The DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Multi-level SSL Feature Gating for Audio Deepfake Detection
Open accessAbstract
Recent advancements in generative AI, particularly in speech synthesis, have enabled the generation of highly natural-sounding synthetic speech that closely mimics human voices. While these innovations hold promise for applications like assistive technologies, they also pose significant risks, including misuse for fraudulent activities, identity theft, and security threats. Current research on spoofing detection countermeasures remains limited by generalization to unseen deepfake attacks and languages. To address this, we propose a gating mechanism extracting relevant feature from the speech foundation XLS-R model as a front-end feature extractor. For downstream back-end classifier, we employ Multi-kernel gated Convolution (MultiConv) to capture both local and global speech artifacts. Additionally, we introduce Centered Kernel Alignment (CKA) as a similarity metric to enforce diversity in learned features across different MultiConv layers. By integrating CKA with our gating mechanism, we hypothesize that each component helps improving the learning of distinct synthetic speech patterns. Experimental results demonstrate that our approach achieves state-of-the-art performance on in-domain benchmarks while generalizing robustly to out-of-domain datasets, including multilingual speech samples. This underscores its potential as a versatile solution for detecting evolving speech deepfake threats.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
The publisher hasn’t deposited this paper’s reference list.
Research works printed but not linked: 57
- 10.5120/20312-2362 · doi:10.5120/20312-2362
- Rosana Ardila Megan Branson Kelly Davis Michael Kohler Josh Meyer Michael Henretty Reuben Morais Lindsay Saunders Francis Tyers and Gregor Weber. 2020. Common Voice: A Massively-Multilingual Speech Corpus. In Proceedings of the Twelfth Language Resources and Evaluation Conference Nicoletta Calzolari Frédéric Béchet Philippe Blache Khalid Choukri Christopher Cieri Thierry Declerck Sara Goggi Hitoshi Isahara Bente Maegaard Joseph Mariani Hélène Mazo Asuncion Moreno Jan Odijk and Stelios Piperidis (Eds.). European Language Resources Association Marseille France 4218-4222. https://aclanthology.org/2020.lrec-1.520/
- 10.1145/3543507.3583222 · DOI
- Alexei Baevski, Yuhao Zhou, Abdelrahman Mohamed, and Michael Auli. 2020. wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations. In Advances in NeurIPS, Vol. 33.
- 10.1109/JSTSP.2022.3188113 · DOI · Paper page
- 10.18653/v1/2024.findings-naacl.160 · DOI
- 10.1016/j.csl.2020.101182 · DOI
- 10.1109/SLT61566.2024.10832250 · DOI
- Mark J. F. Gales, Kate M. Knill, Anton Ragni, and Shakti P. Rath. 2014. Speech recognition and keyword spotting for low-resource languages: Babel project research at CUED. In 4th Workshop on Spoken Language Technologies for Under-resourced Languages, SLTU 2014, St. Petersburg, Russia, May 14-16, 2014. ISCA, 16-23. https://www.isca-archive.org/sltu_2014/gales14_sltu.html
- Albert Gu and Tri Dao. 2024. Mamba: Linear-Time Sequence Modeling with Selective State Spaces. In First Conf. on Lang. Modeling.
- 10.21437/Interspeech.2020-3015 · DOI · Paper page
- Yinlin Guo Haofan Huang Xi Chen He Zhao and Yuehai Wang. 2024. Audio Deepfake Detection With Self-Supervised Wavlm And Multi-Fusion Attentive Classifier. In ICASSP. doi:10.1109/ICASSP48485.2024.10447923 · DOI · Paper page
- 10.1109/ICASSP49660.2025.10889337 · DOI
- Weizhe Hua, Yuan Zhou, Christopher M De Sa, Zhiru Zhang, and G. Edward Suh. 2019. Channel Gating Neural Networks. In Advances in Neural Information Processing Systems, H. Wallach, H. Larochelle, A. Beygelzimer, F. dtextquotesingle Alché-Buc, E. Fox, and R. Garnett (Eds.), Vol. 32. Curran Associates, Inc. https://proceedings.neurips.cc/paper_files/paper/2019/file/68b1fbe7f16e4ae3024973f12f3cb313-Paper.pdf
- 10.1109/ICASSP49660.2025.10888328 · DOI
- Miquel India Pooyan Safari and Javier Hernando. 2019. Self Multi-Head Attention for Speaker Recognition. In Interspeech. doi:10.21437/Interspeech.2019-2616 · DOI
- Jiachen Jiang, Jinxin Zhou, and Zhihui Zhu. 2025. Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity. In The Thirteenth International Conference on Learning Representations. https://openreview.net/forum?id=vVxeFSR4fU
- 10.1109/ICASSP49660.2025.10890563 · DOI
- 10.1109/ICASSP43922.2022.9747766 · DOI · Paper page
- Yassine El Kheir, Youness Samih, Suraj Maharjan, Tim Polzehl, and Sebastian Möller. 2025. Comprehensive Layer-wise Analysis of SSL Models for Audio Deepfake Detection. arXiv preprint arXiv:2502.03559 (2025). · arXiv
- 10.21437/Interspeech.2017-1111 · DOI · Paper page
- Simon Kornblith, Mohammad Norouzi, Honglak Lee, and Geoffrey Hinton. 2019. Similarity of neural network representations revisited. In International conference on machine learning. PMLR, 3519-3529.
