Residual acoustic echo suppression based on efficient multi-task convolutional neural network
This work addresses echo degradation for users in voice communication systems, presenting an incremental improvement with a novel loss function and multi-task learning approach.
The paper tackled residual acoustic echo in voice communication systems by proposing a real-time suppression method using an efficient multi-task convolutional neural network, achieving effective echo suppression under various conditions.
Acoustic echo degrades the user experience in voice communication systems thus needs to be suppressed completely. We propose a real-time residual acoustic echo suppression (RAES) method using an efficient convolutional neural network. The double talk detector is used as an auxiliary task to improve the performance of RAES in the context of multi-task learning. The training criterion is based on a novel loss function, which we call as the suppression loss, to balance the suppression of residual echo and the distortion of near-end signals. The experimental results show that the proposed method can efficiently suppress the residual echo under different circumstances.