Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method for monitoring and automatically classifying music factions based on decorrelation sparse mapping

An automatic classification and supervised technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve the problem of undiscovered music genres with supervised automatic classification.

Active Publication Date: 2011-07-20
南通捷晶半导体技术有限公司
View PDF2 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] There is currently no report on the supervised automatic classification of music genres based on the least one-norm sparse mapping

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 monitoring and automatically classifying music factions based on decorrelation sparse mapping
  • Method for monitoring and automatically classifying music factions based on decorrelation sparse mapping
  • Method for monitoring and automatically classifying music factions based on decorrelation sparse mapping

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] In the following, the method for supervised automatic classification of music genres through decorrelation sparse mapping according to the present invention will be described in detail in conjunction with the accompanying drawings and specific embodiments.

[0053] The method of the present invention fully considers the characteristics of music and combines the latest pattern recognition and classification method - sparse matrix, can realize automatic classification of n genres of music, and the classification accuracy is high. specific use figure 1 A method and system for improving the accuracy of music genre classification, comprising the following steps:

[0054] (1) Establish a music database.

[0055] The music of 9 music genres was obtained by downloading from the Internet. Each genre of music contained 400 songs, and each genre of music contained more than 60 singers. They were manually classified to prepare for the test of the entire system.

[0056] (2) Extra...

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 relates to audio signal processing, in particular to a method for monitoring and automatically classifying music factions, which is based on minimum-norm sparse mapping, aims to improving the automatic classification accuracy of music factions and facilitating the organization and the retrieval of a music audio database and can also be used other retrieval based on content music information to improve the retrieval performance. The invention adopts the technical scheme that the method for monitoring and automatically classifying music factions based on decorrelation sparse mapping comprises the following steps of: (a) establishing a monitoring training database; (b) extracting short-time music characteristics and rhythm characteristics from a training music sample, wherein the short-time music characteristics comprise MFCC (Mel Frequency Cepstrum Coefficient) and timber characteristics; (c) denoising and reducing dimensions of the extracted characteristic data by adopting a PCA (Primary Component Analysis) technology; (d) partitioning a characteristic matrix according to faction categories; and (e) confirming y class as argmini*abs(y-A*deltai (x)*i)*2, wherein i equals to 1,2, ......,k, and the nonzero value of deltai (x) is the i(th) class. The method is mainly applied to audio signal processing.

Description

technical field [0001] The invention relates to audio signal processing, in particular to a supervised automatic classification method for decorrelation sparse mapping music genres. Background technique [0002] Today's digitalization and network era, the rapid development of data storage technology and multimedia compression technology such as JPEG, MPEG and other technologies have led to an increase in the storage capacity of digital multimedia data, and also led to an increase in audio data on the Internet. At present, multimedia content such as images, audio and video has become the main part of the data transmitted on the Internet information highway, and music is the main part of audio. With the development of the Internet, more and more people can more conveniently and quickly , Economic access to digital music, the problem people face is no longer the lack of media content, but how to find the information they need in the vast multimedia world. Music genres are crea...

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): G06F17/30
Inventor 关欣徐星李锵
Owner 南通捷晶半导体技术有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com