MMM : Exploring Conditional Multi-Track Music Generation with the Transformer
This work addresses the problem of generating controllable and structured multi-track music for musicians and AI researchers, though it is incremental as it builds on existing Transformer methods with a novel representation.
The paper tackles multi-track music generation by proposing MMM, a Transformer-based system that represents each track as a separate sequence and concatenates them, enabling better handling of long-term dependencies and offering user control through interactive features like inpainting and instrumentation adjustments.
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.