Symbolic Music Generation with Diffusion Models
arXiv:2103.16091
Abstract
Score-based generative models and diffusion probabilistic models have been successful at generating high-quality samples in continuous domains such as images and audio. However, due to their Langevin-inspired sampling mechanisms, their application to discrete and sequential data has been limited. In this work, we present a technique for training diffusion models on sequential data by parameterizing the discrete domain in the continuous latent space of a pre-trained variational autoencoder. Our method is non-autoregressive and learns to generate sequences of latent embeddings through the reverse process and offers parallel generation with a constant number of iterative refinement steps. We apply this technique to modeling symbolic music and show strong unconditional generation and post-hoc conditional infilling results compared to autoregressive language models operating over the same continuous embeddings.
ISMIR 2021
References in corpus (7)
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- GANSynth: Adversarial Neural Audio Synthesis
- Improved Techniques for Training Score-Based Generative Models
- Jukebox: A Generative Model for Music
- Counterpoint by Convolution
- DDSP: Differentiable Digital Signal Processing
- PIANOTREE VAE: Structured Representation Learning for Polyphonic Music
Cited by in corpus (6)
- Structured Denoising Diffusion Models in Discrete State-Spaces
- CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation
- On Fast Sampling of Diffusion Probabilistic Models
- Gotta Go Fast When Generating Data with Score-Based Models
- Score-based Generative Modeling in Latent Space
- D2C: Diffusion-Denoising Models for Few-shot Conditional Generation