Totally-blind digital speech authentication method

A technology of digital voice and authentication method, applied in the field of digital voice authentication, digital voice material tampering authentication and tampering area positioning

Inactive Publication Date: 2009-10-21
SHANGHAI UNIV
View PDF1 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This invention compresses the samples in MP3 audio format according to the encoding principle of MP3, and determines the frame offset to estimate the tampering position. Full-blind authentication and tamper location determination in the case of compressed domains

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
  • Totally-blind digital speech authentication method
  • Totally-blind digital speech authentication method
  • Totally-blind digital speech authentication method

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment 1

[0040]The full-blind digital voice authentication method of the present invention is used to discriminate the replacement and tampering voice waveform display and the bispectrum contour map display of each frame of voice, such as figure 2 As shown in the figure (a), the replacement voice "No. 199 Yanchang Road" is replaced by "99" in the original voice 2 "No. 99 Shangda Road" in the original voice 1 "No. 149 Yanchang Road" A new audio signal is obtained. In the analysis process, the replaced speech signal is divided into 6 frames for processing, and the joints of the above-mentioned replaced speech are respectively in the 4th and 5th frames. Figure (b) shows the bispectrum contour of each frame obtained by this method analysis In the figure, the 4th frame and the 5th frame have obvious nonlinear coupling phenomenon, and it is determined that these two frames have been tampered with.

specific Embodiment 2

[0041] The fully blind digital voice authentication method of the present invention is used to discriminate splicing and tampering voice waveform display and each frame of voice bispectrum contour map display, such as image 3 As shown, the spliced ​​voice "LV830" in Figure (a) is a new voice obtained by splicing the voice segment "LV" in the original voice 1 "LV316" and the voice segment "830" in the original voice 2 "PY830". voice. In the analysis process, the spliced ​​speech is divided into 5 frames for processing, and the junction of the two speech segments is in the third frame. Figure (b) shows the framing of the spliced ​​and tampered speech signal in Figure (a) and this The method analyzes the obtained bispectral contour map of each speech frame, and the third frame has obvious nonlinear coupling phenomenon, and it is judged that the speech of this frame is tampered with.

specific Embodiment 3

[0042] The fully blind digital voice authentication method of the present invention is used to discriminate the insertion tampering voice waveform display and the bispectrum contour map display of each frame of voice, such as Figure 4 As shown, the insertion of Figure (a) tampers with the speech "I don't like it", which is cut and inserted into the original speech 2 "I like it" by the monophonic "No" in the original speech 1 "Nobody wants this" The new voice obtained in the. In the analysis process, the inserted tampered speech is divided into 5 frames for processing, and the two joints of the inserted single tone are respectively in the second frame and the third frame. Figure (b) shows the inserted tampered speech signal in Figure (a). The framing situation and the bispectral contour map of each speech frame obtained by this method analysis, in which the second and third frames have obvious nonlinear coupling phenomenon, it is judged that the speech of the second and third ...

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 totally-blind digital speech authentication method, which comprises the following steps: (1) performing framing treatment on a speech signal to be judged; (2) dividing each frame signal into K sections, and performing mean value processing on various sections of values; (3) performing FFT transformation on various sections of data of various frames, and solving double spectral values of the various frames of data; (4) making a double spectral contour diagram through the double spectral estimate values of the various frames of data, which are obtained by smoothing; (5) judging whether nonlinear coupling exists through the double spectral contour diagram of the frame speech signals; (6) judging whether the falsified frame speech signal which is determined for the first time needs the secondary determination of more precise falsified position; and (7) performing more fine framing on the falsified frame speech signal requiring secondary determination, repeating the steps from (2) to (6), and determining more accurate falsified position of the frame speech signal. The method can effectively judge whether the digital speech signal is falsified and determine the falsified position of the digital speech signal under the condition of the deficiency of an authentication message of digital watermarking or digital signature, and does not need to embed any data into the speech signal in advance in the authentication process.

Description

technical field [0001] The present invention relates to the technical field of safe processing of multimedia voice signals, in particular to a digital voice authentication method in the case of total blindness, which utilizes the bispectral characteristics of digital voice signals and is used in the absence of digital watermarks or digital signatures. A method for tampering authentication and tampering area positioning of digital voice material under the condition of so-called "total blindness" of authentication messages. Background technique [0002] With the development of multimedia technology and the continuous decline of its cost, digital voice materials have been widely used in many fields, bringing a lot of convenience to people's life. At the same time, due to the continuous emergence of increasingly powerful voice non-linear editing software such as Adobe Audition, people can easily perform post-processing such as replacement, splicing, deletion and insertion of var...

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
IPC IPC(8): G10L19/00G10L19/022
Inventor 宋波方勇王正宁徐斌
Owner SHANGHAI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap