Why Not Put a Microphone Near the Loudspeaker? A New Paradigm for Acoustic Echo Cancellation

TL;DR

This paper presents a novel dual-microphone setup with preprocessing and neural network-based suppression to improve acoustic echo cancellation in environments with nonlinear distortions and complex acoustics.

Contribution

Introduces a dual-microphone configuration with a preprocessing module and deep neural network for enhanced nonlinear acoustic echo cancellation.

Findings

Outperforms baseline methods on matched test sets.

Achieves significant gains on mismatched datasets.

Effective in practical nonlinear environments.

Abstract

Acoustic echo cancellation (AEC) remains challenging in real-world environments due to nonlinear distortions caused by low-cost loudspeakers and complex room acoustics. To mitigate these issues, we introduce a dual-microphone configuration, where an auxiliary reference microphone is placed near the loudspeaker to capture the nonlinearly distorted far-end signal. Although this reference signal is contaminated by near-end speech, we propose a preprocessing module based on Wiener filtering to estimate a compressed time-frequency mask to suppress near-end components. This purified reference signal enables a more effective linear AEC stage, whose residual error signal is then fed to a deep neural network for joint residual echo and noise suppression. Evaluation results show that our method outperforms baseline approaches on matched test sets. To evaluate its robustness under strong nonlinearities, we further test it on a mismatched dataset and observe that it achieves substantial performance gains. These results demonstrate its effectiveness in practical scenarios where the nonlinear distortions are typically unknown.