Journal of Beijing University of Posts and Telecommunications

  • EI核心期刊

JOURNAL OF BEIJING UNIVERSITY OF POSTS AND TELECOM ›› 2015, Vol. 38 ›› Issue (2): 89-93.doi: 10.13190/j.jbupt.2015.02.016

• Papers • Previous Articles     Next Articles

Perceptual Hashing Based on Correlation Coefficient of MFCC for Speech Authentication

LI Jin-feng1, WU Tao2, WANG Hong-xia1   

  1. 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

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

CLC Number: