A-Muze-Net: Music Generation by Composing the Harmony based on the Generated Melody

TL;DR

This paper introduces A-Muze-Net, a novel approach for generating piano MIDI files by first creating a melody and then composing harmony conditioned on that melody, with scale-invariant representations and enriched note addition.

Contribution

The method models right and left hand parts separately, with the left hand conditioned on the right, and employs scale-invariant representations for improved music generation.

Findings

Significant improvement over state-of-the-art methods.

Effective conditioning of harmony on melody.

Enhanced musical diversity through random note addition.

Abstract

We present a method for the generation of Midi files of piano music. The method models the right and left hands using two networks, where the left hand is conditioned on the right hand. This way, the melody is generated before the harmony. The Midi is represented in a way that is invariant to the musical scale, and the melody is represented, for the purpose of conditioning the harmony, by the content of each bar, viewed as a chord. Finally, notes are added randomly, based on this chord representation, in order to enrich the generated audio. Our experiments show a significant improvement over the state of the art for training on such datasets, and demonstrate the contribution of each of the novel components.