Abstract
Denoising Diffusion Probabilistic Models (DDPMs) have made great strides in generating high-quality samples in both discrete and continuous domains.
However, Discrete DDPMs (D3PMs) have yet to be applied to the domain of Symbolic Music.
This work presents the direct generation of Polyphonic Symbolic Music using D3PMs.
Our model exhibits state-of-the-art sample quality, according to current quantitative evaluation metrics, and allows for flexible infilling at the note level.
We further show, that our models are accessible to post-hoc classifier guidance, widening the scope of possible applications.
However, we also cast a critical view on quantitative evaluation of music sample quality via statistical metrics, and present a simple algorithm that can confound our metrics with completely spurious, non-musical samples.
Keywords
- Methods and resources: Machine learning, deep learning, neural models, reinforcement learning
- Application domains: Music and sound
- Theory and philosophy of arts and creativity in AI systems: Autonomous creative or artistic AI
- Theory and philosophy of arts and creativity in AI systems: Evaluation of artistic or creative outputs produced by AI Systems
