Automated classification of Croatian traditional music
Croatian traditional music is rich with different music styles. Four of them are on the UNESCO Representative list of the intangible cultural heritage of humanity: two-part singing and playing in the Istrian scale, Becarac singing and playing from Slavonia, Klapa multipart singing of Dalmatia and Ojkanje singing. Every region of Croatia is represented by different instruments, singing styles, rhythm and dynamics. This paper describes an automated classification of Croatian traditional music into regions. The regions are defined by historical and geographical factors and music style similarities: Slavonia, central Croatia, Me?imurje, Istria&Kvarner and Dalmatia. Each region is presented with 20 typical music songs. A sample of each song lasts for 30 seconds. The primary used features are mel-frequency cepstral coefficients, as well as zero crossing rate and sound volume. Extracted features are used in machine learning. As a result, more than 80% of the songs are correctly classified. The result shows how specific Croatian traditional music is and how important is to preserve it for future generations.
Cepstral analysis, Feature extraction, Machine learning, Music, classification, machine learning, mel-frequency cepstral coefficients,traditional music
STRIZREP, Ivan Strizrep; KRZIC, Ana Sovic; SERSIC, Damir (2018) "Automated classification of Croatian traditional music". In 2018 41st International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO), Opatija, Croatia, 2018. 1028-1033. [online] Available at: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8400188&isnumber=8399814 [Accessed 10/07/2018]