{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0276012,0.0005707684,0.0006161383,0.0008754489,0.0005279558,0.002089377,0.0006898741,0.0005519352,0.001320998],"category_scores_gemma":[0.1251388,0.0003379596,0.0005875561,0.0006994721,0.0008229289,0.001895223,0.001277196,0.000683877,0.0004997022],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005326518,"about_ca_system_score_gemma":0.0007736636,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002245166,"about_ca_topic_score_gemma":0.003831139,"domain_scores_codex":[0.9804509,0.01182758,0.001429139,0.001850513,0.003993077,0.0004488006],"domain_scores_gemma":[0.7141353,0.2442859,0.01904168,0.00793962,0.01100274,0.003594718],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002799876,0.001215494,0.9232199,0.0001295387,0.0002738255,0.0001204004,0.004019212,0.001097117,0.01186227,0.0001894528,0.0001485276,0.05492426],"study_design_scores_gemma":[0.00002893162,0.003095093,0.9895056,0.00002535039,0.00005838739,0.00008529557,0.001024094,0.001676191,0.004172727,0.0001572137,0.0001474342,0.0000236309],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9975151,0.00009934288,0.00154056,0.00004908243,0.000007638987,0.00003830981,0.00002942575,0.00001274445,0.0007077893],"genre_scores_gemma":[0.996762,0.00006673537,0.002521081,0.00005072579,0.00001429689,0.00006319594,0.00007304451,0.00001640098,0.0004325242],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0276012,"threshold_uncertainty_score":0.1459708,"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."}}