{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006140794,0.0001025871,0.0001649026,0.0001197224,0.0003911645,0.00005434689,0.0004018506,0.00007545382,0.000007717594],"category_scores_gemma":[0.001182033,0.00007011711,0.0004120001,0.0005270405,0.00004285779,0.00004506929,0.000007165649,0.0001087238,0.000003789849],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003402292,"about_ca_system_score_gemma":0.0002209559,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000287611,"about_ca_topic_score_gemma":0.00001003857,"domain_scores_codex":[0.9987789,0.0001123159,0.0004543136,0.0001360543,0.0003774699,0.0001409427],"domain_scores_gemma":[0.9963386,0.001797346,0.0003815749,0.0002333609,0.001227295,0.00002184335],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000120474,0.0008686565,0.001830245,0.0001288232,0.001096172,2.320689e-7,0.0003641318,0.2176661,0.000566499,0.6267067,0.00397746,0.1466746],"study_design_scores_gemma":[0.001001425,0.0001813449,0.05486301,0.000130588,0.0001545363,0.000001342425,0.00003102253,0.7963356,0.007274291,0.1364807,0.003390729,0.0001553716],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005411647,0.00002125128,0.9895384,0.0008745218,0.001165434,0.0004167568,0.000165975,0.00005633581,0.002349617],"genre_scores_gemma":[0.9754187,0.000007753943,0.02370362,0.00004155175,0.00004261034,0.00001915064,0.00001430911,0.000005539405,0.0007467186],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9700071,"threshold_uncertainty_score":0.3008561,"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."}}