WaveFake: A Data Set to Facilitate Audio Deepfake Detection
This work addresses the threat of audio deepfakes for society by providing a foundational resource for researchers and practitioners in the field.
The paper tackles the lack of research on audio deepfake detection by introducing WaveFake, a dataset of generated audio samples from five network architectures across two languages, and provides baseline models to support further studies.
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.