The DOI matches its Crossref record; 98 of the 118 references it cites were found in a registry or an index.
Domain Generalization via Aggregation and Separation for Audio Deepfake Detection
Abstract
In this paper, we propose an Aggregation and Separation Domain Generalization (ASDG) method for Audio DeepFake Detection (ADD). Fake speech generated from different methods exhibits varied amplitude and frequency distributions rather than genuine speech. In addition, the spoofing attacks in training sets may not keep pace with the evolving diversity of real-world deepfake distributions. In light of this, we attempt to learn an ideal feature space that can aggregate real speech and separate fake speech to achieve better generalizability in the detection of unseen target domains. Specifically, we first propose a feature generator based on Lightweight Convolutional Neural Networks (LCNN), which is employed for generating a feature space and categorizing the feature into real and fake. Meanwhile, single-side domain adversarial learning is leveraged to make only the real speech from different domains indistinguishable, which enables the distribution of real speech to be aggregated in the feature space. Furthermore, a triplet loss is adopted to separate the distribution of fake speech while aggregating the distribution of real speech. Finally, in order to test the generalizability of the model, we train it with three different English datasets and evaluate in harsh conditions: cross-language and noisy datasets. The extensive experiments show that ASDG outperforms the baseline models in cross-domain tasks and decreases Equal Error Rate (EER) by up to 39.24% when compared to that of RawNet2. It is proved that the proposed Aggregation and Separation Domain Generalization method can be an effective strategy to improve the model generalizability.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
(2008) · Journal of Machine Learning Research · Cited by 33,051
Xception: Deep Learning with Depthwise Separable Convolutions
Chollet, F. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.195 · Cited by 20,380
FaceNet: A unified embedding for face recognition and clustering
Schroff, F., Kalenichenko, D., & Philbin, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298682 · Cited by 15,267
Denoising Diffusion Probabilistic Models
Ho, J., Jain, A., & Abbeel, P. (2020) · arXiv · doi:10.48550/arxiv.2006.11239 · Cited by 8,712
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
Deng, J., Guo, J., Xue, N., & Zafeiriou, S. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00482 · Cited by 7,781
“Librispeech: an ASR corpus based on public domain audio books,”
Panayotov, V., Chen, G., Povey, D., & Khudanpur, S. (2015) · 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2015.7178964 · Cited by 6,072
IEMOCAP: Interactive emotional dyadic motion capture database
Busso, C., Bulut, M., Lee, C.-C., Kazemzadeh, A., Mower, E., Kim, S., Chang, J. N., Lee, S., & Narayanan, S. S. (2008) · Language Resources and Evaluation · doi:10.1007/s10579-008-9076-6 · Cited by 3,869
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
Park, D. S., Chan, W., Zhang, Y., Chiu, C.-C., Zoph, B., Cubuk, E. D., & Le, Q. V. (2019) · Interspeech 2019 · doi:10.21437/interspeech.2019-2680 · Cited by 3,558
Natural TTS Synthesis by Conditioning Wavenet on MEL Spectrogram Predictions
Shen, J., Pang, R., Weiss, R. J., Schuster, M., Jaitly, N., Yang, Z., Chen, Z., Zhang, Y., Wang, Y., Skerrv-Ryan, R., et al. (2018) · 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2018.8461368 · Cited by 2,791
Self-citationUnsupervised Domain Adaptation by Backpropagation
Ganin, Y., & Lempitsky, V. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1409.7495 · Cited by 2,521
Research works printed but not linked: 2
- Baevski, wav2vec 2.0: A framework for self-supervised learning of speech representations, 33, 12449
- Chakroborty, 2009, Improved text-independent speaker identification using fused MFCC & IMFCC feature sets based on Gaussian filter, Int. J. Signal Process., 5, 11
Cited by
Dual Defense: Adversarial, Traceable, and Invisible Robust Watermarking Against Face Swapping
Zhang, Y., Ye, D., Xie, C., Tang, L., Liao, X., Liu, Z., Chen, C., & Deng, J. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3383648 · Cited by 82
“Passive detection involves training detectors to retrospectively validate forged images [4], [6], [7], [8], while active defense methods primarily include deep watermarking-based defense [9], [10] and adversarial examples-based defense [11], [12], [13].”
BackgroundKhan, A. A., Laghari, A. A., Inam, S. A., Ullah, S., Shahzad, M., & Syed, D. (2025) · Discover Computing · doi:10.1007/s10791-025-09550-0 · Cited by 97
Zhang, K., Hua, Z., Zhang, Y., Guo, Y., & Xiang, T. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3520001 · Cited by 20
“Previous adversarial and contrastive learning-based methods [35], [40], [41] concentrate on clustering feature spaces from different domain samples.”
InfluentialCoarse-to-Fine Proposal Refinement Framework for Audio Temporal Forgery Detection and Localization
Wu, J., Lu, W., Luo, X., Yang, R., Wang, Q., & Cao, X. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3680585 · Cited by 39
“In addition, ASDG [32] utilized aggregation and separation domain generalization to learn an optimal feature space that can aggregate real audio and fake audio, resulting in better generalizability in detecting unseen target domains.”
MethodLeveraging Mixture of Experts for Improved Speech Deepfake Detection
Negroni, V., Salvi, D., Mezza, A. I., Bestagini, P., & Tubaro, S. (2025) · ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp49660.2025.10890398 · Cited by 14
Metadata
- Authors
- Xie, Y., Cheng, H., Wang, Y., & Ye, L.
- Affiliations
- State Key Laboratory of Media Convergence and Communication (CN)
- Venue
- IEEE Transactions on Information Forensics and Security
- Published
- 2024
- Volume
- 19
- Pages
- 344-358
- ISSN
- 1556-6013 (ISSN-L)
- 1556-6021
- OpenAlex
- W4387665604
- Cited by
- 59
- References
- 118
- Citations by year
- 2026: 22 · 2025: 24 · 2024: 13
- FWCI
- 5.55
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Information Forensics and Security (publishedVersion)
- Funders
- Natural Science Foundation of China (62201524, 62271455, 61971383)
- Fundamental Research Funds for the Central Universities (CUC23GZ016)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Keywords
- audio deepfake detection, domain generalization, anti-spoofing, lightweight convolutional neural network, domain adversarial learning, triplet loss, cross-lingual generalization, noisy speech, unseen target domains, voice spoofing
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: Domain Generalization via Aggregation and Separation for Audio Deepfake Detection. https://app.cochat.ai/papers/10.1109/tifs.2023.3324724
- The paper
- Xie, Y., Cheng, H., Wang, Y., & Ye, L. (2024). Domain Generalization via Aggregation and Separation for Audio Deepfake Detection. IEEE Transactions on Information Forensics and Security. https://doi.org/10.1109/tifs.2023.3324724
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.