Music Generation System Based on LSTM

DOI

10.2991/iceeecs-16.2016.108How to use a DOI?

Keywords

LSTM Model; Automatic Music Generation System; Musical Notation

Abstract

Traditional music generation is manual, so it's of great significance to generate music automatically by machines. This paper proposes a method of using the Long-Short Term Memory (LSTM) Unit model to format music file, extract characters and generate music. And then constructing an automatic music generation system through the formalization processing and neural network supervised learning. The experimental results show that the system can effectively generate a new music which is similar to the original one.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Yuan Xiao
AU  - Shengwu Xiong
AU  - Pengfei Duan
PY  - 2016/12
DA  - 2016/12
TI  - Music Generation System Based on LSTM
BT  - Proceedings of the 2016 4th International Conference on Electrical & Electronics Engineering and Computer Science (ICEEECS 2016)
PB  - Atlantis Press
SP  - 534
EP  - 539
SN  - 2352-538X
UR  - https://doi.org/10.2991/iceeecs-16.2016.108
DO  - 10.2991/iceeecs-16.2016.108
ID  - Xiao2016/12
ER  -