KS-Net: Multi-band joint speech restoration and enhancement network for 2024 ICASSP SSI Challenge
Sound
2024-02-06 v1 Audio and Speech Processing
Abstract
This paper presents the speech restoration and enhancement system created by the 1024K team for the ICASSP 2024 Speech Signal Improvement (SSI) Challenge. Our system consists of a generative adversarial network (GAN) in complex-domain for speech restoration and a fine-grained multi-band fusion module for speech enhancement. In the blind test set of SSI, the proposed system achieves an overall mean opinion score (MOS) of 3.49 based on ITU-T P.804 and a Word Accuracy Rate (WAcc) of 0.78 for the real-time track, as well as an overall P.804 MOS of 3.43 and a WAcc of 0.78 for the non-real-time track, ranking 1st in both tracks.
Keywords
Cite
@article{arxiv.2402.01808,
title = {KS-Net: Multi-band joint speech restoration and enhancement network for 2024 ICASSP SSI Challenge},
author = {Guochen Yu and Runqiang Han and Chenglin Xu and Haoran Zhao and Nan Li and Chen Zhang and Xiguang Zheng and Chao Zhou and Qi Huang and Bing Yu},
journal= {arXiv preprint arXiv:2402.01808},
year = {2024}
}
Comments
Accepted to ICASSP 2024; Rank 1st in ICASSP 2024 Speech Signal Improvement (SSI) Challenge