Iranian Traditional Music Dastgah Classification

Abstract

In this study, a system for Iranian traditional music Dastgah classification is presented. Persian music is based upon a set of seven major Dastgahs. The Dastgah in Persian music is similar to western musical scales and also Maqams in Turkish and Arabic music. Fuzzy logic type 2 as the basic part of our system has been used for modeling the uncertainty of tuning the scale steps of each Dastgah. The method assumes each performed note as a Fuzzy Set (FS), so each musical piece is a set of FSs. The maximum similarity between this set and theoretical data indicates the desirable Dastgah. In this study, a collection of small-sized dataset for Persian music is also given. The results indicate that the system works accurately on the dataset.

Sajjad Abdoli

Ph.D. Machine Learning Scientist

My research interests include Audio and Speech Processing, Music Information Retrieval, Adversarial Machine Learning and object localization/classification.