{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007819247,0.000911745,0.0008110374,0.0006436031,0.0006225262,0.001706688,0.000768193,0.001199417,0.002946713],"category_scores_gemma":[0.03240842,0.000453176,0.0006372456,0.0003487165,0.0008588507,0.001588417,0.001522685,0.0007080208,0.002613284],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004476697,"about_ca_system_score_gemma":0.0006593482,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002260427,"about_ca_topic_score_gemma":0.003164515,"domain_scores_codex":[0.9926159,0.003809844,0.0009525254,0.001405821,0.0008390718,0.0003768132],"domain_scores_gemma":[0.9624854,0.02730573,0.00147924,0.002754671,0.005015309,0.0009596837],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.01744239,0.004475288,0.163221,0.001870151,0.0008054796,0.001330124,0.03511522,0.01074277,0.4238254,0.0007537169,0.002566303,0.3378523],"study_design_scores_gemma":[0.001473053,0.04464585,0.5340939,0.0001992388,0.0009155987,0.003463444,0.02442698,0.06030031,0.3175886,0.001182489,0.01093011,0.0007804005],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.994474,0.00007031882,0.003724035,0.00004736378,0.00003266753,0.0001646363,0.000152539,0.000144968,0.001189449],"genre_scores_gemma":[0.9777483,0.0001010663,0.01823526,0.0001396643,0.00004859922,0.0003597927,0.0008074681,0.00008456331,0.002475287],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007819247,"threshold_uncertainty_score":0.04135263,"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."}}