A Small-footprint Acoustic Echo Cancellation Solution for Mobile Full-Duplex Speech Interactions
This work addresses echo cancellation for mobile speech interactions, offering incremental improvements in robustness and deployment efficiency.
The paper tackled acoustic echo cancellation in mobile full-duplex speech interactions by developing a neural network-based solution with data augmentation and progressive learning, achieving improvements in Echo Return Loss Enhancement, Perceptual Evaluation of Speech Quality, and downstream tasks like Voice Activity Detection and Automatic Speech Recognition.
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.