{"ID":2891599,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.16190","arxiv_id":"2507.16190","title":"LABNet: A Lightweight Attentive Beamforming Network for Ad-hoc Multichannel Microphone Invariant Real-Time Speech Enhancement","abstract":"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","short_abstract":"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 recordin...","url_abs":"https://arxiv.org/abs/2507.16190","url_pdf":"https://arxiv.org/pdf/2507.16190v3","authors":"[\"Haoyin Yan\",\"Jie Zhang\",\"Chengqian Jiang\",\"Shuang Zhang\"]","published":"2025-07-22T03:07:30Z","proceeding":"cs.SD","tasks":"[\"cs.SD\",\"eess.AS\"]","methods":"[]","has_code":false,"code_links":[{"ID":611895,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2891599,"paper_url":"https://arxiv.org/abs/2507.16190","paper_title":"LABNet: A Lightweight Attentive Beamforming Network for Ad-hoc Multichannel Microphone Invariant Real-Time Speech Enhancement","repo_url":"https://github.com/Jokejiangv/LABNet.git","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}