Active Speech Enhancement: Active Speech Denoising Decliping and Deveraberation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yaish, Ofir, Mishaly, Yehuda, Nachmani, Eliya
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909620786692096
author Yaish, Ofir
Mishaly, Yehuda
Nachmani, Eliya
author_facet Yaish, Ofir
Mishaly, Yehuda
Nachmani, Eliya
contents We introduce a new paradigm for active sound modification: Active Speech Enhancement (ASE). While Active Noise Cancellation (ANC) algorithms focus on suppressing external interference, ASE goes further by actively shaping the speech signal -- both attenuating unwanted noise components and amplifying speech-relevant frequencies -- to improve intelligibility and perceptual quality. To enable this, we propose a novel Transformer-Mamba-based architecture, along with a task-specific loss function designed to jointly optimize interference suppression and signal enrichment. Our method outperforms existing baselines across multiple speech processing tasks -- including denoising, dereverberation, and declipping -- demonstrating the effectiveness of active, targeted modulation in challenging acoustic environments.
format Preprint
id arxiv_https___arxiv_org_abs_2505_16911
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Active Speech Enhancement: Active Speech Denoising Decliping and Deveraberation
Yaish, Ofir
Mishaly, Yehuda
Nachmani, Eliya
Audio and Speech Processing
Artificial Intelligence
We introduce a new paradigm for active sound modification: Active Speech Enhancement (ASE). While Active Noise Cancellation (ANC) algorithms focus on suppressing external interference, ASE goes further by actively shaping the speech signal -- both attenuating unwanted noise components and amplifying speech-relevant frequencies -- to improve intelligibility and perceptual quality. To enable this, we propose a novel Transformer-Mamba-based architecture, along with a task-specific loss function designed to jointly optimize interference suppression and signal enrichment. Our method outperforms existing baselines across multiple speech processing tasks -- including denoising, dereverberation, and declipping -- demonstrating the effectiveness of active, targeted modulation in challenging acoustic environments.
title Active Speech Enhancement: Active Speech Denoising Decliping and Deveraberation
topic Audio and Speech Processing
Artificial Intelligence
url https://arxiv.org/abs/2505.16911