Saved in:
Bibliographic Details
Main Authors: Makris, Dimos, Barják, András, Kaliakatsos-Papakostas, Maximos
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.10256
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916000231849984
author Makris, Dimos
Barják, András
Kaliakatsos-Papakostas, Maximos
author_facet Makris, Dimos
Barják, András
Kaliakatsos-Papakostas, Maximos
contents Most recent advances in audio dereverberation focus almost exclusively on speech, leaving percussive and drum signals largely unexplored despite their importance in music production. Percussive dereverberation poses distinct challenges due to sharp transients and dense temporal structure. In this work, we propose a cold diffusion framework for dereverberating stereo drum stems (downmixes), modeling reverberation as a deterministic degradation process that progressively transforms anechoic signals into reverberant ones. We investigate two reverse-process parameterizations, Direct (next-state) and a Delta-normalized residual (velocity-style) prediction, and implement the framework using both a UNet and a diffusion Transformer backbone. The models are trained and evaluated on curated datasets comprising both acoustic and electronic drum recordings, with reverberation generated using a combination of synthetic and real room impulse responses. Extensive experiments on in-domain and fully out-of-domain test sets demonstrate that the proposed method consistently outperforms strong score-based and conditional diffusion baselines, evaluated using signal-based and perceptual metrics tailored to percussive audio.
format Preprint
id arxiv_https___arxiv_org_abs_2605_10256
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Cold Diffusion Approach for Percussive Dereverberation
Makris, Dimos
Barják, András
Kaliakatsos-Papakostas, Maximos
Sound
Artificial Intelligence
Most recent advances in audio dereverberation focus almost exclusively on speech, leaving percussive and drum signals largely unexplored despite their importance in music production. Percussive dereverberation poses distinct challenges due to sharp transients and dense temporal structure. In this work, we propose a cold diffusion framework for dereverberating stereo drum stems (downmixes), modeling reverberation as a deterministic degradation process that progressively transforms anechoic signals into reverberant ones. We investigate two reverse-process parameterizations, Direct (next-state) and a Delta-normalized residual (velocity-style) prediction, and implement the framework using both a UNet and a diffusion Transformer backbone. The models are trained and evaluated on curated datasets comprising both acoustic and electronic drum recordings, with reverberation generated using a combination of synthetic and real room impulse responses. Extensive experiments on in-domain and fully out-of-domain test sets demonstrate that the proposed method consistently outperforms strong score-based and conditional diffusion baselines, evaluated using signal-based and perceptual metrics tailored to percussive audio.
title A Cold Diffusion Approach for Percussive Dereverberation
topic Sound
Artificial Intelligence
url https://arxiv.org/abs/2605.10256