Supercharge Your Innovation With Domain-Expert AI Agents!

Spliced audio detection and positioning method and system based on spectrogram segmentation

A technology of audio detection and localization methods, applied in neural learning methods, speech analysis, character and pattern recognition, etc. Set mismatch, the effect of large scope

Pending Publication Date: 2022-07-29
INST OF INFORMATION ENG CAS
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

To the best of our knowledge and literature review, encoder-decoder architectures have not been used in audio splice detection and localization studies

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
  • Spliced audio detection and positioning method and system based on spectrogram segmentation
  • Spliced audio detection and positioning method and system based on spectrogram segmentation
  • Spliced audio detection and positioning method and system based on spectrogram segmentation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] Below through specific implementation examples, combined with the appendix figure 2 The invention is further described.

[0046] The splicing audio detection and localization method based on spectrogram segmentation proposed by the present invention, the specific operation details are as follows:

[0047] 1) Detection segment division: the minimum positioning area length L according to audio splicing and tampering positioning slr , the audio to be tested is divided into several audio segments S to be detected g , each audio segment consists of consecutive sample points, and the length of each audio segment is L slr .

[0048] 2) Preprocessing: Extract the audio segment S g The spectrogram feature F of g , and divide the t audio clips S according to the size of the network input g compose a concatenated audio segment S' g , and the corresponding spectrogram feature F g Splicing into a spectrogram feature F' to be input into the network g .

[0049] 3) Calculat...

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 relates to a spliced audio detection and positioning method and system based on spectrogram segmentation. The method comprises the following steps: dividing an audio to be detected into a plurality of audio clips Sg to be detected according to the minimum positioning area length of audio splicing tampering positioning; extracting spectrogram features Fg of the Sg, splicing the t Sg into an audio clip S'g, and splicing the Fg into a spectrogram feature F'g to be input into the network; inputting the F'g into the trained spliced audio detection and positioning network, and calculating a binary prediction mask corresponding to the S 'g; calculating the proportion rho of the number of the sample points which are spliced sample points in the binary prediction mask of each Sg in the total number of the sample points; and comparing the rho with a preset judgment threshold value T, and judging whether the audio clip Sg is a spliced clip or not. According to the method, whether the audio of the block with the specific length is the spliced audio block or not can be accurately judged, the accuracy of spliced audio detection and positioning can be improved, and expandability is achieved.

Description

technical field [0001] The invention relates to a tampering audio detection method, in particular to a spliced ​​audio detection and positioning method based on spectrogram segmentation and its application in the field of digital audio forensics, which belongs to the field of multimedia privacy protection in the technical field of information security. Background technique [0002] The methods of audio tampering are mainly divided into Copy-Move and Splicing. Among them, the audio copy and paste operation is to intercept a small audio clip in a piece of audio, and paste the clipped audio clip to another position of the same piece of audio, thereby constructing a new audio clip; the audio splicing technology is at the beginning, middle or Insert another piece of audio at the end to form a new audio clip; two methods of audio tampering are mainly used to change the original content of the audio to achieve the purpose of making fake audio; audio tampering detection and position...

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): G06N3/04G06N3/08G10L25/30G10L25/60G06K9/00
CPCG06N3/08G10L25/30G10L25/60G06N3/047G06N3/048G06N3/045G06F2218/10
Inventor 张振宇赵险峰易小伟
Owner INST OF INFORMATION ENG CAS
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More