{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003617206,0.0004174152,0.0004570011,0.0006609888,0.0001953322,0.0002322689,0.000870331,0.0003669533,0.0003398969],"category_scores_gemma":[0.00003091594,0.0004615012,0.0002521895,0.0006681645,0.00008835253,0.0003329609,0.000478826,0.0004741755,0.0006029274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002238529,"about_ca_system_score_gemma":0.0001871752,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001205148,"about_ca_topic_score_gemma":0.00004345959,"domain_scores_codex":[0.997488,0.0001609633,0.0002844862,0.001399809,0.0001976808,0.0004690745],"domain_scores_gemma":[0.9983169,0.0001663013,0.0001772518,0.0008051269,0.0002159698,0.0003184511],"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":[0.0006874122,0.002021475,0.004497924,0.001912799,0.001304823,0.003567974,0.004644156,0.1015241,0.0102391,0.01919903,0.001082621,0.8493186],"study_design_scores_gemma":[0.00154951,0.0001231641,0.001503499,0.0009267178,0.0003370547,0.0001109465,0.0002120255,0.9477568,0.03379854,0.01020016,0.001537339,0.001944235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6132774,0.0000307,0.3803973,0.000122226,0.0006552408,0.0004777586,0.00004726854,0.0001517292,0.004840375],"genre_scores_gemma":[0.9835809,0.0001551516,0.0153493,0.0002539816,0.00008789065,0.000001371107,0.00002272914,0.00002862148,0.00051999],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8473743,"threshold_uncertainty_score":0.9997837,"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."}}