Published October 19, 2020
| Version v1
Conference paper
Open
Generation and visualization of rhythmic latent spaces
Description
In this paper we extend R-VAE, a system designed for the modeling and exploration of latent spaces of musical rhythms. R-VAE employs a data representation that encodes simple and compound meter rhythms, common in some contemporary popular music genres. It can be trained with small datasets, enabling rapid customization and exploration by individual users. To facilitate the exploration of the latent space, we provide R-VAE with a web-based visualizer designed for the dynamic representation of rhythmic latent spaces. To the best of our knowledge, this is the first time that a dynamic visualization has been implemented to observe a latent space learned from rhythmic patterns.
Files
CSMC__MuMe_2020_paper_13.pdf
Files
(487.1 kB)
Name | Size | Download all |
---|---|---|
md5:c551f1f6cb7aa8d2286111d7f5af73ef
|
487.1 kB | Preview Download |