{"id":"W2148681587","doi":"10.1155/2009/928974","title":"A Joint Time-Frequency and Matrix Decomposition Feature Extraction Methodology for Pathological Voice Classification","year":2009,"lang":"en","type":"article","venue":"EURASIP Journal on Advances in Signal Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Non-negative matrix factorization; Speech recognition; Matrix decomposition; SIGNAL (programming language); Feature extraction; Pattern recognition (psychology); Artificial intelligence; Joint (building); Feature (linguistics); Abnormality","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":[0.001334636,0.0002028007,0.000288493,0.0002842768,0.0004247441,0.0004229411,0.000298018,0.0001380867,0.000004623665],"category_scores_gemma":[0.0002205174,0.0001688702,0.00006664901,0.0003843599,0.0000524995,0.002579224,0.00002076526,0.0006012043,0.000004715524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001242211,"about_ca_system_score_gemma":0.00008115863,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":1.0234e-7,"about_ca_topic_score_gemma":3.500695e-7,"domain_scores_codex":[0.9982361,0.0002637836,0.0004372238,0.0004500804,0.0002575421,0.0003552768],"domain_scores_gemma":[0.9987747,0.0002869603,0.0005290984,0.0001107889,0.0001811825,0.0001172361],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00009401652,0.00008052095,0.0001470368,0.00003002819,0.000001771828,0.00004831225,0.0001472189,0.0002859176,0.2467221,0.0005248697,0.00002849144,0.7518897],"study_design_scores_gemma":[0.004384505,0.004695943,0.04739964,0.002152345,0.00006498933,0.01081541,0.0004067129,0.09474812,0.1892763,0.6410853,0.003383047,0.001587668],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02791857,0.007723549,0.9594514,0.003927134,0.0001493324,0.0001771251,7.259264e-7,0.0000848996,0.0005672562],"genre_scores_gemma":[0.4817944,0.0002582069,0.5171087,0.0005808995,0.0002138894,0.000007025517,0.000001780492,0.000007626045,0.00002745994],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.750302,"threshold_uncertainty_score":0.6886326,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05492277920802405,"score_gpt":0.3857681327184371,"score_spread":0.3308453535104131,"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."}}