@inproceedings{2830928e6f6d4831a5f1d8106e52c309,
title = "Rad-Net: A Repairing and Denoising Network for Speech Signal Improvement",
abstract = "This paper introduces our repairing and denoising network (RaD-Net) for the ICASSP 2024 Speech Signal Improvement (SSI) Challenge. We extend our previous framework based on a two-stage network and propose an upgraded model. Specifically, we replace the repairing network with COM-Net from TEA-PSE. In addition, multi-resolution discriminators and multi-band discriminators are adopted in the training stage. Finally, we use a three-step training strategy to optimize our model. We submit two models with different sets of parameters to meet the RTF requirement of the two tracks.",
keywords = "generative adversarial network, two-stage",
author = "Mingshuai Liu and Zhuangqi Chen and Xiaopeng Yan and Yuanjun Lv and Xianjun Xia and Chuanzeng Huang and Yijian Xiao and Lei Xie",
note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops, ICASSPW 2024 ; Conference date: 14-04-2024 Through 19-04-2024",
year = "2024",
doi = "10.1109/ICASSPW62465.2024.10626968",
language = "英语",
series = "2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops, ICASSPW 2024 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "49--50",
booktitle = "2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops, ICASSPW 2024 - Proceedings",
}