YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone
This addresses the problem of generating speech for diverse speakers and low-resource languages, offering incremental improvements in zero-shot TTS and voice conversion.
The paper tackles zero-shot multi-speaker text-to-speech and voice conversion by introducing YourTTS, a multilingual model based on VITS with novel modifications, achieving state-of-the-art results on VCTK and enabling fine-tuning with less than 1 minute of speech for high voice similarity.
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.