EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Survey on Audio Deepfake Detection: Techniques, Datasets, and Key Challenges

imran javed, Aamer Nadeem

International Journal of Innovations in Science and Technology · 17.05.2026 · 574

DOI: 10.33411/ijist/1808 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Innovations in Science and Technology, online erschienen am 17.05.2026. Verfasst von imran javed und 1 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Audio deepfake detection has become a critical research area in response to the rapid proliferation of deep learning-based speech synthesis and voice conversion technologies. This survey systematically reviews recent advances (2019–2025) in audio deepfake detection, covering attack typologies, detection methodologies, benchmark datasets, and open challenges. A total of 40 peer-reviewed studies were analyzed using a structured inclusion/exclusion protocol based on searches of IEEE Xplore, ACM Digital Library, Google Scholar, and ScienceDirect. The reviewed detection systems report accuracy ranges of 87–98.5% across benchmark datasets, with Equal Error Rates (EER) ranging from approximately 1.8% to 8.3%, and tandem detection cost function (t-DCF) values between 0.041 and 0.212 on ASVspoof 2019. Deep learning approaches, particularly residual networks (ResNet), squeeze-excitation networks (SENet), and hybrid convolutional-recurrent architectures, consistently outperform classical machine learning methods (SVM, GMM) by 5–12% in accuracy under matched conditions. However, cross-dataset and cross-language generalization remain critical unresolved challenges. This survey identifies self-supervised learning and imitation-based detection as high-priority future research directions.

Zitieren

APA

javed, I., & Nadeem, A. (2026). A Survey on Audio Deepfake Detection: Techniques, Datasets, and Key Challenges. International Journal of Innovations in Science and Technology, 574. https://doi.org/10.33411/ijist/1808

Vancouver

javed I, Nadeem A. A Survey on Audio Deepfake Detection: Techniques, Datasets, and Key Challenges. International Journal of Innovations in Science and Technology. 2026:574. doi:10.33411/ijist/1808

BibTeX
@article{javed2026,
  author = {javed, imran and Nadeem, Aamer},
  title = {A Survey on Audio Deepfake Detection: Techniques, Datasets, and Key Challenges},
  journal = {International Journal of Innovations in Science and Technology},
  year = {2026},
  pages = {574},
  doi = {10.33411/ijist/1808}
}
Kostenlos starten →