mlsanityData to 7 Oct 2026

AASIST3: KAN-Enhanced AASIST Speech Deepfake Detection using SSL Features and Additional Regularization for the ASVspoof 2024 Challenge

arXiv 2408.17352 ↗First posted 30 Aug 2024cs.SD cs.AI eess.AScited by 8

Not on the map. Why?

Abstract (arXiv)

Automatic Speaker Verification (ASV) systems, which identify speakers based on their voice characteristics, have numerous applications, such as user authentication in financial transactions, exclusive access control in smart devices, and forensic fraud detection. However, the advancement of deep learning algorithms has enabled the generation of synthetic audio through Text-to-Speech (TTS) and Voice Conversion (VC) systems, exposing ASV systems to potential vulnerabilities. To counteract this, we propose a novel architecture named AASIST3. By enhancing the existing AASIST framework with Kolmogorov-Arnold networks, additional layers, encoders, and pre-emphasis techniques, AASIST3 achieves a more than twofold improvement in performance. It demonstrates minDCF results of 0.5357 in the closed condition and 0.1414 in the open condition, significantly enhancing the detection of synthetic voices and improving ASV security. textbfThe new version of the model is publicly available at hrefhttps://huggingface.co/lab260/Spectra-AASIST3underlineHuggingFace (2026)

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 34 of its 49 references that are in the map. First posted on arXiv 30 Aug 2024.

Builds on

34 of 49 references.

References · 34

  1. 2017Attention Is All You Needcited by 59,932
  2. 2017Squeeze-and-Excitation Networkscited by 4,763
  3. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  4. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  5. 2020Sharpness-Aware Minimization for Efficiently Improving Generalizationcited by 1,404
  6. 2024KAN: Kolmogorov-Arnold Networkscited by 634
  7. 2019Attention Augmented Convolutional Networkscited by 363
  8. 2021ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networkscited by 293
  9. 2024U-KAN Makes Strong Backbone for Medical Image Segmentation and Generationcited by 176
  10. 2021AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networkscited by 173
  11. 2018Speaker Recognition from Raw Waveform with SincNetcited by 166
  12. 2022ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wildcited by 118
22 more
  1. 2022Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentationcited by 110
  2. 2021LEAF: A Learnable Frontend for Audio Classificationcited by 69
  3. 2021End-to-End Spectro-Temporal Graph Attention Networks for Speaker Verification Anti-Spoofing and Speech Deepfake Detectioncited by 68
  4. 2021RawBoost: A Raw Data Boosting and Augmentation Method applied to Automatic Speaker Verification Anti-Spoofingcited by 64
  5. 2019STC Antispoofing Systems for the ASVspoof2019 Challengecited by 51
  6. 2022Pushing the limits of raw waveform speaker recognitioncited by 49
  7. 2024Towards Robust Speech Representation Learning for Thousands of Languagescited by 48
  8. 2019Deep Residual Neural Networks for Audio Spoofing Detectioncited by 33
  9. 2024Kolmogorov-Arnold Convolutions: Design Principles and Empirical Studiescited by 26
  10. 2019ASSERT: Anti-Spoofing with Squeeze-Excitation and Residual neTworkscited by 23
  11. 2023SingFake: Singing Voice Deepfake Detectioncited by 21
  12. 2022SAMO: Speaker Attractor Multi-Center One-Class Learning for Voice Anti-Spoofingcited by 18
  13. 2023LibAUC: A Deep Learning Library for X-Risk Optimizationcited by 15
  14. 2023Improving Short Utterance Anti-Spoofing with AASIST2cited by 11
  15. 2020AReLU: Attention-based Rectified Linear Unitcited by 9
  16. 2021UR Channel-Robust Synthetic Speech Detection System for ASVspoof 2021cited by 8
  17. 2024ELA: Efficient Local Attention for Deep Convolutional Neural Networkscited by 8
  18. 2024Generalized Fake Audio Detection via Deep Stable Learningcited by 5
  19. 2023Robust Audio Anti-Spoofing with Fusion-Reconstruction Learning on Multi-Order Spectrogramscited by 4
  20. 2023Spatial Reconstructed Local Attention Res2Net with F0 Subband for Fake Speech Detectioncited by 2
  21. 2024Beyond Silence: Bias Analysis through Loss and Asymmetric Approach in Audio Anti-Spoofingcited by 2
  22. 2022ConvNeXt Based Neural Network for Audio Anti-Spoofingcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 6.

8 papers.

  1. 2026Towards Robust Speech Deepfake Detection via Human-Inspired Reasoningcited by 4
  2. 2025Discrete Optimal Transport and Voice Conversioncited by 1
  3. 2026An Intervention-Based Framework for Shortcut Diagnosis in Spoofing Countermeasurescited by 1
  4. 2025Novel Loss-Enhanced Universal Adversarial Patches for Sustainable Speaker Privacycited by 0
  5. 2026Probabilistic Verification of Voice Anti-Spoofing Modelscited by 0
  6. 2026What Do Deepfake Speech Detectors Actually Hear?cited by 0
  7. 2026SpAArSIST: Sparsified AASIST for Efficient and Reliable Anti-Spoofingcited by 0
  8. 2026Domain-Adaptive Dual-Gating Mixture of Experts for Generalizable Speech Deepfake Detectioncited by 0