mlsanityData to 14 Oct 2026

How Deep Are the Fakes? Focusing on Audio Deepfake: A Survey

arXiv 2111.14203 ↗First posted 28 Nov 2021cs.SD cs.AI eess.AScited by 6

Not on the map. Why?

Abstract (arXiv)

Deepfake is content or material that is synthetically generated or manipulated using artificial intelligence (AI) methods, to be passed off as real and can include audio, video, image, and text synthesis. This survey has been conducted with a different perspective compared to existing survey papers, that mostly focus on just video and image deepfakes. This survey not only evaluates generation and detection methods in the different deepfake categories, but mainly focuses on audio deepfakes that are overlooked in most of the existing surveys. This paper critically analyzes and provides a unique source of audio deepfake research, mostly ranging from 2016 to 2020. To the best of our knowledge, this is the first survey focusing on audio deepfakes in English. This survey provides readers with a summary of 1) different deepfake categories 2) how they could be created and detected 3) the most recent trends in this domain and shortcomings in detection methods 4) audio deepfakes, how they are created and detected in more detail which is the main focus of this paper. We found that Generative Adversarial Networks(GAN), Convolutional Neural Networks (CNN), and Deep Neural Networks (DNN) are common ways of creating and detecting deepfakes. In our evaluation of over 140 methods we found that the majority of the focus is on video deepfakes and in particular in the generation of video deepfakes. We found that for text deepfakes there are more generation methods but very few robust methods for detection, including fake news detection, which has become a controversial area of research because of the potential of heavy overlaps with human generation of fake content. This paper is an abbreviated version of the full survey and reveals a clear need to research audio deepfakes and particularly detection of audio deepfakes.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 35 of its 77 references that are in the map. First posted on arXiv 28 Nov 2021.

Builds on

35 of 77 references.

References · 35

  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  2. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  3. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  4. 2016WaveNet: A Generative Model for Raw Audiocited by 1,722
  5. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,154
  6. 2018VoxCeleb2: Deep Speaker Recognitioncited by 875
  7. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 804
  8. 2019MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesiscited by 354
  9. 2018Everybody Dance Nowcited by 315
  10. 2018WaveGlow: A Flow-based Generative Network for Speech Synthesiscited by 309
  11. 2019Few-Shot Adversarial Learning of Realistic Neural Talking Head Modelscited by 284
  12. 2018Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesiscited by 282
23 more
  1. 2020The Creation and Detection of Deepfakes: A Surveycited by 247
  2. 2020DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detectioncited by 233
  3. 2020Emotions Don't Lie: An Audio-Visual Deepfake Detection Method Using Affective Cuescited by 111
  4. 2016Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesiscited by 102
  5. 2019Deep Learning for Deepfakes Creation and Detection: A Surveycited by 102
  6. 2017Deep Voice: Real-time Neural Text-to-Speechcited by 83
  7. 2018StarGAN-VC: Non-parallel many-to-many voice conversion with star generative adversarial networkscited by 78
  8. 2017Deep Voice 2: Multi-Speaker Neural Text-to-Speechcited by 75
  9. 2020One-class Learning Towards Synthetic Voice Spoofing Detectioncited by 61
  10. 2016Fully Character-Level Neural Machine Translation without Explicit Segmentationcited by 55
  11. 2019MelNet: A Generative Model for Audio in the Frequency Domaincited by 42
  12. 2019Deep Residual Neural Networks for Audio Spoofing Detectioncited by 33
  13. 2020TextGAIL: Generative Adversarial Imitation Learning for Text Generationcited by 28
  14. 2019Non-Parallel Sequence-to-Sequence Voice Conversion with Disentangled Linguistic and Speaker Representationscited by 23
  15. 2018Voice Impersonation using Generative Adversarial Networkscited by 17
  16. 2017Statistical Parametric Speech Synthesis Incorporating Generative Adversarial Networkscited by 16
  17. 2018High-quality nonparallel voice conversion based on cycle-consistent adversarial networkcited by 13
  18. 2018Attentive Filtering Networks for Audio Replay Attack Detectioncited by 7
  19. 2019Fake News, Disinformation, and Deepfakes: Leveraging Distributed Ledger Technologies and Blockchain to Combat Digital Deception and Counterfeit Realitycited by 6
  20. 2019Towards robust audio spoofing detection: a detailed comparison of traditional and learned featurescited by 6
  21. 2019DGSAN: Discrete Generative Self-Adversarial Networkcited by 4
  22. 2020Audio Spoofing Verification using Deep Convolutional Neural Networks by Transfer Learningcited by 3
  23. 2017A Study on Replay Attack and Anti-Spoofing for Automatic Speaker Verificationcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 0; 2024: 2; 2025: 1; 2026: 1.

6 papers.

  1. 2022GAN-generated Faces Detection: A Survey and New Perspectivescited by 30
  2. 2024XAI-Based Detection of Adversarial Attacks on Deepfake Detectorscited by 9
  3. 2024VoiceWukong: Benchmarking Deepfake Voice Detectioncited by 5
  4. 2025Reliable Audio Deepfake Detection in Variable Conditions via Quantum-Kernel SVMscited by 3
  5. 2026Quantum Kernels for Audio Deepfake Detection Using Spectrogram Patch Featurescited by 1
  6. 2022Deep Fake Detection, Deterrence and Response: Challenges and Opportunitiescited by 0