{"id":"W2716649223","doi":"10.1109/ccece.2017.7946647","title":"Speech enhancement using both spectral and spectral modulation domains","year":2017,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"PESQ; Estimator; Speech enhancement; Minimum mean square error; Modulation (music); Computer science; Speech recognition; Signal-to-noise ratio (imaging); Noise (video); Mathematics; SIGNAL (programming language); Algorithm; Statistics; Artificial intelligence; Acoustics; Physics; Noise reduction","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":[0.0001641887,0.0001112064,0.0001108167,0.00004880688,0.0005680655,0.0008814855,0.0004443658,0.00003329209,0.00003590882],"category_scores_gemma":[0.00001624615,0.000098078,0.00002882807,0.00004938993,0.00005690896,0.001098506,0.0001875091,0.00006928782,0.00001194295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004932252,"about_ca_system_score_gemma":0.00004262397,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007380872,"about_ca_topic_score_gemma":0.00003650732,"domain_scores_codex":[0.9990454,0.00001034234,0.0001321059,0.0003262549,0.0001996077,0.0002863143],"domain_scores_gemma":[0.9992935,0.000008605712,0.0001120643,0.0004796659,0.00002190916,0.00008426878],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001511559,0.0001174788,0.02029214,0.00003792346,0.00003812996,0.00009804676,0.0006555173,0.000115119,0.6458954,0.02454095,0.0002000498,0.3079942],"study_design_scores_gemma":[0.000532991,0.00006974753,0.0702291,0.00003604514,0.000006768612,0.00007265656,0.0000182469,0.110928,0.7975324,0.02006424,0.0002124687,0.0002973789],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5555098,0.00002732659,0.435378,0.0003931637,0.0001467187,0.00005604363,1.582823e-7,0.00004652772,0.008442247],"genre_scores_gemma":[0.6776735,0.000008133983,0.3217269,0.00009033596,0.0001215531,6.202863e-7,2.260602e-7,0.000003878168,0.0003747975],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3076968,"threshold_uncertainty_score":0.8500185,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02742055141142517,"score_gpt":0.2872277145663094,"score_spread":0.2598071631548842,"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."}}