Cover Image

A study on feature selection and classification techniques for automatic genre classification of traditional Malay music

Machine learning techniques for automated musical genre classification is currently widely studied. With large collections of digital musical files, one approach to classification is to classify by musical genres such as pop, rock and classical in Western music. Beat, pitch and temporal related feat...

Full description

Saved in:
Bibliographic Details
Main Authors: Doraisamy, Shyamala, Golzari, Shahram, Mohd. Norowi, Noris, Sulaiman, Md. Nasir, Udzir, Nur Izura
Format: Conference or Workshop Item
Language:English
Published: ISMIR 2008
Online Access:http://psasir.upm.edu.my/id/eprint/40721/1/40721.pdf
http://psasir.upm.edu.my/id/eprint/40721/
http://ismir2008.ismir.net/papers/ISMIR2008_256.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.upm.eprints.40721
record_format eprints
spelling my.upm.eprints.407212015-09-21T09:28:29Z http://psasir.upm.edu.my/id/eprint/40721/ A study on feature selection and classification techniques for automatic genre classification of traditional Malay music Doraisamy, Shyamala Golzari, Shahram Mohd. Norowi, Noris Sulaiman, Md. Nasir Udzir, Nur Izura Machine learning techniques for automated musical genre classification is currently widely studied. With large collections of digital musical files, one approach to classification is to classify by musical genres such as pop, rock and classical in Western music. Beat, pitch and temporal related features are extracted from audio signals and various machine learning algorithms are applied for classification. Features that resulted in better classification accuracies for Traditional Malay Music (TMM), in comparison to western music, in a previous study were beat related features. However, only the J48 classifier was used and in this study we perform a more comprehensive investigation on improving the classification of TMM. In addition, feature selection was performed for dimensionality reduction. Classification accuracies using classifiers of varying paradigms on a dataset comprising ten TMM genres were obtained. Results identify potentially useful classifiers and show the impact of adding a feature selection phase for TMM genre classification. ISMIR 2008 Conference or Workshop Item NonPeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/40721/1/40721.pdf Doraisamy, Shyamala and Golzari, Shahram and Mohd. Norowi, Noris and Sulaiman, Md. Nasir and Udzir, Nur Izura (2008) A study on feature selection and classification techniques for automatic genre classification of traditional Malay music. In: 9th International Conference on Music Information Retrieval, ISMIR 2008, 14-18 Sep. 2008, Philadelphia, USA. (pp. 331-336). http://ismir2008.ismir.net/papers/ISMIR2008_256.pdf
institution Universiti Putra Malaysia
building UPM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Putra Malaysia
content_source UPM Institutional Repository
url_provider http://psasir.upm.edu.my/
language English
description Machine learning techniques for automated musical genre classification is currently widely studied. With large collections of digital musical files, one approach to classification is to classify by musical genres such as pop, rock and classical in Western music. Beat, pitch and temporal related features are extracted from audio signals and various machine learning algorithms are applied for classification. Features that resulted in better classification accuracies for Traditional Malay Music (TMM), in comparison to western music, in a previous study were beat related features. However, only the J48 classifier was used and in this study we perform a more comprehensive investigation on improving the classification of TMM. In addition, feature selection was performed for dimensionality reduction. Classification accuracies using classifiers of varying paradigms on a dataset comprising ten TMM genres were obtained. Results identify potentially useful classifiers and show the impact of adding a feature selection phase for TMM genre classification.
format Conference or Workshop Item
author Doraisamy, Shyamala
Golzari, Shahram
Mohd. Norowi, Noris
Sulaiman, Md. Nasir
Udzir, Nur Izura
spellingShingle Doraisamy, Shyamala
Golzari, Shahram
Mohd. Norowi, Noris
Sulaiman, Md. Nasir
Udzir, Nur Izura
A study on feature selection and classification techniques for automatic genre classification of traditional Malay music
author_facet Doraisamy, Shyamala
Golzari, Shahram
Mohd. Norowi, Noris
Sulaiman, Md. Nasir
Udzir, Nur Izura
author_sort Doraisamy, Shyamala
title A study on feature selection and classification techniques for automatic genre classification of traditional Malay music
title_short A study on feature selection and classification techniques for automatic genre classification of traditional Malay music
title_full A study on feature selection and classification techniques for automatic genre classification of traditional Malay music
title_fullStr A study on feature selection and classification techniques for automatic genre classification of traditional Malay music
title_full_unstemmed A study on feature selection and classification techniques for automatic genre classification of traditional Malay music
title_sort study on feature selection and classification techniques for automatic genre classification of traditional malay music
publisher ISMIR
publishDate 2008
url http://psasir.upm.edu.my/id/eprint/40721/1/40721.pdf
http://psasir.upm.edu.my/id/eprint/40721/
http://ismir2008.ismir.net/papers/ISMIR2008_256.pdf
_version_ 1643832797792567296
score 13.211869

Similar Items