Music Genre Classification using Naïve Bayes Algorithm

International Journal of Computer Trends and Technology (IJCTT)          
© 2018 by IJCTT Journal
Volume-62 Number-1
Year of Publication : 2018
Authors : Ardiansyah, Boy Yuliadi, Riad Sahara


MLA Style: Ardiansyah, Boy Yuliadi, Riad Sahara "Music Genre Classification using Naïve Bayes Algorithm" International Journal of Engineering Trends and Technology 62.1 (2018): 50-57.

APA Style: Ardiansyah, Boy Yuliadi, Riad Sahara (2018). Music Genre Classification using Naïve Bayes Algorithm. International Journal of Engineering Trends and Technology, 62(1), 50-57.

Classification of music genres that are processed consist of, rock, pop, dangdut and jazz. The number of each genre for training data is 20 data for rock music, 20 data for pop music, 20 data for jazz music, and 17 data for dangdut music. While for data testing there are 10 data for rock music, 8 data for pop music, 10 data for jazz music, and 8 data for dangdut music. So that the total digital music that will be used is 113 digital music. Data taken in the form of * .mp3 data is changed into * .wav data. The classification method used is Naive Bayes. And feature features that are used are short time energy, zero crossing rate, spectral centroid and spectral flux. The results obtained from the overall testing data are correctly classified as 15 data from 36 data so that the success percentage is 41.67%. To classify the highest success is the highest classification of pop music by 70.5%, followed by dangdut music by 62.5%, then rock music by 30%. For jazz music the success of the classification is very small, which is only 10%.

[1] Al-Shoshan, Abdullah I. Speech and Music Classification and Separation: A Revie. J. King Saud Univ., Vol. 19, Eng. Sci. (1), pp. 95-133. Riyadh, Saudi. 2006.
[2] Dewi, Andi Imrah., Hidayat, Andi Nurul. Analisis Music Mining Information Retrieval Untuk Klasifikasi Jenis Music Bergenre Menggunakan Algoritma Naive Bayes. Jurnal Elektronik Sistem Informasi dan Komputer. Vol 1 No 2. Juli-Desember 2015. p. ISSN: 2777-888 e. ISSN: 2502-2148.
[3] Deshpande, Hrishikesh., Singh, Rohit., Nam, Unjung. Classification Of Music Signals In The Visual Domain. Proceedings of the COST G-6 Conference on Digital Audio Effects (DAFX-01). Limerick, Ireland. December 6-8,2001.
[4] Genre Musik. (accessed on July 25th, 2018)
[6] Kour, Gursimran., Mehan, Neha. Music Genre Classification using MFCC, SVM and BPNN. International Journal of Computer Applications (0975 – 8887), Volume 112 No. 6, February 2015.
[7] Lartillot, Olivier danToiviainen, Petri. A Matlab Toolbox For Musical Feature Extraction From Audio. Proc. of the 10th Int. Conference on Digital Audio Effects (DAFx-07). Bordeaux, France. September 10-15, 2007.
[8] Li, Tao.,Ogihara, Mitsunori., Li, Qi. A Comparative Study on Content-Based Music Genre Classification. Proceeding of SIGIR’03.Toronto, Canada. 28 Juli – 1 Agustus, 2003.
[9] Rathore, Archit. Music Genre Classification. (accessed on July 30, 2018)
[10] Mauludiya, Rosyita Ayuning., Magdalena, Rita.,Ramatryana, I Nyoman Apraz. Simulation And Analysis Of Music Genre Classification Based On Fft And Support Vector Machine. Teknik Telekomunikasi, Fakultas Teknik Elektro, Universitas Telkom.
[11] Wongso, Rini., Santika, Diaz D. Automatic Music Genre Classificaation Using Dual Tree Complex Wavelet Transform and Support Vector Machine. Journal of Theoretical and Applied Information Technology, Volume 63 No 1, 10 Mei 2014.
[12] Wikipedia (accessed on July 30, 2018)
[13] Zhou, Lijuan., Lin, Hongfei., Liu, Wenfei. Enriching Music Information Retrieval Using Emotion Detection. SIGIR 2011 Workshop on Enriching Information Retrieval (ENIR 2011), Beijing, China. July 28, 2011.

Music genre, Classification, Naïve Bayes.