Audio-frequency fingerprint method of compressed domain based on Zernike moment

An audio fingerprint and compressed domain technology, applied in the field of entropy-based compressed domain audio information recognition, can solve problems such as failure to give retrieval results

Inactive Publication Date: 2010-11-10
FUDAN UNIV
View PDF3 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Analysis experiments show that the algorithm is robust to attacks such as downsam

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-frequency fingerprint method of compressed domain based on Zernike moment
  • Audio-frequency fingerprint method of compressed domain based on Zernike moment
  • Audio-frequency fingerprint method of compressed domain based on Zernike moment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0067] In order to verify the effectiveness of the above method, the present invention has carried out the following experiments. Firstly, a database containing 1182 Chinese popular songs is established, and fingerprints are constructed according to the above method. The parameter settings of each song are: mono, 30S long, sampling rate 44.1KHz, bit rate 64Kbps, roughly 1141Bits fingerprint. In order to have a better compromise between fingerprint granularity, robustness, and retrieval efficiency, we use 100 5S-long segments to be identified for testing, and each track will be subject to more signal processing. For the determination of BER, we selected a song and its 15 processed versions, and obtained the corresponding FPR in the case of a specific BER threshold according to the above method. As shown in Table 1:

[0068] Table 1. PR and its corresponding BER thresholds

[0069]

[0070] When we selected the BER threshold as 0.32, our false detection rate was 2.7668e-00...

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 music search based on contents, in particular to an audio-frequency fingerprint method of a compressed domain based on Zernike moment. The invention combines the frequency and time information of the modified discrete cosine transform coefficient (the MDCT coefficient) of the data of the compressed domain of an MP3 and some properties of the Zernike moment skillfully, such as low-order moment representing the integral properties of a signal and high-order moment representing the detailed properties of the signal; and the Zernike moment has the invariable properties of rotation, scaling and translation, so that the fingerprint of the audio-frequency compressed domain which is finally formed can resist the processing of a plurality of signals of a time domain robustly and resists the processing of the signals of the time domain slightly.

Description

technical field [0001] The invention belongs to the technical field of content-based music retrieval, and in particular relates to an entropy-based compression domain audio information recognition method. Background technique [0002] Audio fingerprint refers to a content-based compact digital signature that can represent important acoustic features of a piece of music in the field of content-based reference retrieval technology. Its main purpose is to establish an effective mechanism to compare the perceived auditory quality of two audio data The degree of similarity enables people to obtain metadata related to the audio segment, such as the name of the audio, only through an audio segment without any text mark. The audio data itself, which is usually large, is not directly compared here, but its corresponding digital fingerprint, which is usually small, is compared. The fingerprints of a large amount of audio data are stored in a database together with their corresponding...

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): G10L15/00G06F17/30G10L25/54
Inventor 李伟刘亚多冯瑞薛向阳
Owner FUDAN 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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap