{"id":"W2771813982","doi":"10.1109/waspaa.2017.8170001","title":"Modulation spectrum based beamforming for speech enhancement","year":2017,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"PESQ; Speech enhancement; Beamforming; Reverberation; Computer science; Speech recognition; Noise (video); Modulation (music); Signal-to-noise ratio (imaging); Electronic engineering; Acoustics; Background noise; Telecommunications; Artificial intelligence; Engineering; 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":[],"consensus_categories":[],"category_scores_codex":[0.0001876803,0.0000715825,0.00007337063,0.00003813331,0.0005139003,0.0004887323,0.0006024954,0.0000239838,0.00002326788],"category_scores_gemma":[0.00004204745,0.0000621314,0.00004004383,0.0000319289,0.00001773394,0.0009755803,0.00008226326,0.00002887417,0.0000200642],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002976867,"about_ca_system_score_gemma":0.00004607192,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001548111,"about_ca_topic_score_gemma":0.00001936551,"domain_scores_codex":[0.9993159,0.000002786325,0.0001080227,0.0002251637,0.0001396943,0.0002084856],"domain_scores_gemma":[0.9992867,0.00001546222,0.000108665,0.0005112443,0.00003508439,0.00004292032],"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":[0.000009283396,0.00005996363,0.0008739966,0.00003927851,0.000008853613,0.000003263376,0.00006601882,0.0003054334,0.05437623,0.008599383,0.0006158036,0.9350425],"study_design_scores_gemma":[0.000254417,0.00003770952,0.0006336201,0.00001381199,0.000001327324,9.875437e-7,0.000001911318,0.2494868,0.7368899,0.01046552,0.002126288,0.0000877554],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01658531,0.000006189062,0.9728228,0.003766925,0.0003194115,0.0001456487,2.805102e-7,0.00007472517,0.006278708],"genre_scores_gemma":[0.5219085,4.643827e-7,0.4769504,0.0002194748,0.00007489173,0.000008615488,0.000001156954,0.000002878255,0.0008336783],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9349548,"threshold_uncertainty_score":0.4712857,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02718626600270197,"score_gpt":0.2886005119537863,"score_spread":0.2614142459510844,"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."}}