{"id":"W2016557737","doi":"10.1109/iscas.2012.6271907","title":"On sparsity issues in compressive sensing based speech enhancement","year":2012,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Discrete cosine transform; Compressed sensing; Speech enhancement; Computer science; Speech recognition; Noise (video); Wavelet; Focus (optics); Wavelet transform; SIGNAL (programming language); Noise reduction; Algorithm; Pattern recognition (psychology); Artificial intelligence; Image (mathematics); 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":[0.0002273863,0.000100612,0.0001183256,0.00008836959,0.00006906981,0.0000852646,0.0002431536,0.00003135716,0.0000715737],"category_scores_gemma":[0.00002726863,0.0000863117,0.00002389525,0.000211905,0.00002049184,0.0005035715,0.00009452047,0.00009282596,0.0001435652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005054214,"about_ca_system_score_gemma":0.00002412772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007259453,"about_ca_topic_score_gemma":0.00002630944,"domain_scores_codex":[0.9990706,0.00003702859,0.0001210316,0.0002047421,0.0002249714,0.0003416226],"domain_scores_gemma":[0.9995254,0.00005565033,0.00004763119,0.0002604516,0.00002980429,0.0000811073],"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":[0.00005893085,0.001357779,0.02442336,0.00009483785,0.00002728444,0.0001680656,0.002953235,0.0007839243,0.09972444,0.0106501,0.01563328,0.8441247],"study_design_scores_gemma":[0.0002533086,0.00003323864,0.002594891,0.00006779803,0.000001111712,0.000003331549,0.00001900466,0.01113691,0.9829594,0.001043512,0.001740503,0.0001469219],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3746009,0.0001316897,0.610317,0.001649981,0.0003798352,0.0001004376,1.81057e-7,0.0001095123,0.01271051],"genre_scores_gemma":[0.7892167,0.000001724114,0.20913,0.001280446,0.0000575214,5.779283e-7,8.291718e-7,0.000003059773,0.0003091952],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.883235,"threshold_uncertainty_score":0.3519689,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0224087707899601,"score_gpt":0.2768149910474321,"score_spread":0.2544062202574719,"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."}}