NN3A: Neural Network supported Acoustic Echo Cancellation, Noise Suppression and Automatic Gain Control for Real-Time Communications

2021/10/16 by Wang, Ziteng, Na, Yueyue, Tian, Biao +1 · 1 citation
#Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Sound (cs.SD) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2110.08437

Abstract

Acoustic echo cancellation (AEC), noise suppression (NS) and automatic gain control (AGC) are three often required modules for real-time communications (RTC). This paper proposes a neural network supported algorithm for RTC, namely NN3A, which incorporates an adaptive filter and a multi-task model for residual echo suppression, noise reduction and near-end speech activity detection. The proposed algorithm is shown to outperform both a method using separate models and an end-to-end alternative. It is further shown that there exists a trade-off in the model between residual suppression and near-end speech distortion, which could be balanced by a novel loss weighting function. Several practical aspects of training the joint model are also investigated to push its performance to limit.

Cited by

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

Related

• Acoustic Echo Cancellation by Combining Adaptive Digital Filter and Recurrent Neural Network
• Weighted Recursive Least Square Filter and Neural Network based Residual Echo Suppression for the AEC-Challenge
• Residual acoustic echo suppression based on efficient multi-task convolutional neural network
• Low-Complexity, Real-Time Joint Neural Echo Control and Speech Enhancement Based On PercepNet
• Deep Learning-Based Joint Control of Acoustic Echo Cancellation, Beamforming and Postfiltering