{"id":"W2116375618","doi":"10.1109/chinsl.2004.1409573","title":"A comparative study on various confidence measures in large vocabulary speech recognition","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Dictation; Vocabulary; Word error rate; Computer science; Speech recognition; Mandarin Chinese; Word (group theory); Task (project management); Artificial intelligence; A priori and a posteriori; Language model; Interpolation (computer graphics); Natural language processing; Pattern recognition (psychology); 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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00075251,0.0001672685,0.0002610317,0.0002681896,0.00008938513,0.0001411305,0.0004400275,0.0000574139,0.0003522826],"category_scores_gemma":[0.0000815324,0.0001477893,0.00005167878,0.0004402658,0.00002081778,0.0004999815,0.00007688403,0.0001967417,0.001859493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007467242,"about_ca_system_score_gemma":0.00005116169,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008347347,"about_ca_topic_score_gemma":0.001555578,"domain_scores_codex":[0.9981992,0.0002815278,0.0003090085,0.0004685278,0.0004503574,0.0002914413],"domain_scores_gemma":[0.9991246,0.0002334727,0.00006692504,0.0003634473,0.0001235617,0.00008803474],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001040499,0.006342642,0.004672864,0.000006482505,0.00008667127,0.0003465282,0.01188476,0.00002629252,0.0008878661,0.00448078,0.003027675,0.9681334],"study_design_scores_gemma":[0.01698764,0.004823235,0.3762079,0.0005503618,0.0001024077,0.0005126644,0.0219753,0.1738828,0.3602699,0.02271136,0.01765184,0.004324522],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8085315,0.00004952026,0.1182221,0.001441038,0.0002239564,0.001028369,0.000007488113,0.0003963159,0.0700998],"genre_scores_gemma":[0.9742985,0.000006947922,0.0239945,0.001287718,0.00004867325,0.00004885086,0.000002485302,0.00000590093,0.0003064302],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9638089,"threshold_uncertainty_score":0.9989177,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0777816752275478,"score_gpt":0.3098407658864848,"score_spread":0.232059090658937,"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."}}