ISSN 1000-1239 CN 11-1777/TP

计算机研究与发展 ›› 2020, Vol. 57 ›› Issue (10): 2201-2208.doi: 10.7544/issn1000-1239.2020.20200474

所属专题: 2020密码学与数据隐私保护研究专题

• 信息安全 • 上一篇    下一篇



  1. 1(桂林电子科技大学计算机与信息安全学院 广西桂林 541004);2(桂林电子科技大学数学与计算科学学院 广西桂林 541004);3(桂林电子科技大学电子工程与自动化学院 广西桂林 541004);4(广西密码学与信息安全重点实验室(桂林电子科技大学) 广西桂林 541004);5(鹏城实验室网络安全研究中心 广东深圳 518055) (
  • 出版日期: 2020-10-01
  • 基金资助: 

Template Protection of Speaker Recognition Based on Random Mapping Technology

Ding Yong1,4,5, Li Jiahui2,4, Tang Shijie1,3, Wang Huiyong2,4   

  1. 1(School of Computer Science & Information Security, Guilin University of Electronic Technology, Guilin, Guangxi 541004);2(School of Mathematics & Computing Science, Guilin University of Electronic Technology, Guilin, Guangxi 541004);3(School of Electronic Engineer & Automation, Guilin University of Electronic Technology, Guilin, Guangxi 541004);4(Guangxi Key Laboratory of Cryptography and Information Security (Guilin University of Electronic Technology), Guilin, Guangxi 541004);5(Cyberspace Security Research Center, Peng Cheng Laboratory, Shenzhen, Guangdong 518055)
  • Online: 2020-10-01
  • Supported by: 
    This work was supported by the National Natural Science Foundation of China (61772150, 61862012, 61962012), the Guangxi Key Research and Development Program (AB17195025), the Guangxi Natural Science Foundation (2018GXNSFDA281054, 2018GXNSFAA281232, 2019GXNSFFA245015, 2019GXNSFGA245004, AD19245048), and the Peng Cheng Laboratory Project of Guangdong Province (PCL2018KP004).

摘要: 声纹识别实现了一种非接触式、不易伪造、可远程认证的简便快捷的生物特征认证方式,这种生物特征认证方式不是完全安全的,因为在身份认证过程中,将用户数据存储在第三方会带来许多安全和隐私问题.为了解决这一挑战,研究了基于身份向量(i-Vector)和线性判别分析技术(LDA)的声纹模板保护方案,提出一种改进的随机映射技术.利用改进的随机映射算法对声纹特征进行随机化处理,构造了一个声纹识别的模板保护方案,允许用户在随机域注册并完成声纹识别.随后,基于公开的中文语音数据集AISHELL对所提出的方案进行了实验仿真.结果表明:该方案不会对声纹识别的准确性造成显著影响,且实现了声纹模板的保密比对,能够有效保证语音数据的安全.

关键词: 随机映射, 正交矩阵, 随机域, 声纹识别, 隐私保护

Abstract: Speaker recognition realizes a simple and fast biometric authentication method which is non-contact, not easy to forge and can be authenticated remotely, However, it is not completely secure, as in the process of authentication, storing user data in a third party brings many security and privacy concerns. In order to mitigate the challenge, the template protection of speaker recognition problem is studied based on identity vector (i-Vector) and linear discriminant analysis (LDA), and an improved random mapping technique is proposed, which is used to randomize the voiceprint features. Then we construct a template protection scheme for speaker recognition, which allows users to register in random domain and to complete speaker recognition. Finally, we use the open Chinese speech data set (AISHELL) to simulate the proposed scheme. The results show that the scheme does not significantly affect the accuracy of voiceprint authentication, and realize confidential comparisons of voiceprint templates, which effectively ensures the security and privacy of voice data in speaker recognition.

Key words: random mapping, orthogonal matrix, random domain, speaker recognition, privacy protection