{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006147415,0.0001667749,0.0001969473,0.0002225324,0.0002065994,0.0001505177,0.0006364316,0.00006057786,0.0001479932],"category_scores_gemma":[0.0002428778,0.0001090523,0.00009698779,0.00116636,0.00006419112,0.0003060898,0.0001653028,0.0001687303,0.000192841],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002461742,"about_ca_system_score_gemma":0.0000751504,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002138264,"about_ca_topic_score_gemma":0.0001161723,"domain_scores_codex":[0.9983151,0.0001614168,0.0003129349,0.0004300139,0.0004783536,0.0003021938],"domain_scores_gemma":[0.9981573,0.0007690006,0.000140228,0.0006364876,0.000209807,0.0000871783],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000293333,0.000160941,0.0003756766,0.00004533349,0.00009347225,0.00009480187,0.005331097,0.00002417811,0.01308265,0.0002128538,0.00074604,0.9798036],"study_design_scores_gemma":[0.001150517,0.0001521084,0.001691261,0.00009625901,0.00004911698,0.0001078829,0.01850311,0.114107,0.8619091,0.001161183,0.0006283279,0.0004441095],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9256777,0.0000149724,0.02036124,0.002244765,0.0001411189,0.0007199175,0.00003598554,0.001335836,0.04946847],"genre_scores_gemma":[0.7389375,0.00001385939,0.259048,0.0003817697,0.0001137535,0.00005472913,0.00003202681,0.00002864625,0.001389695],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9793595,"threshold_uncertainty_score":0.4447023,"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."}}