Genre of Bangla Music: A Machine Classification Learning Approach

Abstract

—The necessity for designing autonomous indexing
tools to establish expressive and efficient means of describing
musical media content is well recognized. Music genre
classification systems are significant to manage and use music
databases. This research paper proposes an enhanced method to
automatically classify music into different genre using a machine
learning approach and presents the insight and results of the
application of the proposed scheme to the classification of a large
set of The Bangla music content, a South-East Asian language
rich with a variety of music genres developed over many
centuries. Building upon musical feature extraction and decision
making techniques, we propose new features and procedures to
achieve enhanced accuracy. We demonstrate the efficacy of the
proposed method by extracting features from a dataset of
hundreds of The Bangla music pieces and testing the automatic
classification decisions. This is the first development of an
automated classification technique applied specifically to the
Bangla music to the best of our knowledge, while the superior
accuracy of the method makes it universally applicable.