Acoustic Echo Cancellation with Cross-Domain Learning
Published in
Interspeech(2021)External Links:
TL
TL;DR
This paper proposes the Cross-Domain Echo-Controller (CDEC), submitted to the Interspeech 2021 AEC-Challenge, which achieves an overall MOS score of 3.80, while only using 2.1 million parameters at a system latency of 32ms.
Abstract
This paper proposes the Cross-Domain Echo-Controller (CDEC), submitted to the Interspeech 2021 AEC-Challenge. The algorithm consists of three building blocks: (i) a Time-Delay Compensation (TDC) module, (ii) a frequency-domain block-based Acoustic Echo Canceler (AEC), and (iii) a Time-Domain Neural-Network (TD-NN) used as a post-processor. Our system achieves an overall MOS score of 3.80, while only using 2.1 million parameters at a system latency of 32ms.