EZ-VC: Easy Zero-shot Any-to-Any Voice Conversion

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.

@article{joglekar2025_2505.16691,
  title={ EZ-VC: Easy Zero-shot Any-to-Any Voice Conversion },
  author={ Advait Joglekar and Divyanshu Singh and Rooshil Rohit Bhatia and S. Umesh },
  journal={arXiv preprint arXiv:2505.16691},
  year={ 2025 }
}