- Hanxiao Liu Zihang Dai David So and Quoc V Le. 2021. Pay Attention to MLPs. In Advances in NeurIPS.
- 10.1109/TASLP.2023.3285283 · DOI · Paper page
- Bartłomiej Marek, Piotr Kawa, and Piotr Syga. 2024. Are audio DeepFake detection models polyglots? arXiv preprint arXiv:2412.17924 (2024). · arXiv
- 10.1109/ICASSP43922.2022.9747768 · DOI · Paper page
- Nicolas Müller Pavel Czempin Franziska Diekmann Adam Froghyar and Konstantin Böttinger. 2022. Does Audio Deepfake Detection Generalize?. In Interspeech. doi:10.21437/Interspeech.2022-108 · DOI · Paper page
- 10.1109/IJCNN60899.2024.10650962 · DOI · Paper page
- Zihan Pan Tianchi Liu Hardik B. Sailor and Qiongqiong Wang. 2024. Attentive Merging of Hidden Embeddings from Pre-trained Speech Model for Anti-spoofing Detection. In Interspeech. doi:10.21437/Interspeech.2024-1472 · DOI · Paper page
- 10.1073/pnas.2015509117 · DOI · Paper page
- 10.1109/ASRU51503.2021.9688093 · DOI · Paper page
- 10.1109/ICASSP49357.2023.10096149 · DOI
- Darshan Prabhu Yifan Peng Preethi Jyothi and Shinji Watanabe. 2024. MULTI-CONVFORMER: Extending Conformer with Multiple Convolution Kernels. In Interspeech. doi:10.21437/Interspeech.2024-2384 · DOI
- Vineel Pratap, Andros Tjandra, Bowen Shi, Paden Tomasello, Arun Babu, Sayani Kundu, Ali Elkahky, Zhaoheng Ni, Apoorv Vyas, Maryam Fazel-Zarandi, Alexei Baevski, Yossi Adi, Xiaohui Zhang, Wei-Ning Hsu, Alexis Conneau, and Michael Auli. 2024. Scaling Speech Technology to 1,000+ Languages. Journal of Machine Learning Research, Vol. 25, 97 (2024).
- 10.21437/Interspeech.2020-2826 · DOI · Paper page
- 10.1109/SPED.2019.8906599 · DOI · Paper page
- 10.1109/ICASSP43922.2022.9746213 · DOI
- 10.21437/Odyssey.2022-16 · DOI · Paper page
- 10.21437/Interspeech.2023-2272 · doi:10.21437/interspeech.2023-2272
- 10.1016/j.csl.2017.01.001 · DOI · Paper page
- Hoan My Tran David Guennec Philippe Martin Aghilas Sini Damien Lolive Arnaud Delhay and Pierre-François Marteau. 2024. Spoofed Speech Detection with a Focus on Speaker Embedding. In Interspeech. doi:10.21437/Interspeech.2024-481 · DOI · Paper page
- 10.21437/Interspeech.2024-659 · DOI
- 10.1109/SLT48900.2021.9383459 · DOI
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in NeurIPS, Vol. 30.
