Unlock instant, AI-driven research and patent intelligence for your innovation.

Audio clip authentication method based on frequency spectrum SIFT feature descriptor

A technology for feature descriptors and audio clips, used in speech analysis, instruments, etc.

Inactive Publication Date: 2014-04-16
FUDAN UNIV
View PDF2 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The experiment mainly tests the compression distortion of MP3, and the average error rate can reach below 7% when the sampling bit rate is higher such as 128kbps, but the average error rate is about 40% when the sampling rate is lower such as 32kbps

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
  • Audio clip authentication method based on frequency spectrum SIFT feature descriptor
  • Audio clip authentication method based on frequency spectrum SIFT feature descriptor
  • Audio clip authentication method based on frequency spectrum SIFT feature descriptor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0064] First, establish a database containing 1030 audio files, covering different voice signals and music signals. Each audio file is 2 minutes long, in WAVE format, with a sampling rate of 44.1kHz and mono. The length of the intercepted suspicious audio clip to be authenticated is 10s, which is randomly intercepted from the above original audio file. In this embodiment, the audio content authentication system constructed according to the above method is first tested for the authentication pass rate (True Positive Rates, TPR) for the operation of maintaining the content and the authentication failure rate (True Negative Rates, TNR) for the malicious tampering operation. Both are regarded as the accuracy of the authentication system, that is, the larger the value of the two, the higher the accuracy of the system.

[0065] Table 1. is the modification type and its corresponding TPR / TNR.

[0066] Table 1.

[0067]

[0068] The results show that the system’s certification pass rate i...

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 information safety and protection, and relates to an audio clip authentication method based on a frequency spectrum SIFT feature descriptor, in particular to a content authentication method which is based on the computer vision technology and can use audio clips as detection objects. The SIFT feature matching is utilized for extracting the feature descriptor, and the detected suspicious audio clips are aligned in a reference audio file; the suspicious audio clips are divided into a plurality of blocks through contraction-expansion factors extracted from an SIFT key point; the time domain blocks can be directly used for recognizing malicious clipping, malicious insertion and other actions; modified factors are estimated and used for describing corresponding time domain units, so that robust Hash is calculated conveniently. Due to matching and Hash detection, not only can the integrity and authenticity of the suspicious audio clips be authenticated accurately, but also the positions of malicious tamper operations are accurately locked and classified according to types.

Description

Technical field [0001] The invention belongs to the technical field of information security and protection in audio authentication, and relates to an audio segment authentication method based on spectrum SIFT feature descriptors, and in particular to a content authentication method based on computer vision technology that can use audio segments as detection objects . Background technique [0002] Audio content authentication technology is an effective technology to detect and protect the integrity and authenticity of audio data such as music and voice. Its purpose is to ensure that the data received by the receiver of audio transmission is not subject to a third party during transmission. The malicious editing and tampering of the audio is exactly the same as the original audio from the perspective of the human perception system. Different from traditional signature authentication, multimedia authentication such as audio ensures the authentication of file content rather than sim...

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): G10L25/03G10L19/00
Inventor 李伟殷玥董旭炯
Owner FUDAN UNIV