English

Bach2Bach: Generating Music Using A Deep Reinforcement Learning Approach

Sound 2018-12-05 v1 Machine Learning Audio and Speech Processing Machine Learning

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 deep reinforcement learning architecture that predicts and generates polyphonic music aligned with musical rules. The probabilistic model presented is a Bi-axial LSTM trained with a pseudo-kernel reminiscent of a convolutional kernel. To encourage exploration and impose greater global coherence on the generated music, a deep reinforcement learning approach DQN is adopted. When analyzed quantitatively and qualitatively, this approach performs well in composing polyphonic music.

Keywords

Cite

@article{arxiv.1812.01060,
  title  = {Bach2Bach: Generating Music Using A Deep Reinforcement Learning Approach},
  author = {Nikhil Kotecha},
  journal= {arXiv preprint arXiv:1812.01060},
  year   = {2018}
}

Comments

42 pages

R2 v1 2026-06-23T06:30:06.563Z