Volltext-Downloads (blau) und Frontdoor-Views (grau)

Preprint: Creation and Detection of German Voice Deepfakes

  • Synthesizing voice with the help of machine learning techniques has made rapid progress over the last years [1]. Given the current increase in using conferencing tools for online teaching, we question just how easy (i.e. needed data, hardware, skill set) it would be to create a convincing voice fake. We analyse how much training data a participant (e.g. a student) would actually need to fakeSynthesizing voice with the help of machine learning techniques has made rapid progress over the last years [1]. Given the current increase in using conferencing tools for online teaching, we question just how easy (i.e. needed data, hardware, skill set) it would be to create a convincing voice fake. We analyse how much training data a participant (e.g. a student) would actually need to fake another participants voice (e.g. a professor). We provide an analysis of the existing state of the art in creating voice deep fakes and align the identified as well as our own optimization techniques in the context of two different voice data sets. A user study with more than 100 participants shows how difficult it is to identify real and fake voice (on avg. only 37 percent can recognize a professor’s fake voice). From a longer-term societal perspective such voice deep fakes may lead to a disbelief by default.show moreshow less

Export metadata

Additional Services

Search Google Scholar

Statistics

frontdoor_oas
Metadaten
Document Type:Working Paper
Zitierlink: https://opus.hs-offenburg.de/5200
Bibliografische Angaben
Title (English):Preprint: Creation and Detection of German Voice Deepfakes
Conference:International Symposium on Foundations & Practice of Security (14. : December 8-9-10, 2021 : Paris, France)
Author:Vanessa Barnekow, Dominik BinderStaff MemberGND, Niclas Kromrey, Pascal Munaretto, Andreas SchaadStaff MemberORCiDGND, Felix SchmiederStaff MemberGND
Year of Publication:2021
Page Number:10
First Page:1
Last Page:10
URL:https://www.researchgate.net/publication/353677657
Language:English
Inhaltliche Informationen
Institutes:Fakultät Medien (M) (ab 22.04.2021)
Collections of the Offenburg University:Bibliografie
DDC classes:600 Technik, Medizin, angewandte Wissenschaften
Formale Angaben
Open Access: Open Access 
Licence (German):License LogoCreative Commons - CC BY - Namensnennung 4.0 International
ArXiv Id:http://arxiv.org/abs/2108.01469