{"id":"W4403863506","doi":"10.1109/taslp.2024.3487410","title":"CL-MASR: A Continual Learning Benchmark for Multilingual ASR","year":2024,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval; Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Benchmark (surveying); Computer science; Artificial intelligence; Geography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006072866,0.003741314,0.001720106,0.002647203,0.001342472,0.0024637,0.004907603,0.003392667,0.006848223],"category_scores_gemma":[0.02006544,0.0005583785,0.001351291,0.001765869,0.001556939,0.003598246,0.003878022,0.002880309,0.005580097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001321611,"about_ca_system_score_gemma":0.001967532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00682539,"about_ca_topic_score_gemma":0.008465981,"domain_scores_codex":[0.9936396,0.001814532,0.0007187382,0.001747502,0.00161418,0.0004654741],"domain_scores_gemma":[0.9907055,0.004047405,0.0004762645,0.002008813,0.002241367,0.0005206098],"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":[0.002247832,0.001441145,0.006321596,0.002700868,0.0005727432,0.0006543513,0.0003421948,0.2071751,0.01814193,0.005382375,0.0747027,0.6803172],"study_design_scores_gemma":[0.0003732318,0.002426684,0.004617407,0.0002703957,0.0001788633,0.001310737,0.0004907796,0.9011226,0.03657743,0.01512845,0.03727592,0.0002275558],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.335794,0.02181104,0.4636325,0.002733783,0.003769376,0.002023895,0.02685004,0.08368411,0.0597012],"genre_scores_gemma":[0.6425709,0.002152683,0.2677144,0.00120958,0.0005550128,0.001408006,0.06278276,0.003844098,0.01776263],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006848223,"threshold_uncertainty_score":0.03211677,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01732500977189165,"score_gpt":0.2885879270057755,"score_spread":0.2712629172338838,"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."}}