Detection of cloned voices in realistic forensic voice comparison scenarios
Frontiers in Artificial Intelligence · 13.11.2025 · 8
DOI: 10.3389/frai.2025.1678043 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Artificial Intelligence, online erschienen am 13.11.2025. Verfasst von Pedro Univaso und 1 weiteren Autor:innen. Beteiligte Einrichtung: BlackVOX, Buenos Aires, Argentina. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 19 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Deepfakes and synthetic audio significantly degrade the performance of automatic speaker recognition systems commonly used in forensic laboratories. We investigate the effectiveness of Mel-Frequency Cepstral Coefficients (MFCCs) for detecting cloned voices, ultimately concluding that MFCC-based methods are insufficient as a universal anti-spoofing tool due to their inability to generalize across different cloning algorithms. Furthermore, we evaluate the performance of the HIVE AI-deepfake Content Detection tool, noting its vulnerability to babble noise and signal saturation, which are common in real-world forensic recordings. This investigation emphasizes the ongoing competition between voice cloning and detection technologies, underscoring the urgent need for more robust and generalized anti-spoofing systems for forensic applications.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- BlackVOX, Buenos Aires, Argentina.
- Phonetics Laboratory, Spanish National Research Council, Madrid, Spain.
Zitieren
APA
Univaso, P., & San Segundo, E. (2025). Detection of cloned voices in realistic forensic voice comparison scenarios. Frontiers in Artificial Intelligence, 8. https://doi.org/10.3389/frai.2025.1678043
Vancouver
Univaso P, San Segundo E. Detection of cloned voices in realistic forensic voice comparison scenarios. Frontiers in Artificial Intelligence. 2025;8. doi:10.3389/frai.2025.1678043
BibTeX
@article{Univaso2025,
author = {Univaso, Pedro and San Segundo, Eugenia},
title = {Detection of cloned voices in realistic forensic voice comparison scenarios},
journal = {Frontiers in Artificial Intelligence},
year = {2025},
volume = {8},
doi = {10.3389/frai.2025.1678043}
}
EUVIMED