{"ID":2879375,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.16232","arxiv_id":"2508.16232","title":"Hybrid Pruning: In-Situ Compression of Self-Supervised Speech Models for Speaker Verification and Anti-Spoofing","abstract":"Although large-scale self-supervised learning (SSL) models like WavLM have achieved state-of-the-art performance in speech processing, their significant size impedes deployment on resource-constrained devices. While structured pruning is a key technique for model compression, existing methods typically separate it from task-specific fine-tuning. This multi-stage approach struggles to create optimal architectures tailored for diverse downstream tasks. In this work, we introduce a unified framework that integrates structured pruning into the downstream fine-tuning process. Our framework unifies these steps, jointly optimizing for task performance and model sparsity in a single stage. This allows the model to learn a compressed architecture specifically for the end task, eliminating the need for complex multi-stage pipelines and knowledge distillation. Our pruned models achieve up to a 70\\% parameter reduction with negligible performance degradation on large-scale datasets, achieving equal error rates of 0.7\\%, 0.8\\%, and 1.6\\% on Vox1-O, -E, and -H, respectively. Furthermore, our approach demonstrates improved generalization in low-resource scenarios, reducing overfitting and achieving a state-of-the-art 3.7\\% EER on ASVspoof5.","short_abstract":"Although large-scale self-supervised learning (SSL) models like WavLM have achieved state-of-the-art performance in speech processing, their significant size impedes deployment on resource-constrained devices. While structured pruning is a key technique for model compression, existing methods typically separate it from...","url_abs":"https://arxiv.org/abs/2508.16232","url_pdf":"https://arxiv.org/pdf/2508.16232v2","authors":"[\"Junyi Peng\",\"Lin Zhang\",\"Jiangyu Han\",\"Oldřich Plchot\",\"Johan Rohdin\",\"Themos Stafylakis\",\"Shuai Wang\",\"Jan Černocký\"]","published":"2025-08-22T09:10:37Z","proceeding":"eess.AS","tasks":"[\"eess.AS\"]","methods":"[]","has_code":false}