VoxHakka：面向台湾客家话的方言多样化多说话人文本转语音系统
VoxHakka: A Dialectally Diverse Multi-speaker Text-to-Speech System for Taiwanese Hakka
AI总结：
本文提出基于 YourTTS 的台湾客家话 TTS 系统 VoxHakka，通过网络抓取与 ASR 清洗构建多方言多说话人语料，支持六种方言并在 CMOS 评测中显著优于现有系统。
摘要：
本文介绍 VoxHakka，这是一个为台湾客家话设计的文本转语音（TTS）系统；台湾客家话是在台湾使用、资源极度匮乏的语言。VoxHakka 利用 YourTTS 框架，在支持六种不同客家话方言的同时，实现了高自然度、高准确性和较低的语音合成实时率。这是通过使用方言专属数据训练模型实现的，从而能够生成具备说话人感知能力的客家话语音。为解决公开可用客家话语音语料库稀缺的问题，本文采用了一种高成本效益方法：使用网络抓取流程，并结合基于自动语音识别（ASR）的数据清洗技术。该过程确保获得适用于 TTS 训练的高质量、多说话人、多方言数据集。采用比较平均意见得分（CMOS）进行的主观听辨测试表明，VoxHakka 在发音准确性、声调正确性和整体自然度方面显著优于现有公开可用的客家话 TTS 系统。本工作代表了客家话语言技术的重大进步，并为语言保存与振兴工作提供了宝贵资源。
英文摘要：
This paper introduces VoxHakka, a text-to-speech (TTS) system designed for Taiwanese Hakka, a critically under-resourced language spoken in Taiwan. Leveraging the YourTTS framework, VoxHakka achieves high naturalness and accuracy and low real-time factor in speech synthesis while supporting six distinct Hakka dialects. This is achieved by training the model with dialect-specific data, allowing for the generation of speaker-aware Hakka speech. To address the scarcity of publicly available Hakka speech corpora, we employed a cost-effective approach utilizing a web scraping pipeline coupled with automatic speech recognition (ASR)-based data cleaning techniques. This process ensured the acquisition of a high-quality, multi-speaker, multi-dialect dataset suitable for TTS training. Subjective listening tests conducted using comparative mean opinion scores (CMOS) demonstrate that VoxHakka significantly outperforms existing publicly available Hakka TTS systems in terms of pronunciation accuracy, tone correctness, and overall naturalness. This work represents a significant advancement in Hakka language technology and provides a valuable resource for language preservation and revitalization efforts.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
