{"id":"W34011602","doi":"10.21437/interspeech.2006-40","title":"Measuring the acceptable word error rate of machine-generated webcast transcripts","year":2006,"lang":"en","type":"article","venue":"","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University; University of Toronto","funders":"","keywords":"Webcast; Computer science; Broadcasting (networking); Word (group theory); Metadata; The Internet; Speech recognition; Information retrieval; World Wide Web; Linguistics","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":[0.0004831676,0.0001222577,0.0001655109,0.00006487125,0.0001143338,0.0001244868,0.0007561281,0.00004085437,0.00005274642],"category_scores_gemma":[0.00001369086,0.0000751704,0.00007962876,0.0004996971,0.00003368327,0.0002698963,0.00005699082,0.00007696167,0.00005315339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001618138,"about_ca_system_score_gemma":0.00005746642,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003486039,"about_ca_topic_score_gemma":0.001233495,"domain_scores_codex":[0.9988949,0.0001266722,0.0002838629,0.0002334797,0.0001901162,0.0002710143],"domain_scores_gemma":[0.9992761,0.00004393701,0.000074837,0.0004726805,0.00008511363,0.00004733336],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001011889,0.0005412275,0.006722528,0.0001045629,0.0001224688,0.00005197323,0.001401154,0.006801843,0.7914954,0.1164604,0.04168654,0.03451069],"study_design_scores_gemma":[0.002068174,0.0001494806,0.03374431,0.00004845675,0.00002560263,0.00005284754,0.000152285,0.1018251,0.8328958,0.004268717,0.02411038,0.0006588473],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4381617,0.001340724,0.4527061,0.002224415,0.002162684,0.0006549727,0.00001617429,0.0004929072,0.1022403],"genre_scores_gemma":[0.9939458,0.000002147696,0.003135691,0.0001598323,0.0001028236,0.00001036703,0.000003812219,0.00000774328,0.00263175],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5557842,"threshold_uncertainty_score":0.5269872,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03675406798063769,"score_gpt":0.2255474388374474,"score_spread":0.1887933708568097,"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."}}