Robust Deepfake Audio Detection via Bi-Level Optimization
The DOI matches its Crossref record; 29 of the 29 references it cites were found in a registry or an index.
Abstract
ASVspoof Challenges have been launched to motivate research on Deepfake audio detection due to its threats to society. However, the state-of-the-art detection models produce an unsatisfactory performance on the Speech Deepfake (DF) of the challenge. The DF subset includes spoofed audio from various sources, which can better reflect the robustness of the detector. In this paper, we propose a novel detection architecture to improve the robustness and generalization ability in two ways. The first way is aggregating both learned embeddings and hand-crafted features to obtain more generalizable representations for Deepfake audio. Our second contribution is formulating the training process a bi-level optimization problem to make use of the knowledge of different Deepfake generation methods. Evaluations of our proposed method provide the best detection output reported in the literature as a single system without the help of ensemble modeling and data augmentation.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Li et al. [119] combined SincNet-learned features with the Mel-Spectrogram to provide high-dimensional embeddings for subsequent classifiers, thereby enhancing the model’s robustness against diverse deepfake audio scenarios.”
From Audio Deepfake Detection: What Has Been Achieved and What Lies Ahead (2025) · cites this paper as [119]
Citations
Cites
Transformers: State-of-the-Art Natural Language Processing
Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtowicz, M., et al. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations · doi:10.18653/v1/2020.emnlp-demos.6 · Cited by 8,741
An overview of bilevel optimization
Colson, B., Marcotte, P., & Savard, G. (2007) · Annals of Operations Research · doi:10.1007/s10479-007-0176-2 · Cited by 1,409
AST: Audio Spectrogram Transformer
Gong, Y., Chung, Y.-A., & Glass, J. (2021) · Interspeech 2021 · doi:10.21437/interspeech.2021-698 · Cited by 1,159
ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detection
Todisco, M., Wang, X., Vestman, V., Sahidullah, M., Delgado, H., Nautsch, A., Yamagishi, J., Evans, N., Kinnunen, T., & Lee, K. A. (2019) · arXiv · doi:10.48550/arxiv.1904.05441 · Cited by 688 · cited 1×
“The ASVspoof Challenges are hosted regularly to inspire academicians to propose cutting-edge research spoofed audio detection [1].”
BackgroundASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detection
Todisco, M., Wang, X., Vestman, V., Sahidullah, M., Delgado, H., Nautsch, A., Yamagishi, J., Evans, N., Kinnunen, T. H., & Lee, K. A. (2019) · Interspeech 2019 · doi:10.21437/interspeech.2019-2249 · Cited by 687
End-to-End anti-spoofing with RawNet2
Tak, H., Patino, J., Todisco, M., Nautsch, A., Evans, N., & Larcher, A. (2021) · ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp39728.2021.9414234 · Cited by 402 · cited 2×
“Tak et al. [6] first adopted SincNet to process the raw audio data and produce deep embeddings in an End-to-End Deepfake audio detector.”
MethodInfluentialA comparison of features for synthetic speech detection
Sahidullah, M., Kinnunen, T., & Hanilçi, C. (2015) · Interspeech 2015 · doi:10.21437/interspeech.2015-472 · Cited by 382 · cited 1×
“…hand-crafted acoustic and perceptual features, such as Mel-frequency Cepstral Coefficients (MFCC) [8], [9], Constant Q Cepstral Coefficients (CQCC) [10], [11], and Perceptual Linear Predictive Coefficient (PLP) [12], have been widely used in the Deepfake detectors to extract audio representations.”
MethodASVspoof 2021: accelerating progress in spoofed and deepfake speech detection
Yamagishi, J., Wang, X., Todisco, M., Sahidullah, M., Patino, J., Nautsch, A., Liu, X., Lee, K. A., Kinnunen, T., Evans, N., et al. (2021) · 2021 Edition of the Automatic Speaker Verification and Spoofing Countermeasures Challenge · doi:10.21437/asvspoof.2021-8 · Cited by 380
ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wild
Liu, X., Wang, X., Sahidullah, M., Patino, J., Delgado, H., Kinnunen, T., Todisco, M., Yamagishi, J., Evans, N., Nautsch, A., et al. (2023) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2023.3285283 · Cited by 312 · cited 2×
“The full DF evaluation database contains spoofed audio from various sources in different storage formats, which are generated with more than 100 spoofing algorithms that differ from those seen in the training set [4].”
BackgroundMethodSTC Antispoofing Systems for the ASVspoof2019 Challenge
Lavrentyeva, G., Novoselov, S., Tseren, A., Volkova, M., Gorlanov, A., & Kozlov, A. (2019) · Interspeech 2019 · doi:10.21437/interspeech.2019-1768 · Cited by 245
Cited by
Audio Deepfake Detection: What Has Been Achieved and What Lies Ahead
Zhang, B., Cui, H., Nguyen, V., & Whitty, M. (2025) · Sensors · doi:10.3390/s25071989 · Cited by 72
Advancements in AI-Generated Content Forensics: A Systematic Literature Review
Xu, Q., Mu, W., Li, J., Sun, T., & Jiang, X. (2025) · ACM Computing Surveys · doi:10.1145/3760526 · Cited by 26
A Hybrid CNN-LSTM Approach for Deepfake Audio Detection
Chitale, M., Dhawale, A., Dubey, M., & Ghane, S. (2024) · International Conference on Artificial Intelligence for Internet of Things (AIIoT) · doi:10.1109/aiiot58432.2024.10574576 · Cited by 30
A Robust and Lightweight CNN-Transformer Model for Audio Deepfake Detection in Indian Languages
Gaikawad, M., & Ghosh, S. N. (2025) · International Conference on Signal Processing, Computing and Control (ISPCC) · doi:10.1109/ispcc66872.2025.11039572 · Cited by 4
Uddin, K., Khan, A. A., Farooq, M. U., & Malik, K. M. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00161 · Cited by 15
Metadata
- Authors
- Li, M., Ahmadiadli, Y., & Zhang, X.-P.
- Affiliations
- Toronto Metropolitan University (CA)
- Venue
- 2023 IEEE 25th International Workshop on Multimedia Signal Processing (MMSP)
- Publisher
- IEEE
- Published
- 2023-09-27
- Pages
- 1-6
- OpenAlex
- W4389474419
- Cited by
- 7
- References
- 29
- Citations by year
- 2026: 1 · 2025: 5 · 2024: 1
- FWCI
- 1.24
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Workshop on Multimedia Signal Processing (MMSP) (publishedVersion)
- 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, voice spoofing, ASVspoof, bi-level optimization, learned embeddings, handcrafted features, feature fusion, robustness, generalization, spoofed speech
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: Robust Deepfake Audio Detection via Bi-Level Optimization. https://app.cochat.ai/papers/10.1109/mmsp59012.2023.10337724
- The paper
- Li, M., Ahmadiadli, Y., & Zhang, X.-P. (2023). Robust Deepfake Audio Detection via Bi-Level Optimization. 2023 IEEE 25th International Workshop on Multimedia Signal Processing (MMSP). https://doi.org/10.1109/mmsp59012.2023.10337724
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.