Detail publikace

Diffuse or Confuse: A Diffusion Deepfake Speech Dataset

FIRC, A. MALINKA, K. HANÁČEK, P.

Originální název

Diffuse or Confuse: A Diffusion Deepfake Speech Dataset

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

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.

Klíčová slova

deepfakes, deepfake speech, dataset, diffusion, detection

Autoři

FIRC, A.; MALINKA, K.; HANÁČEK, P.

Vydáno

11. 12. 2024

Nakladatel

GI - Group for computer science

Místo

Darmstadt

ISBN

978-3-88579-749-4

Kniha

2024 International Conference of the Biometrics Special Interest Group (BIOSIG)

Strany od

1

Strany do

7

Strany počet

7

URL

https://ieeexplore.ieee.org/document/10786752

BibTex

@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"
}