ICASSP 2022 Acoustic Echo Cancellation Challenge

TL;DR

The ICASSP 2022 Acoustic Echo Cancellation Challenge aims to advance AEC research by providing large datasets, new evaluation metrics including speech recognition, and a platform for benchmarking in real-world scenarios.

Contribution

This challenge introduces new datasets, incorporates speech recognition metrics, and expands to mobile scenarios, fostering progress in acoustic echo cancellation research.

Findings

Open sourced large real and synthetic datasets for AEC

Inclusion of speech recognition rate as a challenge metric

Development of online testing and benchmarking tools

Abstract

The ICASSP 2022 Acoustic Echo Cancellation Challenge is intended to stimulate research in acoustic echo cancellation (AEC), which is an important area of speech enhancement and still a top issue in audio communication. This is the third AEC challenge and it is enhanced by including mobile scenarios, adding speech recognition rate in the challenge goal metrics, and making the default sample rate 48 kHz. In this challenge, we open source two large datasets to train AEC models under both single talk and double talk scenarios. These datasets consist of recordings from more than 10,000 real audio devices and human speakers in real environments, as well as a synthetic dataset. We also open source an online subjective test framework and provide an online objective metric service for researchers to quickly test their results. The winners of this challenge are selected based on the average Mean Opinion Score achieved across all different single talk and double talk scenarios, and the speech recognition word acceptance rate.