{"id":"W2112739286","doi":"10.1109/icassp.2013.6639347","title":"Deep convolutional neural networks for LVCSR","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":1070,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Convolutional neural network; Pooling; Artificial intelligence; Speech recognition; Focus (optics); Vocabulary; Feature (linguistics); Deep neural networks; Artificial neural network; Pattern recognition (psychology)","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":[0.000706135,0.0006787954,0.0004663835,0.000446165,0.0002609138,0.0006365124,0.0006445991,0.0006788456,0.007154326],"category_scores_gemma":[0.001788571,0.0002940558,0.0004010272,0.0007817377,0.0002348472,0.0008133929,0.0004637369,0.001187491,0.002231268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008486422,"about_ca_system_score_gemma":0.0007850384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01048977,"about_ca_topic_score_gemma":0.01589982,"domain_scores_codex":[0.9996916,0.00005837731,0.00001979167,0.00007717498,0.0001205008,0.0000325977],"domain_scores_gemma":[0.9995717,0.0001927324,0.00003861947,0.00006403483,0.0001189458,0.000013928],"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":[0.0001620965,0.00006183166,0.001348672,0.0002767598,0.0000878722,0.0001251242,0.00004645986,0.2000703,0.03197932,0.01615645,0.02077486,0.7289102],"study_design_scores_gemma":[0.00001529478,0.00005346682,0.001546493,0.00005508114,0.00002288795,0.00007461795,0.00001949167,0.9630255,0.01076705,0.01090359,0.01349001,0.00002657242],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0192983,0.006190907,0.9577954,0.0008113713,0.0003241138,0.0000829026,0.001391464,0.004557498,0.009548021],"genre_scores_gemma":[0.4612855,0.004437977,0.5107877,0.0004934167,0.0003615009,0.0002623274,0.005046591,0.0004737134,0.01685129],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01048977,"threshold_uncertainty_score":0.02393359,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01317611183544196,"score_gpt":0.2283655173825606,"score_spread":0.2151894055471187,"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."}}