Diffuse or Confuse: A Diffusion Deepfake Speech Dataset
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F24%3APU151921" target="_blank" >RIV/00216305:26230/24:PU151921 - isvavai.cz</a>
Result on the web
<a href="https://ieeexplore.ieee.org/document/10786752" target="_blank" >https://ieeexplore.ieee.org/document/10786752</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/BIOSIG61931.2024.10786752" target="_blank" >10.1109/BIOSIG61931.2024.10786752</a>
Alternative languages
Result language
angličtina
Original language name
Diffuse or Confuse: A Diffusion Deepfake Speech Dataset
Original language description
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.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
2024 International Conference of the Biometrics Special Interest Group (BIOSIG)
ISBN
978-3-88579-749-4
ISSN
—
e-ISSN
—
Number of pages
7
Pages from-to
1-7
Publisher name
GI - Group for computer science
Place of publication
Darmstadt
Event location
Darmstadt
Event date
Sep 25, 2024
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—