Classification of classic Turkish music makams by using deep belief networks

Merve Ayyuce Kizrak Sagun; Bulent Bolat

doi:10.1109/INISTA.2016.7571850

Classification of classic Turkish music makams by using deep belief networks

Merve Ayyuce Kizrak Sagun, Bulent Bolat

Yildiz Technical University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Citations (Scopus)

Abstract

Automatic classification of makams from sound data is a challenging yet rarely studied topic. In this work, it is aimed to develop an MIR system which determines a song's makam. To overcome this problem, mel frequency cepstral coefficients were utilized as features. Five classifiers were considered. The best result was obtained by deep belief network as 93.10 which is comparable to the recent works.

Original language	English
Title of host publication	Proceedings of the 2016 International Symposium on INnovations in Intelligent SysTems and Applications, INISTA 2016
Editors	Tulay Yuldirim, Mirel Cosulschi, Adina Magda Florea, Costin Badica, Petia Koprinkova-Hristova
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781467399104
DOIs	https://doi.org/10.1109/INISTA.2016.7571850
Publication status	Published - 19 Sept 2016
Externally published	Yes
Event	2016 International Symposium on INnovations in Intelligent SysTems and Applications, INISTA 2016 - Sinaia, Romania Duration: 2 Aug 2016 → 5 Aug 2016

Publication series

Name	Proceedings of the 2016 International Symposium on INnovations in Intelligent SysTems and Applications, INISTA 2016

Conference

Conference	2016 International Symposium on INnovations in Intelligent SysTems and Applications, INISTA 2016
Country/Territory	Romania
City	Sinaia
Period	2/08/16 → 5/08/16

Bibliographical note

Publisher Copyright:
© 2016 IEEE.

Keywords

Classic Turkish Music Makams
Deep Belief Networks
Generalized Regression Neural Network
Mel-Frequency Cepstrum Coefficients
Probabilistic Neural Network
Radial Basis Function Network
Support Vector Machine

Access to Document

10.1109/INISTA.2016.7571850

Cite this

Sagun, M. A. K., & Bolat, B. (2016). Classification of classic Turkish music makams by using deep belief networks. In T. Yuldirim, M. Cosulschi, A. M. Florea, C. Badica, & P. Koprinkova-Hristova (Eds.), Proceedings of the 2016 International Symposium on INnovations in Intelligent SysTems and Applications, INISTA 2016 Article 7571850 (Proceedings of the 2016 International Symposium on INnovations in Intelligent SysTems and Applications, INISTA 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/INISTA.2016.7571850

Sagun, Merve Ayyuce Kizrak ; Bolat, Bulent. / Classification of classic Turkish music makams by using deep belief networks. Proceedings of the 2016 International Symposium on INnovations in Intelligent SysTems and Applications, INISTA 2016. editor / Tulay Yuldirim ; Mirel Cosulschi ; Adina Magda Florea ; Costin Badica ; Petia Koprinkova-Hristova. Institute of Electrical and Electronics Engineers Inc., 2016. (Proceedings of the 2016 International Symposium on INnovations in Intelligent SysTems and Applications, INISTA 2016).

@inproceedings{9deb0b424d9249389da790bdf5a39997,

title = "Classification of classic Turkish music makams by using deep belief networks",

abstract = "Automatic classification of makams from sound data is a challenging yet rarely studied topic. In this work, it is aimed to develop an MIR system which determines a song's makam. To overcome this problem, mel frequency cepstral coefficients were utilized as features. Five classifiers were considered. The best result was obtained by deep belief network as 93.10 which is comparable to the recent works.",

keywords = "Classic Turkish Music Makams, Deep Belief Networks, Generalized Regression Neural Network, Mel-Frequency Cepstrum Coefficients, Probabilistic Neural Network, Radial Basis Function Network, Support Vector Machine",

author = "Sagun, {Merve Ayyuce Kizrak} and Bulent Bolat",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 2016 International Symposium on INnovations in Intelligent SysTems and Applications, INISTA 2016 ; Conference date: 02-08-2016 Through 05-08-2016",

year = "2016",

month = sep,

day = "19",

doi = "10.1109/INISTA.2016.7571850",

language = "English",

series = "Proceedings of the 2016 International Symposium on INnovations in Intelligent SysTems and Applications, INISTA 2016",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

