{"id":"W2172097686","doi":"10.1109/icassp.2012.6288863","title":"Understanding how Deep Belief Networks perform acoustic modelling","year":2012,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":270,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Deep belief network; TIMIT; Computer science; Hidden Markov model; Artificial intelligence; Artificial neural network; Similarity (geometry); Feature (linguistics); Pattern recognition (psychology); Speech recognition; Feature vector; Visualization; Representation (politics)","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":[0.001687313,0.0007813609,0.0004277925,0.000724728,0.0004480001,0.003367307,0.0012641,0.001427115,0.003534873],"category_scores_gemma":[0.01084562,0.0007498211,0.0005334429,0.0006587364,0.001022219,0.005933099,0.001097015,0.002342584,0.0008149823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001231862,"about_ca_system_score_gemma":0.0009341554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01372974,"about_ca_topic_score_gemma":0.009991081,"domain_scores_codex":[0.9994228,0.0002515773,0.00002638164,0.00008848029,0.0001333953,0.00007738709],"domain_scores_gemma":[0.9976507,0.00161869,0.0001254587,0.0001904199,0.0003214082,0.00009327093],"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":[0.00006522417,0.00004182141,0.002295271,0.0001485242,0.00009920784,0.0001109725,0.0004306845,0.5040702,0.001929257,0.4055953,0.002860168,0.08235339],"study_design_scores_gemma":[0.000005367444,0.000009629904,0.0002320043,0.00003057209,0.000009293662,0.00001713316,0.00005462345,0.7638219,0.0006656916,0.2334282,0.001713624,0.00001190787],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02090118,0.001131864,0.9638004,0.002627853,0.00009725292,0.0000294571,0.000190441,0.0005428229,0.01067876],"genre_scores_gemma":[0.7642179,0.002722459,0.2245065,0.000345097,0.0001084119,0.00009391319,0.0002590599,0.0001805796,0.007566052],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01372974,"threshold_uncertainty_score":0.02729964,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1542638219167346,"score_gpt":0.2391786981223847,"score_spread":0.08491487620565008,"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."}}