{"id":"W2963403664","doi":"10.21437/interspeech.2016-1446","title":"Towards End-to-End Speech Recognition with Deep Convolutional Neural Networks","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":341,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; Université de Montréal","funders":"","keywords":"End-to-end principle; Computer science; Speech recognition; Convolutional neural network; Deep learning; Artificial intelligence","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":[0.0009233562,0.001382523,0.0007525792,0.0004814634,0.0003201676,0.001071959,0.001736085,0.001614629,0.003091725],"category_scores_gemma":[0.002103507,0.0004994198,0.000519193,0.0004705319,0.0004734243,0.00177488,0.001292192,0.001964099,0.003504051],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007616364,"about_ca_system_score_gemma":0.0008674857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004642928,"about_ca_topic_score_gemma":0.009980625,"domain_scores_codex":[0.9992722,0.0001433424,0.00004161678,0.0002466746,0.0002071808,0.00008907293],"domain_scores_gemma":[0.999126,0.000243215,0.00006001582,0.0002261375,0.000296323,0.00004828269],"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":[0.0004493821,0.0002997171,0.001238209,0.0002453565,0.00008810541,0.000273938,0.0001594382,0.1179103,0.1040898,0.01459995,0.0142164,0.7464294],"study_design_scores_gemma":[0.00001033993,0.00006413283,0.0003329234,0.00001810489,0.00001491401,0.0000592811,0.00002508425,0.9489625,0.03842642,0.007799723,0.004271243,0.00001536359],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009250979,0.0003119954,0.9830112,0.0001551842,0.00006832998,0.00003954097,0.0002558733,0.005293387,0.001613373],"genre_scores_gemma":[0.2262653,0.0003971161,0.7613549,0.0003421691,0.00007610745,0.0001259369,0.002115375,0.0003463506,0.008976784],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004642928,"threshold_uncertainty_score":0.01034284,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03436162498600204,"score_gpt":0.2491030066026894,"score_spread":0.2147413816166874,"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."}}