{"id":"W2229498876","doi":"10.1007/978-3-662-48331-2_5","title":"A Modified NMF-Based Filter Bank Approach for Enhancement of Speech Data in Nonstationary Noise","year":2015,"lang":"en","type":"book-chapter","venue":"Signals and communication technology","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University; University of Waterloo","funders":"","keywords":"PESQ; Speech recognition; Speech enhancement; Computer science; Noise (video); Filter bank; Non-negative matrix factorization; Filter (signal processing); Noise measurement; Pattern recognition (psychology); Noise reduction; Artificial intelligence; Matrix decomposition; Computer vision; Image (mathematics)","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":[0.0006232631,0.0001952302,0.0003684626,0.0004723387,0.00007289593,0.00003597159,0.00246144,0.0003258961,0.00001396105],"category_scores_gemma":[0.00005471784,0.0001955654,0.0000325689,0.0001419081,0.0002201341,0.0001912299,0.00101585,0.0002749368,0.000002296312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003821889,"about_ca_system_score_gemma":0.0002396067,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006796419,"about_ca_topic_score_gemma":0.00001008727,"domain_scores_codex":[0.9986752,0.00002575109,0.000465486,0.0004677662,0.0001948048,0.0001710039],"domain_scores_gemma":[0.9968321,0.0001398057,0.0004149628,0.002321775,0.0002553322,0.00003599895],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005827516,0.000187809,0.00002065789,0.0002792858,0.00006519987,0.000002571406,0.0001217488,0.0001552745,0.005670855,0.170145,0.001686669,0.8216066],"study_design_scores_gemma":[0.002802881,0.0005197795,0.00001404634,0.0008831892,0.00007613246,0.00002252632,0.00009931353,0.118849,0.112646,0.7268749,0.03621652,0.000995692],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001339771,0.01215428,0.9341636,0.003029553,0.00002762328,0.0008215072,0.0001126955,0.0001153446,0.0494414],"genre_scores_gemma":[0.1079795,0.0007341609,0.884733,0.0002446545,0.00001957622,0.000176008,0.0008207363,0.00003152348,0.005260849],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8206109,"threshold_uncertainty_score":0.7974926,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08591726844962995,"score_gpt":0.3013729122506905,"score_spread":0.2154556438010606,"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."}}