Speech enhancement by CycleGAN using feature map regularization
Journal of Computer and Forensic Sciences · 2023
DOI: 10.5937/jcfs2-45100 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Computer and Forensic Sciences, 2023. Verfasst von Branislav Popović und 1 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben.
Abstract (Originalsprache)
The state-of-the-art results of single-channel speech enhancement were recently obtained by applying the unpaired dataset CycleGAN network approach, which is comparable to the paired dataset neural network approach. As only a relatively small amount of noisy speech data is usually available in applications, an augmented, semi-supervised CycleGAN is proposed. Recently, the feature map regularized CycleGAN approach was proposed and applied to the image transfer task, obtaining significant improvements on several standard image domain transfer databases. In this paper, we use a feature map regularized CycleGAN and combine it with the augmented semi-supervised approach in order to further improve CycleGAN Speech enhancement. Significant improvements in the speech enhancement task by means of several standard measures are obtained by using the proposed approach in comparison to baseline CycleGAN as well as the augmented CycleGAN approach.
Zitieren
APA
Popović, B., & Janev, M. (2023). Speech enhancement by CycleGAN using feature map regularization. Journal of Computer and Forensic Sciences. https://doi.org/10.5937/jcfs2-45100
Vancouver
Popović B, Janev M. Speech enhancement by CycleGAN using feature map regularization. Journal of Computer and Forensic Sciences. 2023. doi:10.5937/jcfs2-45100
BibTeX
@article{Popovi2023,
author = {Popović, Branislav and Janev, Marko},
title = {Speech enhancement by CycleGAN using feature map regularization},
journal = {Journal of Computer and Forensic Sciences},
year = {2023},
doi = {10.5937/jcfs2-45100}
}
EUVIMED