Spectral-based features ranking for gamelan instruments identification using filter techniques

Aris Tjahyanto*, Yoyon K. Suprapto, Diah P. Wulandari

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

12 Citations (Scopus)

Abstract

In this paper, we describe an approach of spectral-based features ranking for Javanese gamelan instruments identification using filter techniques. The model extracted spectral-based features set of the signal using Short Time Fourier Transform (STFT). The rank of the features was determined using the five algorithms; namely ReliefF, Chi-Squared, Information Gain, Gain Ratio, and Symmetric Uncertainty. Then, we tested the ranked features by cross validation using Support Vector Machine (SVM). The experiment showed that Gain Ratio algorithm gave the best result, it yielded accuracy of 98.93%.

Original languageEnglish
Pages (from-to)95-106
Number of pages12
JournalTelkomnika (Telecommunication Computing Electronics and Control)
Volume11
Issue number1
DOIs
Publication statusPublished - Mar 2013

Keywords

  • Automatic transcription
  • Features extraction
  • Gain ratio
  • Support vector machine

Fingerprint

Dive into the research topics of 'Spectral-based features ranking for gamelan instruments identification using filter techniques'. Together they form a unique fingerprint.

Cite this