Abstract
Advances in speech synthesis have made deepfake speeches increasingly convincing, posing growing threats to security. While self-supervised learning (SSL) based detectors achieve state-of-the-art performance, their computational demands (typically 300M+ parameters) prevent deployment on resource-constrained devices. Existing compression methods, designed mainly for content-centric tasks, struggle to maintain competitive performance when directly adapted to deepfake detection. We propose a Task-Aware Joint Pruning and Distillation framework that combines cross-domain knowledge distillation with movement-guided structured pruning to transfer forgery-discriminative knowledge and preserve critical structures under aggressive compression. Our framework reduces the model to 31.9M parameters with 6.3$\times$ FLOPs reduction, with an average performance drop of only 1.30\% across multiple datasets compared to the uncompressed baseline, demonstrating strong potential for on-device deployment.
Keywords
Subject
Publication details
- DOI
- 10.21437/interspeech.2026-1766
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
He, M., Cheng, P., Ba, Z., Wen, Q., Lu, L., Yang, X., & Ren, K. (2026). Task-Aware Joint Pruning and Distillation for Efficient Audio Deepfake Detection. https://doi.org/10.21437/interspeech.2026-1766
MLA 9
He, Miao, et al. "Task-Aware Joint Pruning and Distillation for Efficient Audio Deepfake Detection." https://doi.org/10.21437/interspeech.2026-1766.
Chicago (author–date)
He, Miao, Peng Cheng, Zhongjie Ba, Qing Wen, Li Lu, Xin Yang, and Kui Ren. 2026. "Task-Aware Joint Pruning and Distillation for Efficient Audio Deepfake Detection." https://doi.org/10.21437/interspeech.2026-1766.
Harvard
He, M., Cheng, P., Ba, Z., Wen, Q., Lu, L., Yang, X. and Ren, K. (2026) 'Task-Aware Joint Pruning and Distillation for Efficient Audio Deepfake Detection', doi:10.21437/interspeech.2026-1766.
Vancouver
He M, Cheng P, Ba Z, Wen Q, Lu L, Yang X, et al. Task-Aware Joint Pruning and Distillation for Efficient Audio Deepfake Detection. doi:10.21437/interspeech.2026-1766
IEEE
M. He, P. Cheng, Z. Ba, Q. Wen, L. Lu, X. Yang, and K. Ren, "Task-Aware Joint Pruning and Distillation for Efficient Audio Deepfake Detection," doi: 10.21437/interspeech.2026-1766.