{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002207342,0.002146777,0.0007412459,0.0008162549,0.0004683178,0.001015058,0.001374022,0.001033069,0.01128243],"category_scores_gemma":[0.005053435,0.0005645458,0.0008808899,0.0008372563,0.0003394705,0.002184368,0.001330412,0.002364846,0.005451932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001339116,"about_ca_system_score_gemma":0.001235548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01406809,"about_ca_topic_score_gemma":0.02755317,"domain_scores_codex":[0.9988124,0.0001967589,0.00008566775,0.000288958,0.0004810342,0.0001351715],"domain_scores_gemma":[0.9987746,0.0003911745,0.00006105851,0.0003056689,0.0004176463,0.00004977902],"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":[0.0005685511,0.0002158496,0.002106557,0.0003932465,0.0001947671,0.0002105419,0.0001010442,0.1236252,0.06066368,0.0106385,0.02550494,0.7757772],"study_design_scores_gemma":[0.0001062163,0.0004224544,0.004069316,0.0001304713,0.0001464993,0.0003783126,0.00006459358,0.8587371,0.07052094,0.01081438,0.0545213,0.00008845339],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05614044,0.008303492,0.8904836,0.001810927,0.0008677364,0.0001979107,0.002545603,0.0166616,0.02298883],"genre_scores_gemma":[0.473146,0.00382232,0.4819203,0.0009163507,0.0005155596,0.0003056596,0.009061891,0.001175576,0.02913621],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01406809,"threshold_uncertainty_score":0.03774351,"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."}}