{"id":"W4390037801","doi":"10.1162/tacl_a_00627","title":"AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASR","year":2023,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Benchmark (surveying); Computer science; Speech recognition; Domain (mathematical analysis); Set (abstract data type); Productivity; Natural language processing; Test set; Test (biology); Artificial intelligence; Biology","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":[0.001114227,0.0001191074,0.0002262917,0.0001375295,0.0003547458,0.0000871831,0.0004215704,0.0001079743,0.000006293557],"category_scores_gemma":[0.002235937,0.0001088157,0.0002118646,0.000477472,0.00005942516,0.00006553385,0.00003196935,0.0001138119,0.00001021098],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007179853,"about_ca_system_score_gemma":0.000123009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001306607,"about_ca_topic_score_gemma":0.00001674859,"domain_scores_codex":[0.9984844,0.0001143187,0.0005347872,0.0002790425,0.0003719049,0.0002154905],"domain_scores_gemma":[0.9960313,0.002563846,0.0003467819,0.00023152,0.0007614666,0.00006503862],"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":[0.0005093823,0.002140602,0.02217109,0.0004551674,0.002603493,0.00000748578,0.001513031,0.03347242,0.0002495657,0.3619883,0.3560663,0.2188231],"study_design_scores_gemma":[0.003128363,0.0001990988,0.03233039,0.00003914139,0.0002408775,0.000006851478,0.0001291899,0.5345359,0.0006791473,0.2051614,0.2230967,0.000452887],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004646251,0.00001277055,0.9822262,0.002400682,0.001841101,0.0007155606,0.00771043,0.0001354424,0.0003115977],"genre_scores_gemma":[0.3593456,0.00005278211,0.6367134,0.0004424211,0.0005730782,0.0001062088,0.001542805,0.00003146881,0.001192297],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5010635,"threshold_uncertainty_score":0.4437374,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05812305070298272,"score_gpt":0.3487872494558333,"score_spread":0.2906641987528506,"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."}}