KS-Net: Multi-band joint speech restoration and enhancement network for 2024 ICASSP SSI Challenge

Autor:	Yu, Guochen, Han, Runqiang, Xu, Chenglin, Zhao, Haoran, Li, Nan, Zhang, Chen, Zheng, Xiguang, Zhou, Chao, Huang, Qi, Yu, Bing
Rok vydání:	2024
Předmět:	Computer Science - Sound Electrical Engineering and Systems Science - Audio and Speech Processing
Druh dokumentu:	Working Paper
Popis:	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. Comment: Accepted to ICASSP 2024; Rank 1st in ICASSP 2024 Speech Signal Improvement (SSI) Challenge
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2402.01808 Zobrazit plný text záznamu View this record from Arxiv