KS-Net：面向2024年ICASSP SSI挑战赛的多频带联合语音恢复与增强网络
KS-Net: Multi-band joint speech restoration and enhancement network for 2024 ICASSP SSI Challenge
AI总结：
针对ICASSP 2024 SSI挑战赛，提出结合复数域GAN与多频带融合的语音恢复增强网络，在实时与非实时赛道均获第一。
摘要：
本文介绍了1024K团队为ICASSP 2024语音信号改善（SSI）挑战赛构建的语音恢复与增强系统。该系统由用于语音恢复的复数域生成对抗网络（GAN）和用于语音增强的细粒度多频带融合模块组成。在SSI盲测集中，所提系统在实时赛道取得了基于ITU-T P.804的总体平均意见分（MOS）3.49和词准确率（WAcc）0.78，在非实时赛道取得了总体P.804 MOS 3.43和WAcc 0.78，在两个赛道均排名第一。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
