{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000361275,0.0002140086,0.000230004,0.00008932281,0.0003607159,0.0003165478,0.002031693,0.00008359571,0.00009070845],"category_scores_gemma":[0.0001106538,0.0002205413,0.00007979489,0.0007244993,0.00007195138,0.0008237677,0.0009448768,0.0002918649,0.0001987388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001641948,"about_ca_system_score_gemma":0.0001309441,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004740887,"about_ca_topic_score_gemma":0.00001453097,"domain_scores_codex":[0.9981797,0.0001603442,0.0004060541,0.0004451865,0.0004414251,0.0003673392],"domain_scores_gemma":[0.9979851,0.00007384207,0.0002531804,0.001320279,0.0001853692,0.0001822167],"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":[0.00006696849,0.0003459427,0.0008600813,0.0001043337,0.00008762155,0.00003891609,0.003521014,0.000212262,0.6666241,0.001240387,0.005850593,0.3210478],"study_design_scores_gemma":[0.0006702003,0.0001327715,0.0003138608,0.0001167354,0.00002038177,0.00002663539,0.000125358,0.05651174,0.9252821,0.001372497,0.0150557,0.0003720743],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4924265,0.001610021,0.4753863,0.01897955,0.0002399899,0.0007441871,0.000005324005,0.0006477091,0.009960418],"genre_scores_gemma":[0.5947099,0.0001157936,0.4021926,0.002722727,0.00007331811,0.00001719236,0.00002157767,0.00001810311,0.0001287712],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3206757,"threshold_uncertainty_score":0.8993412,"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."}}