Saved in:
Bibliographic Details
Main Authors: Matsumoto, Kazuki, Uchida, Ren, Yatabe, Kohei
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.21684
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908906765156352
author Matsumoto, Kazuki
Uchida, Ren
Yatabe, Kohei
author_facet Matsumoto, Kazuki
Uchida, Ren
Yatabe, Kohei
contents The robustness of deep neural networks (DNNs) can be certified through their Lipschitz continuity, which has made the construction of Lipschitz-continuous DNNs an active research field. However, DNNs for audio processing have not been a major focus due to their poor compatibility with existing results. In this paper, we consider the amplitude modifier (AM), a popular architecture for handling audio signals, and propose its Lipschitz-continuous variants, which we refer to as LipsAM. We prove a sufficient condition for an AM to be Lipschitz continuous and propose two architectures as examples of LipsAM. The proposed architectures were applied to a Plug-and-Play algorithm for speech dereverberation, and their improved stability is demonstrated through numerical experiments.
format Preprint
id arxiv_https___arxiv_org_abs_2603_21684
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LipsAM: Lipschitz-Continuous Amplitude Modifier for Audio Signal Processing and its Application to Plug-and-Play Dereverberation
Matsumoto, Kazuki
Uchida, Ren
Yatabe, Kohei
Sound
Machine Learning
The robustness of deep neural networks (DNNs) can be certified through their Lipschitz continuity, which has made the construction of Lipschitz-continuous DNNs an active research field. However, DNNs for audio processing have not been a major focus due to their poor compatibility with existing results. In this paper, we consider the amplitude modifier (AM), a popular architecture for handling audio signals, and propose its Lipschitz-continuous variants, which we refer to as LipsAM. We prove a sufficient condition for an AM to be Lipschitz continuous and propose two architectures as examples of LipsAM. The proposed architectures were applied to a Plug-and-Play algorithm for speech dereverberation, and their improved stability is demonstrated through numerical experiments.
title LipsAM: Lipschitz-Continuous Amplitude Modifier for Audio Signal Processing and its Application to Plug-and-Play Dereverberation
topic Sound
Machine Learning
url https://arxiv.org/abs/2603.21684