Residual acoustic echo suppression based on efficient multi-task convolutional neural network

TL;DR

This paper introduces a real-time residual acoustic echo suppression method using an efficient multi-task convolutional neural network, incorporating a double talk detector and a novel loss function to improve echo suppression while preserving near-end signals.

Contribution

It presents a novel multi-task CNN architecture with a suppression loss function for effective real-time residual echo suppression in voice communication systems.

Findings

Efficient suppression of residual echo across various scenarios.

Improved performance with the multi-task learning approach.

Real-time processing capability demonstrated.

Abstract

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.