Attentive Merging of Hidden Embeddings from Pre-trained Speech Model for Anti-spoofing Detection
Open accessThe DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
Abstract
Self-supervised learning (SSL) speech representation models, trained on large speech corpora, have demonstrated effectiveness in extracting hierarchical speech embeddings through multiple transformer layers. However, the behavior of these embeddings in specific tasks remains uncertain. This paper investigates the multi-layer behavior of the WavLM model in anti-spoofing and proposes an attentive merging method to leverage the hierarchical hidden embeddings. Results demonstrate the feasibility of fine-tuning WavLM to achieve the best equal error rate (EER) of 0.65%, 3.50%, and 3.19% on the ASVspoof 2019LA, 2021LA, and 2021DF evaluation sets, respectively. Notably, We find that the early hidden transformer layers of the WavLM large model contribute significantly to anti-spoofing task, enabling computational efficiency by utilizing a partial pre-trained model.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
The publisher hasn’t deposited this paper’s reference list.
Cited by
Mixture of Experts Fusion for Fake Audio Detection Using Frozen wav2vec 2.0
Wang, Z., Fu, R., Wen, Z., Tao, J., Wang, X., Xie, Y., Qi, X., Shi, S., Lu, Y., Liu, Y., et al. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888990 · Cited by 54
Generalizable Audio Deepfake Detection via Latent Space Refinement and Augmentation
Huang, W. C., Gu, Y., Wang, Z., Zhu, H., & Qian, Y. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888328 · Cited by 45
Nes2Net: A Lightweight Nested Architecture for Foundation Model Driven Speech Anti-Spoofing
Liu, T., Truong, D.-T., Das, R. K., Lee, K. A., & Li, H. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3626963 · Cited by 69
Self-citationGuragain, A., Liu, T., Pan, Z., Sailor, H. B., & Wang, Q. (2024) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt61566.2024.10832226 · Cited by 39
Self-citationSVDD 2024: The Inaugural Singing Voice Deepfake Detection Challenge
Zhang, Y., Zang, Y., Shi, J., Yamamoto, R., Toda, T., & Duan, Z. (2024) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt61566.2024.10832284 · Cited by 20
Comprehensive Layer-wise Analysis of SSL Models for Audio Deepfake Detection
El Kheir, Y., Samih, Y., Maharjan, S., Polzehl, T., & Möller, S. (2025) · Findings of the Association for Computational Linguistics: NAACL 2025 · doi:10.18653/v1/2025.findings-naacl.227 · Cited by 16
DFADD: The Diffusion and Flow-Matching Based Audio Deepfake Dataset
Du, J., Lin, I.-M., Chiu, I.-H., Chen, X., Wu, H., Ren, W., Tsao, Y., Lee, H.-Y., & Jang, J. R. (2024) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt61566.2024.10832250 · Cited by 54
Generalizable Audio Deepfake Detection via Latent Space Refinement and Augmentation
Huang, W., Gu, Y., Wang, Z., Zhu, H., & Qian, Y. (2025) · arXiv · doi:10.48550/arxiv.2501.14240 · Cited by 16
Angra, A., Muralikrishna, H., Dinesh, D. A., & Thenkanidiyoor, V. (2024) · IEEE Access · doi:10.1109/access.2024.3523951 · Cited by 14
Towards Quantifying and Reducing Language Mismatch Effects in Cross-Lingual Speech Anti-Spoofing
Liu, T., Kukanov, I., Pan, Z., Wang, Q., Sailor, H. B., & Lee, K. A. (2024) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt61566.2024.10832142 · Cited by 18
Self-citationLin, T.-Q., Huang, W.-P., Tang, H., & Lee, H.-Y. (2025) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2025.3635827 · Cited by 11
MoLEx: Mixture of LoRA Experts in Speech Self-Supervised Models for Audio Deepfake Detection
Pan, Z., Sailor, H. B., & Wu, J. (2025) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru65441.2025.11434670 · Cited by 13
Self-citationHao, Y., Chen, Y., Xu, M., Zhan, J., He, L., Fang, L., Fang, S., & Liu, L. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228261 · Cited by 8
RPRA-ADD: Forgery Trace Enhancement-Driven Audio Deepfake Detection
Fu, R., Wang, X., Wen, Z., Tao, J., Xie, Y., Wang, Z., Qiang, C., Liu, X., Fan, C., Li, C., et al. (2025) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2025.3646051 · Cited by 5
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 You Hear the Truth? Audio Deepfake Detection with Kolmogorov–Arnold Networks
