{"id":"W3023862501","doi":"10.1186/s13636-020-00174-4","title":"Quadratic approach for single-channel noise reduction","year":2020,"lang":"en","type":"article","venue":"EURASIP Journal on Audio Speech and Music Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"Israel Science Foundation; National Natural Science Foundation of China","keywords":"PESQ; Quadratic equation; Speech enhancement; Kronecker product; Algorithm; Filter (signal processing); Linear filter; Computer science; Noise reduction; Mathematics; Noise (video); Speech recognition; Kronecker delta; Artificial intelligence; Physics","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004789489,0.0003177439,0.0003652044,0.0001788937,0.0008177198,0.001300359,0.0005418362,0.0001012754,0.000005845131],"category_scores_gemma":[0.0002836445,0.000269954,0.00012324,0.0006016718,0.00007547872,0.00145593,0.00009564044,0.0004872323,0.000008412547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007490256,"about_ca_system_score_gemma":0.0002108955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":5.659081e-7,"about_ca_topic_score_gemma":1.818047e-7,"domain_scores_codex":[0.9978455,0.00006021874,0.0004826732,0.0006322136,0.0004252078,0.0005542044],"domain_scores_gemma":[0.9985804,0.00004714315,0.0004463215,0.0001843598,0.0002384281,0.000503352],"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":[0.0001572609,0.0002138255,0.0000270014,0.0004258638,0.00003565693,0.00007980075,0.00343268,0.0003784137,0.1609899,0.0001111633,0.003347676,0.8308008],"study_design_scores_gemma":[0.00648735,0.003622272,0.0002597573,0.00124443,0.0001803698,0.01134595,0.002309642,0.1260843,0.8267603,0.01206369,0.007259928,0.002382062],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03139628,0.00159059,0.9568457,0.006203909,0.0004618025,0.0003110024,0.000001742597,0.000242661,0.002946293],"genre_scores_gemma":[0.7678347,0.00004095899,0.2274303,0.003132763,0.001413462,0.00001216668,0.000003200018,0.00003620925,0.00009627773],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8284187,"threshold_uncertainty_score":0.9999753,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05541412199844772,"score_gpt":0.2512059560916214,"score_spread":0.1957918340931737,"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."}}