{"id":"W4412944958","doi":"10.18653/v1/2025.acl-long.961","title":"ZIPA: A family of efficient models for multilingual phone recognition","year":2025,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Phone; Computer science; Speech recognition; Artificial intelligence; Pattern recognition (psychology); Linguistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002449737,0.00007673421,0.0001397272,0.0001695182,0.00005112575,0.00003003506,0.0002440248,0.00004830006,0.0000203726],"category_scores_gemma":[0.0001002597,0.00006816501,0.00009779671,0.000288799,0.00002247716,0.0000917286,0.00005871343,0.00003393716,0.00002361353],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000177178,"about_ca_system_score_gemma":0.00006848605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002573637,"about_ca_topic_score_gemma":0.000005589159,"domain_scores_codex":[0.9992481,0.00002427443,0.0002291191,0.000234628,0.0001235176,0.0001403286],"domain_scores_gemma":[0.9992256,0.0002528472,0.00005046996,0.0002076746,0.0002311817,0.00003226153],"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":[0.00002693522,0.0002322388,0.00000292303,0.00003866687,0.00002548524,8.419054e-7,0.0002317442,0.0003899607,0.007670942,0.0101548,0.001027896,0.9801975],"study_design_scores_gemma":[0.0005544195,0.00002718456,0.00005206934,0.00004431031,0.000009327317,9.055042e-7,0.0001263772,0.7769732,0.2062119,0.01563902,0.0002738102,0.00008744963],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0731851,0.00004344228,0.9011866,0.0001872228,0.0002667098,0.0002463565,0.00001108618,0.0001055754,0.02476792],"genre_scores_gemma":[0.6452978,0.000009258113,0.3532995,0.0005534667,0.00001466266,0.00005077281,0.000004177087,0.000003895142,0.0007664818],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9801101,"threshold_uncertainty_score":0.2779688,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05388308592547792,"score_gpt":0.2870036363835925,"score_spread":0.2331205504581146,"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."}}