{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001841259,0.0004493019,0.001296787,0.001258301,0.0001184303,0.000143064,0.0009601919,0.0005532542,0.001602374],"category_scores_gemma":[0.0007046267,0.0003430493,0.001273882,0.001402359,0.00004291213,0.0003934069,0.0001888735,0.0002004139,0.00002607668],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001573446,"about_ca_system_score_gemma":0.0002707909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004787226,"about_ca_topic_score_gemma":0.0002297692,"domain_scores_codex":[0.9961384,0.0001839907,0.001198041,0.0008860396,0.0009960375,0.0005974767],"domain_scores_gemma":[0.9955986,0.001018131,0.0009367216,0.001035308,0.001230713,0.0001805949],"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":[0.00001170943,0.0001210624,0.0001204096,0.0001507403,0.001731342,0.00001699327,0.00003391261,0.00001401103,0.00001127379,0.00004805534,0.003278594,0.9944619],"study_design_scores_gemma":[0.0004276676,0.0001045561,0.002066663,0.0001562088,0.002077343,0.00005094353,0.00001434361,0.991159,0.0004458471,0.0006403819,0.002302529,0.0005545476],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001001081,0.0002388395,0.9794715,0.0002263295,0.001133988,0.0008737138,0.0002112834,0.0004554728,0.0163878],"genre_scores_gemma":[0.1533922,0.001872228,0.8152501,0.001609316,0.002357604,0.001227753,0.003954077,0.000295901,0.02004078],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9939073,"threshold_uncertainty_score":0.9999021,"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."}}