TY - CPAPER
KW - Artificial intelligence
KW - Automated classification
KW - Classification (of information)
KW - Croatians
KW - Future generations
KW - Geographical regions
KW - Intangible cultural heritages
KW - Learning systems
KW - Mel frequency cepstral co-efficient
KW - Microelectronics
KW - Singing styles
KW - Speech recognition
KW - Zero crossing rate
KW - machine learning
KW - Mel-frequency cepstral coefficients
KW - traditional music
AU - Ivan Strizrep
AU - Ana Krzic
AU - Damir Sersic
AB - 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 Dimurje, 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.
C2 - Int. Conv. Inf. Commun. Technol., Electron. Microelectron., MIPRO - Proc.
DO - 10.23919/MIPRO.2018.8400188
LA - English
N1 - Journal Abbreviation: Int. Conv. Inf. Commun. Technol., Electron. Microelectron., MIPRO - Proc.
N2 - 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 Dimurje, 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.
PB - Institute of Electrical and Electronics Engineers Inc.
PY - 2018
SN - 9789532330977 (ISBN)
SP - 1028
EP - 1033
TI - Automated classification of Croatian traditional music
UR - https://www.scopus.com/inward/record.uri?eid=2-s2.0-85050243344&doi=10.23919%2fMIPRO.2018.8400188&partnerID=40&md5=3416aff8ebc389c21f1e355e37e5a3d9
ER -