{"id":"W1942035323","doi":"10.21437/interspeech.2015-654","title":"A study of the recurrent neural network encoder-decoder for large vocabulary speech recognition","year":2015,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":95,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Speech recognition; Vocabulary; Encoder; Artificial neural network; Recurrent neural network; Artificial intelligence; Natural language processing; Linguistics","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":[0.002038904,0.0007921914,0.0006147786,0.0003724874,0.0003538187,0.001136003,0.001266552,0.001437914,0.002879829],"category_scores_gemma":[0.006510768,0.0006826376,0.0004880332,0.0004872086,0.000858651,0.001878767,0.0005696581,0.001767214,0.0007999822],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00139837,"about_ca_system_score_gemma":0.001114922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006712916,"about_ca_topic_score_gemma":0.009440484,"domain_scores_codex":[0.999161,0.0003889634,0.00005134672,0.0001691417,0.0001730716,0.00005647816],"domain_scores_gemma":[0.9971227,0.002206251,0.000128238,0.0001735786,0.0003191075,0.00004998798],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002953852,0.0001583909,0.001588382,0.000313015,0.0001494402,0.0004495709,0.0002680169,0.6183497,0.02557932,0.1433841,0.0045417,0.204923],"study_design_scores_gemma":[0.000004737166,0.00004354166,0.0001164682,0.000007640826,0.00001077541,0.00005411333,0.000006855256,0.990035,0.002427764,0.006561972,0.0007254746,0.000005701708],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02623893,0.002881761,0.9624009,0.000671528,0.0001250437,0.00006152707,0.0001408981,0.0007498294,0.00672958],"genre_scores_gemma":[0.6821048,0.002729347,0.3005431,0.0003065197,0.0002798039,0.0002054301,0.0004560176,0.000297494,0.01307746],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006712916,"threshold_uncertainty_score":0.01334769,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1039695865947861,"score_gpt":0.2999294749775426,"score_spread":0.1959598883827565,"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."}}