{"id":"W1509434377","doi":"10.1109/nnsp.1991.239500","title":"Neural-network architecture for linear and nonlinear predictive hidden Markov models: application to speech recognition","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Speech recognition; Artificial neural network; Hidden Markov model; Linear prediction; Nonlinear system; Artificial intelligence; Term (time); Frame (networking); Markov model; Pattern recognition (psychology); Linear model; Markov chain; Machine learning","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":[0.0002042536,0.0001572694,0.0001624285,0.000111016,0.0001390144,0.00009652417,0.0002806995,0.0000925624,0.00006690104],"category_scores_gemma":[0.00005999096,0.0001404116,0.00006307054,0.0003306692,0.00002242895,0.0003143245,0.00009692567,0.0001035979,0.00008952837],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002157951,"about_ca_system_score_gemma":0.000007173585,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001100942,"about_ca_topic_score_gemma":0.00002461384,"domain_scores_codex":[0.9987663,0.00004769966,0.0002155331,0.0005080398,0.0001870783,0.0002753456],"domain_scores_gemma":[0.999093,0.0002223699,0.00005961852,0.0003053359,0.0001522313,0.0001674552],"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":[0.00002169139,0.00004077725,0.00001047583,0.0000104067,0.00001180507,0.000001209994,0.0001471037,0.0002819519,0.00007542814,0.0001366594,0.003607513,0.995655],"study_design_scores_gemma":[0.0002722307,0.0001418215,0.00005474984,0.00001828727,0.00001275637,0.00003175807,0.00001964345,0.9787624,0.001551183,0.0146668,0.004270711,0.0001976146],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006425261,0.00005568791,0.9825097,0.00357778,0.0001088047,0.0009571029,0.00003739777,0.0002895885,0.006038722],"genre_scores_gemma":[0.0190709,0.00004737057,0.9775318,0.002073063,0.000432466,0.0002499365,0.00002476153,0.00001854771,0.0005511593],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9954574,"threshold_uncertainty_score":0.5725819,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03361325991909431,"score_gpt":0.241170703534018,"score_spread":0.2075574436149237,"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."}}