{"id":"W2898940603","doi":"10.1109/mlsp.2018.8517027","title":"NOISE-ADAPTIVE DEEP NEURAL NETWORK FOR SINGLE-CHANNEL SPEECH ENHANCEMENT","year":2018,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke; Université de Montréal; McGill University","funders":"","keywords":"Speech enhancement; Computer science; Noise (video); Artificial neural network; Speech recognition; Benchmark (surveying); Channel (broadcasting); Exploit; Noise measurement; Artificial intelligence; Pattern recognition (psychology); Adaptation (eye); Noise reduction; Image (mathematics); Telecommunications","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":[0.0001891648,0.0001540471,0.0001462031,0.00004020009,0.0002777692,0.0002033337,0.0005769326,0.00004771122,0.00004284758],"category_scores_gemma":[0.0000260062,0.0001303993,0.00006601593,0.0002979026,0.00007544502,0.0005503857,0.0001837147,0.00005912462,0.00009296095],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004266568,"about_ca_system_score_gemma":0.00002983643,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008931109,"about_ca_topic_score_gemma":0.00004659386,"domain_scores_codex":[0.9986246,0.00001539781,0.0001932333,0.0004287044,0.0001991751,0.0005388892],"domain_scores_gemma":[0.9992366,0.00005653034,0.00008675216,0.0003122695,0.0002012927,0.0001065646],"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":[0.00009947101,0.0002430944,0.00009543906,0.00002876206,0.00005796803,0.0000182002,0.001043484,0.0005885971,0.04688581,0.006739774,0.01608708,0.9281123],"study_design_scores_gemma":[0.0004777003,0.001008436,0.00005026113,0.00002787578,0.000008525211,0.00002371563,0.00004629562,0.2274579,0.746583,0.02021267,0.003758346,0.0003453126],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006176469,0.0001230584,0.9799058,0.0008871109,0.001184022,0.0002330439,4.389615e-7,0.0001829709,0.01130703],"genre_scores_gemma":[0.525785,0.000001227979,0.470523,0.001764205,0.001019249,0.00002094427,0.00000149609,0.00001006415,0.000874751],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.927767,"threshold_uncertainty_score":0.5317529,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03478754792219929,"score_gpt":0.2560041248135321,"score_spread":0.2212165768913328,"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."}}