MMM : Exploring Conditional Multi-Track Music Generation with the Transformer

TL;DR

This paper introduces MMM, a Transformer-based system for multi-track music generation that uses separate track sequences and offers interactive control over musical features.

Contribution

It presents a novel multi-track music generation method using Transformers with track-specific sequences and interactive control features.

Findings

Effective multi-track music generation demonstrated.

Interactive control over instrumentation and note density achieved.

Handles long-term dependencies in music sequences.

Abstract

We propose the Multi-Track Music Machine (MMM), a generative system based on the Transformer architecture that is capable of generating multi-track music. In contrast to previous work, which represents musical material as a single time-ordered sequence, where the musical events corresponding to different tracks are interleaved, we create a time-ordered sequence of musical events for each track and concatenate several tracks into a single sequence. This takes advantage of the Transformer's attention-mechanism, which can adeptly handle long-term dependencies. We explore how various representations can offer the user a high degree of control at generation time, providing an interactive demo that accommodates track-level and bar-level inpainting, and offers control over track instrumentation and note density.