{"id":"W2064082346","doi":"10.1109/icassp.2010.5495651","title":"Phone recognition using Restricted Boltzmann Machines","year":2010,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":108,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"TIMIT; Hidden Markov model; Computer science; Phone; Conditional independence; Boltzmann machine; Independence (probability theory); Set (abstract data type); Speech recognition; Generative model; Artificial intelligence; Restricted Boltzmann machine; Markov model; Generative grammar; Machine learning; Pattern recognition (psychology); Markov chain; Artificial neural network; 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":[0.00009072199,0.00007353049,0.00006988824,0.00007202879,0.0001433825,0.0001683779,0.0002746337,0.00004752217,0.0001538496],"category_scores_gemma":[0.00004276345,0.00006047876,0.00002355931,0.0003393973,0.00002216795,0.0005147915,0.00009268303,0.0001472269,0.00009021538],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005554281,"about_ca_system_score_gemma":0.00004400952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008337165,"about_ca_topic_score_gemma":0.00002115843,"domain_scores_codex":[0.9993867,0.00001362649,0.0001177128,0.0002052417,0.0001240344,0.0001527394],"domain_scores_gemma":[0.999584,0.00002413024,0.0000544807,0.0002166521,0.00006690974,0.00005380743],"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":[0.000002904769,0.00004866575,0.0004448002,0.00001337916,0.000005611818,0.00001178472,0.0002160486,0.000007834833,0.2761,0.001605725,0.003576546,0.7179667],"study_design_scores_gemma":[0.0009051968,0.00004351475,0.008438568,0.0000655102,0.00001719698,0.0002185857,0.00002398074,0.8227779,0.1178112,0.03710332,0.01181411,0.0007809811],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4544834,0.00001496354,0.5321239,0.0006160265,0.0006091491,0.0000396005,5.12375e-7,0.0002201725,0.01189232],"genre_scores_gemma":[0.6130918,0.000002232125,0.3852795,0.0010404,0.0002197278,0.0000017827,0.000002767977,0.000005942432,0.0003558118],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8227701,"threshold_uncertainty_score":0.2466252,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0326160043459392,"score_gpt":0.2635966483133135,"score_spread":0.2309806439673743,"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."}}