Music generation with variational recurrent autoencoder supported by history
Sound
2021-05-21 v4
Abstract
A new architecture of an artificial neural network that helps to generate longer melodic patterns is introduced alongside with methods for post-generation filtering. The proposed approach called variational autoencoder supported by history is based on a recurrent highway gated network combined with a variational autoencoder. Combination of this architecture with filtering heuristics allows generating pseudo-live acoustically pleasing and melodically diverse music.
Cite
@article{arxiv.1705.05458,
title = {Music generation with variational recurrent autoencoder supported by history},
author = {Ivan P. Yamshchikov and Alexey Tikhonov},
journal= {arXiv preprint arXiv:1705.05458},
year = {2021}
}