{"id":"W3177268625","doi":"10.21467/proceedings.115.20","title":"End-to-End Speech Recognition Using Recurrent Neural Network (RNN)","year":2021,"lang":"en","type":"article","venue":"AIJR Proceedings","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University of Edmonton","funders":"","keywords":"Computer science; Recurrent neural network; End-to-end principle; Deep learning; Speech recognition; Artificial intelligence; Long short term memory; Language model; Artificial neural network; Deep neural networks; Voice activity detection; Acoustic model; Speech processing","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":[0.0004137385,0.0002193847,0.0002436566,0.0001382355,0.0002436579,0.0004937713,0.0004414343,0.0001003548,0.0004779315],"category_scores_gemma":[0.0002581423,0.0002309447,0.0001256499,0.001232841,0.00002927011,0.0008590368,0.000296213,0.0002292532,0.0003926803],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009220794,"about_ca_system_score_gemma":0.00008573364,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000150185,"about_ca_topic_score_gemma":0.000007866493,"domain_scores_codex":[0.9979658,0.00002983691,0.0003359134,0.0006794767,0.0004479945,0.000540995],"domain_scores_gemma":[0.9988113,0.00008171552,0.0001240652,0.0001958771,0.0005381405,0.0002489058],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000009215598,0.00006524808,0.0005125478,0.00002515058,0.00002018665,0.0000536557,0.0002940071,0.00000457869,0.004088194,0.0007020188,0.006714737,0.9875104],"study_design_scores_gemma":[0.002300235,0.0007149312,0.009002789,0.001639547,0.0002543871,0.004591093,0.001317898,0.2442068,0.5190843,0.04116903,0.1717612,0.003957772],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9355468,0.000260911,0.030952,0.00525293,0.002950747,0.0005076791,0.00001373357,0.0007342817,0.02378098],"genre_scores_gemma":[0.3471332,0.00007558341,0.6462411,0.004643803,0.001361178,0.00004571862,0.00001997797,0.00004714623,0.0004323153],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9835527,"threshold_uncertainty_score":0.9417652,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05651186344519452,"score_gpt":0.27158804131575,"score_spread":0.2150761778705555,"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."}}