Borhan Beigzadeh - Biomechatronics and Cognitive Engineering Research Lab, School of Mechanical Engineering, Iran University of Science and Technology, Tehran, Iran
Mojtaba Belali Koochesfahani - Biomechatronics and Cognitive Engineering Research Lab, School of Mechanical Engineering, Iran University of Science and Technology, Tehran, Iran

The concept of Iranian traditional musical modes, namelyDASTGÄH, is the basis for the traditional music system. The conceptintroduces seven DASTGÄHs. It is not an easy process to distinguishthese modes and such practice is commonly performed by anexperienced person in this field. Apparently, applying artificialintelligence to do such classification requires a combination of thebasic information in the field of traditional music with mathematicalconcepts and knowledge. In this paper, it has been shown that it ispossible to classify the Iranian traditional musical modes(DASTGÄH) with acceptable errors. The seven Iranian musicalmodes including SHÖR, HOMÄYÖN, SEGÄH, CHEHÄRGÄH,MÄHÖR, NAVÄ and RÄST-PANJGÄH are studied for the twomusical instruments NEY and Violin as well as for a vocal song. Forthe purpose of classification, a multilayer perceptron neural networkwith supervised learning method is used. Inputs to the neural networkinclude the top twenty peaks from the frequency spectrum of eachmusical piece belonging to the three aforementioned categories. Theresults indicate that the trained neural networks could distinguish theDASTGÄH of test tracks with accuracy around 65% for NEY, 72%for violin and 56% for vocal song.

Iranian traditional musical modes ,(DASTGÄH),Classification,Artificial Neural Network,Feature extraction