Hash Authentication Algorithm of Compressed Domain Speech Perception Based on MFCC and NMF

Yi Bo Huang; Qiu Yu Zhang; Zhan Ting Yuan; Yang Wei Liu

doi:10.4028/www.scientific.net/AMM.719-720.1166

Paper Titles

An Efficient Image Encryption Using Merkle-Hellman, Elgamal and Genetic Algorithm for Color Images
p.1140

A Novel Texture Extraction Method for Digital Radiography
p.1148

Active Contour Model Coupling Local and Global Information
p.1155

An Improved Random Seed Searching Clustering Algorithm Based on Shared Nearest Neighbor
p.1160

Hash Authentication Algorithm of Compressed Domain Speech Perception Based on MFCC and NMF
p.1166

Adaptive Mean Ridgelet Transform Filtering for Detecting Signal and Comparison of Algorithm's Implements
p.1171

A Research of Intra Prediction Coding with Variance of Prediction Mode Number
p.1177

A Novel Camera Calibration Method Based on Simulated Annealing Genetic Algorithm
p.1184

Three-Dimensional Object Surface Reconstruction Based on Camera Calibration and SIFT
p.1191

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 719-720Hash Authentication Algorithm of Compressed Domain...

Hash Authentication Algorithm of Compressed Domain Speech Perception Based on MFCC and NMF

Abstract:

A Hash authentication algorithm of speech perception based on MDCT coefficients was proposed to solve the problems of large amount of computation and bad real-time capability when using traditional authentication algorithm in compressed domain speech. Firstly, the algorithm extracts MDCT coefficients by partly decompressing speech sound in MP3 format. Then MDCT coefficients of each frame of speech are processed by Mel filter in the compressed domain, forming the 15-dimensional MFCC coefficient vector. Finally the perceptual Hash string is generated by Hash structure. The perceptual Hash string can perceive the content of voice authentication. Experimental results show that the algorithm keeping on content presents the strong robustness and good real-time capability.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 719-720)

Pages:

1166-1170

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.719-720.1166

Citation:

Cite this paper

Online since:

January 2015

Authors:

Yi Bo Huang*, Qiu Yu Zhang, Zhan Ting Yuan, Yang Wei Liu

Keywords:

Compressed Domain, MFCC, NMF, Perceptual Hashing, Speech Authentication

Export:

RIS, BibTeX

Price:

Permissions:

Request Permissions

* - Corresponding Author

References

[1] GUPTA S, CHO S and KUO C-C J. Current developments and future trends in audio authentication,. IEEE Multimedia, 2012, 19(1): 50-59.

DOI: 10.1109/mmul.2011.74

Google Scholar

[2] Yuhua Jiao, Mingyu li and Xiamu Niu. Key-dependent compressed domain audio hashing,. The 8th IEEE International Conference on Inteeligent Systems Design and Applications. 2008: 29 - 32.

DOI: 10.1109/icme.2008.4607742

Google Scholar

[3] Yuhua Jiao, Mingyu Li, Bian Yang and Xiamu Niu. Compressed Domain Rubost Hashing for AAC Audio,. IEEE International Conference on Multimedia and Expo, Hannover, 2008: 1545-1548.

DOI: 10.1109/icme.2008.4607742

Google Scholar

[4] Yuhua Jiao, Qiong Li, Xiamu Niu. Compressed Domain Perceptual Hashing for MELP Coded Speech,. Intelligent Information Hiding and Multimedia Signal Processing, Harbin, 2008: 410-413.

DOI: 10.1109/iih-msp.2008.210

Google Scholar

[5] Y. Wang, Leonid P. Yaroslavsky and M. Vilermo. On the Relationship Between MDCT, SDFT and DFT,. Proceedings of the 5th International Conference on Signal Processing, Beijing, 2000: 44-47.

DOI: 10.1109/icosp.2000.894440

Google Scholar

[6] Chen N, Xiao H.D. and Wan W.G. Audio hash function based on non-negative matrix factorizations of Mel-frequency cepstral coefficients,. Information Security, IET, 2011, 5(1): 19-25.

DOI: 10.1049/iet-ifs.2010.0097

Google Scholar