Gesper: A Unified Framework for General Speech Restoration
Jun Chen, Yupeng Shi, Wenzhe Liu, Wei Rao, Shulin He, Andong Li, Yannan Wang, Zhiyong Wu
Abstract
This paper describes the legends-tencent team’s real-time General Speech Restoration (Gesper) system submitted to the ICASSP 2023 Speech Signal Improvement (SSI) Challenge. This newly proposed system is a two-stage architecture, in which the speech restoration is performed, and then followed by speech enhancement. We propose a complex spectral mapping-based generative adversarial network (CSM-GAN) as the speech restoration module for the first time. For noise suppression and dereverberation, the enhancement module is presented with fullband-wideband parallel processing. On the blind test set of ICASSP 2023 SSI Challenge, the proposed Gesper system, which satisfies the real-time condition, achieves 3.27 P.804 overall mean opinion score (MOS) and 3.35 P.835 overall MOS, ranked 1st in both track 1 and track 2.
BibTeX
@inproceedings{icassp2023_gesperaunifiedfr,
title = {Gesper: A Unified Framework for General Speech Restoration},
author = {Jun Chen and Yupeng Shi and Wenzhe Liu and Wei Rao and Shulin He and Andong Li and Yannan Wang and Zhiyong Wu and Shidong Shang and Chengshi Zheng},
booktitle = {ICASSP 2023},
year = {2023}
}