{"id":"W1524112065","doi":"10.1109/iscas.1995.523768","title":"The investigation of using limited precision on a TDNN for consonant recognition","year":2002,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Technical University of Nova Scotia","funders":"","keywords":"TIMIT; Speech recognition; Computer science; Time delay neural network; Artificial neural network; Backpropagation; Consonant; Speech processing; Set (abstract data type); Recurrent neural network; Artificial intelligence; Pattern recognition (psychology); Hidden Markov model","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":[0.001930721,0.0004800512,0.0004728429,0.0003726114,0.0003603643,0.0009026702,0.001245295,0.0008891142,0.001365469],"category_scores_gemma":[0.01374542,0.0002725301,0.0002565914,0.0004683886,0.0005218133,0.00157267,0.0004717127,0.0007592295,0.0004104909],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006281045,"about_ca_system_score_gemma":0.0006074602,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002475603,"about_ca_topic_score_gemma":0.002885858,"domain_scores_codex":[0.9988661,0.0002676828,0.0001070258,0.00020666,0.0004876677,0.00006490156],"domain_scores_gemma":[0.9909225,0.006473841,0.0004714594,0.0009353901,0.001123386,0.00007345462],"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":[0.00178653,0.0001480446,0.00736363,0.0005825413,0.0001608458,0.0006249944,0.0003005846,0.2506843,0.1519512,0.01359101,0.0006219557,0.5721843],"study_design_scores_gemma":[0.0001046472,0.001473309,0.00436799,0.0001219346,0.0001790089,0.001483571,0.00009325624,0.86834,0.1138489,0.004450573,0.005478236,0.00005855244],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.219036,0.001220966,0.7747103,0.0003305321,0.00009432642,0.00008552799,0.00004372435,0.0007078071,0.003770877],"genre_scores_gemma":[0.7217839,0.000445179,0.2756699,0.0001084849,0.00005253303,0.00007156295,0.00005312921,0.00005665162,0.001758554],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002475603,"threshold_uncertainty_score":0.01021081,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1382744163063619,"score_gpt":0.2768611195221183,"score_spread":0.1385867032157564,"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."}}