EchoFree: Towards Ultra Lightweight and Efficient Neural Acoustic Echo Cancellation

TL;DR

EchoFree introduces an ultra lightweight neural acoustic echo cancellation framework that combines linear filtering with a neural post filter, achieving high performance with minimal computational resources.

Contribution

We propose EchoFree, a novel neural AEC framework with a neural post filter on spectral features and a two-stage SSL-based optimization, enhancing efficiency and performance.

Findings

Outperforms existing low-complexity AEC models

Achieves performance comparable to state-of-the-art lightweight models

Uses only 278K parameters and 30 MMACs computational complexity

Abstract

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.