EZ-VC: Easy Zero-shot Any-to-Any Voice Conversion
This work addresses voice conversion challenges for multilingual and accented speakers, offering a practical solution for applications like speech synthesis and translation, though it builds incrementally on existing self-supervised and diffusion methods.
The paper tackles the problem of zero-shot cross-lingual voice conversion by proposing a model that combines discrete speech representations with a Diffusion-Transformer decoder, achieving strong performance in converting voices for unseen languages and accents without requiring multiple encoders.
Voice Conversion research in recent times has increasingly focused on improving the zero-shot capabilities of existing methods. Despite remarkable advancements, current architectures still tend to struggle in zero-shot cross-lingual settings. They are also often unable to generalize for speakers of unseen languages and accents. In this paper, we adopt a simple yet effective approach that combines discrete speech representations from self-supervised models with a non-autoregressive Diffusion-Transformer based conditional flow matching speech decoder. We show that this architecture allows us to train a voice-conversion model in a purely textless, self-supervised fashion. Our technique works without requiring multiple encoders to disentangle speech features. Our model also manages to excel in zero-shot cross-lingual settings even for unseen languages. For Demo: https://ez-vc.github.io/EZ-VC-Demo/