WaveFake: A data set to facilitate audio DeepFake detection
Year: 2021
Type: dataset
Abstract: The main purpose of this data set is to facilitate research into audio DeepFakes. These generated media files have been increasingly used to commit impersonation attempts or online harassment. The data set consists of 88,600 generated audio clips (16-bit PCM wav). All of these samples were generated by four different neural network architectures: MelGAN Parallel WaveGAN Multi-Band MelGAN WaveGlow Additionally, we examined a bigger version of MelGAN and investigated a variant of Multi-Band MelGAN that computes its auxiliary loss over the full audio instead of its subbands. Collection Process For WaveGlow, we utilize the official implementation (commit 8afb643) in conjunction with the official pre-trained network on PyTorch Hub. We use a popular implementation available on GitHub (commit 12c677e) for the remaining networks. The repository also offers pre-trained models. We used the pre-trained networks to generate samples that are similar to their respective training distributions, LJ Speech and JSUT. When sampling the data set, we first extract Mel spectrograms from the original audio files, using the pre-processing scripts of the corresponding repositories. We then feed these Mel spectrograms to the respective models to obtain the data set. This data set is licensed with a CC-BY-SA 4.0 license. This work was supported by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany's Excellence Strategy -- EXC-2092 CaSa -- 390781972.
Authors: Frank, Joel, Schönherr, Lea
Institution: Ruhr University Bochum
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4393707478