{"id":"W4417275930","doi":"10.1162/tacl.a.54","title":"The Impact of Automatic Speech Transcription on Speaker Attribution","year":2025,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université TÉLUQ; Université du Québec à Montréal","funders":"","keywords":"Attribution; Transcription (linguistics); Task (project management); Speaker diarisation; Phonetic transcription; Speech processing","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":[0.0181842,0.001088014,0.0008494884,0.001029287,0.001006703,0.002615976,0.001023237,0.001236728,0.002140767],"category_scores_gemma":[0.2278911,0.0004284653,0.0003897981,0.001119119,0.001408916,0.002495368,0.002209859,0.001575474,0.002050024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009321132,"about_ca_system_score_gemma":0.0009023989,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002745805,"about_ca_topic_score_gemma":0.001612927,"domain_scores_codex":[0.9617702,0.02243109,0.002972779,0.004602919,0.007254244,0.0009686448],"domain_scores_gemma":[0.6311768,0.2919121,0.02159804,0.03164111,0.02134322,0.00232874],"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":[0.008938152,0.0008559735,0.1188267,0.001486371,0.0007077683,0.001296658,0.006582418,0.1274363,0.1767625,0.001933371,0.007291877,0.5478819],"study_design_scores_gemma":[0.0002151317,0.004442165,0.2277292,0.0006374141,0.0006670598,0.002714825,0.004561025,0.3941679,0.3484959,0.009045025,0.006651521,0.0006729754],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.922733,0.001250912,0.06596328,0.0007841224,0.000633007,0.0001494675,0.0006722307,0.003159028,0.004655025],"genre_scores_gemma":[0.9883636,0.0001773955,0.009109929,0.0001530546,0.000104016,0.00003343148,0.0007677997,0.0004441745,0.0008467015],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0181842,"threshold_uncertainty_score":0.0961684,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01855258785467077,"score_gpt":0.296895449186917,"score_spread":0.2783428613322462,"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."}}