Tonic and scale recognition in Persian audio musical signals

Author

Heydarian, Peyman ; Jones, Lewis

Author_Institution

London Metropolitan Univ., London, UK

fYear

2014

fDate

19-23 Oct. 2014

Firstpage

18

Lastpage

21

Abstract

This paper proposes methods for computational identification of the tonic and scale in Persian audio musical signals. The chroma, a simplified spectrum is taken as the feature set and Bit-masking and Manhattan distance are used as the classifiers. The results are applicable to various musical traditions in the Mediterranean and the Near East. This approach enables content-based analysis of, and content-based searches of, musical archives.

Keywords

audio signal processing; natural language processing; speech processing; Manhattan distance; Persian audio musical signals; bit-masking; content-based analysis; content-based searches; musical archives; scale recognition; tonic recognition; Educational institutions; Histograms; Multiple signal classification; Music information retrieval; Training; Transforms; Tuning; Bit-masking; Computational musicology; DSP; Machine Learning; Manhattan distance; Persian scale identification; Pitch Class Profiles; chroma; dastgàh; maqàm; mode; santur; tonic detection;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing (ICSP), 2014 12th International Conference on

Conference_Location

Hangzhou

ISSN

2164-5221

Print_ISBN

978-1-4799-2188-1

Type

conf

DOI

10.1109/ICOSP.2014.7014961

Filename

7014961