Publication Details
Deepfake Speech Detection: A Spectrogram Analysis
Deepfake, Speech, Image-based, Deepfake Detection, Spectrogram
The current voice biometric systems have no natural mechanics to defend against
deepfake spoofing attacks. Thus, supporting these systems with a deepfake
detection solution is necessary. One of the latest approaches to deepfake speech
detection is representing speech as a spectrogram and using it as an input for
a deep neural network. This work thus analyzes the feasibility of different
spectrograms for deepfake speech detection. We compare types of them regarding
their performance, hardware requirements, and speed. We show the majority of the
spectrograms are feasible for deepfake detection. However, there is no general,
correct answer to selecting the best spectrogram. As we demonstrate, different
spectrograms are suitable for different needs.
@inproceedings{BUT188028,
author="Anton {Firc} and Kamil {Malinka} and Petr {Hanáček}",
title="Deepfake Speech Detection: A Spectrogram Analysis",
booktitle="Proceedings of the ACM Symposium on Applied Computing",
year="2024",
pages="1312--1320",
publisher="Association for Computing Machinery",
address="Avila",
doi="10.1145/3605098.3635911",
isbn="979-8-4007-0243-3",
url="https://dl.acm.org/doi/10.1145/3605098.3635911"
}