One-Shot Voice Conversion by Vector Quantization

Da-Yi Wu, Hung-Yi LeeICASSP 2020 · OpenReview

Abstract

In this paper, we propose a vector quantization (VQ) based one-shot voice conversion (VC) approach without any supervision on speaker label. We model the content embedding as a series of discrete codes and take the difference between quantize-before and quantize-after vector as the speaker embedding. We show that this approach has a strong ability to disentangle the content and speaker information with reconstruction loss only, and one-shot VC is thus achieved.
BibTeX
@inproceedings{wu2020one,
  author = {Da-Yi Wu and Hung-Yi Lee},
  title = {{One-Shot Voice Conversion by Vector Quantization}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2020},
  url = {https://openreview.net/forum?id=9praSyMby2I},
}

Loading related content...

Figure