mlsanityData to 7 Oct 2026

WaveFake: A Data Set to Facilitate Audio Deepfake Detection

arXiv 2111.02813 ↗First posted 4 Nov 2021cs.LG cs.CR cs.SDcited by 78

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 78 papers in the map (data through 7 Oct 2026). Builds on 63 of its 114 references that are in the map. First posted on arXiv 4 Nov 2021.

Builds on

63 of 114 references.

References · 63

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2017Neural Discrete Representation Learningcited by 4,650
  4. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  5. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  6. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  7. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,358
  8. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  9. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
  10. 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,095
  11. 2019CNN-generated images are surprisingly easy to spot... for nowcited by 842
  12. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 800
38 more
  1. 2020FastSpeech 2: Fast and High-Quality End-to-End Text to Speechcited by 710
  2. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 636
  3. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 620
  4. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 554
  5. 2020Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Cluescited by 518
  6. 2020Leveraging Frequency Analysis for Deep Fake Image Recognitioncited by 501
  7. 2019On Evaluating Adversarial Robustnesscited by 442
  8. 2019MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesiscited by 351
  9. 2019Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogramcited by 337
  10. 2017Real-valued (Medical) Time Series Generation with Recurrent Conditional GANscited by 329
  11. 2018Exposing DeepFake Videos By Detecting Face Warping Artifactscited by 318
  12. 2018WaveGlow: A Flow-based Generative Network for Speech Synthesiscited by 308
  13. 2019Detecting and Simulating Artifacts in GAN Fake Imagescited by 293
  14. 2020Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral Distributionscited by 278
  15. 2018Audio Adversarial Examples: Targeted Attacks on Speech-to-Textcited by 268
  16. 2018GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classificationcited by 242
  17. 2018Adversarial Audio Synthesiscited by 222
  18. 2018Efficient Neural Audio Synthesiscited by 218
  19. 2018Do GANs leave artificial fingerprints?cited by 188
  20. 2019ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detectioncited by 173
  21. 2020End-to-end anti-spoofing with RawNet2cited by 160
  22. 2019Detecting GAN generated Fake Images using Co-occurrence Matricescited by 124
  23. 2016SampleRNN: An Unconditional End-to-End Neural Audio Generation Modelcited by 110
  24. 2019High Fidelity Speech Synthesis with Adversarial Networkscited by 90
  25. 2017Deep Voice: Real-time Neural Text-to-Speechcited by 83
  26. 2018Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic Hidingcited by 83
  27. 2020ESPnet-ST: All-in-One Speech Translation Toolkitcited by 82
  28. 2020Evading Deepfake-Image Detectors with White- and Black-Box Attackscited by 80
  29. 2020End-to-End Adversarial Text-to-Speechcited by 77
  30. 2017Deep Voice 2: Multi-Speaker Neural Text-to-Speechcited by 75
  31. 2018Detecting GAN-generated Imagery using Color Cuescited by 75
  32. 2018ClariNet: Parallel Wave Generation in End-to-End Text-to-Speechcited by 70
  33. 2018CommanderSong: A Systematic Approach for Practical Adversarial Voice Recognitioncited by 63
  34. 2020Multi-band MelGAN: Faster Waveform Generation for High-Quality Text-to-Speechcited by 63
  35. 2020Attribution in Scale and Spacecited by 61
  36. 2019ESPnet-TTS: Unified, Reproducible, and Integratable Open Source End-to-End Text-to-Speech Toolkitcited by 60
  37. 2017JSUT corpus: free large-scale Japanese speech corpus for end-to-end speech synthesiscited by 57
  38. 2021ASVspoof 2019: spoofing countermeasures for the detection of synthesized, converted and replayed speechcited by 56

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 7; 2023: 11; 2024: 26; 2025: 15; 2026: 19.

78 papers.

Sort:

By area:

