Android平台声纹解锁系统的仿真与研究  

Android platform voiceprint unlock system simulation and research

作　　者：刘宁[1] 张晶[1] 郝晓雪 赵圣芳 

机构地区：[1]山东科技大学自动化学院,山东青岛266000 [2]哈尔滨理工大学自动化学院,黑龙江哈尔滨150001

出　　处：《电声技术》2017年第9期63-66,共4页Audio Engineering

摘　　要：随着人工智能技术的日益发展,人类活动中越来越多的使用到各种不同类型的智能设备。在所有的智能产品中,手持式智能终端设备已成为人类活动中不可或缺的智能产品。如今,传统的手机功能已经不能满足需求,人们通常会使用手机来完成金钱交易,因此手机的保密性以及安全性就成为研究重点。本文将个人的身份识别及其认证与Android智能系统进行有机结合,提出了一种新的方法即将声纹识别技术应用在Android智能系统的个人身份认证,并对这一过程中所涉及的相关的问题进行了深入的探索和研究。通过实验验证LMS自适应滤波为降噪算法所具备的优势,而且利用端点检测的方法来处理声纹中含噪的这种现象。提出改进的端点检测方法即频带方差端点与谱减法相结合的方法可以更加有效的检测出语段的端点。此外本文还设计了声纹锁即语音和语义双重认证以此来确保手机的安全。With the continuous development of intelligent technology,human life is getting more and more inseparable from all kinds of intelligent products. Among them,a hand-held intelligent terminal has become the indispensable equipment in human life. Today,the traditional phone functions has can＇t meet the demand,people usually use a mobile phone to complete the money,so the privacy and the security of mobile phones has become research focus. In this paper,combining the identity authentication and the Android system,put forward a voiceprint recognition technology is applied to the Android system identification,and the issues involved in this process are analyzed and studied. In this article,through the experiment to determine the LMS adaptive filter for noise reduction algorithm,and by using the method of endpoint detection to handle with noise phenomenon in the voice print. In this paper,proposed an improved endpoint detection method,which is the combination of the spectral variance endpoint and spectral subtraction. In addition this paper also designs the voiceprint lock the phonetic and semantic dual certification in order to ensure the safety of the mobile phone.

关 键 词：声纹解锁 ANDROID系统 特征提取 端点检测 

分 类 号：TB54[理学—物理]