Two-Step Band-Split Neural Network Approach For Full-Band Residual Echo Suppression
Zihan Zhang, Shimin Zhang, Mingshuai Liu, Yanhong Leng, Zhe Han, Li Chen, Lei Xie
Abstract
This paper describes a Two-step Band-split Neural Network (TBNN) approach for full-band acoustic echo cancellation. Specifically, after linear filtering, we split the full-band signal into wideband (16KHz) and high-band (16-48KHz) for residual echo removal with lower modeling difficulty. The wide-band signal is processed by an updated gated convolutional recurrent network (GCRN) with U <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> encoder while the high-band signal is processed by a high-band post-filter net with lower complexity. Our approach submitted to ICASSP 2023 AEC Challenge has achieved an overall mean opinion score (MOS) of 4.344 and a word accuracy (WAcc) ratio of 0.795, leading to the 2 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">nd</sup> (tied) in the ranking of the non-personalized track.
BibTeX
@inproceedings{icassp2023_twostepbandsplit,
title = {Two-Step Band-Split Neural Network Approach For Full-Band Residual Echo Suppression},
author = {Zihan Zhang and Shimin Zhang and Mingshuai Liu and Yanhong Leng and Zhe Han and Li Chen and Lei Xie},
booktitle = {ICASSP 2023},
year = {2023}
}