WaveFake: A Data Set to Facilitate Audio Deepfake Detection

Joel Frank, Lea Schönherr

Keywords: generative model, audio Deepfake detection, signal processing, data set

TL;DR: We present a novel data set for facilitating research into audio Deepfake detection. Additionally, we review common signal processing techniques and provide baseline models.

Abstract: Deep generative modeling has the potential to cause significant harm to society. Recognizing this threat, a magnitude of research into detecting so-called "Deepfakes'' has emerged. This research most often focuses on the image domain, while studies exploring generated audio signals have---so-far---been neglected. In this paper we make three key contributions to narrow this gap. First, we provide researchers with an introduction to common signal processing techniques used for analyzing audio signals. Second, we present a novel data set, for which we collected nine sample sets from five different network architectures, spanning two languages. Finally, we supply practitioners with two baseline models, adopted from the signal processing community, to facilitate further research in this area.

URL: https://zenodo.org/record/5642694

Contribution Process Agreement: Yes

Dataset Url: https://zenodo.org/record/5642694

License:

This data set is licensed with a CC-BY-SA 4.0 license.

You can find the accompanying code repository at: https://github.com/RUB-SysSec/WaveFake

Author Statement: Yes

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:2111.02813/code)