{"id":"W4389115567","doi":"10.48550/arxiv.2311.15077","title":"Multilingual self-supervised speech representations improve the speech recognition of low-resource African languages with codeswitching","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institute for Advanced Research; National Science Foundation","keywords":"Computer science; Bespoke; Code (set theory); Natural language processing; Artificial intelligence; Speech recognition; Language model; Scratch; Programming language","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005599565,0.0003435116,0.0003922502,0.0003872037,0.0002537237,0.0001693363,0.001597363,0.0002221747,0.00005495993],"category_scores_gemma":[0.0002010175,0.0002941982,0.0002488719,0.001012686,0.0001436186,0.0002950908,0.0009838687,0.0006324159,0.0001054871],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000118217,"about_ca_system_score_gemma":0.0002277121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006294089,"about_ca_topic_score_gemma":0.0002729885,"domain_scores_codex":[0.9976209,0.0003337592,0.0003308209,0.001090534,0.0002585549,0.0003654275],"domain_scores_gemma":[0.9969131,0.0007607047,0.0004394162,0.001371888,0.0003756869,0.0001391638],"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":[0.001124311,0.00333669,0.01165765,0.002436124,0.00448024,0.009613018,0.03798435,0.05039525,0.008748909,0.009106701,0.00206238,0.8590544],"study_design_scores_gemma":[0.002702385,0.0002557386,0.002264216,0.0009144058,0.0005955239,0.00009320366,0.01875341,0.8302543,0.1240197,0.01811055,0.0002681216,0.001768497],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9021213,0.00001806477,0.08808164,0.0003768024,0.0002940619,0.0009056983,0.0001347365,0.0008580456,0.007209667],"genre_scores_gemma":[0.9584031,0.00005203148,0.04006696,0.00008606714,0.0001091537,0.000006116894,0.00005987303,0.00004272917,0.001174012],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8572859,"threshold_uncertainty_score":0.999951,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07033471131280217,"score_gpt":0.2221951529390186,"score_spread":0.1518604416262165,"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."}}