Plug-and-play audio restoration with diffusion denoiser

Plug-and-play audio restoration with diffusion denoiser

Paper in proceedings (conference paper)

There have been a plethora of methods developed to tackle diverse audio reconstruction problems. Recently, deep generative models have affected this field strongly, some of them allowing to solve multiple problems with only a minimal need for adaptation. However, long inference times still represent a barrier to their real-world deployment. We propose a plug-and-play approach to audio reconstruction enabling a shorter duration of signal generation. We present our approach on a number of inverse problems, all evaluated on a piano sound dataset. Subjectively, the proposed strategy performs competitively with recent methods, however, this is rarely reflected by objective metrics.

There have been a plethora of methods developed to tackle diverse audio reconstruction problems. Recently, deep generative models have affected this field strongly, some of them allowing to solve multiple problems with only a minimal need for adaptation. However, long inference times still represent a barrier to their real-world deployment. We propose a plug-and-play approach to audio reconstruction enabling a shorter duration of signal generation. We present our approach on a number of inverse problems, all evaluated on a piano sound dataset. Subjectively, the proposed strategy performs competitively with recent methods, however, this is rarely reflected by objective metrics.

diffusion model, plug-and-play, audio restoration, reconstruction, declipping, denoising, inpainting

diffusion model, plug-and-play, audio restoration, reconstruction, declipping, denoising, inpainting

ŠVENTO, M.; RAJMIC, P.; MOKRÝ, O.

2025

04.10.2024

IEEE

Aalborg, Denmark

979-8-3503-6185-8

2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)

115

119

5

https://ieeexplore.ieee.org/document/10694642

http://hdl.handle.net/