Title :
Real-time classification of Persian musical Dastgahs using artificial neural network
Author :
Hajimolahoseini, H. ; Amirfattahi, R. ; Zekri, M.
Author_Institution :
Dept. of Electr. & Comput. Eng., Isfahan Univ. of Technol., Isfahan, Iran
Abstract :
In this paper, a three layer artificial neural network is proposed that, independent of Root note selection, classifies the Persian musical Dastgahs into five main groups: Shur, Homayun, Segah, Chahargah and Mahur. It implies the training of the network in order to be able to classify all of 120 possible cases for the Persian musical Dastgahs based on 24 different Root notes in an octave of Persian music. The network receives a vector of 24 possible notes of an octave in which the used notes are represented by a “1” and unused notes are represented by a “0”. After training, the network is able to correctly classify 100 percent of the 120 possible cases for Persian musical Dastgahs in five main groups.
Keywords :
music; neural nets; pattern classification; Chahargah; Homayun; Mahur; Persian music octave; Persian musical Dastgahs; Segah; Shur; artificial neural network; real-time classification; root note selection; Artificial neural networks; Biological neural networks; Multiple signal classification; Neurons; Support vector machine classification; Training; Vectors; Artificial Neural Network; Classification; Dastgah; Musical Scale; Persian Music;
Conference_Titel :
Artificial Intelligence and Signal Processing (AISP), 2012 16th CSI International Symposium on
Conference_Location :
Shiraz, Fars
Print_ISBN :
978-1-4673-1478-7
DOI :
10.1109/AISP.2012.6313736