{"id":"W2116379893","doi":"10.1016/j.specom.2007.02.002","title":"On the optimal linear filtering techniques for noise reduction","year":2007,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Wiener filter; Noise reduction; Computer science; Speech enhancement; Noise (video); Filter (signal processing); Reduction (mathematics); A priori and a posteriori; Algorithm; Speech recognition; Subspace topology; Signal-to-noise ratio (imaging); Linear filter; Noise measurement; Distortion (music); Mathematics; Artificial intelligence; Telecommunications; Computer vision","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":[0.001249267,0.00008594067,0.00006923007,0.00007654609,0.0003842826,0.0001169524,0.001068324,0.0000519626,0.000004049296],"category_scores_gemma":[0.0001351452,0.00006678628,0.00004452082,0.0002417981,0.00004457383,0.0003260824,0.0001817697,0.0001656962,0.00001408634],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005728145,"about_ca_system_score_gemma":0.00002431193,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008845324,"about_ca_topic_score_gemma":0.000003515864,"domain_scores_codex":[0.9992815,0.00003834522,0.0001785483,0.0001677155,0.0001501228,0.0001837879],"domain_scores_gemma":[0.9984953,0.0002265781,0.0001124158,0.001012141,0.0001228361,0.00003075862],"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":[0.00004399037,0.00008916893,0.000009039447,0.00001579319,0.00001085455,8.97686e-7,0.0006736756,0.00008754047,0.1759371,0.02473861,0.002282097,0.7961112],"study_design_scores_gemma":[0.00007537382,0.00006738753,0.00005873033,0.00005265939,0.000002186143,0.00001446123,0.00005801311,0.003166975,0.982033,0.007016954,0.007361716,0.00009260351],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0589159,0.0001117533,0.9312132,0.004620777,0.00009546683,0.0003460087,8.014727e-7,0.0003202948,0.004375815],"genre_scores_gemma":[0.42184,0.00002932842,0.5776727,0.0002294192,0.00007187215,0.00002817414,0.000005104453,0.000007590954,0.0001157588],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8060958,"threshold_uncertainty_score":0.295563,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02789165738821853,"score_gpt":0.3013961836864198,"score_spread":0.2735045262982013,"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."}}