A robust speech authentication algorithm based on perceptual characteristics

doi:10.7523/j.issn.2095-6134.2009.4.007

Abstract

Abstract:

At present, there is a growing need for multimedia information authentication, but studies on speech authentication are rare. Based on perceptual characteristics, a robust speech authentication algorithm is proposed to combine the psychoacoustic properties with signature algorithm. It meets the requirements of entity authentication and content authentication, and resists the channel noise as well. Analyzing the perceptual properties, such as masking effect and non-linear effect, speech redundancy in both temporal field and frequency field is eliminated, and perceptual parameters are extracted. Then an improved Rainbow algorithm is used to sign the extracted data. Experiment results demonstrate good robustness and uniqueness of the algorithm when applied to the robust authentication of audio communication.

Key words: perceptual, robustness, speech authentication

CLC Number:

TP309.7

GU Jin, GUO Li, ZHENG Dong-Fei. A robust speech authentication algorithm based on perceptual characteristics[J]. , 2009, 26(4): 474-482.

References

[1] Cox P J, Miller M L, Bloom J A. Digital Watermarking
[M]. New York:Morgan Kaufmann. 2001.225-230.

[2] Zhu B B, Swanson M D, Tewfik A H. When seeing isn't believing-multimedia authentication technologies
[J]. IEEE signal Processing Magazine, 2004,21(2):40-49.

[3] Kaller T, Haitsma J, Oostveen J. Robust audio hashing for content identification //Content Based Multimedia Indexing 2001. Brescia, Italy:IEEE,2001.

[4] Mihcak M K, Venkatesan R. A perceptual audio hashing algorithm a tool for robust audio identification and information hiding //Information Hiding.Berlin/Heidelberg:Springer Pittsburgh,2001:51-65.

[5] Burges C J, Patt J C, Jana S. Distortion discriminant analysis for audio fingerprinting
[J]. IEEE Trans. Speech Audio Processing, 2003,11(3):165-174.

[6] Sukittanon S, Atlas L E. Modulation frequency feature for audio fingerprinting //International Conference Acoustics,Speech,Signal Processing.Orlando,Fla,USA:IEEE,2002:1773-1776.

[7] Foote J T. Content-based retrieval of music and audio //Kuo C C J,et al. Multimedia Storage and Archiving Systems Ⅱ,Proc of SPIE, 1997, 3229:138-147.

[8] 韩纪庆,冯淘,郑贵滨,等.音频信息处理技术
[M].北京:清华大学出版社,2007.

[9] 丁爱明.基于MFCC和GMM的说话人识别系统研究 . 南京:河海大学,2006.

[10] Peter W S. Polynomial-time algorithms for prime factorization and discrete logarithms on a quantum computer
[J]. SIAM Review, 1999, 41(2):303-332.

[11] Ding J, Gower J E, Schmidt D S. Multivariate Public Key Cryptosystems . New York:Springer-Verlag, 2006:2-15.

[12] Jesteadt W, Bacon S P, Lehman J R. Forward masking as a function of frequency, masker lever, and signal delay
[J]. Journal of Acoustic Society of America, 1982, 71(4):950-962.

[13] Kohonen T, Barna G, Chrisley R. Statistical pattern recognition with neural networks:benchmarking studies //Neural Networks.California:IEEE,1988:61-68.

[14] Ding J, Schmidt D S. Rainbow, a new multivariate polynomial signature scheme //Applied Cryptography and Network Security. Berlin/Heidelberg:Springer,2005:164-175.

[15] Xiang Q, Liu Z. Simplest accomplishment of arithmetic on Galois fields . Journal of University of Electronic Science and Technology of China, 2000, 29(1):5-8(in Chinese). 向茜,刘钊.伽华罗域上代数运算的最简实现
[J].电子科技大学学报,2000,29(1):5-8.

[16] ?zer H, Sankur B, Memon N. Perceptual audio hashing functions //EURASIP Journal on Applied Signal Processing.New York:Hindawi,2005:1780-1793.

[17] Quan X M, Zhang H B. Statistical audio watermarking algorithm based on perceptual ayalysis //Proceedings of the 5th ACM Workshop on Digital Rights Management.Alexandria,VA,USA:ACM,2005:112-118.