基于MFCC相关系数的语音感知哈希认证算法

doi:10.13190/j.jbupt.2015.02.016

北京邮电大学学报 ›› 2015, Vol. 38 ›› Issue (2): 89-93.doi: 10.13190/j.jbupt.2015.02.016

基于MFCC相关系数的语音感知哈希认证算法

李金凤¹, 吴涛², 王宏霞¹

1. 西南交通大学信息科学与技术学院, 成都 610031;
2. 北京邮电大学信息与通信工程学院, 北京 100876

收稿日期:2014-01-21 出版日期:2015-04-28 发布日期:2015-05-14
作者简介:李金凤(1985—), 女, 博士生, E-mail:jflee85@163. com; 王宏霞(1973—), 女, 教授, 博士生导师.
基金资助:
国家自然科学基金项目(61170226, 61373180)

Perceptual Hashing Based on Correlation Coefficient of MFCC for Speech Authentication

LI Jin-feng¹, WU Tao², WANG Hong-xia¹

1. School of Information Science and Technology, Southwest Jiaotong University, Chengdu 610031, China;
2. School of Information and Communicaiton Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, China

Received:2014-01-21 Online:2015-04-28 Published:2015-05-14

摘要/Abstract

摘要：

提出了一种基于梅尔频率倒谱系数相关性的语音感知哈希内容认证算法. 该算法提取分段语音的声纹梅尔频率倒谱系数作为感知特征. 为提高算法的安全性,算法利用伪随机序列作为密钥,计算得到梅尔频率倒谱系数与伪随机之间的相关度,最后量化相关值并加密生成感知哈希序列. 语音认证过程中,采用相似性度量函数用来衡量哈希序列之间的距离,同时与汉明距离方法进行了比较. 仿真结果表明,该算法对语音内容保持操作,如重采样、MP3压缩等具有较好的鲁棒性,相似性度量函数也对语音篡改检测定位具有较高的灵敏性.

关键词: 感知哈希, 梅尔频率倒谱系数, 语音认证, 相关系数, 篡改检测

Abstract:

A perceptual hashing algorithm for speech content authentication based on correlation coefficient of mel-frequency cepstrum coefficients (MFCC) was proposed. The MFCC of the framed speech signal is extracted as perceptual feature. The correlation coefficients between MFCC and a pseudo-random sequence, which is generated by keys for security, were calculated. Hash sequence is generated by quantifying the correlation coefficients and then scrambling. For audio authentication procedure, a new method, similarity metric, was used to measure the distance of hashes, which is compared with the hamming distance method. Simulations show that the algorithm is robust against content-preserving manipulations such as re-sampling, MP3 compression, and so on. It is very sensitive to tamper of speech by similarity metric.

Key words: perceptual Hashing, Mel-frequency cepstrum coefficients, speech authentication, correlation coefficient, tamper detection

中图分类号:

TN929.53

李金凤, 吴涛, 王宏霞. 基于MFCC相关系数的语音感知哈希认证算法[J]. 北京邮电大学学报, 2015, 38(2): 89-93.

LI Jin-feng, WU Tao, WANG Hong-xia. Perceptual Hashing Based on Correlation Coefficient of MFCC for Speech Authentication[J]. JOURNAL OF BEIJING UNIVERSITY OF POSTS AND TELECOM, 2015, 38(2): 89-93.

参考文献

[1] 牛夏牧, 焦玉华. 感知哈希综述[J]. 电子学报, 2008, 36(7): 1405-1411. Niu Xiamu, Jiao Yuhua. An overview of perceptual Hashing[J]. Acta Electronic Sinica, 2008, 36(7): 1405-1411.

[2] Tang Zhenjun, Zhang Xianquan, Huang Liyan, et al. Robust image Hashing using ring-based entropies[J]. Signal Processing, 2013, 93(7): 2061-2069.

[3] Li Yuenan, Lu Zheming, Zhu Ce, et al. Robust image Hashing based on random Gabor filtering and dithered lattice vector quantization[J]. Image Processing, IEEE Transactions on, 2012, 21(4): 1963-1980.

[4] 陈慧婷, 覃团发, 唐振华, 等. 综合纹理统计模型与全局主颜色的图像检索方法[J]. 北京邮电大学学报, 2011, 34 (s1): 100-103. Chen Huiting, Qin Tuanfa, Tang Zhenhua, et al. A method of image retrivals based on texture probability statistics and global dominant color[J]. Journal of Beijing University of Posts and Telecommunications, 2011, 34(s1): 100-103.

[5] Jiao Yuhua, Ji Liping, Niu Xiamu. Robust speech Hashing for content authentication[J]. Signal Processing Letters, IEEE, 2009, 16(9): 818-821.

[6] Chen Ning, Wan Wanggen. Robust speech Hash function[J]. ETRI Journal, 2010, 32(2): 345-347.

[7] Chen Ning, Wan Wanggen. Speech Hashing algorithm based on short-time stability[C] //Artificial Neural Networks-ICANN 2009. Cyprus: Artificial Neural Networks, 2009: 426-434.

[8] Nouri M, Farhangian N. Conceptual authentication speech hashing base upon hypotr- ochoid graph[C]//Telecommunications (IST), Sixth International Symposium on. Tehran: IEEE, 2012: 1136-1141.

[9] Tang Zhenjun, Wang Shuozhong, Zhang Xinpeng, et al. Structural feature-based image hashing and similarity metric for tampering detection[J]. Fundamenta Informaticae, 2011, 106(1): 75-91.

[10] Chen Ning, Wan Wanggen. Robust audio hashing based on discrete-wavelet-transform and non-negative matrix factorization[J]. Communications IET, 2010, 4(14): 1722-1731.

基于MFCC相关系数的语音感知哈希认证算法

Perceptual Hashing Based on Correlation Coefficient of MFCC for Speech Authentication

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 7

编辑推荐

Metrics

本文评价

[1]	周楷, 黄赛, 曾昱祺, 高晖, 卢华. 基于稳态循环谱特征的通信辐射源识别方法[J]. 北京邮电大学学报, 2021, 44(3): 100-105.
[2]	仇利克, 刘竞, 孙中卫, 赵扬帆. 一种快速的特征选择框架和方法[J]. 北京邮电大学学报, 2019, 42(3): 127-132.
[3]	吴新忠, 夏令祥, 张旭, 周成. 基于谱熵梅尔积的语音端点检测方法[J]. 北京邮电大学学报, 2019, 42(2): 83-89.
[4]	张俐, 袁玉宇, 王枞. 基于最大相关信息系数的FCBF特征选择算法[J]. 北京邮电大学学报, 2018, 41(4): 86-90.
[5]	仇利克, 郭忠文, 刘青, 刘颖健, 仇志金. 基于冗余分析的特征选择算法[J]. 北京邮电大学学报, 2017, 40(1): 36-41.
[6]	张秋余, 省鹏飞, 黄羿博, 董瑞洪, 杨仲平. 多格式音频感知哈希算法[J]. 北京邮电大学学报, 2016, 39(4): 77-82.
[7]	牛少彰, 黄艳丽, 孙晓婷. 投影与光照方向一致性的图像篡改检测[J]. 北京邮电大学学报, 2014, 37(5): 61-65.