editor = "Tulay Yuldirim and Mirel Cosulschi and Florea, {Adina Magda} and Costin Badica and Petia Koprinkova-Hristova",

booktitle = "Proceedings of the 2016 International Symposium on INnovations in Intelligent SysTems and Applications, INISTA 2016",

address = "United States",

}

Sagun, MAK & Bolat, B 2016, Classification of classic Turkish music makams by using deep belief networks. in T Yuldirim, M Cosulschi, AM Florea, C Badica & P Koprinkova-Hristova (eds), Proceedings of the 2016 International Symposium on INnovations in Intelligent SysTems and Applications, INISTA 2016., 7571850, Proceedings of the 2016 International Symposium on INnovations in Intelligent SysTems and Applications, INISTA 2016, Institute of Electrical and Electronics Engineers Inc., 2016 International Symposium on INnovations in Intelligent SysTems and Applications, INISTA 2016, Sinaia, Romania, 2/08/16. https://doi.org/10.1109/INISTA.2016.7571850

Classification of classic Turkish music makams by using deep belief networks. / Sagun, Merve Ayyuce Kizrak; Bolat, Bulent.
Proceedings of the 2016 International Symposium on INnovations in Intelligent SysTems and Applications, INISTA 2016. ed. / Tulay Yuldirim; Mirel Cosulschi; Adina Magda Florea; Costin Badica; Petia Koprinkova-Hristova. Institute of Electrical and Electronics Engineers Inc., 2016. 7571850 (Proceedings of the 2016 International Symposium on INnovations in Intelligent SysTems and Applications, INISTA 2016).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Classification of classic Turkish music makams by using deep belief networks

AU - Sagun, Merve Ayyuce Kizrak

AU - Bolat, Bulent

PY - 2016/9/19

Y1 - 2016/9/19

N2 - Automatic classification of makams from sound data is a challenging yet rarely studied topic. In this work, it is aimed to develop an MIR system which determines a song's makam. To overcome this problem, mel frequency cepstral coefficients were utilized as features. Five classifiers were considered. The best result was obtained by deep belief network as 93.10 which is comparable to the recent works.

AB - Automatic classification of makams from sound data is a challenging yet rarely studied topic. In this work, it is aimed to develop an MIR system which determines a song's makam. To overcome this problem, mel frequency cepstral coefficients were utilized as features. Five classifiers were considered. The best result was obtained by deep belief network as 93.10 which is comparable to the recent works.

KW - Classic Turkish Music Makams

KW - Deep Belief Networks

KW - Generalized Regression Neural Network

KW - Mel-Frequency Cepstrum Coefficients

KW - Probabilistic Neural Network

KW - Radial Basis Function Network

KW - Support Vector Machine

UR - http://www.scopus.com/inward/record.url?scp=84992045348&partnerID=8YFLogxK

U2 - 10.1109/INISTA.2016.7571850

DO - 10.1109/INISTA.2016.7571850

M3 - Conference contribution

AN - SCOPUS:84992045348

T3 - Proceedings of the 2016 International Symposium on INnovations in Intelligent SysTems and Applications, INISTA 2016

BT - Proceedings of the 2016 International Symposium on INnovations in Intelligent SysTems and Applications, INISTA 2016

A2 - Yuldirim, Tulay

A2 - Cosulschi, Mirel

A2 - Florea, Adina Magda

A2 - Badica, Costin

A2 - Koprinkova-Hristova, Petia

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2016 International Symposium on INnovations in Intelligent SysTems and Applications, INISTA 2016

Y2 - 2 August 2016 through 5 August 2016

ER -

Sagun MAK, Bolat B. Classification of classic Turkish music makams by using deep belief networks. In Yuldirim T, Cosulschi M, Florea AM, Badica C, Koprinkova-Hristova P, editors, Proceedings of the 2016 International Symposium on INnovations in Intelligent SysTems and Applications, INISTA 2016. Institute of Electrical and Electronics Engineers Inc. 2016. 7571850. (Proceedings of the 2016 International Symposium on INnovations in Intelligent SysTems and Applications, INISTA 2016). doi: 10.1109/INISTA.2016.7571850

Classification of classic Turkish music makams by using deep belief networks

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this