{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008227921,0.0001297183,0.0001879352,0.0000538464,0.0001185756,0.00006838788,0.0006105669,0.00005207405,0.00004825521],"category_scores_gemma":[0.0001801311,0.00008648943,0.0001162851,0.0003841609,0.00001453545,0.0002668278,0.0002188256,0.00009700871,0.00003568338],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002653584,"about_ca_system_score_gemma":0.00006151021,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001831558,"about_ca_topic_score_gemma":0.0002184188,"domain_scores_codex":[0.9985192,0.0002027113,0.0003181031,0.000313695,0.000359116,0.0002871723],"domain_scores_gemma":[0.9988191,0.0001749207,0.000133494,0.0004836151,0.0002891069,0.0000997559],"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":[0.00007232705,0.002019749,0.005124742,0.00001935773,0.00008471228,0.00001048768,0.002497881,0.00005570353,0.00002628138,0.001115382,0.0544728,0.9345006],"study_design_scores_gemma":[0.01966892,0.005989898,0.02526549,0.0003168963,0.0003885319,0.0003407422,0.01341978,0.7771531,0.02312812,0.09285585,0.03894813,0.00252448],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7755547,0.000123012,0.2053574,0.001961393,0.003619611,0.002709585,0.00002504368,0.0003004142,0.0103489],"genre_scores_gemma":[0.9254738,0.000005161017,0.07270037,0.0009374295,0.0002505679,0.0001416333,0.000006514573,0.0000161803,0.0004683258],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9319761,"threshold_uncertainty_score":0.3526937,"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."}}