{"id":"W4405250561","doi":"10.32920/27997979","title":"Assessing the Performance of Automatic Speech Recognition Systems When Used by Native and Non-Native Speakers of Three Major Languages in Dictation Workflows","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"European Commission; Copenhagen Business School","keywords":"Dictation; Computer science; Transcription (linguistics); Speech recognition; Workflow; Natural language processing; First language; Competence (human resources); Artificial intelligence; Linguistics; Psychology","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":[0.007725582,0.0009656276,0.0008721872,0.0006525609,0.0006240925,0.001769134,0.0007825736,0.001273522,0.003086923],"category_scores_gemma":[0.03339739,0.0004627562,0.0006558723,0.0003690538,0.0008677801,0.001606056,0.001578496,0.0007420626,0.002763844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000449897,"about_ca_system_score_gemma":0.0006772659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00217204,"about_ca_topic_score_gemma":0.002824008,"domain_scores_codex":[0.9924684,0.003825356,0.0009664291,0.001480481,0.00087748,0.0003816992],"domain_scores_gemma":[0.960741,0.02872702,0.001519212,0.002979607,0.00501583,0.001017418],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.01797486,0.004168434,0.1499859,0.002053919,0.000851674,0.001293324,0.03351869,0.01131691,0.4335507,0.0008013439,0.002751324,0.3417329],"study_design_scores_gemma":[0.001551555,0.04152835,0.511016,0.000207927,0.001000146,0.003552289,0.02324002,0.06229863,0.3417885,0.00136899,0.01164146,0.0008061801],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9937711,0.00008226504,0.004271102,0.00005150849,0.00003691038,0.0001700037,0.0001799516,0.0001745179,0.001262614],"genre_scores_gemma":[0.9764924,0.0001113799,0.01926805,0.0001398374,0.00005420184,0.0003622801,0.0009427549,0.0001019458,0.002527116],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007725582,"threshold_uncertainty_score":0.04085726,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02114569251695,"score_gpt":0.3013939600955164,"score_spread":0.2802482675785665,"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."}}