Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Method for identifying sound recording locations

A recognition method and location technology, applied in special data processing applications, instruments, biological neural network models, etc., can solve the problems of difficulty in recording location recognition and high efficiency, and achieve the effect of accelerated recognition and high efficiency.

Inactive Publication Date: 2014-10-15
NANJING INST OF TECH
View PDF1 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a method for identifying the recording location, using BP neural network as the main identification method, which has high efficiency and solves the problem that the existing digital audio forensics technology is difficult to identify the recording location

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
  • Method for identifying sound recording locations
  • Method for identifying sound recording locations
  • Method for identifying sound recording locations

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0046] The embodiment discloses a recording location recognition method, which is a recognition method based on BP neural network. BP neural network is a multilayer feed-forward network trained by error backpropagation algorithm, and it is one of the most widely used neural network models at present. BP neural network has higher recognition efficiency, but it also has obvious disadvantages. For this reason, the present invention adopts KDA dimensionality reduction algorithm to improve the recognition speed, and simultaneously uses simulated annealing algorithm to search for recognition results, and can quickly and accurately identify the recording location.

[0047] to combine figure 1 , this recording location recognition method includes the following parts: grid frequency data dimension reduction, grid frequency extraction in audio, establishment of BP neural network recognition model, search for recognition results, and convert recognition results into specific locations. ...

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 provides a method for identifying sound recording locations. The method includes reducing dimensions of data of power grid frequencies; extracting the power grid frequencies in audio frequencies; building identification models of BP (back propagation) neural networks; simulating annealing searching identifying results; converting the identifying results into particular locations. The method has the advantages that the problem that sound recording locations cannot be identified by the traditional method for collecting evidences by the aid of audio frequencies is solved; the method is used for identifying the sound recording locations mainly by the aid of the BP neural networks and accordingly is high in efficiency; the identifying speeds can be increased owing to a KDA (knowledge driven automation) dimension reducing algorithm; the sound recording locations can be quickly determined by the aid of the simulated annealing searching identifying results; the method is based on the BP neural networks, the sound recording locations are identified on the basis of the power grid frequencies, and accordingly the difficult problem that the sound recording locations cannot be identified by the traditional method is solved.

Description

technical field [0001] The invention relates to a method for identifying a recording location. Background technique [0002] Nowadays, with the digital technology in the information field advancing to all areas of human life, the audio digital storage method has almost replaced the traditional storage method. At the same time, the rapid development of computer technology has made digital audio editing easier and more professional. [0003] According to the survey statistics of relevant departments: the crime rate based on digital audio is increasing year by year. According to Article 69 of the Supreme People's Court's "Several Provisions on Evidence in Civil Procedures", audio-visual materials with doubtful points cannot be used alone as the basis for determining the facts of a case. When digital audio files are used as evidence in court, their originality and integrity are often areas of concern. However, under the premise that the recording time and recording location c...

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): G06F19/00G06N3/02
Inventor 王学强吉建梅
Owner NANJING INST OF TECH
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
Eureka Blog
Learn More
PatSnap group products