{"id":"W2131525232","doi":"10.1109/asru.2005.1566525","title":"A constrained joint optimization method for large margin HMM estimation","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Minimax; Margin (machine learning); Hidden Markov model; Computer science; Mathematical optimization; Optimization problem; Algorithm; Mathematics; Artificial intelligence; 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":[0.0005568949,0.0000757183,0.0001028309,0.00009748429,0.00008306433,0.0001073457,0.0001439467,0.00004440178,0.0006019837],"category_scores_gemma":[0.0001626849,0.0000673926,0.00006222194,0.0001433512,0.000006397034,0.0003690264,0.00002954515,0.00002890607,0.00007426443],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002886825,"about_ca_system_score_gemma":0.00003410559,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002618265,"about_ca_topic_score_gemma":0.000006202084,"domain_scores_codex":[0.9992887,0.00005062202,0.0001835029,0.0002026927,0.0001124572,0.000162039],"domain_scores_gemma":[0.9994866,0.0001417689,0.00005626568,0.0001659188,0.00009366203,0.00005577088],"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":[0.000004513571,0.00008482899,0.000002949215,0.000009217935,0.00001245228,6.52027e-7,0.0001395513,0.01080817,0.0003545342,0.137902,0.00315981,0.8475213],"study_design_scores_gemma":[0.0004357866,0.00001885877,0.00001927557,0.000006079268,0.0000049259,0.00001378156,0.00001891263,0.9824625,0.01159411,0.001527964,0.003802156,0.00009563022],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002523952,0.000005904074,0.9836609,0.004935639,0.00007315301,0.0002580186,0.000006130908,0.0002242391,0.01081083],"genre_scores_gemma":[0.008274655,0.000002374014,0.98952,0.001326229,0.00004072865,0.00004693895,0.00001222942,0.00000536075,0.0007714728],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9716544,"threshold_uncertainty_score":0.6591299,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03204761856645677,"score_gpt":0.296035801664542,"score_spread":0.2639881830980852,"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."}}