Low-Complexity, Real-Time Joint Neural Echo Control and Speech Enhancement Based On PercepNet

2021/02/10 by Valin, Jean-Marc, Tenneti, Srikanth, Helwani, Karim +2 · 2 citations
#Audio and Speech Processing (eess.AS) #FOS: Electrical engineering #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2102.05245

Abstract

Speech enhancement algorithms based on deep learning have greatly surpassed their traditional counterparts and are now being considered for the task of removing acoustic echo from hands-free communication systems. This is a challenging problem due to both real-world constraints like loudspeaker non-linearities, and to limited compute capabilities in some communication systems. In this work, we propose a system combining a traditional acoustic echo canceller, and a low-complexity joint residual echo and noise suppressor based on a hybrid signal processing/deep neural network (DSP/DNN) approach. We show that the proposed system outperforms both traditional and other neural approaches, while requiring only 5.5% CPU for real-time operation. We further show that the system can scale to even lower complexity levels.

Cited by

• IS³ : Generic Impulsive--Stationary Sound Separation in Acoustic Scenes using Deep Filtering
• EchoFree: Towards Ultra Lightweight and Efficient Neural Acoustic Echo Cancellation

Related

• Deep Learning-Based Joint Control of Acoustic Echo Cancellation, Beamforming and Postfiltering
• Efficient High-Performance Bark-Scale Neural Network for Residual Echo and Noise Suppression
• Nonlinear Acoustic Echo Cancellation with Deep Learning
• NN3A: Neural Network supported Acoustic Echo Cancellation, Noise Suppression and Automatic Gain Control for Real-Time Communications
• Deep Residual Echo Suppression and Noise Reduction: A Multi-Input FCRN Approach in a Hybrid Speech Enhancement System