# Acoustic Echo Cancellation using Residual U-Nets

arXiv: https://arxiv.org/abs/2109.09686 · HTML: https://mlsanity.com/paper/2109.09686/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 31 references that are in the map.
- First posted on arXiv 20 Sep 2021.

## Builds on (most cited first, 8 of 8)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Road Extraction by Deep Residual U-Net](https://mlsanity.com/paper/1711.10684/) (2017)
- [An Open source Implementation of ITU-T Recommendation P.808 with Validation](https://mlsanity.com/paper/2005.08138/) (2020)
- [Weighted Speech Distortion Losses for Neural-network-based Real-time Speech Enhancement](https://mlsanity.com/paper/2001.10601/) (2020)
- [Gleason Grading of Histology Prostate Images through Semantic Segmentation via Residual U-Net](https://mlsanity.com/paper/2005.11368/) (2020)
- [Multi-channel U-Net for Music Source Separation](https://mlsanity.com/paper/2003.10414/) (2020)
- [ICASSP 2021 Acoustic Echo Cancellation Challenge: Datasets, Testing Framework, and Results](https://mlsanity.com/paper/2009.04972/) (2020)
- [Nonlinear Residual Echo Suppression Based on Multi-stream Conv-TasNet](https://mlsanity.com/paper/2005.07631/) (2020)

## Abstract (arXiv)

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.