{"ID":2865805,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.22727","arxiv_id":"2509.22727","title":"DiaMoE-TTS: A Unified IPA-Based Dialect TTS Framework with Mixture-of-Experts and Parameter-Efficient Zero-Shot Adaptation","abstract":"Dialect speech embodies rich cultural and linguistic diversity, yet building text-to-speech (TTS) systems for dialects remains challenging due to scarce data, inconsistent orthographies, and complex phonetic variation. To address these issues, we present DiaMoE-TTS, a unified IPA-based framework that standardizes phonetic representations and resolves grapheme-to-phoneme ambiguities. Built upon the F5-TTS architecture, the system introduces a dialect-aware Mixture-of-Experts (MoE) to model phonological differences and employs parameter-efficient adaptation with Low-Rank Adaptors (LoRA) and Conditioning Adapters for rapid transfer to new dialects. Unlike approaches dependent on large-scale or proprietary resources, DiaMoE-TTS enables scalable, open-data-driven synthesis. Experiments demonstrate natural and expressive speech generation, achieving zero-shot performance on unseen dialects and specialized domains such as Peking Opera with only a few hours of data.","short_abstract":"Dialect speech embodies rich cultural and linguistic diversity, yet building text-to-speech (TTS) systems for dialects remains challenging due to scarce data, inconsistent orthographies, and complex phonetic variation. To address these issues, we present DiaMoE-TTS, a unified IPA-based framework that standardizes phone...","url_abs":"https://arxiv.org/abs/2509.22727","url_pdf":"https://arxiv.org/pdf/2509.22727v1","authors":"[\"Ziqi Chen\",\"Gongyu Chen\",\"Yihua Wang\",\"Chaofan Ding\",\"Zihao chen\",\"Wei-Qiang Zhang\"]","published":"2025-09-25T07:02:04Z","proceeding":"cs.SD","tasks":"[\"cs.SD\",\"cs.CL\",\"eess.AS\"]","methods":"[\"LoRA\"]","has_code":false}