MMT-BERT: Chord-aware Symbolic Music Generation Based on Multitrack Music Transformer and MusicBERT

TL;DR

This paper introduces MMT-BERT, a novel framework for symbolic multitrack music generation that leverages a new music representation, a chord analysis model, and a fine-tuned MusicBERT discriminator to improve musical coherence and quality.

Contribution

It presents a new symbolic music representation with MusicLang, adapts MusicBERT for generation, and fine-tunes it as a discriminator, addressing data and architecture challenges in symbolic music synthesis.

Findings

Outperforms state-of-the-art methods in music quality.

Enhances musical consonance and human-likeness.

Demonstrates robustness across diverse musical styles.

Abstract

We propose a novel symbolic music representation and Generative Adversarial Network (GAN) framework specially designed for symbolic multitrack music generation. The main theme of symbolic music generation primarily encompasses the preprocessing of music data and the implementation of a deep learning framework. Current techniques dedicated to symbolic music generation generally encounter two significant challenges: training data's lack of information about chords and scales and the requirement of specially designed model architecture adapted to the unique format of symbolic music representation. In this paper, we solve the above problems by introducing new symbolic music representation with MusicLang chord analysis model. We propose our MMT-BERT architecture adapting to the representation. To build a robust multitrack music generator, we fine-tune a pre-trained MusicBERT model to serve as the discriminator, and incorporate relativistic standard loss. This approach, supported by the in-depth understanding of symbolic music encoded within MusicBERT, fortifies the consonance and humanity of music generated by our method. Experimental results demonstrate the effectiveness of our approach which strictly follows the state-of-the-art methods.