{"id":"W2140682244","doi":"10.32920/27997979.v1","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":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"European Commission; Copenhagen Business School","keywords":"Dictation; Speech recognition; Computer science; Workflow; Natural language processing; First language; Linguistics; Database","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":[0.0006246619,0.0001099775,0.0001739645,0.0001881388,0.0000386327,0.0002319704,0.0002875134,0.00005635875,0.000004898506],"category_scores_gemma":[0.00006575326,0.00007104638,0.00002224396,0.0005087536,0.00007702829,0.001441188,0.00008622993,0.0001602817,0.000001079394],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005439675,"about_ca_system_score_gemma":0.00004926569,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002823854,"about_ca_topic_score_gemma":0.0000634118,"domain_scores_codex":[0.9990237,0.0000803629,0.0002909117,0.000215331,0.0002717608,0.0001179432],"domain_scores_gemma":[0.9992275,0.0003517348,0.0001524955,0.0001563658,0.00009527758,0.00001669179],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001133683,0.00009902459,0.006827477,0.002747753,0.0001117399,0.00003025447,0.03391393,0.00002071354,0.04439068,0.002132974,0.0005614359,0.9091527],"study_design_scores_gemma":[0.0002160458,0.0001017506,0.002277903,0.002744653,0.00001951526,0.00001470848,0.002216735,0.8572479,0.130106,0.004878215,0.000002567035,0.0001739198],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8685406,0.002796447,0.1273977,0.0002332069,0.00007941612,0.0003583969,0.000004718663,0.000179752,0.0004097915],"genre_scores_gemma":[0.8611988,0.00001369155,0.1386929,0.00001210145,0.00001128958,0.00001962359,0.000005100631,0.000007133704,0.00003928712],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9089788,"threshold_uncertainty_score":0.2897187,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01732166725866894,"score_gpt":0.2933360615419495,"score_spread":0.2760143942832806,"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."}}