构建统一藏语多方言语音合成框架，生成三大方言语音数据。
TMD-TTS: A Unified Tibetan Multi-Dialect Text-to-Speech Framework for Ü-Tsang, Amdo and Kham Speech Dataset Generation
- 通过方言融合模块与动态路由网络捕捉多方言差异。
- 在客观与主观评测中显著优于基线模型。
- 可生成高质量语音，适用于方言转换任务。
藏语为低资源语言，其三大方言（卫藏、安多、康巴）缺乏平行语音语料库，制约了语音建模发展。为此，我们提出TMD-TTS，一种统一的藏语多方言文本转语音框架，能根据显式方言标签合成多方言语音。该方法包含方言融合模块与方言特化动态路由网络（DSDR-Net），有效捕捉方言间的声学与语言细微差异。大量客观与主观评估表明，TMD-TTS在方言表现力上显著优于基线模型。进一步通过具有挑战性的语音到语音方言转换（S2SDC）任务验证了合成语音的质量与实用性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。