- 10.1109/CVPR52733.2024.01035 · DOI
- 10.1016/j.csl.2020.101114 · DOI · Paper page
- Zhiyong Wang Ruibo Fu Zhengqi Wen Jianhua Tao Xiaopeng Wang Yuankun Xie Xin Qi Shuchen Shi Yi Lu Yukun Liu et al. 2024b. Mixture of experts fusion for fake audio detection using frozen wav2vec 2.0. arXiv preprint arXiv:2409.11909 (2024). · DOI
- 10.21437/Interspeech.2015-462 · DOI · Paper page
- 10.1109/LSP.2025.3547861 · DOI
- Junichi Yamagishi Christophe Veaux and Kirsten MacDonald. 2019. CSTR VCTK Corpus: English Multi-speaker Corpus for CSTR Voice Cloning Toolkit. https://api.semanticscholar.org/CorpusID:213060286
- 10.21437/ASVSPOOF.2021-8 · DOI · Paper page
- Jiangyan Yi, Jianhua Tao, Ruibo Fu, Xinrui Yan, Chenglong Wang, Tao Wang, Chu Yuan Zhang, Xiaohui Zhang, Yan Zhao, Yong Ren, Le Xu, Junzuo Zhou, Hao Gu, Zhengqi Wen, Shan Liang, Zheng Lian, Shuai Nie, and Haizhou Li. 2023. ADD 2023: the Second Audio Deepfake Detection Challenge. In Proceedings of the Workshop on Deepfake Audio Detection and Analysis co-located with 32th International Joint Conference on Artificial Intelligence (IJCAI 2023), Macao, China, August 19, 2023 (CEUR Workshop Proceedings, Vol. 3597), Jianhua Tao, Haizhou Li, Jiangyan Yi, and Cunhang Fan (Eds.). CEUR-WS.org, 125-130. https://ceur-ws.org/Vol-3597/paper21.pdf
- 10.21437/VCCBC.2020-14 · DOI · Paper page
- Lin Zhang Xin Wang Erica Cooper Mireia Diez Federico Landini Nicholas Evans and Junichi Yamagishi. 2024b. Spoof Diarization: ''What Spoofed When'' in Partially Spoofed Audio. In Interspeech. doi:10.21437/Interspeech.2024-1365 · DOI
- Lin Zhang Xin Wang Erica Cooper Nicholas Evans and Junichi Yamagishi. 2023. Range-Based Equal Error Rate for Spoof Localization. In Interspeech. doi:10.21437/Interspeech.2023-1214 · DOI
- 10.1145/3664647.3681345 · DOI
- Yuxiang Zhang Jingze Lu Zengqiang Shang Wenchao Wang and Pengyuan Zhang. 2024a. Improving Short Utterance Anti-Spoofing with Aasist2. In ICASSP. doi:10.1109/ICASSP48485.2024.10448049 · DOI
Cited by
Nguyen-Le, H.-H., Tran, V.-T., Nguyen, D.-T., & Le-Khac, N.-A. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-026-11608-4 · Cited by 28
KAN We Make Models Simpler for Audio Deepfake Detection with Kolmogorov–Arnold Networks?
Tran, H. M., Sini, A., Guennec, D., Delhay, A., Lolive, D., & Marteau, P.-F. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11460320
Self-citationLAW: A Training-Free Latent Watermark for Diffusion-Generated Audio Attribution
Zhu, R., Zou, L., Lai, S., Shen, Z., Li, Z., & Qiao, T. (2026) · IEEE Signal Processing Letters · doi:10.1109/lsp.2026.3702794 · Cited by 1
MSLA-XLS-R: Enhancing hierarchical SSL representations for audio deepfake detection
Meng, H., Tang, Y., Sun, Y., Deng, Y., Li, Z., & Li, Y. (2026) · Computer Speech & Language · doi:10.1016/j.csl.2026.102019
Tran, H. M., Lolive, D., Sini, A., Guennec, D., Delhay, A., & Marteau, P.-F. (2026) · Journées d'Études sur la Parole (JEP) · doi:10.21437/jep.2026-48
Self-citation
Metadata
- Authors
- Tran, H. M., Lolive, D., Sini, A., Delhay, A., Marteau, P.-F., & Guennec, D.
- Affiliations
- Centre National de la Recherche Scientifique (FR)
- Le Mans Université (FR)
- Venue
- Proceedings of the 33rd ACM International Conference on Multimedia
- Publisher
- ACM
- Published
- 2025-10-27
- Pages
- 11766-11775
- OpenAlex
- W4415348517
- Cited by
- 4
- References
- 0
- Citations by year
- 2026: 4
- FWCI
- 3.79
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- ACM International Conference on Multimedia (ACM MM) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- HAL (submittedVersion, cc-by)
- arXiv (Cornell University)
- Funders
- Agence Nationale de la Recherche (ANR-20-THIA-0018)
- Grand Équipement National De Calcul Intensif
- 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, speech spoofing detection, synthetic speech, feature gating, centered kernel alignment, multilingual speech, out-of-domain generalization
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: Multi-level SSL Feature Gating for Audio Deepfake Detection. https://app.cochat.ai/papers/10.1145/3746027.3754568
- The paper
- Tran, H. M., Lolive, D., Sini, A., Delhay, A., Marteau, P.-F., & Guennec, D. (2025). Multi-level SSL Feature Gating for Audio Deepfake Detection. Proceedings of the 33rd ACM International Conference on Multimedia. https://doi.org/10.1145/3746027.3754568
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.