{"id":"W2020683423","doi":"10.1109/asru.2013.6707749","title":"Improvements to Deep Convolutional Neural Networks for LVCSR","year":2013,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Dropout (neural networks); Pooling; Convolutional neural network; Word error rate; Speech recognition; Task (project management); Artificial intelligence; Deep neural networks; Baseline (sea); Deep learning; Adaptation (eye); Machine learning; Pattern recognition (psychology)","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":[0.0001956175,0.0002318668,0.0002452624,0.000123241,0.0000983808,0.000377629,0.001110803,0.000199983,0.0005149997],"category_scores_gemma":[0.00006389948,0.000209007,0.0001950613,0.00009844097,0.0000191099,0.0001547927,0.001184283,0.000198668,0.0002267077],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007141095,"about_ca_system_score_gemma":0.00005610385,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007403371,"about_ca_topic_score_gemma":0.00002402964,"domain_scores_codex":[0.9983669,0.00003463136,0.000308762,0.0006577395,0.0002489137,0.0003830612],"domain_scores_gemma":[0.99868,0.0001531918,0.0001043614,0.0005631971,0.0002800853,0.0002191911],"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":[0.00001234248,0.0001068228,0.000127352,0.00004282722,0.0001010511,0.000002463553,0.00007021848,0.003249267,0.00005921915,0.02439992,0.04736192,0.9244666],"study_design_scores_gemma":[0.0001958176,0.00004449988,0.0006137104,0.00001515135,0.000008386768,0.000002556437,0.00000681437,0.9854051,0.0002714021,0.009377535,0.003763435,0.0002955423],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00225664,0.00004181735,0.9887207,0.002100525,0.002338667,0.001124381,0.00001358006,0.0002360827,0.00316763],"genre_scores_gemma":[0.1713176,0.00001334537,0.8078754,0.01212596,0.0008284998,0.00187555,0.00009267051,0.00003670589,0.005834311],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9821559,"threshold_uncertainty_score":0.852306,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03345089616549939,"score_gpt":0.2662116572029797,"score_spread":0.2327607610374803,"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."}}