Year: 2025
Type: conference-paper
Abstract: 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 these tasks into a single framework, as both involve generating musically aligned parts and can be seen as facets of the same generative process. In this work, we introduce a latent diffusion-based multi-track generation model capable of both source separation and multi-track music synthesis by learning the joint probability distribution of tracks sharing a musical context. Our model also enables arrangement generation by creating any subset of tracks given the others. We trained our model on the Slakh2100 dataset, compared it with an existing simultaneous generation and separation model, and observed significant improvements across objective metrics for source separation, music, and arrangement generation tasks. Sound examples are available at https://msg-ld.github.io/.
Authors: Tornike Karchkhadze, Mohammad Rasool Izadi, Shlomo Dubnov
Institutions: University of California San Diego, Bose (United States)
Language: English
Topic: Music and Audio Processing
Subfield: Signal Processing
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4408352240