Comparison of the Ability of Neural Network Model and Humans to Detect a Cloned Voice
Electronics · 30.10.2023 · 12 (21) · 4458
DOI: 10.3390/electronics12214458 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 30.10.2023. Verfasst von Krzysztof Milewski und 2 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Polish National Centre for Research and Development (NCBR) from the European Regional Development Fund, Electronics, Telecommunications, and Informatics Faculty, Gdańsk University of Technology.
Abstract (Originalsprache)
The vulnerability of the speaker identity verification system to attacks using voice cloning was examined. The research project assumed creating a model for verifying the speaker’s identity based on voice biometrics and then testing its resistance to potential attacks using voice cloning. The Deep Speaker Neural Speaker Embedding System was trained, and the Real-Time Voice Cloning system was employed based on the SV2TTS, Tacotron, WaveRNN, and GE2E neural networks. The results of attacks using voice cloning were analyzed and discussed in the context of a subjective assessment of cloned voice fidelity. Subjective test results and attempts to authenticate speakers proved that the tested biometric identity verification system might resist voice cloning attacks even if humans cannot distinguish cloned samples from original ones.
Förderung
- Polish National Centre for Research and Development (NCBR) from the European Regional Development Fund
- Electronics, Telecommunications, and Informatics Faculty, Gdańsk University of Technology
Zitieren
APA
Milewski, K., Zaporowski, S., & Czyżewski, A. (2023). Comparison of the Ability of Neural Network Model and Humans to Detect a Cloned Voice. Electronics, 12(21), 4458. https://doi.org/10.3390/electronics12214458
Vancouver
Milewski K, Zaporowski S, Czyżewski A. Comparison of the Ability of Neural Network Model and Humans to Detect a Cloned Voice. Electronics. 2023;12(21):4458. doi:10.3390/electronics12214458
BibTeX
@article{Milewski2023,
author = {Milewski, Krzysztof and Zaporowski, Szymon and Czyżewski, Andrzej},
title = {Comparison of the Ability of Neural Network Model and Humans to Detect a Cloned Voice},
journal = {Electronics},
year = {2023},
volume = {12},
number = {21},
pages = {4458},
doi = {10.3390/electronics12214458}
}
EUVIMED