{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000559976,0.0001734396,0.0001880963,0.0004622731,0.0006489053,0.0004266612,0.0004967604,0.00004917071,0.0005084591],"category_scores_gemma":[0.00008982255,0.0001639873,0.00006276766,0.0009660475,0.00005825128,0.004256032,0.0001690259,0.0001864638,0.0004211778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003275968,"about_ca_system_score_gemma":0.0001309848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004755872,"about_ca_topic_score_gemma":0.000006497574,"domain_scores_codex":[0.9983349,0.0001371453,0.0004679535,0.0001769273,0.0005817199,0.0003013069],"domain_scores_gemma":[0.9989649,0.00008327219,0.0003157219,0.0003564428,0.0001845014,0.00009518254],"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":[0.00001354313,0.00003529797,0.0002105078,0.00006919241,0.00002238386,0.00001486322,0.002969113,0.0000266788,0.00003062543,0.000799351,0.0004270022,0.9953814],"study_design_scores_gemma":[0.00772248,0.003265568,0.04632855,0.0009494725,0.0002035408,0.01079903,0.02111253,0.7014899,0.03874516,0.06676506,0.09774349,0.004875245],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5636976,0.00003636457,0.3757736,0.0006332805,0.0007365425,0.0009720636,0.00005813708,0.001547751,0.0565447],"genre_scores_gemma":[0.8745731,0.000005778293,0.1237314,0.001056926,0.00004088818,0.0003516647,0.0001434534,0.0000148599,0.00008192792],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9905062,"threshold_uncertainty_score":0.6687208,"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."}}