{"id":"W1993882792","doi":"10.1109/tasl.2011.2109382","title":"Acoustic Modeling Using Deep Belief Networks","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1746,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"University of Pennsylvania","keywords":"TIMIT; Hidden Markov model; Discriminative model; Computer science; Artificial intelligence; Pattern recognition (psychology); Deep belief network; Mixture model; Artificial neural network; Speech recognition; Feature (linguistics); Backpropagation; Feature extraction; Markov model; Generative model; Gaussian; Generative grammar; Machine learning; Markov chain","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":[0.0005778009,0.0008502359,0.0007439477,0.0007547314,0.0003251124,0.001316572,0.001527908,0.001127754,0.003588366],"category_scores_gemma":[0.002565627,0.0008324791,0.0007777965,0.0008260459,0.0005630906,0.00156945,0.001062735,0.001887814,0.001492608],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008714126,"about_ca_system_score_gemma":0.0008337053,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01257958,"about_ca_topic_score_gemma":0.01330214,"domain_scores_codex":[0.9996896,0.00007965523,0.00001767339,0.00007048782,0.0001105741,0.00003201232],"domain_scores_gemma":[0.9993027,0.0003858157,0.00006012429,0.00006559764,0.0001549583,0.00003064143],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000238556,0.00001309323,0.0002074249,0.00003131824,0.00002638274,0.00002641532,0.00002036994,0.9595362,0.0007421607,0.007592321,0.0007504394,0.03103003],"study_design_scores_gemma":[0.000001272441,0.000001755705,0.00001970453,0.000002226835,0.000001300314,0.000003277009,0.000001187371,0.9955257,0.0001048448,0.004118285,0.0002186096,0.000001939185],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004071795,0.0004399762,0.9926538,0.0001838752,0.00004359268,0.0000159388,0.0001936221,0.0008661503,0.001531209],"genre_scores_gemma":[0.647759,0.001791405,0.3382541,0.0002449809,0.0001663079,0.0002424901,0.001130731,0.0003693275,0.0100416],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01257958,"threshold_uncertainty_score":0.02501273,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03523967748347272,"score_gpt":0.249923230056549,"score_spread":0.2146835525730763,"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."}}