{"id":"W4220982091","doi":"10.1080/15434303.2022.2038172","title":"Investigating the Effects of Task Type and Linguistic Background on Accuracy in Automated Speech Recognition Systems: Implications for Use in Language Assessment of Young Learners","year":2022,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute for Christian Studies; University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Task (project management); Computer science; Natural language processing; Artificial intelligence; Meaning (existential); Task analysis; Language proficiency; Test (biology); Psychology; Speech recognition","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0007901873,0.0001376777,0.0002578178,0.0002632455,0.00009964306,0.0001197882,0.0003134268,0.00004047323,0.000007160274],"category_scores_gemma":[0.0004106816,0.0001208793,0.00004151708,0.000671074,0.00003731088,0.0002187025,0.00005566734,0.0002094251,7.998246e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000149962,"about_ca_system_score_gemma":0.0001346493,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001161538,"about_ca_topic_score_gemma":0.0002669494,"domain_scores_codex":[0.9983001,0.0004852442,0.0004469017,0.0003127513,0.0002515895,0.0002034236],"domain_scores_gemma":[0.9968898,0.002262396,0.0003245895,0.0003838889,0.00009759433,0.00004167946],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00007194033,0.002177156,0.09075653,0.002364651,0.0002893207,0.0002100774,0.07732934,0.0003813506,0.2397976,0.01711576,0.0005045187,0.5690017],"study_design_scores_gemma":[0.003811826,0.003415609,0.5500887,0.001022584,0.000107409,0.00008704417,0.05579581,0.3804032,0.003116983,0.001361287,0.00004726583,0.0007422416],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9951417,0.00009034952,0.003044118,0.0001155248,0.0002428165,0.0009524125,0.00005021445,0.00008451298,0.0002783866],"genre_scores_gemma":[0.9772757,0.000005544649,0.02219416,0.00009742351,0.00002048904,0.0003024883,0.00007095152,0.0000138024,0.00001940587],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5682595,"threshold_uncertainty_score":0.4929315,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03373161378752211,"score_gpt":0.3391697548696433,"score_spread":0.3054381410821213,"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."}}