{"id":"W2160815625","doi":"10.1109/msp.2012.2205597","title":"Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups","year":2012,"lang":"en","type":"article","venue":"IEEE Signal Processing Magazine","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10313,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; University of Toronto","funders":"","keywords":"Hidden Markov model; Speech recognition; Computer science; Mixture model; Artificial neural network; Margin (machine learning); Deep neural networks; Pattern recognition (psychology); Frame (networking); Artificial intelligence; Acoustic model; Gaussian; Speech processing; Machine learning","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":[0.01315874,0.001442838,0.001326207,0.002396411,0.0008975053,0.00589638,0.00161119,0.003095706,0.001366946],"category_scores_gemma":[0.008225771,0.0007235217,0.0008312339,0.001817255,0.004765124,0.01145104,0.005651735,0.009063808,0.0009994664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002269783,"about_ca_system_score_gemma":0.002395683,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002025291,"about_ca_topic_score_gemma":0.002222325,"domain_scores_codex":[0.9950436,0.001783625,0.0004169985,0.0006967066,0.001820782,0.0002382268],"domain_scores_gemma":[0.9931086,0.00279588,0.000264526,0.0009318378,0.002332389,0.0005667629],"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":[0.0003367613,0.0001863531,0.002146824,0.00057611,0.0001541525,0.00009470756,0.00194325,0.01846118,0.005896172,0.2474447,0.01615771,0.706602],"study_design_scores_gemma":[0.00008538799,0.0004456573,0.001850493,0.001209946,0.0002201439,0.0003931353,0.00186053,0.1307112,0.02232201,0.5292698,0.3112701,0.000361579],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01926742,0.1446086,0.7136167,0.09515172,0.001905257,0.00009614295,0.0001043898,0.0007403491,0.02450955],"genre_scores_gemma":[0.3152172,0.2327047,0.4113754,0.01139741,0.007566518,0.0003176606,0.0003657571,0.00046198,0.02059343],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01315874,"threshold_uncertainty_score":0.06959087,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2083977889980022,"score_gpt":0.3405780427773996,"score_spread":0.1321802537793973,"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."}}