{"id":"W2165730518","doi":"10.1109/icassp.2008.4518579","title":"Perceptually based speech enhancement using the weighted β-SA estimator","year":2008,"lang":"en","type":"article","venue":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Estimator; Weighting; Loudness; Computer science; Bayesian probability; Speech enhancement; Speech recognition; A-weighting; Set (abstract data type); Masking (illustration); Mathematics; Statistics; Artificial intelligence; Noise reduction; Acoustics","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":[0.00187081,0.0008191898,0.0007374306,0.0007020188,0.0001881114,0.0007923518,0.0008158365,0.0009871668,0.001984723],"category_scores_gemma":[0.005287992,0.0003861685,0.0005875847,0.0003584214,0.0004189504,0.001428261,0.0007937764,0.00073669,0.00149617],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002158592,"about_ca_system_score_gemma":0.0003467906,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006198106,"about_ca_topic_score_gemma":0.001238294,"domain_scores_codex":[0.998943,0.0003642173,0.00005049883,0.0001478241,0.0004571699,0.00003731552],"domain_scores_gemma":[0.9983553,0.0008144798,0.0001473372,0.0001602823,0.0004844746,0.00003802534],"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":[0.0006003268,0.0001881093,0.002168122,0.0004110321,0.000238296,0.00008069906,0.0001310542,0.07169178,0.2255011,0.01016429,0.001780872,0.6870443],"study_design_scores_gemma":[0.00004301457,0.0002964616,0.003005012,0.00005088934,0.0001103697,0.0003768215,0.00002747579,0.9220901,0.06446017,0.003304641,0.00616612,0.00006884303],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005373067,0.0002986028,0.9934808,0.00003275611,0.00002200339,0.0000140959,0.00001496599,0.0002081054,0.0005556976],"genre_scores_gemma":[0.1753474,0.0006474461,0.8196833,0.0001608766,0.0001005012,0.00008388964,0.0001760937,0.0001928973,0.003607638],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001984723,"threshold_uncertainty_score":0.009893894,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06555149317474095,"score_gpt":0.2955163017015629,"score_spread":0.2299648085268219,"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."}}