{"id":"W2611386872","doi":"10.2172/1289367","title":"Analysis of Pre-Trained Deep Neural Networks for Large-Vocabulary Automatic Speech Recognition","year":2016,"lang":"en","type":"report","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute of Circulatory and Respiratory Health; Lawrence Livermore National Laboratory; U.S. Department of Energy","keywords":"Convolutional neural network; Sensitivity (control systems); Computer science; Artificial neural network; Pattern recognition (psychology); Event (particle physics); Field (mathematics); Artificial intelligence; Detector; Selection (genetic algorithm); Speech recognition; Vocabulary; Particle (ecology); Nova (rocket); SIGNAL (programming language); Physics; Mathematics; Engineering; Astrophysics; Electronic engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005797952,0.0008230213,0.0003701665,0.0005633926,0.000347908,0.0005599537,0.0005386141,0.0004655105,0.008126015],"category_scores_gemma":[0.002573142,0.0003188766,0.00051312,0.000357111,0.0002189772,0.0007135801,0.0003401223,0.0009530149,0.001476559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001047914,"about_ca_system_score_gemma":0.0008332808,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01353862,"about_ca_topic_score_gemma":0.02639327,"domain_scores_codex":[0.9996632,0.00004347229,0.00001858107,0.00006574307,0.00013908,0.00006991176],"domain_scores_gemma":[0.9981078,0.0010857,0.00004468366,0.0001275042,0.0005999925,0.00003425052],"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":[0.002089189,0.0006447605,0.009759529,0.0004902136,0.0003594726,0.0006970752,0.0001251175,0.2834882,0.2509132,0.004309983,0.01621391,0.4309094],"study_design_scores_gemma":[0.00001465118,0.0001486328,0.009462023,0.00001077871,0.00004446873,0.00006125458,0.00003472044,0.9467585,0.04143233,0.0007139643,0.001304054,0.00001463567],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7561496,0.001690223,0.222688,0.0007717672,0.0003866775,0.0001404273,0.003667842,0.004607018,0.009898368],"genre_scores_gemma":[0.9602655,0.0003572043,0.02326688,0.00009141723,0.00006749007,0.00009848559,0.005624461,0.000351573,0.009876753],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01353862,"threshold_uncertainty_score":0.02718425,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03970584771201347,"score_gpt":0.2976316703037328,"score_spread":0.2579258225917194,"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."}}