Title :
Classification of Classic Turkish Music Makams
Author :
Kizrak, M. Ayyuce ; Bayram, K. Sercan ; Bolat, B.
Author_Institution :
Electr. & Electron. Eng. Dept., Halic Univ., Istanbul, Turkey
Abstract :
In this work, Classical Turkish Music songs are classified into six makams. Makam is a modal framework for melodic development in Classical Turkish Music. The effect of the sound clip length on the system performance was also evaluated. The Mel Frequency Cepstral Coefficients (MFCC) were used as features. Obtained data were classified by using Probabilistic Neural Network. The best correct recognition ratio was obtained as 89,4% by using a clip length of 6 s.
Keywords :
acoustic signal processing; feature extraction; music; neural nets; Classic Turkish Music Makams; Classical Turkish Music; MFCC; Mel frequency cepstral coefficients; melodic development; probabilistic neural network; recognition ratio; songs classification; sound clip length; Accuracy; Filter banks; Instruments; Mel frequency cepstral coefficient; Music; Neural networks; Probabilistic logic; Mel Frequency Cepstral Coefficients (MFCC); Probabilistic Neural Network (PNN); musical information retrieval;
Conference_Titel :
Innovations in Intelligent Systems and Applications (INISTA) Proceedings, 2014 IEEE International Symposium on
Conference_Location :
Alberobello
Print_ISBN :
978-1-4799-3019-7
DOI :
10.1109/INISTA.2014.6873650
