Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 53 of the 53 references it cites were found in a registry or an index.

AWaveFormer: Audio Wavelet Transformer Network for Generalized Audio Deepfake Detection

Wang, Rui, Chen, Zirui, Wang, Bo, Ba, Zhongjie, Ren, Kui · 2025 · IEEE Transactions on Audio, Speech and Language Processing

Abstract

Rapid advancements in speech synthesis technology have made it easier to produce realistic synthetic speech, which poses serious threats to public privacy and security. Recent studies have investigated pre-trained models for feature extraction and adopted advanced architectures, including convolutional and graph neural networks, for deepfake detection. Although these methods improve detection performance to some extent, their generalization and robustness still face challenges. To address this issue, in this paper, we propose a forgery detection method based on the fusion of dual pre-trained features and an optimized Transformer architecture. Specifically, we use a cross-attention mechanism to fuse the audio features extracted from pre-trained Wav2vec 2.0 and WavLM, and replace the token mixer in the traditional Transformer architecture with wavelet transform and multi-scale pooling operations. By combining dual pre-trained features, we extract more comprehensive and discriminative features while optimizing the Transformer architecture, which not only reduces time complexity but also enhances detection performance. We conducted experiments on several datasets, and the results show that our model achieves impressive detection performance with EERs of 0.13%, 2.33%, 3.63%, 10.25%, 5.15%, and 0.21% on the ASVspoof 2019LA, ASVspoof 2021LA, ASVspoof 2021DF, In-the-Wild, Fake-or-Real, and ASVspoof 2015LA evaluation datasets, respectively.

Overview

Integrity signals

Registry

Crossref · 10.1109/taslpro.2025.3611229

Cites

53 of 53 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Citations

Cites

Show all 49 references

Research works printed but not linked: 1

  1. Kang, 2021, CRIMs system description for the ASVSPoof2021 challenge, 100

Cited by

See all 10

Metadata

Authors
Wang, R., Chen, Z., Wang, B., Ba, Z., & Ren, K.
Affiliations
  • Dalian University of Technology (CN)
  • Zhejiang University (CN)
Venue
IEEE Transactions on Audio, Speech and Language Processing
Published
2025
Volume
33
Pages
4020-4032
ISSN
2998-4173 (ISSN-L)
OpenAlex
W4414270811
Cited by
10
References
49
Citations by year
2026: 10
FWCI
4.04
Type
journal article
Language
en
Open access
closed
Locations
IEEE Transactions on Audio Speech and Language Processing (publishedVersion)
Funders
  • National Natural Science Foundation of China (62372452)
  • Youth Innovation Promotion Association of the Chinese Academy of Sciences
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
  • Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
Keywords
audio deepfake detection, synthetic speech detection, wav2vec 2.0, WavLM, cross-attention fusion, wavelet transform, multi-scale pooling, token mixer, pre-trained feature extraction, ASVspoof

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: AWaveFormer: Audio Wavelet Transformer Network for Generalized Audio Deepfake Detection. https://app.cochat.ai/papers/10.1109/taslpro.2025.3611229
The paper
Wang, R., Chen, Z., Wang, B., Ba, Z., & Ren, K. (2025). AWaveFormer: Audio Wavelet Transformer Network for Generalized Audio Deepfake Detection. IEEE Transactions on Audio, Speech and Language Processing. https://doi.org/10.1109/taslpro.2025.3611229

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.