While neural text-to-speech (TTS) has achieved human-like natural synthetic speech, multilingual TTS systems are limited to resource-rich languages due to the need for paired text and studio-quality audio data. This paper proposes a method for zero-shot multilingual TTS using text-only data for the target language. The use of text-only data allows the development of TTS systems for low-resource languages for which only textual resources are available, making TTS accessible to thousands of languages. Inspired by the strong cross-lingual transferability of multilingual language models, our framework first performs masked language model pretraining with multilingual text-only data. Then we train this model with a paired data in a supervised manner, while freezing a language-aware embedding layer. This allows inference even for languages not included in the paired data but present in the text-only data. Evaluation results demonstrate highly intelligible zero-shot TTS with a character error rate of less than 12% for an unseen language. All experiments were conducted using public datasets and the implementation will be made available for reproducibility.

翻译：虽然神经语音合成（TTS）已能生成接近人类自然度的合成语音，但多语言TTS系统因需要配对文本与录音室质量的音频数据，目前仅适用于资源丰富的语言。本文提出了一种仅利用目标语言文本数据即可实现零样本多语言TTS的方法。通过使用纯文本数据，该技术使得仅有文本资源的低资源语言也能开发TTS系统，从而将语音合成覆盖到数千种语言。受多语言语言模型强大跨语言迁移能力的启发，我们的框架首先使用多语言纯文本数据进行掩码语言模型预训练，随后在冻结语言感知嵌入层的前提下，采用配对数据对模型进行监督训练。这使得模型能够对未出现在配对数据中但存在于纯文本数据中的语言进行推理。评估结果表明，对于未见语言，该方法可实现字符错误率低于12%的高可懂度零样本语音合成。所有实验均使用公开数据集完成，且代码实现将公开以保证可复现性。