Unsupervised Estimation of Nonlinear Audio Effects: Comparing Diffusion-based and Adversarial Approaches

Loading...
Thumbnail Image

Access rights

openAccess
CC BY
publishedVersion

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa

Date

Major/Subject

Mcode

Degree programme

Language

en

Pages

8

Series

Proceedings of the 28th International Conference on Digital Audio Effects, pp. 366-373, Proceedings of the International Conference on Digital Audio Effects

Abstract

Accurately estimating nonlinear audio effects without access to paired input-output signals remains a challenging problem. This work studies unsupervised probabilistic approaches for solving this task. We introduce a method, novel for this application, based on diffusion generative models for blind system identification, en- abling the estimation of unknown nonlinear effects using black- and gray-box models. This study compares this method with a previously proposed adversarial approach, analyzing the perfor- mance of both methods under different parameterizations of the effect operator and varying lengths of available effected record- ings. Through experiments on guitar distortion effects, we show that the diffusion-based approach provides more stable results and is less sensitive to data availability, while the adversarial approach is superior at estimating more pronounced distortion effects. Our findings contribute to the robust unsupervised blind estimation of audio effects, demonstrating the potential of diffusion models for system identification in music technology.

Description

Keywords

Other note

Citation

Moliner Juanpere, E, Švento, M, Wright, A, Juvela, L, Rajmic, P & Välimäki, V 2025, Unsupervised Estimation of Nonlinear Audio Effects: Comparing Diffusion-based and Adversarial Approaches. in Proceedings of the 28th International Conference on Digital Audio Effects. Proceedings of the International Conference on Digital Audio Effects, DAFx, pp. 366-373, International Conference on Digital Audio Effects, Ancona, Italy, 02/09/2025. < https://www.dafx.de/paper-archive/2025/DAFx25_paper_75.pdf >