Dual-Path Dilated Convolutional Recurrent Network with Group Attention for Multi-Channel Speech Enhancement
Jiaming Cheng, Cong Pang, Ruiyu Liang, Jingjie Fan, Li Zhao
Abstract
This paper proposes a dual-path convolutional recurrent network with group attention for ICASSP Signal Processing Grand Challenge: L3DAS23 Challenge. We design a structure based on convolutional encoder-decoder, and frequency-time blocks based on group attention are introduced in the middle. The encoder is used to extract the local representation from the complex spectrum, the correlation along the frequency axis and the time axis are captured through groups of time-frequency processing modules and the key information in the feature flow is extracted by the group attention. As a result, our system ranks the 1st place of the 3D speech enhancement task in L3DAS23 Challenge, and significantly outperforms the baseline, while achieving 0.101 WER and 0.902 STOI on the blind test-set.
BibTeX
@inproceedings{icassp2023_dualpathdilatedc,
title = {Dual-Path Dilated Convolutional Recurrent Network with Group Attention for Multi-Channel Speech Enhancement},
author = {Jiaming Cheng and Cong Pang and Ruiyu Liang and Jingjie Fan and Li Zhao},
booktitle = {ICASSP 2023},
year = {2023}
}