|Ross Cutler (Microsoft, USA), Ando Saabas (Microsoft, USA), Tanel Parnamaa (Microsoft, USA), Markus Loide (Microsoft, USA), Sten Sootla (Microsoft, USA), Marju Purin (Microsoft, USA), Hannes Gamper (Microsoft, USA), Sebastian Braun (Microsoft, USA), Karsten Sorensen (Microsoft, USA), Robert Aichner (Microsoft, USA), Sriram Srinivasan (Microsoft, USA)|
The INTERSPEECH 2021 Acoustic Echo Cancellation Challenge is intended to stimulate research in the area of acoustic echo cancellation (AEC), which is an important part of speech enhancement and still a top issue in audio communication. Many recent AEC studies report good performance on synthetic datasets where the training and testing data may come from the same underlying distribution. However, AEC performance often degrades significantly on real recordings. Also, most of the conventional objective metrics such as echo return loss enhancement and perceptual evaluation of speech quality do not correlate well with subjective speech quality tests in the presence of background noise and reverberation found in realistic environments. 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 5,000 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.