Publication Details
Diffuse or Confuse: A Diffusion Deepfake Speech Dataset
deepfakes, deepfake speech, dataset, diffusion, detection
Advancements in artificial intelligence and machine learning have significantly
improved synthetic speech generation. This paper explores diffusion models,
a novel method for creating realistic synthetic speech. We create a diffusion
dataset using available tools and pretrained models. Additionally, this study
assesses the quality of diffusion-generated deepfakes versus non-diffusion ones
and their potential threat to current deepfake detection systems. Findings
indicate that the detection of diffusion-based deepfakes is generally comparable
to non-diffusion deepfakes, with some variability based on detector architecture.
Re-vocoding with diffusion vocoders shows minimal impact, and the overall speech
quality is comparable to non-diffusion methods.
@inproceedings{BUT189345,
author="Anton {Firc} and Kamil {Malinka} and Petr {Hanáček}",
title="Diffuse or Confuse: A Diffusion Deepfake Speech Dataset",
booktitle="2024 International Conference of the Biometrics Special Interest Group (BIOSIG)",
year="2024",
pages="1--7",
publisher="GI - Group for computer science",
address="Darmstadt",
doi="10.1109/BIOSIG61931.2024.10786752",
isbn="978-3-88579-749-4",
url="https://ieeexplore.ieee.org/document/10786752"
}