{"ID":2867866,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.18060","arxiv_id":"2509.18060","title":"TMD-TTS: A Unified Tibetan Multi-Dialect Text-to-Speech Framework for Ü-Tsang, Amdo and Kham Speech Dataset Generation","abstract":"Tibetan is a low-resource language with limited parallel speech corpora spanning its three major dialects (Ü-Tsang, Amdo, and Kham), limiting progress in speech modeling. To address this issue, we propose TMD-TTS, a unified Tibetan multi-dialect text-to-speech (TTS) framework that synthesizes parallel dialectal speech from explicit dialect labels. Our method features a dialect fusion module and a Dialect-Specialized Dynamic Routing Network (DSDR-Net) to capture fine-grained acoustic and linguistic variations across dialects. Extensive objective and subjective evaluations demonstrate that TMD-TTS significantly outperforms baselines in dialectal expressiveness. We further validate the quality and utility of the synthesized speech through a challenging Speech-to-Speech Dialect Conversion (S2SDC) task.","short_abstract":"Tibetan is a low-resource language with limited parallel speech corpora spanning its three major dialects (Ü-Tsang, Amdo, and Kham), limiting progress in speech modeling. To address this issue, we propose TMD-TTS, a unified Tibetan multi-dialect text-to-speech (TTS) framework that synthesizes parallel dialectal speech...","url_abs":"https://arxiv.org/abs/2509.18060","url_pdf":"https://arxiv.org/pdf/2509.18060v2","authors":"[\"Yutong Liu\",\"Ziyue Zhang\",\"Ban Ma-bao\",\"Renzeng Duojie\",\"Yuqing Cai\",\"Yongbin Yu\",\"Xiangxiang Wang\",\"Fan Gao\",\"Cheng Huang\",\"Nyima Tashi\"]","published":"2025-09-22T17:38:52Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[]","has_code":false}