A Small-footprint Acoustic Echo Cancellation Solution for Mobile Full-Duplex Speech Interactions

TL;DR

This paper introduces a neural network-based, small-footprint Acoustic Echo Cancellation solution optimized for mobile devices, improving speech quality and downstream speech processing tasks in full-duplex interactions.

Contribution

It presents a robust, low-latency AEC model with data augmentation, progressive learning, and tailored post-processing for enhanced mobile speech interaction performance.

Findings

Effective echo suppression demonstrated in empirical tests.

Significant improvements in VAD and ASR accuracy.

Model suitable for real-time mobile deployment.

Abstract

In full-duplex speech interaction systems, effective Acoustic Echo Cancellation (AEC) is crucial for recovering echo-contaminated speech. This paper presents a neural network-based AEC solution to address challenges in mobile scenarios with varying hardware, nonlinear distortions and long latency. We first incorporate diverse data augmentation strategies to enhance the model's robustness across various environments. Moreover, progressive learning is employed to incrementally improve AEC effectiveness, resulting in a considerable improvement in speech quality. To further optimize AEC's downstream applications, we introduce a novel post-processing strategy employing tailored parameters designed specifically for tasks such as Voice Activity Detection (VAD) and Automatic Speech Recognition (ASR), thus enhancing their overall efficacy. Finally, our method employs a small-footprint model with streaming inference, enabling seamless deployment on mobile devices. Empirical results demonstrate effectiveness of the proposed method in Echo Return Loss Enhancement and Perceptual Evaluation of Speech Quality, alongside significant improvements in both VAD and ASR results.