Sensing Hash value extracting method and sensing Hash value authenticating method for voice sensing Hash authentication

Abstract

Disclosed are a sensing Hash value extracting method and a sensing Hash value authenticating method for voice sensing Hash authentication. According to the characteristics of LPC (linear prediction coefficients), robustness of an LPC method is improved by optimizing the LPC method and performing three steps of optimizing and blocking of the LPC and disintegrating matrix of parameters after blocking, the optimized LPC are high in robustness and calculating efficiency, and robustness of a sensing Hash sequence formed is improved as well. The sensing Hash value calculated by the optimized LPC maintains the advantages of good instantaneity of a simple LPC method while having good robustness for attacks to the voice during transmission.

Description

technical field [0001] The invention belongs to the field of multimedia information security, and specifically relates to a method for extracting and authenticating voice-perceptual hash features based on linear prediction analysis (Linear Prediction Coefficients, LPC), which can be used for content authentication and speaker authentication of voice signals during voice communication calls . Background technique [0002] Voice is the most important communication tool for human beings. It is natural, convenient, accurate and efficient. With the rapid development of modern network technology and multimedia technology, people get more and more multimedia information from the network. As the most natural, effective and convenient means for human beings to exchange information, voice information enables people in any area on the earth to make phone calls anytime and anywhere, and people are getting closer and closer to each other. The existing form of voice has also been exte...

AI Technical Summary

Problems solved by technology

However, although the pure LPC method has high computational efficiency, its robustness is poor, and it is not robust to the content-preserving operation attack suffered by the speech signal during transmission.

Images