{"id":"W2103359087","doi":"","title":"Phone Recognition with the Mean-Covariance Restricted Boltzmann Machine","year":2010,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":275,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"TIMIT; Boltzmann machine; Computer science; Covariance; Hidden Markov model; Restricted Boltzmann machine; Speech recognition; Mixture model; Artificial intelligence; Covariance matrix; Pattern recognition (psychology); Algorithm; Artificial neural network; Mathematics; Statistics","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":[0.0002398153,0.0001213869,0.0001028057,0.00007393937,0.0001906801,0.0001906731,0.0005930828,0.00005835178,0.0007345024],"category_scores_gemma":[0.00007205134,0.00006753267,0.00003910327,0.0005602447,0.00006106221,0.0003463222,0.00006483474,0.0002708525,0.0007490541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007899986,"about_ca_system_score_gemma":0.00004256955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001165507,"about_ca_topic_score_gemma":0.0007131912,"domain_scores_codex":[0.9990382,0.00006087177,0.0001319271,0.0002962388,0.0002686614,0.0002041636],"domain_scores_gemma":[0.9989732,0.0001938569,0.00007080592,0.0005422967,0.0001431788,0.00007669452],"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":[0.00004954717,0.0001743174,0.000117062,0.000006259807,0.00004776669,0.00004720781,0.0003913259,0.000001585945,0.02422658,0.01178994,0.01510084,0.9480476],"study_design_scores_gemma":[0.005772464,0.0006533781,0.04235618,0.0001149615,0.0001381016,0.001638216,0.0004619315,0.1299054,0.53569,0.03365864,0.2468861,0.002724569],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07910521,0.00003102576,0.801684,0.01852968,0.0007177899,0.0004050687,0.00001208901,0.0007938029,0.09872129],"genre_scores_gemma":[0.6467043,0.00002307235,0.346419,0.00352445,0.0001773212,0.00005753168,0.00001329285,0.00001770695,0.003063296],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.945323,"threshold_uncertainty_score":0.9627824,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01803519807988988,"score_gpt":0.2190759133437164,"score_spread":0.2010407152638265,"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."}}