{"id":"W2156333708","doi":"10.1109/lsp.2009.2018225","title":"Generalized Bayesian Estimators of the Spectral Amplitude for Speech Enhancement","year":2009,"lang":"en","type":"article","venue":"IEEE Signal Processing Letters","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Estimator; Speech enhancement; Bayesian probability; Wiener filter; Mathematics; Noise (video); Computer science; Algorithm; Filter (signal processing); Speech recognition; Statistics; Artificial intelligence","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":[0.0002917388,0.0002209646,0.0002513414,0.00008866713,0.000302914,0.0002720454,0.001069661,0.00005112359,0.000006813544],"category_scores_gemma":[0.00001722433,0.0001642487,0.0001557377,0.0004473671,0.00009404819,0.0004486882,0.00003771463,0.0001433741,0.000002452538],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006666303,"about_ca_system_score_gemma":0.0001534303,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000492811,"about_ca_topic_score_gemma":0.000001027954,"domain_scores_codex":[0.9982145,0.00003549681,0.0003808273,0.000436372,0.0004422257,0.000490526],"domain_scores_gemma":[0.9991635,0.00003860223,0.0002939391,0.0003318771,0.00008852513,0.00008352199],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001948026,0.00006389411,0.0001250431,0.00006975551,0.00001210255,0.000004921751,0.0003206705,0.0007122279,0.8338566,0.0001802351,0.001394462,0.1632406],"study_design_scores_gemma":[0.0004955558,0.00008293514,0.0003875752,0.0001622398,0.0000166825,0.00001753461,0.000006108562,0.01483942,0.9788235,0.004690655,0.0002380407,0.0002396789],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1867293,0.0001280304,0.8056211,0.006875617,0.0002100601,0.0002374584,0.000001134153,0.00008279506,0.0001144868],"genre_scores_gemma":[0.7424581,9.856201e-7,0.2521809,0.005135726,0.0001628184,0.0000109955,7.798579e-7,0.00001039194,0.00003928765],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5557289,"threshold_uncertainty_score":0.6697869,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01507770421667245,"score_gpt":0.2590069115743965,"score_spread":0.2439292073577241,"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."}}