{"id":"W2587210085","doi":"10.1109/slt.2016.7846241","title":"Batch-normalized joint training for DNN-based distant speech recognition","year":2016,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Speech recognition; Computer science; Robustness (evolution); Speech technology; Acoustic model; Voice activity detection; Training set; Speech processing; Speaker recognition; Joint (building); Speech enhancement; Training (meteorology); Artificial intelligence; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00116248,0.0009704974,0.0005961847,0.0004113117,0.0003335293,0.0004514832,0.001412038,0.0007926558,0.005651565],"category_scores_gemma":[0.002015798,0.0004645282,0.0004062395,0.00051331,0.0003869064,0.00109384,0.0008599758,0.001519558,0.003733948],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004664726,"about_ca_system_score_gemma":0.0009701285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007073474,"about_ca_topic_score_gemma":0.01731933,"domain_scores_codex":[0.9995304,0.00009431719,0.00003785751,0.0001436037,0.0001187677,0.00007498769],"domain_scores_gemma":[0.9994437,0.0002002364,0.00002999065,0.000135048,0.0001513573,0.00003968141],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005140772,0.0001524744,0.0007024452,0.0001532643,0.0000839682,0.0001135387,0.00005677169,0.1108045,0.05915261,0.003742723,0.00778652,0.8167371],"study_design_scores_gemma":[0.0000131598,0.0000643545,0.0006246563,0.00001568917,0.00002502355,0.00006171836,0.00001566692,0.9651051,0.02769081,0.00311781,0.003248847,0.00001726668],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01945234,0.0012847,0.9699841,0.0001140769,0.0001931617,0.00006480462,0.0003370459,0.005202857,0.003366805],"genre_scores_gemma":[0.4622757,0.0008177595,0.5198009,0.0002696319,0.0001677651,0.0002166023,0.00278969,0.0005829743,0.01307906],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007073474,"threshold_uncertainty_score":0.01890635,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08675578359859087,"score_gpt":0.2701628841973234,"score_spread":0.1834071005987326,"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."}}