用于自动说话人验证的知识蒸馏中强调非目标说话人知识
Emphasized Non-Target Speaker Knowledge in Knowledge Distillation for Automatic Speaker Verification
AI总结：
本文提出在自动说话人验证的知识蒸馏中解耦并强调非目标说话人的分类概率，该方法在VoxCeleb数据集上使EER平均提升13.67%。
摘要：
知识蒸馏（KD）通过在嵌入层或标签层确保大型教师网络与轻量级学生网络之间的一致性，用于提升自动说话人验证的性能。然而，传统的标签层KD忽略了来自非目标说话人的重要知识，尤其是其分类概率，这对自动说话人验证可能至关重要。在本文中，我们首先证明利用更多数量的训练非目标说话人可以提升自动说话人验证模型的性能。受这一关于非目标说话人知识重要性的发现启发，我们通过在知识蒸馏过程中解耦并强调非目标说话人的分类概率，对传统的标签层KD进行了修改。所提出的方法应用于三种不同的学生模型架构，并在VoxCeleb数据集上与嵌入层和传统标签层KD方法相比，EER平均提升了13.67%。
英文摘要：
Knowledge distillation (KD) is used to enhance automatic speaker verification performance by ensuring consistency between large teacher networks and lightweight student networks at the embedding level or label level. However, the conventional label-level KD overlooks the significant knowledge from non-target speakers, particularly their classification probabilities, which can be crucial for automatic speaker verification. In this paper, we first demonstrate that leveraging a larger number of training non-target speakers improves the performance of automatic speaker verification models. Inspired by this finding about the importance of non-target speakers' knowledge, we modified the conventional label-level KD by disentangling and emphasizing the classification probabilities of non-target speakers during knowledge distillation. The proposed method is applied to three different student model architectures and achieves an average of 13.67% improvement in EER on the VoxCeleb dataset compared to embedding-level and conventional label-level KD methods.
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。
