LABNet: A Lightweight Attentive Beamforming Network for Ad-hoc Multichannel Microphone Invariant Real-Time Speech Enhancement

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yan, Haoyin, Zhang, Jie, Jiang, Chengqian, Zhang, Shuang
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909754474889216
author Yan, Haoyin
Zhang, Jie
Jiang, Chengqian
Zhang, Shuang
author_facet Yan, Haoyin
Zhang, Jie
Jiang, Chengqian
Zhang, Shuang
contents Multichannel speech enhancement (SE) aims to restore clean speech from noisy measurements by leveraging spatiotemporal signal features. In ad-hoc array conditions, microphone invariance (MI) requires systems to handle different microphone numbers and array geometries. From a practical perspective, multichannel recordings inevitably increase the computational burden for edge-device applications, highlighting the necessity of lightweight and efficient deployments. In this work, we propose a lightweight attentive beamforming network (LABNet) to integrate MI in a low-complexity real-time SE system. We design a three-stage framework for efficient intra-channel modeling and inter-channel interaction. A cross-channel attention module is developed to aggregate features from each channel selectively. Experimental results demonstrate our LABNet achieves impressive performance with ultra-light resource overhead while maintaining the MI, indicating great potential for ad-hoc array processing. The code is available:https://github.com/Jokejiangv/LABNet.git
format Preprint
id arxiv_https___arxiv_org_abs_2507_16190
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LABNet: A Lightweight Attentive Beamforming Network for Ad-hoc Multichannel Microphone Invariant Real-Time Speech Enhancement
Yan, Haoyin
Zhang, Jie
Jiang, Chengqian
Zhang, Shuang
Sound
Audio and Speech Processing
Multichannel speech enhancement (SE) aims to restore clean speech from noisy measurements by leveraging spatiotemporal signal features. In ad-hoc array conditions, microphone invariance (MI) requires systems to handle different microphone numbers and array geometries. From a practical perspective, multichannel recordings inevitably increase the computational burden for edge-device applications, highlighting the necessity of lightweight and efficient deployments. In this work, we propose a lightweight attentive beamforming network (LABNet) to integrate MI in a low-complexity real-time SE system. We design a three-stage framework for efficient intra-channel modeling and inter-channel interaction. A cross-channel attention module is developed to aggregate features from each channel selectively. Experimental results demonstrate our LABNet achieves impressive performance with ultra-light resource overhead while maintaining the MI, indicating great potential for ad-hoc array processing. The code is available:https://github.com/Jokejiangv/LABNet.git
title LABNet: A Lightweight Attentive Beamforming Network for Ad-hoc Multichannel Microphone Invariant Real-Time Speech Enhancement
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2507.16190