用于小 footprint 说话人验证的多层 X-vector 知识蒸馏
Distilling Multi-Level X-vector Knowledge for Small-footprint Speaker Verification
AI总结：
针对深度说话人模型尺寸大难部署的问题，提出融合x-vector教师网络多层嵌入蒸馏训练紧凑学生模型的方法，实现模型尺寸75%-91%的缩减且性能接近教师，方法可推广至其他x-vector变体。
摘要：
尽管深度说话人模型已在说话人验证任务中展现出出色的准确率，但这往往以模型尺寸增大和计算时间延长为代价，给资源受限环境下的部署带来了挑战。本研究聚焦于通过知识蒸馏技术开发小 footprint 的深度说话人嵌入提取方法，以解决这一局限。该领域的过往研究主要集中在话语级的说话人嵌入提取，而我们的方法是融合来自 x-vector 模型（教师网络）不同层级的嵌入，来训练一个紧凑的学生网络。实验结果凸显了帧级信息的重要性：根据教师嵌入的尺寸不同，学生模型相较于对应教师模型的尺寸减少了85%-91%。值得注意的是，通过拼接教师嵌入，我们得到的学生网络在保持与教师相当性能的同时，模型尺寸大幅减少了75%。这些发现和见解可推广到其他 x-vector 变体，凸显了我们方法的广泛适用性。
英文摘要：
Even though deep speaker models have demonstrated impressive accuracy in speaker verification tasks, this often comes at the expense of increased model size and computation time, presenting challenges for deployment in resource-constrained environments. Our research focuses on addressing this limitation through the development of small footprint deep speaker embedding extraction using knowledge distillation. While previous work in this domain has concentrated on speaker embedding extraction at the utterance level, our approach involves amalgamating embeddings from different levels of the x-vector model (teacher network) to train a compact student network. The results highlight the significance of frame-level information, with the student models exhibiting a remarkable size reduction of 85%-91% compared to their teacher counterparts, depending on the size of the teacher embeddings. Notably, by concatenating teacher embeddings, we achieve student networks that maintain comparable performance to the teacher while enjoying a substantial 75% reduction in model size. These findings and insights extend to other x-vector variants, underscoring the broad applicability of our approach.
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。
