9133625,0.00005255303,0.0000677403,0.0001264689,0.0004346138,0.00006190937,0.001735036],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001917722,"threshold_uncertainty_score":0.005634248,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1226426330118375,"score_gpt":0.4223486650216448,"score_spread":0.2997060320098073,"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."}}