Unlock instant, AI-driven research and patent intelligence for your innovation.

Pseudo-Zernike moment based voice content authentication method

A technology of voice content and authentication method, which is applied in voice analysis, instruments, etc., can solve the problems of large amount of original audio changes, algorithm loss of copyright protection, original audio signal quality damage, etc., to achieve enhanced security, easy practical application, and reduce The effect of transmission bandwidth

Inactive Publication Date: 2013-01-09
SOUTHWEST JIAOTONG UNIV
View PDF2 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The analysis shows that directly scaling the audio sample value will greatly change the original audio and cause great damage to the quality of the original audio signal; The calculation of Zernike moments) is also known
Therefore, the attacker can find the position of each audio frame and calculate the characteristics of each frame, and re-quantize the pseudo-Zernike moment to remove the embedded watermark, so that the algorithm loses the effect of protecting copyright

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Pseudo-Zernike moment based voice content authentication method
  • Pseudo-Zernike moment based voice content authentication method
  • Pseudo-Zernike moment based voice content authentication method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The technical solution of the present invention will be further described below in combination with appendices and embodiments.

[0020] 1. Generation and embedding of watermark:

[0021] (1) Framing of voice data and division of voice segments in each frame. The original speech signal A={a(l), 1≤l≤LA+K} is divided into P frames (K is used as the key of the watermark system), and the length of each frame is I=LA / P, and the i-th frame is recorded as A (i) (i=1, 2, . . . , P). Each frame is equally divided into N segments, and the length of each segment is I / N. The jth segment of the i-th frame is recorded as A(i, j), 1≤i≤P, 1≤j≤N.

[0022] (2) DCT transformation. Perform DCT transformation on A(i, j), D(i, j) represents the DCT coefficient of the j-th segment of the i-th frame, and the DCT coefficient of the first N / 2 segment of the i-frame is recorded as D 1 (i,j).

[0023] (3) Calculate n-order m-fold pseudo Zernike moments. Will D 1 the first m of (i,j) 1 ×m ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a pseudo-Zernike moment based voice content authentication method. The method comprises the following steps of: during watermark embedding, dividing an original voice signal A into P frames, and dividing each frame into N sections; generating a watermark W according to an average value of the amplitudes of n-order pseudo-Zernike moments of discrete cosine transformation (DCT) low-frequency coefficients of the first N / 2 sections of each frame; and embedding the watermark by quantizing pseudo-Zernike moments of the DCT low-frequency coefficients of the last N / 2 sections of each frame, and thus obtaining a watermark-containing voice signal A'. The method has the advantages that by fully using the characteristic of close relevancy of the amplitudes of the pseudo-Zernike moments of the DCT low-frequency coefficients of the voice signal and voice contents, and the processing robustness of the conventional voice signal, the sensitivity of attack on malicious tampering is ensured, and high tolerance on certain conventional voice signal processing capacity is ensured.

Description

technical field [0001] The invention relates to a voice recognition, especially a solution to the authenticity and integrity authentication of voice content. Background technique [0002] In recent years, the rapid development of digital voice communication, the wide popularization of various voice products, and the emergence of various powerful audio processing software have made the transmission and application of digital voice increasingly frequent and widespread. At the same time, it becomes relatively easy to tamper with transmitted and stored voice content data. For example, if the key part of an important court testimony recording is maliciously tampered with during storage and transmission, the consequences can be imagined! . Therefore, how to identify whether an important or sensitive voice content has been tampered with, where it has been tampered with, and whether the source of the voice recording is authentic and credible, these authentication issues involving ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G10L17/00
Inventor 王宏霞刘正辉
Owner SOUTHWEST JIAOTONG UNIV