用罗马化统一书写系统，让语音合成支持495种语言
UR-BERT: Scaling Text Encoders for Massively Multilingual TTS Through Universal Romanization and Speech Token Prediction
- 将多种文字转为罗马音统一表示，突破百语言限制
- 在495种语言上表现优于现有模型，低资源语言也有效
- 适合需要多语言语音合成的开发者和研究者
我们提出UR-BERT，一种基于罗马化转写的文字到语音（TTS）编码器，用于大规模多语言TTS系统。传统基于字符到音素（G2P）的方法受限于可靠G2P资源，仅能支持约100种语言。相比之下，UR-BERT通过将多样书写系统统一为共享的罗马化表示，扩展至495种语言。为进一步提升语音保真度与文本-语音对齐，我们在训练中引入语音标记预测目标，使编码器以数据高效方式学习语音感知的音素表示。实验表明，基于UR-BERT构建的TTS系统在多种语言和资源条件下均持续优于近期文本编码器基线，并展现出对未见语言的强大泛化能力。
原文摘要 · Abstract (English)
We propose UR-BERT, a Romanized transcription-based text-to-speech (TTS) encoder for massively multilingual TTS systems. Conventional grapheme-to-phoneme (G2P)-based approaches are limited to around 100 languages due to the availability of reliable G2P resources. In contrast, UR-BERT scales to 495 languages by unifying diverse writing systems into a shared Romanization representation. To further enhance phonetic fidelity and text-speech alignment, we introduce a speech token prediction objective during training, which encourages the encoder to learn speech-aware phonetic representations in a data-efficient manner. Experiments show that TTS systems built on UR-BERT consistently outperform recent text encoder baselines across a wide range of languages and resource conditions, and demonstrate strong generalization to unseen languages.
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。