{"id":"W4389518264","doi":"10.18653/v1/2023.calcs-1.8","title":"Multilingual self-supervised speech representations improve the speech recognition of low-resource African languages with codeswitching","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"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; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006496648,0.0009340832,0.0003748012,0.000386349,0.0002812363,0.0007063797,0.000543508,0.000443187,0.002490079],"category_scores_gemma":[0.00298236,0.0002357783,0.0005071234,0.0002790771,0.0004281776,0.001237822,0.001237971,0.001403594,0.002875543],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002933032,"about_ca_system_score_gemma":0.0007396402,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004984977,"about_ca_topic_score_gemma":0.0108686,"domain_scores_codex":[0.9994798,0.0001473158,0.00002556006,0.0002069057,0.0000694485,0.00007093931],"domain_scores_gemma":[0.9989784,0.0004288526,0.00005849939,0.0002203306,0.0002487062,0.00006536717],"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":[0.0007565424,0.0004717711,0.009654268,0.00025242,0.0002078236,0.0002458167,0.0007134095,0.08202528,0.1434421,0.001600006,0.01081624,0.7498144],"study_design_scores_gemma":[0.00004466801,0.0003785785,0.008608477,0.00005728308,0.00008637222,0.000244279,0.0005143887,0.8668135,0.1102234,0.003228328,0.009722793,0.00007793531],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5414225,0.0008927368,0.4277168,0.0006901746,0.000530944,0.000154501,0.00179318,0.01768849,0.009110757],"genre_scores_gemma":[0.8890374,0.0001873635,0.09842346,0.000291094,0.00007298138,0.0001141238,0.004461722,0.0007044694,0.006707452],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004984977,"threshold_uncertainty_score":0.009911895,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02325124685045131,"score_gpt":0.2728288138734833,"score_spread":0.249577567023032,"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."}}