{"id":"W3089869259","doi":"10.1109/iscas45731.2020.9180931","title":"High-Frequency Component Restoration for Kalman Filter Based Speech Enhancement","year":2020,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Concordia University","funders":"","keywords":"Speech enhancement; Kalman filter; Intelligibility (philosophy); Computer science; Speech recognition; Component (thermodynamics); Distortion (music); Artificial intelligence; Noise reduction; Bandwidth (computing); Telecommunications","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":[0.0001175814,0.0001060149,0.0001147517,0.00003482698,0.0001107279,0.0001548317,0.0004239716,0.00003093824,0.0001086916],"category_scores_gemma":[0.00003179323,0.00009241511,0.00004497389,0.0001844892,0.00001560992,0.0004716924,0.00005764572,0.00005216559,0.00007801475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003927896,"about_ca_system_score_gemma":0.00007027933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001986845,"about_ca_topic_score_gemma":0.000009919186,"domain_scores_codex":[0.9990243,0.00001736855,0.0001975536,0.0003367926,0.0002189521,0.0002050897],"domain_scores_gemma":[0.999474,0.00002926296,0.0000720514,0.0002336325,0.00008428135,0.0001067402],"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":[0.00004930988,0.0002021897,0.0003446305,0.0001749396,0.00002540451,0.00002406691,0.0004944535,0.0003527088,0.8064128,0.02127299,0.04443732,0.1262092],"study_design_scores_gemma":[0.0005442615,0.0002003491,0.0001436218,0.00001606166,0.000003759176,7.888763e-7,0.000006179254,0.03016686,0.9605264,0.002296271,0.005928939,0.0001665091],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01599392,0.00002701105,0.9590644,0.02343921,0.0002613621,0.0002372789,0.000001572262,0.0001691931,0.0008061043],"genre_scores_gemma":[0.4155423,9.066547e-7,0.5785714,0.0055797,0.0001322834,0.00002449174,0.0000180842,0.000005303495,0.0001255309],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3995484,"threshold_uncertainty_score":0.3768579,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03518443090018528,"score_gpt":0.2579488168007478,"score_spread":0.2227643859005626,"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."}}