In this work, we define a diffusion-based generative model capable of both music synthesis
and source separation by learning the score of the joint probability density of sources …

Autoregressive models have achieved impressive results over a wide range of domains in
terms of generation quality and downstream task performance. In the continuous domain, a …

Universal source separation targets at separating the audio sources of an arbitrary mix,
removing the constraint to operate on a specific domain like speech or music. Yet, the …

Diffusion models have recently shown strong potential in both music generation and music
source separation tasks. Although in early stages, a trend is emerging towards integrating …

This thesis proposes a journey into sound processing through deep learning, particularly
generative models, exploring the compositional structure of sound, which is layered in …