Acoustic Echo Cancellation using Residual U-Nets

TL;DR

This paper introduces a novel U-Net based neural network for acoustic echo cancellation, optimized for low latency, and demonstrates competitive performance in a major audio processing challenge.

Contribution

It is the first application of U-Net architectures for acoustic echo cancellation, with optimized hyperparameters for real-time performance.

Findings

Ranked 12th in the ICASSP 2021 AEC Challenge

Achieved an overall mean opinion score of 3.57

Performed well in double-talk scenarios

Abstract

This paper presents an acoustic echo canceler based on a U-Net convolutional neural network for single-talk and double-talk scenarios. U-Net networks have previously been used in the audio processing area for source separation problems because of their ability to reproduce the finest details of audio signals, but to our knowledge, this is the first time they have been used for acoustic echo cancellation (AEC). The U-Net hyperparameters have been optimized to obtain the best AEC performance, but using a reduced number of parameters to meet a latency restriction of 40 ms. The training and testing of our model have been carried out within the framework of the 'ICASSP 2021 AEC Challenge' organized by Microsoft. We have trained the optimized U-Net model with a synthetic dataset only (S-U-Net) and with a synthetic dataset and the single-talk set of a real dataset (SR-U-Net), both datasets were released for the challenge. The S-U-Net model presented better results for double-talk scenarios, thus their inferred near-end signals from the blind testset were submitted to the challenge. Our canceler ranked 12th among 17 teams, and 5th among 10 academia teams, obtaining an overall mean opinion score of 3.57.