{"id":"W4288087689","doi":"10.48550/arxiv.1910.13923","title":"Lightweight and Efficient End-to-End Speech Recognition Using Low-Rank\\n Transformer","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Transformer; End-to-end principle; Inference; Computer science; Language model; Software deployment; Artificial neural network; Speech recognition; Artificial intelligence; Engineering","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":[0.0007145379,0.001781218,0.0009962664,0.0006684895,0.0004508143,0.001503518,0.002262874,0.001122657,0.01281607],"category_scores_gemma":[0.002696993,0.0005909529,0.0008731235,0.0006004053,0.0005136288,0.002583997,0.002127655,0.00224989,0.01388093],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000656767,"about_ca_system_score_gemma":0.001639347,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00848981,"about_ca_topic_score_gemma":0.02043077,"domain_scores_codex":[0.9992797,0.0001111439,0.00004017037,0.00020855,0.0002578964,0.0001025724],"domain_scores_gemma":[0.9993045,0.0001869054,0.00003399543,0.0002297892,0.000203133,0.00004171135],"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":[0.0006807694,0.0002935037,0.0008273021,0.000221918,0.0001487387,0.0002738781,0.00009534188,0.07144845,0.06015854,0.007079348,0.02640782,0.8323644],"study_design_scores_gemma":[0.00003847598,0.00008092514,0.0002674994,0.00001323571,0.00002245822,0.0001449886,0.00003530889,0.9514693,0.03781372,0.004905073,0.005183651,0.0000253985],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01273828,0.0004068915,0.9565511,0.0002150241,0.0001801336,0.0001077199,0.0008249646,0.02555766,0.003418144],"genre_scores_gemma":[0.3743667,0.0007252107,0.5866216,0.0005440997,0.0001797146,0.0003670432,0.007916275,0.001526015,0.02775332],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01281607,"threshold_uncertainty_score":0.04287404,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07597558586763042,"score_gpt":0.1964255653594453,"score_spread":0.1204499794918149,"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."}}