{"id":"W2112021726","doi":"10.1109/taslp.2014.2346313","title":"Fast Adaptation of Deep Neural Network Based on Discriminant Codes for Speech Recognition","year":2014,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":139,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"University of Science and Technology of China","keywords":"Computer science; Speech recognition; TIMIT; Normalization (sociology); Adaptation (eye); Artificial neural network; Artificial intelligence; Speaker recognition; Pattern recognition (psychology); Word error rate; Hidden Markov model","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":[0.000426369,0.0002307242,0.0002852806,0.0002325087,0.0003568034,0.0001627947,0.0002863296,0.0001070005,0.00004354782],"category_scores_gemma":[0.0001076568,0.000206259,0.0001263486,0.0003675963,0.00006549773,0.0003740453,0.000004541018,0.0001745881,0.00000980958],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003252941,"about_ca_system_score_gemma":0.00003783945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003752575,"about_ca_topic_score_gemma":0.0001939096,"domain_scores_codex":[0.9984644,0.0001122676,0.0003367709,0.0004580916,0.0002973338,0.000331153],"domain_scores_gemma":[0.9987566,0.0004220583,0.000194131,0.0003500535,0.0001598476,0.0001173385],"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":[0.0001042079,0.0001366535,0.000008567584,0.0001252147,0.00001069364,0.000005004461,0.0006026553,0.003037183,0.001531391,0.000009951091,0.00001253539,0.9944159],"study_design_scores_gemma":[0.000924801,0.0004441584,0.0001605906,0.0002870611,0.00006626725,0.00003346598,0.0006661433,0.8807871,0.1152522,0.0009689324,0.00009304905,0.0003161836],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03578917,0.0001063626,0.962364,0.000552687,0.0002579727,0.0003226584,0.00002754918,0.0001577269,0.0004218609],"genre_scores_gemma":[0.6780998,0.00001042187,0.3211658,0.0004896244,0.0001021704,0.00004978945,0.00001611384,0.00001962879,0.00004675044],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9940997,"threshold_uncertainty_score":0.8411,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02681299895984912,"score_gpt":0.2610017309285276,"score_spread":0.2341887319686785,"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."}}