{"id":"W2109886035","doi":"10.1109/icassp.2016.7472618","title":"End-to-end attention-based large vocabulary speech recognition","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":124,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Computer science; Hidden Markov model; Recurrent neural network; Speech recognition; Decoding methods; Vocabulary; Sequence (biology); Pooling; Artificial intelligence; Character (mathematics); Language model; Process (computing); Pattern recognition (psychology); Artificial neural network; Algorithm","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000829407,0.001477215,0.00123857,0.0008922725,0.0004618996,0.001043357,0.001935661,0.001302293,0.01365783],"category_scores_gemma":[0.002630598,0.000377996,0.0005585971,0.0006390081,0.000416011,0.001441003,0.001575673,0.0013603,0.01601574],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005838146,"about_ca_system_score_gemma":0.0008332974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004164009,"about_ca_topic_score_gemma":0.008928131,"domain_scores_codex":[0.998989,0.0001690589,0.00004720689,0.0003718975,0.000284522,0.0001382888],"domain_scores_gemma":[0.9986934,0.0004593465,0.00005155659,0.0002810703,0.0004514741,0.00006322409],"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":[0.0005154727,0.0002108722,0.0006257042,0.0002039246,0.00007738172,0.0002172624,0.0001029156,0.0148411,0.1017447,0.00246369,0.01588943,0.8631076],"study_design_scores_gemma":[0.00005152865,0.0001883794,0.002096532,0.00003157803,0.00006381438,0.0003936842,0.00007372964,0.8004943,0.1766763,0.008429196,0.011451,0.00004997787],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02080865,0.0006137789,0.9488205,0.0001565062,0.0002592391,0.0001741776,0.001342858,0.0211108,0.006713575],"genre_scores_gemma":[0.3430458,0.0004651333,0.6216968,0.000434281,0.0002400266,0.0003578555,0.008018047,0.00115934,0.02458281],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01365783,"threshold_uncertainty_score":0.04569,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03520127758503985,"score_gpt":0.2663043535830252,"score_spread":0.2311030759979854,"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."}}