{"id":"W2063689849","doi":"10.1109/iscslp.2012.6423452","title":"Investigation of deep neural networks (DNN) for large vocabulary continuous speech recognition: Why DNN surpasses GMMS in acoustic modeling","year":2012,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Speech recognition; Artificial neural network; Vocabulary; Context (archaeology); Mel-frequency cepstrum; Word error rate; Artificial intelligence; Task (project management); Reduction (mathematics); Deep neural networks; Hidden Markov model; Logarithm; Pattern recognition (psychology); Feature extraction; 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":[0.0009144932,0.0001787531,0.0002962467,0.0002085619,0.00008397001,0.00008084323,0.0003263968,0.0001278802,0.00006574961],"category_scores_gemma":[0.0002800436,0.0001711579,0.000106733,0.0004617057,0.00002670749,0.001104626,0.00008788508,0.0001418308,0.00001448901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000420742,"about_ca_system_score_gemma":0.00002695574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004691264,"about_ca_topic_score_gemma":0.0002232823,"domain_scores_codex":[0.9983262,0.0001333,0.0004943685,0.0003023375,0.0002343706,0.0005093906],"domain_scores_gemma":[0.9986672,0.0005131535,0.0001389588,0.0002799341,0.000245413,0.0001553038],"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":[0.0001064118,0.0003992509,0.03643407,0.0002156611,0.00009500178,0.00001838326,0.00147318,0.01261907,0.002550016,0.001498726,0.0024064,0.9421839],"study_design_scores_gemma":[0.0005286934,0.000049324,0.000767538,0.00003471342,0.00002026299,0.00002204804,0.0001794144,0.991209,0.005422439,0.001493381,0.00004348996,0.000229666],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2386157,0.0001360441,0.7597689,0.0002953662,0.0003965321,0.0003236912,0.000005599627,0.0001078248,0.0003503208],"genre_scores_gemma":[0.9012222,0.00001832539,0.09740314,0.0009894428,0.0002339919,0.00005736174,0.00003492455,0.00001620969,0.00002445832],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.97859,"threshold_uncertainty_score":0.6979614,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05066265927163722,"score_gpt":0.2545038198180309,"score_spread":0.2038411605463937,"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."}}