Multi-Channel Acoustic Echo Cancellation Based on Direction-of-Arrival Estimation

TL;DR

This paper introduces a novel multi-channel acoustic echo cancellation method that uses sound source direction estimation to improve echo removal, leveraging spatial cues for better speech quality in various environments.

Contribution

A two-stage algorithm combining sound source direction prediction with multi-channel AEC, enhancing performance over existing methods with robust generalization.

Findings

Outperforms baseline approaches in echo cancellation quality

Demonstrates robustness across diverse acoustic environments

Effectively leverages spatial cues for improved speech clarity

Abstract

Acoustic echo cancellation (AEC) is an important speech signal processing technology that can remove echoes from microphone signals to enable natural-sounding full-duplex speech communication. While single-channel AEC is widely adopted, multi-channel AEC can leverage spatial cues afforded by multiple microphones to achieve better performance. Existing multi-channel AEC approaches typically combine beamforming with deep neural networks (DNN). This work proposes a two-stage algorithm that enhances multi-channel AEC by incorporating sound source directional cues. Specifically, a lightweight DNN is first trained to predict the sound source directions, and then the predicted directional information, multi-channel microphone signals, and single-channel far-end signal are jointly fed into an AEC network to estimate the near-end signal. Evaluation results show that the proposed algorithm outperforms baseline approaches and exhibits robust generalization across diverse acoustic environments.