mlsanityData to 14 Oct 2026

Detect All-Type Deepfake Audio: Wavelet Prompt Tuning for Enhanced Auditory Perception

arXiv 2504.06753 ↗First posted 9 Apr 2025cs.SD cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

The rapid advancement of audio generation technologies has escalated the risks of malicious deepfake audio across speech, sound, singing voice, and music, threatening multimedia security and trust. While existing countermeasures (CMs) perform well in single-type audio deepfake detection (ADD), their performance declines in cross-type scenarios. This paper is dedicated to studying the all-type ADD task. We are the first to comprehensively establish an all-type ADD benchmark to evaluate current CMs, incorporating cross-type deepfake detection across speech, sound, singing voice, and music. Then, we introduce the prompt tuning self-supervised learning (PT-SSL) training paradigm, which optimizes SSL front-end by learning specialized prompt tokens for ADD, requiring 458x fewer trainable parameters than fine-tuning (FT). Considering the auditory perception of different audio types, we propose the wavelet prompt tuning (WPT)-SSL method to capture type-invariant auditory deepfake information from the frequency domain without requiring additional training parameters, thereby enhancing performance over FT in the all-type ADD task. To achieve an universally CM, we utilize all types of deepfake audio for co-training. Experimental results demonstrate that WPT-XLSR-AASIST achieved the best performance, with an average EER of 3.58% across all evaluation sets.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 37 of its 51 references that are in the map. First posted on arXiv 9 Apr 2025.

Builds on

37 of 51 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2022Visual Prompt Tuningcited by 1,681
  3. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,657
  4. 2023Vision Transformers Need Registerscited by 871
  5. 2021XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scalecited by 601
  6. 2023MusicLM: Generating Music From Textcited by 448
  7. 2019A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmarkcited by 425
  8. 2022AudioGen: Textually Guided Audio Generationcited by 295
  9. 2023MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Trainingcited by 181
  10. 2021AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networkscited by 180
  11. 2019ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detectioncited by 178
  12. 2018Speaker Recognition from Raw Waveform with SincNetcited by 166
25 more
  1. 2022ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wildcited by 121
  2. 2022Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentationcited by 117
  3. 2024ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scalecited by 91
  4. 2023Improving Visual Prompt Tuning for Self-supervised Vision Transformerscited by 57
  5. 2022Multitask Vision-Language Prompt Tuningcited by 51
  6. 2024The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake Audiocited by 31
  7. 2023Towards generalisable and calibrated synthetic speech detection with self-supervised representationscited by 23
  8. 2024Mixture of Experts Fusion for Fake Audio Detection Using Frozen wav2vec 2.0cited by 20
  9. 2024Attentive Merging of Hidden Embeddings from Pre-trained Speech Model for Anti-spoofing Detectioncited by 17
  10. 2024CtrSVDD: A Benchmark Dataset and Baseline Analysis for Controlled Singing Voice Deepfake Detectioncited by 16
  11. 2024Heterogeneity over Homogeneity: Investigating Multilingual Speech Pre-Trained Models for Detecting Audio Deepfakecited by 14
  12. 2023The Impact of Silence on Speech Anti-Spoofingcited by 13
  13. 2024FakeMusicCaps: a Dataset for Detection and Attribution of Synthetic Music Generated via Text-to-Music Modelscited by 13
  14. 2024I Can Hear You: Selective Robust Training for Deepfake Audio Detectioncited by 13
  15. 2025Comprehensive Layer-wise Analysis of SSL Models for Audio Deepfake Detectioncited by 13
  16. 2022Defense Against Adversarial Attacks on Audio DeepFake Detectioncited by 12
  17. 2023FSD: An Initial Chinese Dataset for Fake Song Detectioncited by 12
  18. 2024SpeechPrompt: Prompting Speech Language Models for Speech Processing Taskscited by 12
  19. 2024From Audio Deepfake Detection to AI-Generated Music Detection -- A Pathway and Overviewcited by 11
  20. 2024Singing Voice Graph Modeling for SingFake Detectioncited by 9
  21. 2024SVDD 2024: The Inaugural Singing Voice Deepfake Detection Challengecited by 8
  22. 2023Audio Prompt Tuning for Universal Sound Separationcited by 7
  23. 2024Prompt Tuning for Audio Deepfake Detection: Computationally Efficient Test-time Domain Adaptation with Limited Target Datasetcited by 7
  24. 2024Explainable Detection of Machine Generated Music and Early Systematic Evaluationcited by 6
  25. 2024XWSB: A Blend System Utilizing XLS-R and WavLM with SLS Classifier detection system for SVDD 2024 Challengecited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 6.

7 papers.

  1. 2026Interpretable All-Type Audio Deepfake Detection with Audio LLMs via Frequency-Time Reinforcement Learningcited by 6
  2. 2025WaveSP-Net: Learnable Wavelet-Domain Sparse Prompt Tuning for Speech Deepfake Detectioncited by 5
  3. 2026WaveScat: Wavelet Scattering Front-Ends with Self-Supervised Features for Speech Deepfake Detectioncited by 3
  4. 2026AT-ADD: All-Type Audio Deepfake Detection Challenge Evaluation Plancited by 3
  5. 2026REIMU: Efficient Heterogeneous Hierarchical Reasoning for SSL-Based Speech Deepfake Detectioncited by 1
  6. 2026ToolDF: Tool-Integrated Reasoning for Mixed-Authenticity Audio Deepfake Detectioncited by 0
  7. 2026GLAD: Global-Local Adaptive Detector for Robust Speech Deepfake Detectioncited by 0