EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

CBAM-ResNet: A Lightweight ResNet Network Focusing on Time Domain Features for End-to-End Deepfake Speech Detection

Yuezhou Wu, Hua Huang, Zhiri Li, Siling Zhang

Electronics · 17.06.2025 · 14 (12) · 2456

DOI: 10.3390/electronics14122456 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 17.06.2025. Verfasst von Yuezhou Wu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the National Key R&D Program of China, Henan Province Key R&D Special Fund, Civil Aviation Information Technology Research Center, the Civil Aviation Flight University of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the rapid development of synthetic speech and deepfake technology, fake speech poses a severe challenge to voice authentication systems. Traditional detection methods generally rely on manual feature extraction, facing problems such as limited feature expression ability and insufficient cross-scenario generalization performance. To this end, this paper proposes an improved ResNet network based on a Convolutional Block Attention Module (CBAM) for end-to-end fake speech detection. This method introduces channel attention and spatial attention mechanisms into the ResNet network structure to enhance the model’s attention to the temporal characteristics of speech, thereby improving the ability to distinguish between real and fake speech. The proposed model adopts an end-to-end training strategy, directly processes the original spectrogram input, uses the residual structure to alleviate the gradient vanishing problem in the deep network, and enhances the collaborative expression ability of local details and global context through the CBAM module. The experiment is conducted on the ASVspoof2019 LA dataset, and the equal error rate (EER) is used as the main evaluation indicator. The experimental results show that compared with traditional deepfake speech detection methods, the proposed model achieves better performance in indicators such as EER, verifying the effectiveness of the CBAM attention mechanism in forged speech detection.

Förderung

  • the National Key R&D Program of China
  • Henan Province Key R&D Special Fund
  • Civil Aviation Information Technology Research Center, the Civil Aviation Flight University of China
  • Civil Aviation Flight Academy of China Project
  • the Flight Technology and Flight Safety Key Laboratory of CAAC

Zitieren

APA

Wu, Y., Huang, H., Li, Z., & Zhang, S. (2025). CBAM-ResNet: A Lightweight ResNet Network Focusing on Time Domain Features for End-to-End Deepfake Speech Detection. Electronics, 14(12), 2456. https://doi.org/10.3390/electronics14122456

Vancouver

Wu Y, Huang H, Li Z, Zhang S. CBAM-ResNet: A Lightweight ResNet Network Focusing on Time Domain Features for End-to-End Deepfake Speech Detection. Electronics. 2025;14(12):2456. doi:10.3390/electronics14122456

BibTeX
@article{Wu2025,
  author = {Wu, Yuezhou and Huang, Hua and Li, Zhiri and Zhang, Siling},
  title = {CBAM-ResNet: A Lightweight ResNet Network Focusing on Time Domain Features for End-to-End Deepfake Speech Detection},
  journal = {Electronics},
  year = {2025},
  volume = {14},
  number = {12},
  pages = {2456},
  doi = {10.3390/electronics14122456}
}
Kostenlos starten →