mlsanityData to 14 Oct 2026

SpecRNet: Towards Faster and More Accessible Audio DeepFake Detection

arXiv 2210.06105 ↗First posted 12 Oct 2022cs.SD cs.LG eess.AScited by 9

Not on the map. Why?

Abstract (arXiv)

Audio DeepFakes are utterances generated with the use of deep neural networks. They are highly misleading and pose a threat due to use in fake news, impersonation, or extortion. In this work, we focus on increasing accessibility to the audio DeepFake detection methods by providing SpecRNet, a neural network architecture characterized by a quick inference time and low computational requirements. Our benchmark shows that SpecRNet, requiring up to about 40% less time to process an audio sample, provides performance comparable to LCNN architecture - one of the best audio DeepFake detection models. Such a method can not only be used by online multimedia services to verify a large bulk of content uploaded daily but also, thanks to its low requirements, by average citizens to evaluate materials on their devices. In addition, we provide benchmarks in three unique settings that confirm the correctness of our model. They reflect scenarios of low-resource datasets, detection on short utterances and limited attacks benchmark in which we take a closer look at the influence of particular attacks on given architectures.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 29 of its 38 references that are in the map. First posted on arXiv 12 Oct 2022.

Builds on

29 of 38 references.

References · 29

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  3. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,367
  4. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
  5. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,154
  6. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 804
  7. 2017Tacotron: Towards End-to-End Speech Synthesiscited by 490
  8. 2018MesoNet: a Compact Facial Video Forgery Detection Networkcited by 409
  9. 2019MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesiscited by 354
  10. 2019Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogramcited by 340
  11. 2018WaveGlow: A Flow-based Generative Network for Speech Synthesiscited by 309
  12. 2018Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesiscited by 282
17 more
  1. 2021FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Datasetcited by 181
  2. 2020End-to-end anti-spoofing with RawNet2cited by 164
  3. 2021ASVspoof 2021: accelerating progress in spoofed and deepfake speech detectioncited by 161
  4. 2018Neural Voice Cloning with a Few Samplescited by 100
  5. 2018StarGAN-VC: Non-parallel many-to-many voice conversion with star generative adversarial networkscited by 78
  6. 2021WaveFake: A Data Set to Facilitate Audio Deepfake Detectioncited by 78
  7. 2021End-to-End Spectro-Temporal Graph Attention Networks for Speaker Verification Anti-Spoofing and Speech Deepfake Detectioncited by 70
  8. 2020Multi-band MelGAN: Faster Waveform Generation for High-Quality Text-to-Speechcited by 63
  9. 2017JSUT corpus: free large-scale Japanese speech corpus for end-to-end speech synthesiscited by 58
  10. 2021A Comparative Study on Recent Neural Spoofing Countermeasures for Synthetic Speech Detectioncited by 56
  11. 2021SC-GlowTTS: an Efficient Zero-Shot Multi-Speaker Text-To-Speech Modelcited by 56
  12. 2019Mellotron: Multispeaker expressive voice synthesis by conditioning on rhythm, pitch and global style tokenscited by 44
  13. 2021DefakeHop: A Light-Weight High-Performance Deepfake Detectorcited by 31
  14. 2021Multi-Task Learning in Utterance-Level and Segmental-Level Spoof Detectioncited by 16
  15. 2020Improved RawNet with Feature Map Scaling for Text-independent Speaker Verification using Raw Waveformscited by 12
  16. 2022Attack Agnostic Dataset: Towards Generalization and Stabilization of Audio DeepFake Detectioncited by 9
  17. 2020Vocal Tract Length Perturbation for Text-Dependent Speaker Verification with Autoregressive Prediction Codingcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 3; 2024: 2; 2025: 2; 2026: 1.

9 papers.

  1. 2023Improved DeepFake Detection Using Whisper Featurescited by 29
  2. 2022Defense Against Adversarial Attacks on Audio DeepFake Detectioncited by 12
  3. 2024Where are we in audio deepfake detection? A systematic analysis over generative and detection modelscited by 11
  4. 2023Deepfake CAPTCHA: A Method for Preventing Fake Callscited by 7
  5. 2024D-CAPTCHA++: A Study of Resilience of Deepfake CAPTCHA under Transferable Imperceptible Adversarial Attackcited by 1
  6. 2023Recent Advancements In The Field Of Deepfake Detectioncited by 0
  7. 2025LitMAS: A Lightweight and Generalized Multi-Modal Anti-Spoofing Framework for Biometric Securitycited by 0
  8. 2025Zero-Shot to Zero-Lies: Detecting Bengali Deepfake Audio through Transfer Learningcited by 0
  9. 2026Deep-Fake CAPTCHA: Mitigating Next-Generation Social Engineering Attackscited by 0