In this work, we take on the challenging task of building a single text-to-speech synthesis system that is capable of generating speech in over 7000 languages, many of which lack sufficient data for traditional TTS development. By leveraging a novel integration of massively multilingual pretraining and meta learning to approximate language representations, our approach enables zero-shot speech synthesis in languages without any available data. We validate our system's performance through objective measures and human evaluation across a diverse linguistic landscape. By releasing our code and models publicly, we aim to empower communities with limited linguistic resources and foster further innovation in the field of speech technology.
@article{arxiv.2406.06403,
title = {Meta Learning Text-to-Speech Synthesis in over 7000 Languages},
author = {Florian Lux and Sarina Meyer and Lyonel Behringer and Frank Zalkow and Phat Do and Matt Coler and Emanuël A. P. Habets and Ngoc Thang Vu},
journal= {arXiv preprint arXiv:2406.06403},
year = {2024}
}