[3Win5] Poster session 3

[3Win5-28] Music Diffusion Model Using Discrete Diffusion Processes

〇Hiromu Fukumoto¹, Toshiaki Omori¹ (1.Kobe University)

Keywords:diffusion model, music generation

In this study, we propose a music diffusion model (MusicDiffusion) based on discrete diffusion process. To realize music generation with substantial temporal structure, we employ discrete latent space model and integrate the extracted latent space with diffusion modeling. By compressing music signals into compact latent representations, the proposed method reduces dimensionality while preserving essential musical characteristics.