{"ID":5675327,"CreatedAt":"2026-07-03T01:40:09.565152011Z","UpdatedAt":"2026-07-07T01:06:03.009715918Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.02062","arxiv_id":"2607.02062","title":"LMPAN: A Lightweight Multi-Path Alignment Network for Joint Full-Duplex Acoustic Echo Cancellation and Noise Suppression","abstract":"We propose a lightweight multi-path alignment network (LMPAN) for on-device joint acoustic echo cancellation (AEC) and noise suppression (NS) in full-duplex spoken dialogue systems. To address hardware-induced distortions and dynamic acoustic conditions, we introduce three core innovations: (1) a multi-path alignment stage correcting temporal and energy mismatches across reference, linear AEC (LAEC) output, and microphone signals; (2) an attention-based mechanism that dynamically integrates enhanced LAEC and microphone features under varying acoustic scenarios; (3) a post-filtering module with a dynamic target generation strategy for downstream tasks (ASR, VAD). Furthermore, we adopt a two-stage training framework leveraging self-supervised learning representations to enhance perceptual quality. Experiments show that LMPAN, with only 480K parameters and 126 MACs, achieves performance comparable to the state-of-the-art lightweight model DeepVQE-S, while ensuring real-time inference capability.","short_abstract":"We propose a lightweight multi-path alignment network (LMPAN) for on-device joint acoustic echo cancellation (AEC) and noise suppression (NS) in full-duplex spoken dialogue systems. To address hardware-induced distortions and dynamic acoustic conditions, we introduce three core innovations: (1) a multi-path alignment s...","url_abs":"https://arxiv.org/abs/2607.02062","url_pdf":"https://arxiv.org/pdf/2607.02062v1","authors":"[\"Chengwei Liu\",\"Shaofei Xue\",\"Haoyin Yan\",\"Xiaotao Liang\",\"Zheng Xue\"]","published":"2026-07-02T11:40:03Z","proceeding":"eess.AS","tasks":"[\"eess.AS\"]","methods":"[]","has_code":false}