The DOI matches its DataCite record.
WaveFake: A data set to facilitate audio DeepFake detection
Open accessAbstract
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Still being checked.
Cited by
Sorted by citations
MLAAD: The Multi-Language Audio Anti-Spoofing Dataset
Müller, N. M., Kawa, P., Choong, W. H., Casanova, E., Gölge, E., Müller, T., Syga, P., Sperl, P., & Böttinger, K. (2024) · 2024 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650962 · Cited by 73
Attack Agnostic Dataset: Towards Generalization and Stabilization of Audio DeepFake Detection
Kawa, P., Plata, M., & Syga, P. (2022) · Interspeech 2022 · doi:10.21437/interspeech.2022-10078 · Cited by 33
Martín-Doñas, J. M., Álvarez, A., Rosello, E., Gomez, A. M., & Peinado, A. M. (2024) · Interspeech 2024 · doi:10.21437/interspeech.2024-942 · Cited by 18
“…and end silences were removed, as well as the hidden sets of 2021 LA and DF. Finally, to further evaluate the performance with out-domain datasets, we also included WaveFake [29] (two female speakers, English and Japanese) and In-the-Wild [30] (over 50 English politicians and celebrities) datasets.”
BackgroundSecureVision: Advanced Cybersecurity Deepfake Detection with Big Data Analytics
Kumar, N., & Kundu, A. (2024) · Sensors · doi:10.3390/s24196300 · Cited by 14
The MeVer DeepFake Detection Service: Lessons Learnt from Developing and Deploying in the Wild
Baxevanakis, S., Kordopatis-Zilos, G., Galopoulos, P., Apostolidis, L., Levacher, K., Schlicht, I. B., Teyssou, D., Kompatsiaris, I. Y., & Papadopoulos, S. (2022) · doi:10.1145/3512732.3533587 · Cited by 11
Schäfer, K., Choi, J.-E., & Neu, M. (2024) · The Automatic Speaker Verification Spoofing Countermeasures Workshop (ASVspoof 2024) · doi:10.21437/asvspoof.2024-9 · Cited by 10
“Previously to the challenge we performed some preparatory tests using the ASVspoof 2019 LA [18] dataset and WaveFake [19] with its genuine samples of the LJSpeech corpora [20].”
CloneAI: A Deep Learning-Based Approach for Cloned Voice Detection
Kheria, I., & Karani, R. B. (2024) · Lecture notes in networks and systems · doi:10.1007/978-981-99-7817-5_21 · Cited by 6
Attention-based Multimodal learning framework for Generalized Audio-Visual Deepfake Detection
Masood, M., Javed, A., & Irtaza, A. (2023) · Preprint (Research Square) · doi:10.21203/rs.3.rs-3415144/v1 · Cited by 6
Research progress on speech deepfake and its detection techniques
Xu, Y., Li, B., Tan, S., & Huang, J. (2024) · Journal of Image and Graphics · doi:10.11834/jig.230476 · Cited by 4
Deepfake Detection in Call Recordings: A Deep Learning Solution for Voice Authentication
Nimbalkar, M. S. H. (2025) · International Journal for Research in Applied Science and Engineering Technology · doi:10.22214/ijraset.2025.68267 · Cited by 1
“Deepfake Detection in Call Recordings:A Deep Learning Solution for Voice Authentication”
Nimbalkar, P. D. S. (2025) · INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT · doi:10.55041/ijsrem49194
Detection of Synthetic or Cloned Voices Using Deep Learning and Acoustic Feature Analysis
Sinha, K., & Jana, D. S. (2025) · International Journal of Computer Applications · doi:10.5120/ijca2025925228
Future-Proofing Multilingual Fake Speech Detection
Demirörs, M., Özbayoğlu, A. M., & Akgün, T. (2025) · doi:10.5121/csit.2025.151309
Audio Deepfake: Literature Review and Detection Limitations
Mahmoud, B., & Bouzidi, D. (2026) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-032-18927-1_15
Metadata
- Authors
- Frank, J., & Schönherr, L.
- Affiliations
- Ruhr University Bochum (DE)
- Venue
- Zenodo
- Publisher
- Zenodo
- Published
- 2021-06-08
- OpenAlex
- W4393707478
- Cited by
- 10
- References
- 0
- Citations by year
- 2026: 1 · 2025: 4 · 2024: 3 · 2023: 1 · 2022: 1
- Type
- dataset
- Language
- en
- Open access
- green
- zenodo.org
- Licence
- Locations
- Zenodo (CERN European Organization for Nuclear Research) (submittedVersion, other-oa)
- Zenodo (CERN European Organization for Nuclear Research)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Signal Processing › Music and Audio Processing
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Keywords
- deepfake audio, audio deepfake detection, synthetic audio, text-to-speech, speech synthesis, WaveGAN, HiFi-GAN, WaveGlow, LJSpeech, conformational isomers, audio forensics, impersonation, online harassment, Mel spectrogram, audio watermarking, audio fingerprinting
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
