{"ID":2884198,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.07426","arxiv_id":"2508.07426","title":"Scalable Controllable Accented TTS","abstract":"We tackle the challenge of scaling accented TTS systems, expanding their capabilities to include much larger amounts of training data and a wider variety of accent labels, even for accents that are poorly represented or unlabeled in traditional TTS datasets. To achieve this, we employ two strategies: 1. Accent label discovery via a speech geolocation model, which automatically infers accent labels from raw speech data without relying solely on human annotation; 2. Timbre augmentation through kNN voice conversion to increase data diversity and model robustness. These strategies are validated on CommonVoice, where we fine-tune XTTS-v2 for accented TTS with accent labels discovered or enhanced using geolocation. We demonstrate that the resulting accented TTS model not only outperforms XTTS-v2 fine-tuned on self-reported accent labels in CommonVoice, but also existing accented TTS benchmarks.","short_abstract":"We tackle the challenge of scaling accented TTS systems, expanding their capabilities to include much larger amounts of training data and a wider variety of accent labels, even for accents that are poorly represented or unlabeled in traditional TTS datasets. To achieve this, we employ two strategies: 1. Accent label di...","url_abs":"https://arxiv.org/abs/2508.07426","url_pdf":"https://arxiv.org/pdf/2508.07426v1","authors":"[\"Henry Li Xinyuan\",\"Zexin Cai\",\"Ashi Garg\",\"Kevin Duh\",\"Leibny Paola García-Perera\",\"Sanjeev Khudanpur\",\"Nicholas Andrews\",\"Matthew Wiesner\"]","published":"2025-08-10T16:56:39Z","proceeding":"eess.AS","tasks":"[\"eess.AS\"]","methods":"[]","has_code":false}