{"id":"W2006577961","doi":"10.1109/icassp.2014.6854925","title":"Improvements to filterbank and delta learning within a deep neural network framework","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Filter bank; Speech recognition; Filter (signal processing); Word error rate; Artificial neural network; Artificial intelligence; Deep learning; Computer vision","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":[0.0003356793,0.0001081562,0.0001214288,0.00004746229,0.0001532573,0.0002471586,0.0003116368,0.00005388763,0.0001110605],"category_scores_gemma":[0.0002418125,0.0000915636,0.00002925643,0.0002288407,0.00001420105,0.0001826869,0.0002313192,0.0001506891,0.0001012206],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008692948,"about_ca_system_score_gemma":0.000005320382,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002370426,"about_ca_topic_score_gemma":0.00002993679,"domain_scores_codex":[0.9990184,0.00008434909,0.0001589772,0.0003165189,0.0001596626,0.0002620389],"domain_scores_gemma":[0.9992981,0.000212076,0.00004568386,0.0002412903,0.00003693848,0.000165927],"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":[0.000006966638,0.00001693852,0.003409954,0.000005698088,0.00001280377,0.000003418948,0.0005424711,0.0007479223,0.000164546,0.01787166,0.0007868402,0.9764308],"study_design_scores_gemma":[0.0001971726,0.0002236103,0.005005924,0.00003416865,0.000005684199,0.00001275806,0.00005150384,0.9751421,0.001236099,0.01315703,0.004649736,0.0002841799],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08091576,0.00001521316,0.9141111,0.000908559,0.0003150568,0.0001047036,1.465248e-7,0.0001895052,0.003439955],"genre_scores_gemma":[0.5845667,0.00000153164,0.4097849,0.005143322,0.0001174987,0.00001227079,5.712812e-7,0.000007082604,0.0003660427],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9761466,"threshold_uncertainty_score":0.3733855,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0134595717488146,"score_gpt":0.2353835797920289,"score_spread":0.2219240080432143,"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."}}