Dual-Channel Deepfake Audio Detection: Leveraging Direct and Reverberant Waveforms
IEEE Access · 2025 · 13 · 18040-18052
DOI: 10.1109/access.2025.3532775 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2025. Verfasst von Gunwoo Lee und 6 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Science and Information and Communications Technology (MSIT), South Korea, under the Information Technology Research Center (ITRC) Support Program, Institute for Information and Communications Technology Planning and Evaluation, IITP grant funded by Korean Government (MSIT), Robust Deepfake Audio Detection Development Against Adversarial Attacks.
Abstract (Originalsprache)
Deepfake content-including audio, video, images, and text-synthesized or modified using artificial intelligence is designed to convincingly mimic real content. As deepfake generation technology advances, detecting deepfake content presents significant challenges. While recent progress has been made in detection techniques, identifying deepfake audio remains particularly challenging. Previous approaches have attempted to capture deepfake features by combining video and audio content; however, these methods are ineffective when video and audio are mismatched due to occlusion. To address this, we propose a novel dual-channel deepfake audio detection model that leverages the direct and reverberant components extracted from raw audio signals, focusing exclusively on audio-based detection without reliance on video content. Across various datasets, including ASVspoof2019, FakeAVCeleb, and sport press conference datasets collected by our group, the proposed dual-channel model demonstrates significant improvements in quantitative metrics such as equal error rate and area under the curve. The implementation is available at https://github.com/gunwoo5034/Dual-Channel-Audio-Deepfake-Detection.
Förderung
- Ministry of Science and Information and Communications Technology (MSIT), South Korea, under the Information Technology Research Center (ITRC) Support Program
- Institute for Information and Communications Technology Planning and Evaluation
- IITP grant funded by Korean Government (MSIT), Robust Deepfake Audio Detection Development Against Adversarial Attacks
Zitieren
APA
Lee, G., Lee, J., Jung, M., Lee, J., Hong, K., Jung, S., & Han, Y. (2025). Dual-Channel Deepfake Audio Detection: Leveraging Direct and Reverberant Waveforms. IEEE Access, 13, 18040-18052. https://doi.org/10.1109/access.2025.3532775
Vancouver
Lee G, Lee J, Jung M, Lee J, Hong K, Jung S, et al. Dual-Channel Deepfake Audio Detection: Leveraging Direct and Reverberant Waveforms. IEEE Access. 2025;13:18040-18052. doi:10.1109/access.2025.3532775
BibTeX
@article{Lee2025,
author = {Lee, Gunwoo and Lee, Jungmin and Jung, Minkyo and Lee, Joseph and Hong, Kihun and Jung, Souhwan and Han, Yoseob},
title = {Dual-Channel Deepfake Audio Detection: Leveraging Direct and Reverberant Waveforms},
journal = {IEEE Access},
year = {2025},
volume = {13},
pages = {18040--18052},
doi = {10.1109/access.2025.3532775}
}
EUVIMED