{"id":"W3096879251","doi":"10.1016/j.specom.2020.10.007","title":"Speech enhancement using a DNN-augmented colored-noise Kalman filter","year":2020,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; Concordia University","funders":"China Scholarship Council","keywords":"Speech enhancement; Computer science; Kalman filter; Speech recognition; Noise (video); Autoregressive model; Noise reduction; Linear prediction; Colors of noise; Noise measurement; Residual; Artificial intelligence; Algorithm; Mathematics; Statistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005820986,0.0008119824,0.0005552703,0.0003218379,0.0003752683,0.0004592464,0.0005166351,0.0007447607,0.002603524],"category_scores_gemma":[0.0008536844,0.0003343105,0.000646776,0.0003067536,0.0002413888,0.0006967693,0.0005421979,0.0008500443,0.001242832],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004142571,"about_ca_system_score_gemma":0.0009309585,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007539088,"about_ca_topic_score_gemma":0.01484454,"domain_scores_codex":[0.9997093,0.00004284926,0.00001919864,0.00009234095,0.00009847546,0.00003782036],"domain_scores_gemma":[0.9996625,0.00008528161,0.00001836858,0.00002934596,0.0001893496,0.00001512765],"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":[0.0006872629,0.0001984399,0.001340352,0.0002782933,0.000163654,0.0002185943,0.0001388234,0.1449793,0.189175,0.005491274,0.003913175,0.6534159],"study_design_scores_gemma":[0.00001792286,0.00008101803,0.0008545592,0.00002562679,0.00007293921,0.00007337331,0.0000137961,0.9525506,0.04148286,0.0006759766,0.004128796,0.00002243302],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009189451,0.0003911535,0.9873071,0.00007932325,0.0002361808,0.00003077282,0.00006954499,0.0008738616,0.001822588],"genre_scores_gemma":[0.3498294,0.0008903819,0.6356066,0.0002670962,0.0001701967,0.0001083711,0.0004535806,0.0001678248,0.01250667],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007539088,"threshold_uncertainty_score":0.01499045,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04368881874748969,"score_gpt":0.284747555239647,"score_spread":0.2410587364921573,"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."}}