2021/03/30 by Gautam Mittal, Mittal, Gautam, Jesse Engel +5 · 9 citations
Computer Science · Physics and Astronomy · #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Model Reduction and Neural Networks #Music and Audio Processing #Sound (cs.SD) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2103.16091
openalex publication_date 2021/03/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Score-based generative models and diffusion probabilistic models have been successful at generating high-quality samples in a variety of continuous domains. However, due to their Langevin-inspired sampling mechanisms, their application to discrete symbolic music data has been limited. In this work, we present a technique for training diffusion models on symbolic music 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 show strong unconditional generation and post-hoc conditional infilling results compared to autoregressive language models operating over the same continuous embeddings.