  1. 2024Detecting Multimedia Generated by Large AI Models: A Surveycited by 73
  2. 2025Deepfake-Eval-2024: A Multi-Modal In-the-Wild Benchmark of Deepfakes Circulated in 2024cited by 40
  3. 2023UMMAFormer: A Universal Multimodal-adaptive Transformer Framework for Temporal Forgery Localizationcited by 33
  4. 2024The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake Audiocited by 31
  5. 2023Improved DeepFake Detection Using Whisper Featurescited by 28
  6. 2023A Representative Study on Human Detection of Artificially Generated Media Across Countriescited by 22
  7. 2024SpoofCeleb: Speech Deepfake Detection and SASV In The Wildcited by 22
  8. 2024DFADD: The Diffusion and Flow-Matching Based Audio Deepfake Datasetcited by 20
  9. 2022Defense Against Adversarial Attacks on Audio DeepFake Detectioncited by 12
  10. 2024I Can Hear You: Selective Robust Training for Deepfake Audio Detectioncited by 12
  11. 2024Cross-Domain Audio Deepfake Detection: Dataset and Analysiscited by 11
  12. 2024Where are we in audio deepfake detection? A systematic analysis over generative and detection modelscited by 11
38 more
  1. 2023Single and Multi-Speaker Cloned Voice Detection: From Perceptual to Learned Featurescited by 10
  2. 2024Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlookcited by 10
  3. 2022Attack Agnostic Dataset: Towards Generalization and Stabilization of Audio DeepFake Detectioncited by 9
  4. 2022SpecRNet: Towards Faster and More Accessible Audio DeepFake Detectioncited by 9
  5. 2023Multi-Dataset Co-Training with Sharpness-Aware Optimization for Audio Anti-spoofingcited by 9
  6. 2024CLAD: Robust Audio Deepfake Detection Against Manipulation Attacks with Contrastive Learningcited by 9
  7. 2025Forensic deepfake audio detection using segmental speech featurescited by 8
  8. 2023Towards single integrated spoofing-aware speaker verification embeddingscited by 7
  9. 2024Fake Artificial Intelligence Generated Contents (FAIGC): A Survey of Theories, Detection Methods, and Opportunitiescited by 7
  10. 2024Towards Quantifying and Reducing Language Mismatch Effects in Cross-Lingual Speech Anti-Spoofingcited by 7
  11. 2025Adversarial Attacks on Audio Deepfake Detection: A Benchmark and Comparative Studycited by 7
  12. 2022The MeVer DeepFake Detection Service: Lessons Learnt from Developing and Deploying in the Wildcited by 6
  13. 2022Deepfake: Definitions, Performance Metrics and Standards, Datasets and Benchmarks, and a Meta-Reviewcited by 6
  14. 2024The DeepSpeak Datasetcited by 6
  15. 2024Improving Generalization for AI-Synthesized Voice Detectioncited by 6
  16. 2025Soundwave: Less is More for Speech-Text Alignment in LLMscited by 6
  17. 2025Tell me Habibi, is it Real or Fake?cited by 6
  18. 2022SceneFake: An Initial Dataset and Benchmarks for Scene Fake Audio Detectioncited by 5
  19. 2024Codecfake: An Initial Dataset for Detecting LLM-based Deepfake Audiocited by 5
  20. 2024VoiceWukong: Benchmarking Deepfake Voice Detectioncited by 5
  21. 2024Speech-Forensics: Towards Comprehensive Synthetic Speech Dataset Establishment and Analysiscited by 5
  22. 2025SCDF: A Speaker Characteristics DeepFake Speech Dataset for Bias Analysiscited by 5
  23. 2023Vulnerability of Automatic Identity Recognition to Audio-Visual Deepfakescited by 4
  24. 2024RU-AI: A Large Multimodal Dataset for Machine-Generated Content Detectioncited by 4
  25. 2024Passive Deepfake Detection Across Multi-modalities: A Comprehensive Surveycited by 4
  26. 2026Towards Robust Speech Deepfake Detection via Human-Inspired Reasoningcited by 4
  27. 2024Lightweight Model Attribution and Detection of Synthetic Speech via Audio Residual Fingerprintscited by 3
  28. 2025PhonemeFake: Redefining Deepfake Realism with Language-Driven Segmental Manipulation and Adaptive Bilevel Detectioncited by 3
  29. 2025DeepfakeBench-MM: A Comprehensive Benchmark for Multimodal Deepfake Detectioncited by 3
  30. 2026AFSS: Artifact-Focused Self-Synthesis for Mitigating Bias in Audio Deepfake Detectioncited by 3
  31. 2023Towards generalizing deep-audio fake detection networkscited by 2
  32. 2023MFAAN: Unveiling Audio Deepfakes with a Multi-Feature Authenticity Networkcited by 2
  33. 2024SVDD Challenge 2024: A Singing Voice Deepfake Detection Challenge Evaluation Plancited by 2
  34. 2024Gen-AI for User Safety: A Surveycited by 2
  35. 2024GLCF: A Global-Local Multimodal Coherence Analysis Framework for Talking Face Generation Detectioncited by 2
  36. 2025Measuring the Robustness of Audio Deepfake Detection under Real-World Corruptioncited by 2
  37. 2025A Data-Driven Diffusion-based Approach for Audio Deepfake Explanationscited by 2
  38. 2025AUDDT: A Unified Benchmark Toolkit for Audio and Speech Deepfake Detectorscited by 2

50 most cited of 78 All 78 (JSON)