{"id":"W2083025809","doi":"10.1109/ssp.2009.5278556","title":"Bayesian spectral amplitude estimation for speech enhancement with correlated spectral components","year":2009,"lang":"en","type":"article","venue":"2009 IEEE/SP 15th Workshop on Statistical Signal Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"PESQ; Estimator; Speech enhancement; Bayesian probability; Uncorrelated; Amplitude; Computer science; Channel (broadcasting); Mathematics; Algorithm; Upper and lower bounds; Bayes estimator; Speech recognition; Artificial intelligence; Statistics; Noise reduction; Physics; 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":[0.000395456,0.0005541136,0.0005489769,0.0002104233,0.0006435685,0.001034362,0.0006927385,0.000172087,0.00009191566],"category_scores_gemma":[0.00007579903,0.000470824,0.0000862264,0.0008137148,0.0001385141,0.0008370078,0.00003356874,0.0005576078,0.00005985694],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002608938,"about_ca_system_score_gemma":0.0002410282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000520053,"about_ca_topic_score_gemma":0.00000391931,"domain_scores_codex":[0.996004,0.00007213089,0.0007029419,0.001095189,0.0009258452,0.001199921],"domain_scores_gemma":[0.9982957,0.0003482219,0.00034456,0.0003577429,0.0002178332,0.0004359523],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000611675,0.000928832,0.00007513261,0.0001155764,0.00004497449,0.0001984373,0.000313145,0.008083301,0.01025117,0.003884577,0.001396181,0.974097],"study_design_scores_gemma":[0.002616777,0.001848465,0.001763249,0.001276938,0.00008700493,0.0001093506,0.00004398395,0.8854907,0.07074448,0.03463708,0.0001892365,0.001192725],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01048736,0.0001494505,0.9860001,0.0009052128,0.0001875834,0.000654199,0.00001992345,0.0003543223,0.001241884],"genre_scores_gemma":[0.5696234,0.000004151609,0.429363,0.000658304,0.0001372616,0.00001963932,0.00004795053,0.00002420053,0.0001221621],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9729043,"threshold_uncertainty_score":0.9997743,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0213106224888267,"score_gpt":0.2891867086137563,"score_spread":0.2678760861249296,"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."}}