{"id":"W2790470374","doi":"10.1109/globalsip.2017.8308606","title":"Adaptive wavelet packet thresholding with iterative Kalman filter for speech enhancement","year":2017,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"McGill University","keywords":"PESQ; Computer science; Speech enhancement; Speech recognition; Thresholding; Wavelet packet decomposition; Frame (networking); Voice activity detection; Kalman filter; Noise (video); Speech processing; Speech coding; Wavelet transform; Wavelet; Artificial intelligence; Noise reduction; Image (mathematics); Telecommunications","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001865285,0.0001676169,0.0001671734,0.00004545715,0.0006859261,0.0008754397,0.0008608407,0.00003554956,0.00004822891],"category_scores_gemma":[0.00002763328,0.0001149416,0.00004520583,0.00005316215,0.00007969908,0.001555811,0.0002215229,0.00008104266,0.00002460171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003628363,"about_ca_system_score_gemma":0.00006095018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001199625,"about_ca_topic_score_gemma":0.00004488002,"domain_scores_codex":[0.9988261,0.000009735657,0.0001375721,0.0004485352,0.0002206047,0.0003574014],"domain_scores_gemma":[0.9989125,0.00003796244,0.0001644335,0.0006508944,0.0001519825,0.0000822688],"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":[0.000216489,0.0002443755,0.001270746,0.00007912967,0.0002162122,0.0001290369,0.003992343,0.00001442627,0.02228155,0.04790015,0.02001455,0.903641],"study_design_scores_gemma":[0.0007969558,0.0004871364,0.0005621547,0.0001155319,0.000007634431,0.00001547063,0.00008960082,0.007784672,0.9786628,0.007798211,0.00336536,0.0003144318],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0218306,0.0000260317,0.9483193,0.002057459,0.0001780209,0.0003079645,0.000003002064,0.00007194432,0.02720564],"genre_scores_gemma":[0.5129254,0.000002421019,0.4833053,0.000594126,0.0001039064,0.00003934234,0.000001999594,0.000008011664,0.003019482],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9563813,"threshold_uncertainty_score":0.8441885,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04025092827555179,"score_gpt":0.287423985691067,"score_spread":0.2471730574155152,"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."}}