{"id":"W1968419113","doi":"10.1109/asru.2013.6707745","title":"Deep maxout neural networks for speech recognition","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":76,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Université de Montréal","keywords":"Sigmoid function; Computer science; Benchmark (surveying); Artificial neural network; Dropout (neural networks); Artificial intelligence; Task (project management); Deep neural networks; Speech recognition; Nonlinear system; Generalization; Machine learning; Engineering; Mathematics","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001336284,0.0001042453,0.0001091576,0.00007051241,0.00009169871,0.0002626674,0.0003355505,0.00006862831,0.001370234],"category_scores_gemma":[0.00006076336,0.00008774074,0.00009393349,0.0001630332,0.00001639716,0.0006534694,0.00005581647,0.00006279142,0.000830629],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001520051,"about_ca_system_score_gemma":0.000006988034,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003559931,"about_ca_topic_score_gemma":0.00001993199,"domain_scores_codex":[0.9991351,0.00003226936,0.000174519,0.0002695616,0.0001165813,0.0002719252],"domain_scores_gemma":[0.9992546,0.0001898397,0.00004548171,0.000242334,0.000164571,0.0001031995],"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":[0.000001586494,0.00002035865,0.00003656623,0.000002504779,0.000005413162,0.000001257799,0.00001326753,0.000009676658,0.00004767716,0.0003913259,0.005458354,0.994012],"study_design_scores_gemma":[0.0002261859,0.00004452468,0.0005414043,0.000004366284,0.000004414866,0.00002849205,0.0000261402,0.983883,0.003073127,0.01085727,0.00114357,0.0001674612],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006428762,0.00002049425,0.9760064,0.001635993,0.0004508633,0.0004348926,7.923414e-7,0.0002926247,0.01472916],"genre_scores_gemma":[0.2101283,0.00001426361,0.782739,0.004524008,0.0002984794,0.000290963,0.00001860608,0.00001754776,0.001968804],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9938446,"threshold_uncertainty_score":0.9999474,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03354279461887392,"score_gpt":0.2393292948781643,"score_spread":0.2057865002592904,"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."}}