VQ-VAE-Diffusion

The proposed method is the first attempt that uses vector quantized diffusion models to generate symbolic music while providing users with flexible controls to generate symbolic music with desired composer styles.

Data and Resources

Cite this as

Jincheng Zhang, Gy¨orgy Fazekas, Charalampos Saitis (2024). Dataset: VQ-VAE-Diffusion. https://doi.org/10.57702/dyy6zha5

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2310.14044
Author Jincheng Zhang
More Authors
Gy¨orgy Fazekas
Charalampos Saitis