Resources for the paper: Self-Supervised VQ-VAE for One-Shot Music Style Transfer
By O. Cífka
In our paper (Cífka et al., 2021), we present a novel method for one-shot timbre style transfer, based on the vector-quantized variational autoencoder (VQ-VAE) and self-supervised learning.
- Paper preprint
- Companion website with audio examples
- Source code on GitHub
- Interactive Colab notebook
Cífka, O., Ozerov, A., Simsekli, U., & Richard, G. (2021, June). Self-Supervised VQ-VAE For One-Shot Music Style Transfer. 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2021). https://hal.telecom-paris.fr/hal-03132940