通过w2v-BERT 2.0和知识蒸馏引导的结构化剪枝增强语音验证
Enhancing Speaker Verification with w2v-BERT 2.0 and Knowledge Distillation guided Structured Pruning
AI总结：
本文提出利用w2v-BERT 2.0和知识蒸馏引导的结构化剪枝提升语音验证性能，实现模型压缩与精度平衡。
摘要：
大规模自监督预训练模型（PTMs）在语音验证（SV）任务中通过提供丰富的特征表示取得了显著改进。在本文中，我们利用w2v-BERT 2.0，一个在143种语言上训练了450万小时无标签数据、拥有约6亿参数的模型，用于SV任务。采用MFA结构与层适配器处理PTM的多层特征输出，并提取说话人嵌入。此外，我们还引入LoRA进行高效微调。我们的模型在Vox1-O和Vox1-H测试集上分别达到0.12%和0.55%的EER，取得最先进的结果。此外，我们应用知识蒸馏引导的结构化剪枝，将模型大小减少80%，同时仅导致0.04%的EER退化。源代码和模型已发布在https://github.com/ZXHY-82/w2v-BERT-2.0_SV。
英文摘要：
Large-scale self-supervised Pre-Trained Models (PTMs) have shown significant improvements in the speaker verification (SV) task by providing rich feature representations. In this paper, we utilize w2v-BERT 2.0, a model with approximately 600 million parameters trained on 4.5 million hours of unlabeled data across 143 languages, for the SV task. The MFA structure with Layer Adapter is employed to process the multi-layer feature outputs from the PTM and extract speaker embeddings. Additionally, we incorporate LoRA for efficient fine-tuning. Our model achieves state-of-the-art results with 0.12% and 0.55% EER on the Vox1-O and Vox1-H test sets, respectively. Furthermore, we apply knowledge distillation guided structured pruning, reducing the model size by 80% while achieving only a 0.04% EER degradation. Source code and models are released at https://github.com/ZXHY-82/w2v-BERT-2.0_SV.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
