arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2110.04438cs.SDeess.AS
收藏

面向轻量级应用的非对称注册-验证结构在说话人验证中的应用

Towards Lightweight Applications: Asymmetric Enroll-Verify Structure for Speaker Verification

AI Lab, Lenovo Research(联想研究院人工智能实验室);Data Science Research Center, Duke Kunshan University(昆山杜克大学数据科学研究中心)

Qingjian Lin, Lin Yang, Xuyang Wang, Xiaoyi Qin, Junjie Wang, Ming Li

摘要:

随着深度学习的发展,自动说话人确认在过去几年中取得了长足的进步。然而,在有限的计算资源下设计一个轻量级的、鲁棒的系统仍然是一个具有挑战性的问题。传统上,说话人确认系统是对称的,这表明在推理中,相同的嵌入提取模型被应用于注册和确认。本文提出了一种创新的非对称结构,采用大规模ECAPA-TDNN模型进行注册,采用小规模ECAPA-TDNNLite模型进行验证。作为一个对称的系统,我们提出的ECAPA-TDNNLite模型实现了3.07%的EER的Voxceleb 1原始测试集,只有11.6M的FLOPS。此外,非对称结构进一步将EER降低到2.31%,而不会增加验证过程中的任何计算成本。

英文摘要:

With the development of deep learning, automatic speaker verification has made considerable progress over the past few years. However, to design a lightweight and robust system with limited computational resources is still a challenging problem. Traditionally, a speaker verification system is symmetrical, indicating that the same embedding extraction model is applied for both enrollment and verification in inference. In this paper, we come up with an innovative asymmetric structure, which takes the large-scale ECAPA-TDNN model for enrollment and the small-scale ECAPA-TDNNLite model for verification. As a symmetrical system, our proposed ECAPA-TDNNLite model achieves an EER of 3.07% on the Voxceleb1 original test set with only 11.6M FLOPS. Moreover, the asymmetric structure further reduces the EER to 2.31%, without increasing any computational costs during verification.

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。

↑