{"id":"W4315645596","doi":"10.18280/isi.270614","title":"Indonesian Automatic Speech Recognition with XLSR-53","year":2022,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Indonesian; Word error rate; Speech recognition; Computer science; MAGIC (telescope); Word (group theory); Natural language processing; Language model; Training set; Artificial intelligence; Linguistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00115143,0.0007227534,0.0005734611,0.0004628124,0.0002002398,0.0007303864,0.0007497543,0.0004267254,0.01193811],"category_scores_gemma":[0.001438415,0.0003534053,0.0006415215,0.0003323083,0.0002287679,0.0008582302,0.001010102,0.0007972316,0.01162819],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003204406,"about_ca_system_score_gemma":0.0006690762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003432368,"about_ca_topic_score_gemma":0.003398122,"domain_scores_codex":[0.9990377,0.0002217967,0.00008930326,0.0002784221,0.0002926686,0.00008008231],"domain_scores_gemma":[0.9992698,0.0001876615,0.00003902038,0.0002231971,0.0002532497,0.00002700544],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001187722,0.0005069708,0.003930455,0.000389844,0.0002011568,0.0005250935,0.0003536645,0.06369717,0.1634979,0.003139459,0.02230904,0.7402616],"study_design_scores_gemma":[0.0001185256,0.0008991571,0.008107288,0.00006439823,0.0000922148,0.0008323779,0.0001417916,0.7787597,0.1710522,0.001031452,0.03880168,0.00009925979],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1961532,0.00088976,0.6591105,0.0003679944,0.0004591533,0.0004007022,0.005651553,0.1082416,0.02872553],"genre_scores_gemma":[0.5578943,0.0003629056,0.3853232,0.000269951,0.00005751389,0.0005465901,0.02215763,0.002600263,0.03078768],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01193811,"threshold_uncertainty_score":0.0399369,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01775987249685566,"score_gpt":0.2122977714343252,"score_spread":0.1945378989374695,"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."}}