MParrotTTS：低资源环境下的多语言多说话人文本到语音合成
MParrotTTS: Multilingual Multi-speaker Text to Speech Synthesis in Low Resource Setting
AI总结：
本文提出MParrotTTS模型，利用自监督语音表示的模块化训练范式，在低资源下实现高质量多语言多说话人TTS及跨语言声音转换，仅用少量监督数据即超越现有基线。
摘要：
我们提出了MParrotTTS，一个统一的能产生高质量语音的多语言、多说话人文本到语音（TTS）合成模型。得益于利用自监督语音表示的模块化训练范式，MParrotTTS能够以最少的监督数据适应新语言，并泛化至训练自监督主干网络时未见过的语言。此外，在未训练任何双语或平行样本的情况下，MParrotTTS能在保留说话人特定特征的同时进行跨语言声音转换，例如用法语说话人的声音和口音合成流利的印地语语音。我们展示了六种语言在平行和跨语言合成中关于语音自然度和说话人相似度的大量结果。仅使用一小部分监督训练数据，所提出的模型便优于最先进的多语言TTS模型和基线。
英文摘要：
We present MParrotTTS, a unified multilingual, multi-speaker text-to-speech (TTS) synthesis model that can produce high-quality speech. Benefiting from a modularized training paradigm exploiting self-supervised speech representations, MParrotTTS adapts to a new language with minimal supervised data and generalizes to languages not seen while training the self-supervised backbone. Moreover, without training on any bilingual or parallel examples, MParrotTTS 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 on six languages in terms of speech naturalness and speaker similarity in parallel and cross-lingual synthesis. The proposed model outperforms the state-of-the-art multilingual TTS models and baselines, using only a small fraction of supervised training data. Speech samples from our model can be found at https://paper2438.github.io/tts/
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。
