We present ParrotTTS, a modularized text-to-speech synthesis model leveraging disentangled self-supervised speech representations. It can train a multi-speaker variant effectively using transcripts from a single speaker. ParrotTTS adapts to a new language in low resource setup and generalizes to languages not seen while training the self-supervised backbone. Moreover, without training on bilingual or parallel examples, ParrotTTS can transfer voices across languages while preserving the speaker specific characteristics, e.g., synthesizing fluent Hindi speech using a French speaker's voice and accent. We present extensive results in monolingual and multi-lingual scenarios. ParrotTTS outperforms state-of-the-art multi-lingual TTS models using only a fraction of paired data as latter.

翻译：我们提出ParrotTTS，一种模块化的文本到语音合成模型，利用解耦的自监督语音表示。该模型能够仅使用单一说话者的转录数据，有效训练多说话者变体。ParrotTTS可在低资源场景下适应新语言，并泛化至训练自监督主干时未见过的语言。此外，无需基于双语或平行样本训练，ParrotTTS即可实现跨语言语音迁移，同时保留说话者特定特征，例如用法语说话者的声音和口音合成流利的印地语语音。我们在单语和多语场景中展示了广泛的结果。ParrotTTS仅需使用后者（现有最先进多语言TTS模型）所需配对数据的一小部分，即可超越这些模型。