{"id":"W2950689855","doi":"10.48550/arxiv.1303.5778","title":"Speech Recognition with Deep Recurrent Neural Networks","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Recurrent neural network; Computer science; Connectionism; TIMIT; Speech recognition; Artificial intelligence; Context (archaeology); Deep learning; Benchmark (surveying); Time delay neural network; Artificial neural network; Hidden Markov model","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":[0.0007016102,0.0007251881,0.0005351913,0.000551443,0.0001937373,0.001007632,0.0007799946,0.000770273,0.003784657],"category_scores_gemma":[0.002169151,0.0003735762,0.0005357277,0.0006179455,0.0003032693,0.001302769,0.0008106133,0.001018211,0.003419126],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005664132,"about_ca_system_score_gemma":0.0004197967,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004250936,"about_ca_topic_score_gemma":0.007190461,"domain_scores_codex":[0.9993215,0.0001410806,0.00004523105,0.0001937883,0.0002390868,0.00005937248],"domain_scores_gemma":[0.9994159,0.0002123979,0.00004910557,0.000140438,0.0001602178,0.00002192472],"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":[0.0002624928,0.0001000365,0.0008159983,0.0001974441,0.0001819481,0.0001683108,0.00007839064,0.2179235,0.06614842,0.00924355,0.009987552,0.6948923],"study_design_scores_gemma":[0.000008309771,0.00004537922,0.000379938,0.00001547219,0.00001693739,0.00004700211,0.00001260681,0.975993,0.01524109,0.00469236,0.003533855,0.00001395292],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03402681,0.002123219,0.9491483,0.0004380161,0.0002548428,0.00004662406,0.0006412108,0.007904011,0.005416936],"genre_scores_gemma":[0.6146874,0.001505962,0.364493,0.0003122872,0.0002292903,0.0001080195,0.003528577,0.0003594733,0.01477607],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004250936,"threshold_uncertainty_score":0.01266092,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0770478288527954,"score_gpt":0.1795214216656187,"score_spread":0.1024735928128233,"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."}}