Publication detail

Diffuse or Confuse: A Diffusion Deepfake Speech Dataset

FIRC, A. MALINKA, K. HANÁČEK, P.

Original Title

Diffuse or Confuse: A Diffusion Deepfake Speech Dataset

Type

conference paper

Language

English

Original Abstract

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.

Keywords

deepfakes, deepfake speech, dataset, diffusion, detection

Authors

FIRC, A.; MALINKA, K.; HANÁČEK, P.

Released

11. 12. 2024

Publisher

GI - Group for computer science

Location

Darmstadt

ISBN

978-3-88579-749-4

Book

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

Pages from

1

Pages to

7

Pages count

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"
}