English

Generating Music using an LSTM Network

Sound 2018-04-23 v1 Machine Learning Audio and Speech Processing

Abstract

A model of music needs to have the ability to recall past details and have a clear, coherent understanding of musical structure. Detailed in the paper is a neural network architecture that predicts and generates polyphonic music aligned with musical rules. The probabilistic model presented is a Bi-axial LSTM trained with a kernel reminiscent of a convolutional kernel. When analyzed quantitatively and qualitatively, this approach performs well in composing polyphonic music. Link to the code is provided.

Keywords

Cite

@article{arxiv.1804.07300,
  title  = {Generating Music using an LSTM Network},
  author = {Nikhil Kotecha and Paul Young},
  journal= {arXiv preprint arXiv:1804.07300},
  year   = {2018}
}

Comments

8 pages, 11 figures

R2 v1 2026-06-23T01:29:05.884Z