# LMPAN: A Lightweight Multi-Path Alignment Network for Joint Full-Duplex Acoustic Echo Cancellation and Noise Suppression

arXiv: https://arxiv.org/abs/2607.02062 · HTML: https://mlsanity.com/paper/2607.02062/

## Key facts

- No citing papers in the map yet (data through 19 Oct 2026).
- Placed in Speech enhancement and noise suppression, one of 11 directions in Speech and audio language models.
- Builds on 23 of its 34 references that are in the map.
- First posted on arXiv 2 Jul 2026.

## Placed in

- Speech and audio language models / [Speech enhancement and noise suppression](https://mlsanity.com/speech/speech-enhancement-and-noise-suppression/)

## Builds on (most cited first, 23 of 23)

- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Results](https://mlsanity.com/paper/2005.13981/) (2020)
- [Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition](https://mlsanity.com/paper/2206.08317/) (2022)
- [ICASSP 2022 Deep Noise Suppression Challenge](https://mlsanity.com/paper/2202.13288/) (2022)
- [A Full-duplex Speech Dialogue Scheme Based On Large Language Models](https://mlsanity.com/paper/2405.19487/) (2024)
- [Data augmentation and loss normalization for deep noise suppression](https://mlsanity.com/paper/2008.06412/) (2020)
- [Vec-Tok Speech: speech vectorization and tokenization for neural speech generation](https://mlsanity.com/paper/2310.07246/) (2023)
- [LLM-Enhanced Dialogue Management for Full-Duplex Spoken Dialogue Systems](https://mlsanity.com/paper/2502.14145/) (2025)
- [AECMOS: A speech quality assessment metric for echo impairment](https://mlsanity.com/paper/2110.03010/) (2021)
- [ICASSP 2022 Acoustic Echo Cancellation Challenge](https://mlsanity.com/paper/2202.13290/) (2022)
- [DeepVQE: Real Time Deep Voice Quality Enhancement for Joint Acoustic Echo Cancellation, Noise Suppression and Dereverberation](https://mlsanity.com/paper/2306.03177/) (2023)
- [ICASSP 2023 Acoustic Echo Cancellation Challenge](https://mlsanity.com/paper/2309.12553/) (2023)
- [Semantic VAD: Low-Latency Voice Activity Detection for Speech Interaction](https://mlsanity.com/paper/2305.12450/) (2023)
- [Multi-Task Deep Residual Echo Suppression with Echo-aware Loss](https://mlsanity.com/paper/2202.06850/) (2022)
- [A study on more realistic room simulation for far-field keyword spotting](https://mlsanity.com/paper/2006.02774/) (2020)
- [SCA: Streaming Cross-attention Alignment for Echo Cancellation](https://mlsanity.com/paper/2211.00589/) (2022)
- [Two-step Band-split Neural Network Approach for Full-band Residual Echo Suppression](https://mlsanity.com/paper/2303.06828/) (2023)
- [Align-ULCNet: Towards Low-Complexity and Robust Acoustic Echo and Noise Reduction](https://mlsanity.com/paper/2410.13620/) (2024)
- [A Closer Look at Wav2Vec2 Embeddings for On-Device Single-Channel Speech Enhancement](https://mlsanity.com/paper/2403.01369/) (2024)
- [EchoFree: Towards Ultra Lightweight and Efficient Neural Acoustic Echo Cancellation](https://mlsanity.com/paper/2508.06271/) (2025)
- [FADI-AEC: Fast Score Based Diffusion Model Guided by Far-end Signal for Acoustic Echo Cancellation](https://mlsanity.com/paper/2401.04283/) (2024)
- [A Small-footprint Acoustic Echo Cancellation Solution for Mobile Full-Duplex Speech Interactions](https://mlsanity.com/paper/2508.07561/) (2025)

## Abstract (arXiv)

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.