EchoFree: Towards Ultra Lightweight and Efficient Neural Acoustic Echo Cancellation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li, Xingchen, Kang, Boyi, Wang, Ziqian, Zhang, Zihan, Liu, Mingshuai, Fu, Zhonghua, Xie, Lei
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915434696015872
author Li, Xingchen
Kang, Boyi
Wang, Ziqian
Zhang, Zihan
Liu, Mingshuai
Fu, Zhonghua
Xie, Lei
author_facet Li, Xingchen
Kang, Boyi
Wang, Ziqian
Zhang, Zihan
Liu, Mingshuai
Fu, Zhonghua
Xie, Lei
contents In recent years, neural networks (NNs) have been widely applied in acoustic echo cancellation (AEC). However, existing approaches struggle to meet real-world low-latency and computational requirements while maintaining performance. To address this challenge, we propose EchoFree, an ultra lightweight neural AEC framework that combines linear filtering with a neural post filter. Specifically, we design a neural post-filter operating on Bark-scale spectral features. Furthermore, we introduce a two-stage optimization strategy utilizing self-supervised learning (SSL) models to improve model performance. We evaluate our method on the blind test set of the ICASSP 2023 AEC Challenge. The results demonstrate that our model, with only 278K parameters and 30 MMACs computational complexity, outperforms existing low-complexity AEC models and achieves performance comparable to that of state-of-the-art lightweight model DeepVQE-S. The audio examples are available.
format Preprint
id arxiv_https___arxiv_org_abs_2508_06271
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EchoFree: Towards Ultra Lightweight and Efficient Neural Acoustic Echo Cancellation
Li, Xingchen
Kang, Boyi
Wang, Ziqian
Zhang, Zihan
Liu, Mingshuai
Fu, Zhonghua
Xie, Lei
Audio and Speech Processing
In recent years, neural networks (NNs) have been widely applied in acoustic echo cancellation (AEC). However, existing approaches struggle to meet real-world low-latency and computational requirements while maintaining performance. To address this challenge, we propose EchoFree, an ultra lightweight neural AEC framework that combines linear filtering with a neural post filter. Specifically, we design a neural post-filter operating on Bark-scale spectral features. Furthermore, we introduce a two-stage optimization strategy utilizing self-supervised learning (SSL) models to improve model performance. We evaluate our method on the blind test set of the ICASSP 2023 AEC Challenge. The results demonstrate that our model, with only 278K parameters and 30 MMACs computational complexity, outperforms existing low-complexity AEC models and achieves performance comparable to that of state-of-the-art lightweight model DeepVQE-S. The audio examples are available.
title EchoFree: Towards Ultra Lightweight and Efficient Neural Acoustic Echo Cancellation
topic Audio and Speech Processing
url https://arxiv.org/abs/2508.06271