{"id":"W2132037657","doi":"10.1109/icassp.2011.5947700","title":"Learning a better representation of speech soundwaves using restricted boltzmann machines","year":2011,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":229,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Cepstrum; Speech recognition; Computer science; Mel-frequency cepstrum; Linear predictive coding; Boltzmann machine; Restricted Boltzmann machine; Representation (politics); Artificial intelligence; Speech coding; Pattern recognition (psychology); Artificial neural network; Feature extraction","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":[0.0001082853,0.00008017486,0.0001273152,0.0001799707,0.00006949467,0.00004629922,0.0002582915,0.00004203966,0.0003569821],"category_scores_gemma":[0.0001338579,0.00006902261,0.00006371013,0.0004229106,0.00003029679,0.0003782194,0.00009109051,0.00007691366,0.00003773375],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001003962,"about_ca_system_score_gemma":0.00001772979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004551654,"about_ca_topic_score_gemma":0.00001136541,"domain_scores_codex":[0.9991367,0.0001020831,0.0002205412,0.0002189473,0.0001887266,0.0001330186],"domain_scores_gemma":[0.9994141,0.00008807412,0.0001140833,0.0002427587,0.0001003551,0.00004064319],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002325241,0.0001119302,0.06314261,0.00002050016,0.0000612131,0.00004666313,0.002719283,0.00001310465,0.04853439,0.003344656,0.0002776803,0.8817047],"study_design_scores_gemma":[0.0006551478,0.0001829651,0.1251838,0.00006293895,0.00004020578,0.0001534187,0.0005694138,0.2876958,0.5673507,0.01711977,0.000480499,0.0005052941],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7208279,0.000008825077,0.2526343,0.0001009755,0.0001072502,0.00007589275,3.863569e-7,0.0001436255,0.02610077],"genre_scores_gemma":[0.5655645,0.000005041177,0.4337256,0.00009507201,0.00003787461,0.000001865996,0.000001332226,0.000006181275,0.0005625382],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8811994,"threshold_uncertainty_score":0.3908704,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07598615674813156,"score_gpt":0.2849837548539779,"score_spread":0.2089975981058464,"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."}}