{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02228444,0.001185973,0.001307709,0.004346977,0.0005513243,0.001760754,0.002128057,0.001919827,0.002070951],"category_scores_gemma":[0.1312225,0.0004354344,0.0008646704,0.003043934,0.001015561,0.005023774,0.001552654,0.001472084,0.0004221874],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009792933,"about_ca_system_score_gemma":0.0005472831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001316108,"about_ca_topic_score_gemma":0.001099377,"domain_scores_codex":[0.9820801,0.008727144,0.001302812,0.001634613,0.005773276,0.0004820791],"domain_scores_gemma":[0.7665566,0.2075551,0.00541141,0.007826791,0.0114299,0.001220244],"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":[0.002251853,0.000402021,0.02351873,0.001318688,0.000626386,0.0001702126,0.0004903025,0.08972869,0.02176774,0.0115689,0.001465226,0.8466913],"study_design_scores_gemma":[0.0001331399,0.003503364,0.02899516,0.0002697864,0.0003675377,0.001330902,0.0004431159,0.8703278,0.08327291,0.007142814,0.003857936,0.0003556415],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2087779,0.01258832,0.7703208,0.0004521592,0.000152319,0.0001897637,0.0002997261,0.002091561,0.005127367],"genre_scores_gemma":[0.7877798,0.001255004,0.2091356,0.0001032092,0.0001872013,0.0001223327,0.0005641216,0.0001934475,0.0006592417],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02228444,"threshold_uncertainty_score":0.1178528,"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."}}