Deep Learning for Music

TL;DR

This paper explores using deep neural networks to generate polyphonic music with harmony and melody, aiming for human-like musical compositions through end-to-end learning.

Contribution

It introduces a novel approach of using deep neural networks alone for music generation, moving beyond previous methods focused on single melodies or probabilistic models.

Findings

Achieved generation of polyphonic music with harmony and melody

Demonstrated the effectiveness of end-to-end deep learning models for music creation

Improved upon prior probabilistic and RNN-based methods

Abstract

Our goal is to be able to build a generative model from a deep neural network architecture to try to create music that has both harmony and melody and is passable as music composed by humans. Previous work in music generation has mainly been focused on creating a single melody. More recent work on polyphonic music modeling, centered around time series probability density estimation, has met some partial success. In particular, there has been a lot of work based off of Recurrent Neural Networks combined with Restricted Boltzmann Machines (RNN-RBM) and other similar recurrent energy based models. Our approach, however, is to perform end-to-end learning and generation with deep neural nets alone.