Artificial Neural Networks Jamming on the Beat

Alexey Tikhonov, Ivan Yamshchikov

Abstract

This paper addresses the issue of long-scale correlations that is characteristic for symbolic music and is a challenge for modern generative algorithms. It suggests a very simple workaround for this challenge, namely, generation of a drum pattern that could be further used as a foundation for melody generation. The paper presents a large dataset of drum patterns alongside with corresponding melodies. It explores two possible methods for drum pattern generation. Exploring a latent space of drum patterns one could generate new drum patterns with a given music style. Finally, the paper demonstrates that a simple artificial neural network could be trained to generate melodies corresponding with these drum patters used as inputs. Resulting system could be used for end-to-end generation of symbolic music with song-like structure and higher long-scale correlations between the notes.

Download


Paper Citation


in Harvard Style

Tikhonov A. and Yamshchikov I. (2021). Artificial Neural Networks Jamming on the Beat. In Proceedings of the 6th International Conference on Complexity, Future Information Systems and Risk - Volume 1: COMPLEXIS, ISBN 978-989-758-505-0, pages 37-44. DOI: 10.5220/0010461200370044


in Bibtex Style

@conference{complexis21,
author={Alexey Tikhonov and Ivan Yamshchikov},
title={Artificial Neural Networks Jamming on the Beat},
booktitle={Proceedings of the 6th International Conference on Complexity, Future Information Systems and Risk - Volume 1: COMPLEXIS,},
year={2021},
pages={37-44},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010461200370044},
isbn={978-989-758-505-0},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 6th International Conference on Complexity, Future Information Systems and Risk - Volume 1: COMPLEXIS,
TI - Artificial Neural Networks Jamming on the Beat
SN - 978-989-758-505-0
AU - Tikhonov A.
AU - Yamshchikov I.
PY - 2021
SP - 37
EP - 44
DO - 10.5220/0010461200370044