Music Classification Using the Bag of Words Model of Modulation Spectral Features

Chang Hsing Lee, Hwai-San Lin, Ling-Hwei Chen

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

Abstract

In this paper, the bag of words (BoW) representation of modulation spectral analysis of spectral as well as cepstral features will be constructed for music genre classification. First, the modulation spectrum of each spectral and cepstral feature will be obtained through modulation spectral analysis of a longer texture window. Then, the BoW model of the modulation spectral features will be constructed and used for music classification. Experiments conducted on the music database employed in the ISMIR2004 Audio Description Contest have shown that the proposed BoW representation of modulation spectral features can achieve promising classification accuracy, particularly when it is combined with the BoW representation of frame features.
Original languageEnglish
Title of host publication2015 15TH INTERNATIONAL SYMPOSIUM ON COMMUNICATIONS AND INFORMATION TECHNOLOGIES (ISCIT)
PublisherIEEE
Pages121-124
Number of pages4
ISBN (Print)978-1-4673-6820-9
StatePublished - 2015
Event15th International Symposium on Communications and Information Technologies (ISCIT) - Nara Kasugano Int Forum IRAKA, Nara, Japan
Duration: 7 Oct 20159 Oct 2015

Conference

Conference15th International Symposium on Communications and Information Technologies (ISCIT)
CountryJapan
CityNara
Period7/10/159/10/15

Keywords

  • bag of words (BoW) Model; modulation spectral analysis; music genre classifications

Fingerprint Dive into the research topics of 'Music Classification Using the Bag of Words Model of Modulation Spectral Features'. Together they form a unique fingerprint.

Cite this