{"id":"W2154427806","doi":"10.1109/tasl.2010.2096213","title":"Large-Margin Estimation of Hidden Markov Models With Second-Order Cone Programming for Speech Recognition","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Margin (machine learning); Hidden Markov model; Convex optimization; Speech recognition; Pattern recognition (psychology); Task (project management); Artificial intelligence; Regular polygon; Algorithm; Machine learning; Mathematics","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":[0.0004975399,0.0002669668,0.000301754,0.0002722747,0.0003899428,0.000309195,0.0002609475,0.0001523688,0.00005582831],"category_scores_gemma":[0.00002495237,0.0002348045,0.00006597149,0.0005836418,0.00009264363,0.001452588,0.000004944815,0.0003868214,0.000003711611],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002411335,"about_ca_system_score_gemma":0.0001796479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001746035,"about_ca_topic_score_gemma":0.0002844309,"domain_scores_codex":[0.9983563,0.00003097428,0.0003428818,0.0005287759,0.000296883,0.0004441243],"domain_scores_gemma":[0.9989204,0.0001049356,0.0002517065,0.0002839165,0.0003009347,0.0001380713],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00008460206,0.0001597629,0.000004423853,0.0003564126,0.00002549007,0.00001224432,0.001668608,0.0001217434,0.02487093,0.000009595781,0.00001215385,0.972674],"study_design_scores_gemma":[0.001674291,0.0002479717,0.00001294965,0.0003493598,0.00006345353,0.0002176639,0.0006641785,0.1343554,0.8609472,0.0009583248,0.00008590737,0.0004232611],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1714775,0.0002210864,0.8270032,0.0001794559,0.0001321751,0.0004570896,0.00003061416,0.000199138,0.0002997865],"genre_scores_gemma":[0.5140454,0.000006036303,0.4855771,0.00009477725,0.00003486625,0.00005574404,0.000009472506,0.00002087663,0.0001557161],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9722508,"threshold_uncertainty_score":0.9575047,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01193151290476875,"score_gpt":0.2518663633702627,"score_spread":0.239934850465494,"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."}}