[1]赖丽旻,洪青阳.声纹识别在开放仪器管理中的应用[J].华侨大学学报(自然科学版),2015,36(5):517-521.[doi:10.11830/ISSN.1000-5013.2015.05.0517]
　LAI Li-min,HONG Qing-yang.Application of Voiceprint Recognition in Opening Instrument Management[J].Journal of Huaqiao University(Natural Science),2015,36(5):517-521.[doi:10.11830/ISSN.1000-5013.2015.05.0517]
点击复制

声纹识别在开放仪器管理中的应用()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第36卷
期数:
2015年第5期
页码:
517-521
栏目:
出版日期:
2015-09-20

文章信息/Info

Title:
Application of Voiceprint Recognition in Opening Instrument Management
文章编号:
1000-5013(2015)05-0517-05
作者:
赖丽旻1;  洪青阳2
1. 厦门大学 环境与生态学院, 福建 厦门 361005; 2. 厦门大学 信息科学与技术学院, 福建 厦门 361005
Author(s):
LAI Li-min1;  HONG Qing-yang2
1. College of Environment and Ecology, Xiamen University, Xiamen 361005, China; 2. School of Information Science and Technology, Xiamen University, Xiamen 361005, China
关键词:
声纹识别;  仪器管理;  身份认证;  高斯混合模型;  隐马尔可夫模型
Keywords:
voiceprint recognition;  instrument management;  identity authentication;  Gaussian mixture model;  hidden Markov model
分类号:
TP393
DOI:
10.11830/ISSN.1000-5013.2015.05.0517
文献标志码:
A
摘要:
在现有的仪器工作站中加入基于GMM-HMM算法的声纹识别系统,利用声纹的唯一性识别仪器用户,实现开放仪器的无人监管.应用该声纹识别系统,进行语音动态口令测试.结果表明:该系统语音动态口令的错误接受率低于1%,可有效地防范录音冒充,保证系统的可靠性.
Abstract:
In order to have a standard management of opening instruments, we apply the voiceprint recognition system based on GMM-HMM algorithm into the instrument workstation. The uniqueness of voiceprint is utilized to verify the user identity, which realizes unmanned supervision of opening instrument. Based on the voiceprint recognition system, we conducted the experiment of dynamic password speaker verification. The results showed that the false acceptance rate of dynamic password version was lower than 1%, which could avoid the danger of recording playback and assure the system’s reliability.

参考文献/References:

[1] 王云平.国外大学实验室管理及其对国内开放实验室的启示[J].实验技术与管理,2010,27(3):149-151.
[2] HONG Q Y,KWONG S.Discriminative training for speaker identification based on maximum model distance algorithm[C]//IEEE International Conference on Acoustics, Speech, and Signal Processing.Montreal:IEEE Press,2004:25-28.
[3] 张彩红,洪青阳,陈燕.基于GMM-UBM 的说话人确认系统的研究[J].心智与计算,2007,1(4):420-425.
[4] 陈燕,洪青阳,张彩虹.声纹识别在司法身份鉴定中的应用[J].心智与计算,2008,2(1):1-7.
[5] REYNOLDS D A.Speaker identification and verification using Gaussian mixture speaker models[J].Speech Communication,1995,17(1/2):91-108.
[6] REYNOLDS D A,QUATIERI T F,DUNN R B.Speaker verification using adapted Gaussian mixture models[J].Digital Signal Processing,2000,10(1/2/3):19-41.
[7] 韩纪庆,张磊,郑铁然.语音信号处理[M].北京:清华大学出版社,2004:200-213,239-241.
[8] HONG Qing-yang,WANG Sheng,LIU Zhi-jian.A robust speaker-adaptive and text-prompted speaker verification system[J].Lecture Notes in Computer Science,2014,8833:385-393.
[9] 卢畅.基于指纹检测识别的开放式实验室管理系统研究与设计[J].实验室研究与探索,2013,32(12):211-215.
[10] DODDINGTON G R,PRZYBOCKI M A,MARTIN A F,et al.The NIST speaker recognition evaluation: Overview, methodology, systems, results, perspective[J].Speech Communication,2000,31(2/3):225-254.
[11] DEHAK N,KENNY P,DEHAK R,et al.Front-end factor analysis for speaker verification[J].IEEE Transactions on Audio, Speech, and Language Processing,2011,19(4):788-798.

备注/Memo

备注/Memo:
收稿日期: 2015-04-09
通信作者: 洪青阳(1977-),男,副教授,博士,主要从事语音识别和说话人识别的研究.E-mail:qyhong@xmu.edu.cn.
基金项目: 国家自然科学基金资助项目(61105026)
更新日期/Last Update: 2015-09-20