Skip to main navigation Skip to search Skip to main content

Visualized feature fusion and style evaluation for musical genre analysis

  • School of Computer Science and Technology, Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Different kinds of features in time domain, spectral domain and cepstral domain are used for musical genre classification. In this paper, through the fusion of short-term timbral features and long-term rhythmic feature, we propose a novel method where: musical genre vector is constructed using the likelihood ratio of GMM (Gaussian Mixture Model) and radar chart is applied to provide visualized style evaluation for musical genre analysis, a promising performance is achieved over our database consisting of seven different types of music. Because of the fuzzy definition of musical genres, we also investigate the music with dual-genre based on musical genre vector and radar chart.

Original languageEnglish
Title of host publicationProceedings - 2010 1st International Conference on Pervasive Computing, Signal Processing and Applications, PCSPA 2010
Pages883-886
Number of pages4
DOIs
StatePublished - 2010
Externally publishedYes
Event1st International Conference on Pervasive Computing, Signal Processing and Applications, PCSPA 2010 - Harbin, China
Duration: 17 Sep 201019 Sep 2010

Publication series

NameProceedings - 2010 1st International Conference on Pervasive Computing, Signal Processing and Applications, PCSPA 2010

Conference

Conference1st International Conference on Pervasive Computing, Signal Processing and Applications, PCSPA 2010
Country/TerritoryChina
CityHarbin
Period17/09/1019/09/10

Keywords

  • Beat histogram
  • Feature fusion
  • GMM
  • Musical genre analysis
  • Musical genre vector
  • Radar chart

Fingerprint

Dive into the research topics of 'Visualized feature fusion and style evaluation for musical genre analysis'. Together they form a unique fingerprint.

Cite this