Multi-Discriminator Noise Suppression Algorithm Based on Improved CMGAN for Low Signal-to-Noise Ratio Scenarios-Reference-Cited by-同舟云学术

Multi-Discriminator Noise Suppression Algorithm Based on Improved CMGAN for Low Signal-to-Noise Ratio Scenarios

Published:2023-10-20 Issue: Volume:33 Page:384-389
ISSN:
Container-title:Proceedings of the 2023 7th International Conference on Electronic Information Technology and Computer Engineering
language:
Short-container-title:

Author:

Zhao Dinghao¹^ORCID,Luo Liyan¹^ORCID,Wang Mei²^ORCID,Zhou Zou¹^ORCID,Fan Xiaoqing¹^ORCID

Affiliation:

1. School of Information and Communication, Guilin University of Electronic Technology, China

2. School of Information Science & Engineering, China

Funder

This research was funded by the National Natural Science Foundation of China

the Innovation Project of Guangxi Graduate Education

the Project of Guangxi Technology Base and Talent Special Project

the Project of Guangxi Natural Science Foundation

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3650400.3650462

Reference17 articles.

1. I. Goodfellow: Generative adversarial nets. Advances in neural information processing systems, pp. 2672–2680, 2014.

2. Yu GC, Li AD: Dual-branch attention-in-attention transformer for single-channel speech enhancement, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7847–7851. IEEE, Singapore, Singapore, 2022.

3. S.-W. Fu, C.-F. Liao: MetricGAN: Generative adversarial networks based black-box metric scores optimization for speech enhancement, in International Conference on Machine Learning. pp. 2031-2041. MLR-JOURNAL MACHINE LEARNING RESEARCH, Long Beach, CA, 2019.

4. S. Chen , Continuous speech separation with conformer, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5749–5753. IEEE, ELECTR NETWORK, 2021.

5. Cao R: CMGAN: Conformer-based metric GAN for speech enhancement. arXiv preprint arXiv:2203.15149, 2022.