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

Creation and Detection of German Voice Deepfakes

  • Synthesizing voice with the help of machine learning techniques has made rapid progress over the last years. 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 anotherSynthesizing voice with the help of machine learning techniques has made rapid progress over the last years. 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% 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

Share in Twitter Search Google Scholar

Statistics

frontdoor_oas
Metadaten
Document Type:Conference Proceeding
Title (English):Creation and Detection of German Voice Deepfakes
Author:Vanessa Barnekow, Dominik BinderGND, Niclas Kromrey, Pascal Munaretto, Andreas SchaadGND, Felix Schmieder
Edition:1.
Year of Publication:2022
Place of publication:Cham
Publisher:Springer
First Page:355
Last Page:364
Parent Title (English):Foundations and Practice of Security
Editor:Esma Aïmeur, Maryline Laurent, Reda Yaich, Benoît Dupont, Joaquin Garcia-Alfaro
Volume:LNCS 13291
ISBN:978-3-031-08146-0 (Softcover)
ISBN:978-3-031-08147-7 (eBook)
ISSN:0302-9743
ISSN:1611-3349 (E-ISSN)
DOI:https://doi.org/10.1007/978-3-031-08147-7_24
Language:English
Institutes:Fakultät Medien (M) (ab 22.04.2021)
Institutes:Bibliografie
Tag:Deepfake
Open Access: Closed 
Relevance:Konferenzbeitrag: h5-Index < 30
Licence (German):License LogoUrheberrechtlich geschützt
Comment:
Konferenz: 14th International Symposium, FPS 2021, Paris, France, December 7-10, 2021