{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006252322,0.0004638711,0.0003155172,0.0002639407,0.00026642,0.0006060725,0.0007412569,0.0007956707,0.002313944],"category_scores_gemma":[0.001916224,0.0003205833,0.0003097895,0.0004225083,0.0003085986,0.0008486414,0.0004625873,0.0009483583,0.0008385977],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008042277,"about_ca_system_score_gemma":0.0005179037,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008732608,"about_ca_topic_score_gemma":0.009194627,"domain_scores_codex":[0.9998658,0.00004547534,0.00001034398,0.00003086022,0.00003358127,0.00001395292],"domain_scores_gemma":[0.9996803,0.0001935971,0.0000206863,0.00002398322,0.00007086231,0.00001047314],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009411552,0.00005176746,0.0005782267,0.00008538862,0.00005107913,0.000112378,0.0000643592,0.7726627,0.005463512,0.01834114,0.00164376,0.2008516],"study_design_scores_gemma":[0.000001854852,0.000005088593,0.00004058135,0.000002737571,0.000003073253,0.000006943631,0.000001595411,0.9971696,0.0005421824,0.001919551,0.0003045044,0.000002419248],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008911592,0.0005996063,0.9869301,0.0002300878,0.00005244045,0.00002427421,0.00005379084,0.001214526,0.001983484],"genre_scores_gemma":[0.4459667,0.001142045,0.5419329,0.0001581245,0.000095717,0.0001799307,0.0002727241,0.0001690936,0.0100828],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008732608,"threshold_uncertainty_score":0.01736355,"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."}}