{"id":"W2000916836","doi":"10.1109/89.902276","title":"An adaptive KLT approach for speech enhancement","year":2001,"lang":"en","type":"article","venue":"IEEE Transactions on Speech and Audio Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":235,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Speech enhancement; Speech recognition; Noise (video); Computer science; Speech processing; White noise; Additive white Gaussian noise; Residual; Background noise; Colors of noise; Distortion (music); Mathematics; Artificial intelligence; Noise reduction; Algorithm; Telecommunications","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003793208,0.0003627032,0.000335007,0.0002605565,0.0009351995,0.0006181193,0.0005615515,0.0001427727,0.00001857756],"category_scores_gemma":[0.000005508647,0.0003378061,0.0001071528,0.0006636925,0.0001044215,0.001633546,0.00000481275,0.0002994943,0.00001142373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008298166,"about_ca_system_score_gemma":0.0001730986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001124649,"about_ca_topic_score_gemma":0.000009814531,"domain_scores_codex":[0.9975947,0.00004278183,0.0003680629,0.0009449812,0.0003884467,0.0006610174],"domain_scores_gemma":[0.9988582,0.00005173159,0.0001643899,0.0004325808,0.0002102553,0.0002828469],"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":[0.0001182112,0.0004200063,0.00001136037,0.0000742198,0.00002453012,0.00001524419,0.0003972559,0.0005694503,0.02519102,0.00002886638,0.00005488005,0.9730949],"study_design_scores_gemma":[0.001139651,0.00086134,0.00001975301,0.00013081,0.00004352667,0.000253061,0.000312288,0.07282626,0.9212807,0.001520371,0.000997048,0.0006151238],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0130358,0.0003639641,0.983376,0.0003193186,0.0002137498,0.0004566971,0.00000691414,0.0003315542,0.001896022],"genre_scores_gemma":[0.5670416,0.00008143657,0.4317023,0.0004330243,0.0001100211,0.00008947783,0.000002854469,0.00002424589,0.0005149988],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9724798,"threshold_uncertainty_score":0.9999074,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0278643172740081,"score_gpt":0.2735090793971463,"score_spread":0.2456447621231382,"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."}}