Perceptual Hash feature extraction method and system of encrypted voice signal

Abstract

The invention discloses a perceptual Hash feature extraction method and system of an encrypted voice signal. The method includes steps: performing signal framing on the encrypted voice signal, calculating a short-time cross correlation coefficient between each encrypted voice frame and an adjacent encrypted voice frame, and obtaining a cross correlation coefficient matrix; determining the previousshort-time cross correlation coefficients with large values in each row of the cross correlation coefficient matrix as elements of a feature coefficient matrix, and obtaining the feature coefficientmatrix; decomposing the feature coefficient matrix by employing a non-negative matrix decomposition method, and obtaining a feature parameter matrix; and performing binary Hash construction on the feature parameter matrix by employing a Hash function, and obtaining a perpetual Hash value of the encrypted voice signal. By employing the method or system, the short-time cross correlation coefficientsextracted from the encrypted voice signal can be regarded as perpetual features of the encrypted voice signal, and the perpetual Hash value of the encrypted voice signal is generated through Hash construction so that the robustness, the distinction and the abstractness of direct extraction of the voice perpetual features from the encrypted voice signal are improved.

Description

technical field [0001] The invention relates to a speech signal processing technology, in particular to a perceptual hash feature extraction method and system for an encrypted speech signal. Background technique [0002] With the rapid development of computer network and multimedia information technology, multimedia voice is one of the most direct and convenient multimedia applications for transmitting information. In order to ensure the security of the user's voice data, the voice data needs to be encrypted before being uploaded to the cloud server. Due to the encryption process, most of the perceptual content of the voice will be lost. Therefore, how to extract speech features that can satisfy operations such as retrieval and authentication in ciphertext speech has become a concern and a challenging subject. [0003] In recent years, researchers at home and abroad have done a lot of research on the extraction method of speech-aware hash features in the plaintext domain. ...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a perceptual hash feature extraction method and system for encrypted speech signals to solve the problems of poor robustness, poor discrimination and poor abstraction when directly extracting speech perceptual features from encrypted speech signals in the prior art

Images