Supercharge Your Innovation With Domain-Expert AI Agents!

Digital audio tampering passive detection method based on convolutional neural network

A technology of convolutional neural network and digital audio, applied in biological neural network model, neural architecture, speech analysis, etc., can solve the problems of insufficient recognition rate, excessive experience components, strong pertinence, etc.

Active Publication Date: 2020-12-29
HUBEI UNIV OF TECH
View PDF10 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These methods often have the problems of too much experience or too much pertinence and insufficient recognition rate for a certain tampering method.

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
  • Digital audio tampering passive detection method based on convolutional neural network
  • Digital audio tampering passive detection method based on convolutional neural network
  • Digital audio tampering passive detection method based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0075] A kind of digital audio tampering passive detection method based on the convolutional neural network of the present invention, the algorithm flow chart of the present invention is as follows figure 1 As shown, it can be divided into four parts: 1) ENF component acquisition; 2) ENF phase and frequency feature extraction; 3) training UBM to extract ENF Gaussian mean supervector; 4) convolutional neural network training.

[0076] Step 1: Obtain ENF components, the steps are as follows:

[0077] A. Downsample the audio, and set the resampling frequency to 1000HZ or 1200HZ;

[0078] B. Use a 10,000-order linear zero-phase FIR filter for narrow-band filtering. The center frequency is at the ENF standard (50HZ or 60HZ), the bandwidth is 0.6HZ, the passband ripple is 0.5dB, and the stopband attenuation is 100dB;

[0079] Step 2: ENF phase and frequency feature extraction, the steps are as follows:

[0080] A. Calculate the first order derivative of the signal, frame and windo...

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 belongs to the technical field of digital audio tampering detection, and particularly relates to a digital audio tampering passive detection method based on a convolutional neural network. According to the invention, ENF fluctuation super-vector features are classified by adopting the CNN and an attention mechanism Attention. The convolutional neural network can better learn the difference between the original audio and the tampered audio. The attention mechanism screens out important information from a large number of features output by the CNN, and reduces the operation burdenof input data. Compared with traditional digital audio tampering detection methods, the digital audio tampering detection method has the advantages that the recognition performance of a system can beeffectively improved, the system structure is optimized, and the competitiveness of corresponding equipment source recognition products is improved.

Description

technical field [0001] The invention belongs to the technical field of digital audio tampering detection, in particular to a passive detection method for digital audio tampering based on a convolutional neural network. Background technique [0002] With the rapid advancement of digital audio technology, people can easily collect digital audio signals, but at the same time, they can also easily edit and modify them later by using many audio processing software. If this kind of intentional or unintentional tampering digital audio is applied to important occasions such as judicial evidence collection, it will likely cause some bad social problems. Therefore, the research on digital audio tampering detection is of great significance. [0003] Passive detection of digital audio tampering is a technology that analyzes and judges the authenticity and integrity of digital audio only by the characteristics of the audio itself without adding any information, and has practical signific...

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): G10L25/51G10L25/30G06N3/04G06K9/62
CPCG10L25/51G10L25/30G06N3/045G06F18/24
Inventor 曾春艳杨尧冯世雄孔帅余琰
Owner HUBEI UNIV OF TECH
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

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com