Gesper: A Unified Framework for General Speech Restoration

Jun Chen, Yupeng Shi, Wenzhe Liu, Wei Rao, Shulin He, Andong Li, Yannan Wang, Zhiyong Wu, Shidong Shang, Chengshi Zheng

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{chen2023gesper,
  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},
  title = {{Gesper: A Unified Framework for General Speech Restoration}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2023},
  doi = {10.1109/icassp49357.2023.10095557},
}

Loading related content...

Figure