Coding parameter statistical feature-based AAC sound recording document source identification method

A technology for recording files and recognition methods, which is applied in speech recognition, speech analysis, electrical components, etc., and can solve problems such as coding parameter selection and usage differences.

Inactive Publication Date: 2016-08-10
NINGBO UNIV
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Although these methods have achieved good recognition results in the identification of audio source devices, as far as we know, there are no reports on the use of the stream structure and encoding parameter characteristics of recording files to realize mobile phone source identification.
At present, the default recording formats of most smartphones are compressed formats, and the compression standards are mainly MP3 and AAC; in addition, different manufacturers, or even different types of equipment produced by the same manufacturer, have different hardware and software parts of the audio module. The difference is that the specific implementation of the compression algorithm and the cooperation with the hardware also have their own characteristics, which leads to differences in the selection and use of various encoding parameters when different brands and models of mobile phones compress and encode the picked-up sound signals; therefore, It is undoubtedly a very reliable identification method to identify the source of AAC recording files based on the statistical characteristics of encoding parameters.

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
  • Coding parameter statistical feature-based AAC sound recording document source identification method
  • Coding parameter statistical feature-based AAC sound recording document source identification method
  • Coding parameter statistical feature-based AAC sound recording document source identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The embodiments of the present invention will be described in detail below according to the above-mentioned drawings.

[0033] A method for identifying the source of an AAC recording file based on the statistical characteristics of encoding parameters involves studying the use characteristics and statistical characteristics of the encoding parameters of the AAC recording file to determine which brand and model of mobile phone an AAC recording file is recorded by.

[0034] In this recognition method, a concept description about AAC recording files is involved, specifically:

[0035] Overview of the AAC encoding standard

[0036]Advanced Audio Coding (Advanced Audio Coding, AAC) is a new generation of audio coding standards, it is an important part of the ISO / IEC MPEG-2 and MPEG-4 standards. MPEG-2 AAC was released in 1997. As the successor of MP3, it has better sound quality than MP3 audio at the same bit rate, especially at low bit rate. MPEG-2 AAC defines three profi...

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 coding parameter statistical feature-based AAC (advanced audio coding) sound recording document source identification method. According to the design thought of the invention, the use features and statistical features of a plurality of coding parameters of AAC sound recording documents of smart phones are analyzed; the tendencies and characteristics of using the coding parameters when the mobile phones generate the AAC sound recording documents are found out; and features for distinguishing phone models are constructed; and therefore, accurate identification of the sources of the AAC sound recording documents can be realized. The AAC sound recording document source identification method has the advantages of high recognition accuracy, convenience in operation and the like.

Description

technical field [0001] The invention relates to a method for identifying the source of an AAC recording file, in particular to a method for identifying the source of an AAC recording file based on the statistical characteristics of encoding parameters. Background technique [0002] With the advent of the big data era, digital multimedia is experiencing explosive growth. But at the same time, the increase in the magnitude and frequency of multimedia data also promotes the rapid development of multimedia editing software, which makes the forgery and tampering of multimedia data easier and easier. Therefore, the growth of multimedia data scale and the development of editing software make our life full of a large amount of untrue and untrustworthy multimedia data. In order to verify the originality, authenticity and integrity of multimedia data, multimedia forensics technology came into being. At present, the research on digital multimedia forensics at home and abroad is mainl...

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): G10L15/14G10L19/02G10L19/032G10L25/18H04M1/725H04M1/72403
CPCG10L15/14G10L19/0204G10L19/032G10L25/18H04M1/72403
Inventor 王让定金超严迪群
Owner NINGBO 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