FFT-based features selection for Javanese music note and instrument identification using support vector machines

Aris Tjahyanto*, Yoyon K. Suprapto, Mauridhi Hery Purnomo, Diah Puspito Wulandari

*Corresponding author for this work

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

8 Citations (Scopus)

Abstract

Most automatic music transcription research is related with Western music, and still less for the Javanese gamelan music. In this paper, we proposed a method for the features extraction, selection, and identification of gamelan note and the proper instrument. It was an approach based on Fast Fourier Transform (FFT), and support vector machines (SVMs) for note and instrument identification. We selected four spectral features (spectral centroid, two spectral rolloff, and fundamental frequency) as input for SVM. Experimental results show that fundamental frequency, spectral centroid, and spectral rolloff can be used to distinguish gamelan instrument with accuracy or recognition rate more than 95%.

Original languageEnglish
Title of host publicationCSAE 2012 - Proceedings, 2012 IEEE International Conference on Computer Science and Automation Engineering
Pages439-443
Number of pages5
DOIs
Publication statusPublished - 2012
Event2012 IEEE International Conference on Computer Science and Automation Engineering, CSAE 2012 - Zhangjiajie, China
Duration: 25 May 201227 May 2012

Publication series

NameCSAE 2012 - Proceedings, 2012 IEEE International Conference on Computer Science and Automation Engineering
Volume1

Conference

Conference2012 IEEE International Conference on Computer Science and Automation Engineering, CSAE 2012
Country/TerritoryChina
CityZhangjiajie
Period25/05/1227/05/12

Keywords

  • FFT
  • gamelan
  • music transcription
  • spectral features
  • support vector machine

Fingerprint

Dive into the research topics of 'FFT-based features selection for Javanese music note and instrument identification using support vector machines'. Together they form a unique fingerprint.

Cite this