@inproceedings{c2ff7cc51dd049d6932cdc3df05e5b15,
title = "DESNet: A Multi-Channel Network for Simultaneous Speech Dereverberation, Enhancement and Separation",
abstract = "In this paper, we propose a multi-channel network for simultaneous speech dereverberation, enhancement and separation (DESNet). To enable gradient propagation and joint optimization, we adopt the attentional selection mechanism of the multi-channel features, which is originally proposed in end-to-end unmixing, fixed-beamforming and extraction (E2E-UFE) structure. Furthermore, the novel deep complex convolutional recurrent network (DCCRN) is used as the structure of the speech unmixing and the neural network based weighted prediction error (WPE) is cascaded before-hand for speech dereverberation. We also introduce the staged SNR strategy and symphonic loss for the training of the network to further improve the final performance. Experiments show that in non-dereverberated case, the proposed DESNet outperforms DCCRN and most state-of-the-art structures in speech enhancement and separation, while in dereverberated scenario, DESNet also shows improvements over the cascaded WPE-DCCRN networks.",
keywords = "enhancement, multi-channel, separation, speech dereverberation, staged SNR, symphonic loss",
author = "Yihui Fu and Jian Wu and Yanxin Hu and Mengtao Xing and Lei Xie",
note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE Spoken Language Technology Workshop, SLT 2021 ; Conference date: 19-01-2021 Through 22-01-2021",
year = "2021",
month = jan,
day = "19",
doi = "10.1109/SLT48900.2021.9383604",
language = "英语",
series = "2021 IEEE Spoken Language Technology Workshop, SLT 2021 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "857--864",
booktitle = "2021 IEEE Spoken Language Technology Workshop, SLT 2021 - Proceedings",
}