NN3A: Neural Network supported Acoustic Echo Cancellation, Noise Suppression and Automatic Gain Control for Real-Time Communications
This work addresses audio quality issues in real-time communications, but it is incremental as it builds on existing neural network and adaptive filter methods.
The paper tackled the problem of acoustic echo cancellation, noise suppression, and automatic gain control for real-time communications by proposing NN3A, a neural network-supported algorithm that outperformed separate models and an end-to-end alternative, with a trade-off balanced by a novel loss weighting function.
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.