SSI-Net: A Multi-Stage Speech Signal Improvement System for ICASSP 2023 SSI Challenge
Weixin Zhu, Zilin Wang, Jiuxin Lin, Chang Zeng, Tao Yu
Abstract
The ICASSP 2023 Speech Signal Improvement (SSI) Challenge concentrates on improving the speech signal quality of real-time communication (RTC) systems. In this paper, we introduce the speech signal improvement network (SSI-Net) submitted to the ICASSP 2023 SSI Challenge, which satisfies the real-time condition. The proposed SSI-Net has a multi-stage architecture. We present the time-domain restoration generative adversarial network (TRGAN) in the first restoration stage for speech restoration. Regarding the second enhancement stage, we employ a lightweight multi-scale temporal frequency convolutional network with axial self-attention (MTFAA-Net) called MTFAA-Lite to enhance the fullband speech. In the subjective test on the SSI Challenge blind test set, our proposed SSI-Net yields a P.835 overall mean opinion score (MOS) of 3.190 and a P.804 overall MOS of 3.178, which eventually takes the 3rd place in tracks 1&2.
BibTeX
@inproceedings{icassp2023_ssinetamultistag,
title = {SSI-Net: A Multi-Stage Speech Signal Improvement System for ICASSP 2023 SSI Challenge},
author = {Weixin Zhu and Zilin Wang and Jiuxin Lin and Chang Zeng and Tao Yu},
booktitle = {ICASSP 2023},
year = {2023}
}