Tran, H. M., Lolive, D., Guennec, D., Sini, A., Delhay, A., & Marteau, P.-F. (2025) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco63237.2025.11226534 · Cited by 4
Robust Deepfake Audio Detection via Multi-Level Intermediate Feature Fusion
Zhao, J. S., Zhao, J. S., Zhou, Y., Zheng, P., & Du, Y. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462275 · Cited by 1
Ge, Z., Xu, X., Guo, H., Wang, T., & Yang, Z. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3698578 · Cited by 1
Yang, M., Gu, Y., He, Q., Zhang, P., He, H., Wang, Z., Zhu, H., Liu, J., & Wang, W. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755593 · Cited by 4
Yu, G., Guo, W., Zhang, J., & Zhang, Z. (2025) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipaasc65261.2025.11249219 · Cited by 2
Continual Audio Deepfake Detection via Universal Adversarial Perturbation
Li, W., Li, L., & Hong, Q. (2025) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipaasc65261.2025.11249335 · Cited by 2
A Federated Deepfake Speech Detection Method Based on Layer-Wise Center-Guided Weighting Aggregation
Yu, Y., Guo, H., Wang, T., Ge, Z., & Liu, C. (2025) · International Conference on Wireless Communications and Signal Processing (WCSP) · doi:10.1109/wcsp68525.2025.1010653
Robust Speech Forgery Detection via Enhanced Forensic Trace Generation
Wu, S., Cheng, Y., Wang, R., & Yan, D. (2026) · Signal Image and Video Processing · doi:10.1007/s11760-026-05167-y
Jing, H., Wei, W., Yang, F., & Zhang, Y. (2025) · International Conference on Virtual Reality and Visualization · doi:10.1109/icvrv67992.2025.00057
Leveraging Gaussian Attention for Adapter‐Based Fine‐Tuning of WavLM in Audio Deepfake Detection
Wang, Y., Lin, X., Qiu, Y., & Tan, G. (2026) · International Journal of Intelligent Systems · doi:10.1155/int/6786731 · Cited by 1
Stacked Fourier Neural Network for Speech Spoofing Detection
Xie, B. (2025) · International Conference on Big Data, Artificial Intelligence and Risk Management (ICBAR) · doi:10.1145/3800227.3800251
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
Group-Wise Layer Aggregation of Self-Supervised Representations for Speech Emotion Recognition
Park, S., Kim, H. S., & Kong, K. (2026) · IEEE Signal Processing Letters · doi:10.1109/lsp.2026.3707494
Towards Lightweight On-Device Audio Deepfake Detection Using Squeezeformers
Moradi, A., Zhu, Y., & Falk, T. H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-20732-6_24
CL-RASDML: Cross-Lingual Replay Attack Simulation and Detection in Multi-Lingual Datasets
Tiwari, S., Tejani, K., Kasat, D., Mehta, A., & Patel, S. (2026) · International Conference on Speech, Multimodal and Advanced Communication Systems (ICSMACS) · doi:10.1109/icsmacs68968.2026.11628590
Improving Audio Anti-Spoofing with FLA and Local-global Feature Fusion
Sang, J., & Huang, Z. (2026) · International Conference on Electronic Engineering and Informatics (EEI) · doi:10.1109/eei70303.2026.11640547 · Cited by 1
Multi-Prototype Variational Information Bottleneck for SSL-Based Speech Spoofing Detection
Hou, H., Zhou, R., & Yuan, Q. (2026) · IEEE Access · doi:10.1109/access.2026.3722601
Li, Y., Fang, Y., Xue, J., Milling, M., & Schuller, B. W. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1928592
Kim, S.-B., Kim, K.-W., & Yu, H.-J. (2026) · IEEE Access · doi:10.1109/access.2026.3742554
Defending Against Audio Spoofing Attacks via Emotion-Aware Prototype Metric Learning
Li, X., Gong, Y., Zou, D., & Chen, J. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-6834-4_25
Metadata
- Authors
- Pan, Z., Liu, T., Sailor, H. B., & Wang, Q.
- Venue
- Interspeech 2024
- Publisher
- ISCA
- Published
- 2024-09-01
- Pages
- 2090-2094
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W4402111788
- Cited by
- 32
- References
- 0
- Citations by year
- 2026: 13 · 2025: 14 · 2024: 5
- FWCI
- 9.44
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- Interspeech (USB) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Research Foundation
- 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 › Signal Processing › Biometric Identification and Security
- Keywords
- voice spoofing, pre-trained speech models, attention mechanism, speaker verification security
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
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.