Author: Ovunc OZTURK, Didem ABİDİN, Tuğba ÖZACAR
Publishing Date: 2018
E-ISSN: 2147-9364
Volume: 6 Issue: 3
ABSTRACT:
Turkish Music pieces are used in various studies including makam recognition in computational music domain. Turkish Music pieces offer a rich content to the researchers because of their different makam properties. In up to date studies, SymbTr Turkish Music data set is referred the most. In this study, thirteen makams used in similar studies in literature were chosen, the pieces from SymbTr data set belonging these makams were used to execute machine learning algorithms for makam recognition and the performances were compared with similar studies. These algorithms were executed on WEKA application environment and the performances in makam recognition and confusion matrices were obtained. The machine learning algorithms used have performed between 79% and 88%.
Keywords: Makam recognition, Machine learning algorithms, WEKA, SymbTr