{"id":"W1549297448","doi":"10.1109/icassp.2015.7177961","title":"Investigation of a parametric gain approach to single-channel speech enhancement","year":2015,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Parametric statistics; Noise (video); Wiener filter; Noise reduction; Noise measurement; Computer science; Parametric model; Noise figure; Algorithm; Mathematics; Statistics; Telecommunications; Artificial intelligence; Amplifier","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":[0.0004359189,0.00009051602,0.0001277721,0.0002324753,0.00002656106,0.00008531716,0.0004268057,0.00003415142,0.000001995266],"category_scores_gemma":[0.0001627016,0.0000776076,0.0000240924,0.001380922,0.0000270167,0.0003845063,0.0001495216,0.00004578047,0.0000401766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005727732,"about_ca_system_score_gemma":0.00009532931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002913617,"about_ca_topic_score_gemma":0.000001581465,"domain_scores_codex":[0.9989163,0.000027842,0.0002079299,0.0002788083,0.0003713381,0.0001977381],"domain_scores_gemma":[0.9992387,0.0000226961,0.0000834266,0.0002859537,0.0001618425,0.0002074195],"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":[0.00005133099,0.001157228,0.002771805,0.0002994011,0.00008002274,0.00001550426,0.01635811,0.006112098,0.372347,0.01556477,0.0354322,0.5498105],"study_design_scores_gemma":[0.0001937247,0.0001767518,0.00005742036,0.00001775693,0.00000217835,0.000006063249,0.0001101833,0.01427351,0.9766896,0.008183653,0.0001668159,0.0001222804],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1127185,0.00005540178,0.8702832,0.0004834287,0.0001204659,0.0001351483,1.502949e-7,0.0000686315,0.01613512],"genre_scores_gemma":[0.5598155,4.173632e-7,0.4393989,0.0004173904,0.00002346937,0.000007174535,0.000001101866,0.000003009677,0.000333032],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6043426,"threshold_uncertainty_score":0.3164746,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1002085761365864,"score_gpt":0.2592591099070513,"score_spread":0.1590505337704649,"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."}}