ICASSP 2026oral0 citations
VIRTUAL CONSISTENCY FOR AUDIO EDITING
Matthieu Cervera, Francesco Paissan, Mirco Ravanelli, Cem Subakan
Abstract
Free-form, text-based audio editing remains a persistent challenge, despite progress in inversion-based neural methods. Current approaches rely on slow inversion procedures, limiting their practicality. We present a virtual-consistency based audio editing system that bypasses inversion by adapting the sampling process of diffusion models. Our pipeline is model-agnostic, requiring no fine-tuning or architectural changes, and achieves substantial speed-ups over recent neural editing baselines. Crucially, it achieves this efficiency without compromising quality, as demonstrated by quantitative benchmarks and a user study involving 16 participants.
BibTeX
@inproceedings{icassp2026_virtualconsisten,
title = {VIRTUAL CONSISTENCY FOR AUDIO EDITING},
author = {Matthieu Cervera and Francesco Paissan and Mirco Ravanelli and Cem Subakan},
booktitle = {ICASSP 2026},
year = {2026}
}