YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone

TL;DR

YourTTS introduces a multilingual, zero-shot multi-speaker TTS and voice conversion system that achieves state-of-the-art results, works with low-resource languages, and can be fine-tuned with minimal data.

Contribution

It extends the VITS model with novel modifications for zero-shot multilingual and multi-speaker TTS, enabling high-quality synthesis with minimal data and in low-resource languages.

Findings

Achieved SOTA results in zero-shot multi-speaker TTS.

Comparable results to SOTA in zero-shot voice conversion.

Effective fine-tuning with less than 1 minute of speech.

Abstract

YourTTS brings the power of a multilingual approach to the task of zero-shot multi-speaker TTS. Our method builds upon the VITS model and adds several novel modifications for zero-shot multi-speaker and multilingual training. We achieved state-of-the-art (SOTA) results in zero-shot multi-speaker TTS and results comparable to SOTA in zero-shot voice conversion on the VCTK dataset. Additionally, our approach achieves promising results in a target language with a single-speaker dataset, opening possibilities for zero-shot multi-speaker TTS and zero-shot voice conversion systems in low-resource languages. Finally, it is possible to fine-tune the YourTTS model with less than 1 minute of speech and achieve state-of-the-art results in voice similarity and with reasonable quality. This is important to allow synthesis for speakers with a very different voice or recording characteristics from those seen during training.