Published December 8, 2022 | Version Camera Ready
Conference paper Open

Creating latent spaces for modern music genre rhythms using minimal training data

  • 1. Goldsmiths University of London
  • 2. University of the Arts, London

Description

In this paper, we present R-VAE, a system designed for the exploration of latent spaces of musical rhythms. Unlike most previous work in rhythm modeling, R-VAE can be trained with small datasets, enabling rapid customization and exploration by individual users. R-VAE employs a data representation that encodes simple and compound meter rhythms. To the best of our knowledge, this is the first time that a network architecture has been used to encode rhythms with these characteristics, which are common in some modern popular music genres.

Files

vigliensoni20creating_published.pdf

Files (1.8 MB)

Name Size Download all
md5:e4ed29939c4addf2f05e7d596f7ca1ed
1.8 MB Preview Download