{"ID":5438886,"CreatedAt":"2026-07-01T01:17:58.482524686Z","UpdatedAt":"2026-07-03T13:17:43.497842103Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.31642","arxiv_id":"2606.31642","title":"Tone-Conditioned Curriculum Learning for Low-Resource Bantu Speech Recognition","abstract":"Southern Bantu languages are spoken by over 80 million people, yet current foundation ASR models still produce zero-shot WER above 100%, which limits practical use in education and public services. We addressed this gap with a tone conditioned curriculum framework for 6 Southern Bantu languages that combined hybrid difficulty scoring, gated adapters driven by tonal statistics and staged curriculum training. We trained on a community corpus and tested transfer to NCHLT to measure robustness beyond matched evaluation. Results revealed clear interactions between architecture and language, with W2V-BERT outperforming Whisper on Nguni languages by 3 to 4 WER points whilst Whisper performed better on Sotho-Tswana languages. W2V-BERT with tone conditioning reached 28.41% average WER across datasets and 23.79% on Xitsonga transfer. No single model suited all 6 languages, so deployment should pair model selection per language with validation across corpora.","short_abstract":"Southern Bantu languages are spoken by over 80 million people, yet current foundation ASR models still produce zero-shot WER above 100%, which limits practical use in education and public services. We addressed this gap with a tone conditioned curriculum framework for 6 Southern Bantu languages that combined hybrid dif...","url_abs":"https://arxiv.org/abs/2606.31642","url_pdf":"https://arxiv.org/pdf/2606.31642v1","authors":"[\"Kesego Mokgosi\",\"Vukosi Marivate\",\"Sitwala Mundia\",\"Unarine Netshifhefhe\",\"Tsholofelo Hope Mogale\",\"Thapelo Sindane\"]","published":"2026-06-30T13:23:25Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[]","has_code":false}