{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004664594,0.0004756674,0.0004553997,0.0003389994,0.0001526681,0.0004388906,0.001220478,0.0003777322,0.003337984],"category_scores_gemma":[0.00008715614,0.0003407919,0.000214691,0.0003207488,0.0001075623,0.0003941093,0.001061439,0.0005347058,0.0007149164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001797985,"about_ca_system_score_gemma":0.0002488281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001018635,"about_ca_topic_score_gemma":0.0001529085,"domain_scores_codex":[0.9968011,0.0001872962,0.0004569393,0.001179737,0.0007759958,0.0005989544],"domain_scores_gemma":[0.9977834,0.0002349897,0.0002160038,0.0008661639,0.0005113045,0.0003881802],"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":[0.0000388824,0.00006120616,0.00008308882,0.00001592479,0.00007794611,0.00006487328,0.00004426359,0.0001139875,0.00002059851,0.001537913,0.002177414,0.9957639],"study_design_scores_gemma":[0.002431087,0.0006259657,0.01039068,0.001022375,0.0002011937,0.001267631,0.00009493739,0.8698321,0.01236438,0.08674683,0.01069885,0.00432396],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003888024,0.00006163631,0.9373121,0.004494649,0.001550992,0.0005526043,0.00005795111,0.0005705494,0.05151155],"genre_scores_gemma":[0.3964386,0.00007535329,0.5947539,0.004764482,0.001402506,0.0003189176,0.0002029751,0.00007026733,0.001972995],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9914399,"threshold_uncertainty_score":0.9999044,"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."}}