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


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 (1.8 MB)

Name Size Download all
1.8 MB Preview Download