Speech spectrum fusion feature-based mobile phone source identification method

Abstract

The present invention discloses a speech spectrum fusion feature-based mobile phone source identification method. According to the method, fast Fourier transformation is performed on each frame in each speech sample in a speech library corresponding to each mobile phone, so that the amplitude of the frequency value of each frequency point of first J/2+1 frequency points of each frame is obtained; the statistical average information amount features, statistical average logarithmic spectrum features and statistical average phase spectrum features of each speech sample are obtained according to the amplitudes of the frequency values and are adopted to form spectrum fusion features; the spectrum fusion features of all the speech samples corresponding to all the mobile phones are combined to form a spectrum fusion feature matrix; normalization and feature selection are performed on the spectrum fusion feature matrix, so that an optimal feature matrix can be obtained, namely, the final spectrum fusion features of each speech sample are obtained; and model training and test sample identification are performed on the final spectrum fusion features of all the speech samples. The method has the advantages of high identification accuracy, high stability and strong generalization ability.

Description

technical field [0001] The invention relates to a mobile phone source identification technology, in particular to a mobile phone source identification method based on voice spectrum fusion features. Background technique [0002] Nowadays, with the rapid development of mobile Internet and microchip industry, mobile terminal is no longer just a communication device, but an indispensable part of people's life. More and more people start to use portable devices such as smart phones and PADs to capture and collect what they see or hear, instead of using professional devices such as cameras, recording pens, and DV (Digital Video, digital video). However, the availability of a large number of digital capture devices and captured data brings new problems and challenges - multimedia security issues. As a technology to detect the originality, authenticity and integrity of multimedia data, multimedia forensics technology is a hot research issue in the field of information security. ...

AI Technical Summary

Problems solved by technology

[0004] Most of the existing research on mobile phone source identification is based on a single feature of the voice spectrum. Since most of the current research is based on a small number of equipment types and numbers in the voice database, and the equipment models are outdated, the differences in the voices collected by different devices Larger, so that the relevant features have achieved good results in mobile phone source identification

However, when the type and quantity of devices in the voice database reach a certain level, especially as the number of devices of the same brand and different models continues to increase, can the relevant features still achieve good results in mobile phone source identification? By analyzing the spectrograms of the voice signals of different devices on the voice database constructed by 23 models of mobile phones of 7 mainstream brands, it is found that the spectrum information of different devices is not the same, and the differences between devices of different brands are obvious, and a single spectrum can be used Differentiate between devices of the same brand and different models, although there are differences, but they are relatively similar. It is difficult to accurately identify different brands of mobile phones with a single spectrum feature

Images