{"id":"W2148177126","doi":"10.1109/icassp.2005.1416353","title":"Large Margin HMMs for Speech Recognition","year":2006,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Hidden Markov model; Margin (machine learning); Minimax; Computer science; Pattern recognition (psychology); Optimization problem; Artificial intelligence; Speech recognition; Mathematics; Algorithm; Mathematical optimization; 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":[0.0002510684,0.00008491356,0.00009363227,0.00009131514,0.00009003555,0.0001189274,0.0002385907,0.00005287232,0.0005983108],"category_scores_gemma":[0.00003774219,0.00007580207,0.00008540993,0.0001758861,0.000008843178,0.0003106693,0.00003868897,0.00003625956,0.0007315899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001914197,"about_ca_system_score_gemma":0.00001674045,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002755953,"about_ca_topic_score_gemma":0.00007329449,"domain_scores_codex":[0.9991917,0.00002285944,0.0001574979,0.0002489436,0.0001353885,0.000243626],"domain_scores_gemma":[0.9995027,0.0001176541,0.00003847822,0.0002029802,0.00009636567,0.00004183161],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000008685602,0.000221775,0.0001721161,0.00001443792,0.000009379101,0.00001086532,0.00002645735,2.176986e-7,0.001372313,0.03106916,0.09995701,0.8671376],"study_design_scores_gemma":[0.001916896,0.0001196486,0.003220883,0.000031655,0.00001742972,0.00008198587,0.00008746186,0.02968691,0.3325853,0.2648549,0.3667116,0.0006853141],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009931501,0.00002093976,0.8879024,0.0009840102,0.0002721864,0.000252092,0.00002162833,0.0003387638,0.1002764],"genre_scores_gemma":[0.08345556,0.000007061192,0.8999234,0.001561897,0.0003004976,0.0000948888,0.00006133259,0.00001520734,0.01458019],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8664523,"threshold_uncertainty_score":0.9403351,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02562288838684772,"score_gpt":0.2431199957767031,"score_spread":0.2174971073898553,"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."}}