EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Speech Enhancement Performance Based on the MANNER Network Using Feature Fusion

Shijie Wang, Ji Li, Lei Shao, Hongli Liu, Lihua Zhu, Xiaochen Zhu

Electronics · 07.04.2023 · 12 (8) · 1768

DOI: 10.3390/electronics12081768 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 07.04.2023. Verfasst von Shijie Wang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The problems that the multi-view attention network for noise erasure (MANNER) cannot take into account are the local and global features in the speech enhancement of long sequences. An attention and feature fusion MANNER (AF-MANNER) network is proposed, which improves the multi-view attention (MA) module in MANNER and replaces the global and local attention in the module. AF-MANNER also designs the feature-weighted fusion module to fuse the features of flash attention and neighborhood attention to enhance the feature expression of the network. The final ablation studies show that this network exhibits a good performance in speech enhancement and that its structure is valuable for improving the intelligibility and perceptual quality of speech.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Wang, S., Li, J., Shao, L., Liu, H., Zhu, L., & Zhu, X. (2023). Speech Enhancement Performance Based on the MANNER Network Using Feature Fusion. Electronics, 12(8), 1768. https://doi.org/10.3390/electronics12081768

Vancouver

Wang S, Li J, Shao L, Liu H, Zhu L, Zhu X. Speech Enhancement Performance Based on the MANNER Network Using Feature Fusion. Electronics. 2023;12(8):1768. doi:10.3390/electronics12081768

BibTeX
@article{Wang2023,
  author = {Wang, Shijie and Li, Ji and Shao, Lei and Liu, Hongli and Zhu, Lihua and Zhu, Xiaochen},
  title = {Speech Enhancement Performance Based on the MANNER Network Using Feature Fusion},
  journal = {Electronics},
  year = {2023},
  volume = {12},
  number = {8},
  pages = {1768},
  doi = {10.3390/electronics12081768}
}
Kostenlos starten →