{"id":"W2906903188","doi":"","title":"Speech Enhancement with Adaptive Thresholding and Kalman Filtering","year":2017,"lang":"en","type":"dissertation","venue":"Spectrum Research Repository (Concordia University)","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"McGill University","keywords":"Speech enhancement; Intelligibility (philosophy); Computer science; Speech recognition; Noise measurement; Noise (video); Wiener filter; Background noise; Voice activity detection; Speech processing; Noise power; Noise floor; Noise reduction; Telecommunications; Artificial intelligence; Power (physics); Physics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005343253,0.0007027622,0.0008767612,0.0006087762,0.0002933935,0.0006584213,0.0006230967,0.0008752987,0.00176215],"category_scores_gemma":[0.001400446,0.0004284381,0.0008703077,0.0006666937,0.0004244951,0.001002957,0.0007712955,0.0008781658,0.0008457071],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003736652,"about_ca_system_score_gemma":0.0005012772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00342452,"about_ca_topic_score_gemma":0.002953744,"domain_scores_codex":[0.9995769,0.00006596422,0.00003088151,0.0001471116,0.000144162,0.00003506268],"domain_scores_gemma":[0.999689,0.0001509832,0.00003820986,0.00002899322,0.00008321855,0.000009606567],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002417835,0.00008874799,0.0008944861,0.0003569291,0.0001268622,0.0001973081,0.0002159351,0.2893829,0.04713906,0.01693226,0.00215259,0.642271],"study_design_scores_gemma":[0.00001106278,0.00005578544,0.0004957566,0.00001955152,0.00002920757,0.00009181217,0.0000170063,0.9840283,0.009080278,0.002992929,0.003156737,0.00002160597],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.003863855,0.0009954356,0.993313,0.00005569403,0.0000647448,0.00002176852,0.00001854004,0.0003290013,0.001337927],"genre_scores_gemma":[0.2704639,0.003713701,0.7140307,0.0001424551,0.0002096212,0.0001500675,0.0002081932,0.0001706983,0.01091052],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.00342452,"threshold_uncertainty_score":0.006809175,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03296958574724919,"score_gpt":0.2829974343657756,"score_spread":0.2500278486185264,"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."}}