{"id":"W2125226720","doi":"10.1109/asru.2009.5373248","title":"Discriminative training of n-gram language models for speech recognition via linear programming","year":2009,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Discriminative model; Computer science; Speech recognition; Word error rate; Viterbi algorithm; Artificial intelligence; n-gram; Vocabulary; Language model; Metric (unit); Pattern recognition (psychology); Viterbi decoder; Hidden Markov model; Decoding methods; Algorithm","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":[0.001104604,0.001299981,0.001087979,0.0004866279,0.0004851706,0.0006610577,0.00173682,0.0009014325,0.002797778],"category_scores_gemma":[0.004908013,0.0008377295,0.0007247736,0.0007587615,0.000641403,0.00140062,0.001314293,0.002477573,0.002045046],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007114324,"about_ca_system_score_gemma":0.001001777,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004193316,"about_ca_topic_score_gemma":0.007455751,"domain_scores_codex":[0.9991341,0.0003562541,0.00004048911,0.0002281801,0.0001748488,0.00006610337],"domain_scores_gemma":[0.9983463,0.00117095,0.0001169849,0.0001558438,0.00016085,0.0000490228],"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":[0.00019492,0.0001393647,0.0004398634,0.000139345,0.00006457786,0.00009900037,0.0001038836,0.4211625,0.01414652,0.01072205,0.003224745,0.5495633],"study_design_scores_gemma":[0.000005651324,0.00002460174,0.00006006479,0.000003546701,0.000004519822,0.00002132336,0.000005979875,0.9944066,0.001977139,0.002963585,0.0005215566,0.000005499524],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002610827,0.000103212,0.9960805,0.000053767,0.00001090378,0.00001387718,0.00002147086,0.0008387437,0.0002667864],"genre_scores_gemma":[0.1728109,0.0002848624,0.8218299,0.000212271,0.00007781559,0.0002678601,0.0006222617,0.000462434,0.003431579],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004193316,"threshold_uncertainty_score":0.009359539,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0839183369757153,"score_gpt":0.3085977370139907,"score_spread":0.2246794000382754,"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."}}