Analisis dan Seleksi Fitur Audio pada Musik Tradisional Indonesia
DOI:
https://doi.org/10.24014/coreit.v4i2.6506Abstract
Fitur-fitur yang digunakan untuk menemukan kemiripan pada audio antara lain dengan menggunakan fitur yang ditentukan secara manual sampai fitur yang diekstraksi secara otomatis dari sebuah file audio. Para peneliti terdahulu juga telah merekomendasikan beberapa nilai numerik dari fitur yang dapat mewakili audio untuk diekstraksi. Meskipun demikian, set fitur yang optimal dalam menemukan kemiripan musik mungkin berbeda pada setiap penelitian, tergantung pada metode atau jenis musik yang digunakan dalam penelitian. Untuk menemukan fitur audio yang optimal untuk musik tradisional Indonesia, proses seleksi fitur dilakukan dalam penelitian ini. Empat musik tradisional Indonesia dari 4 provinsi yang berbeda disegmentasi secara otomatis menjadi 60 segmen audio. Sebelas set fitur dengan total 36 fitur audio ini diekstraksi langsung dari 60 segmen audio tersebut dengan kombinasi nilai rata-rata dan standar deviasi standar. Principal Component Analysis (PCA) digunakan untuk mengurangi set fitur. Kemudian, untuk membuktikan set fitur yang dihasilkan adalah fitur yang optimal, clustering dilakukan pada 60 segmen audio. Proses clustering dengan metode x-Means dengan fitur-fitur yang diperoleh dalam penelitian ini menunjukkan bahwa setiap segmen audio dari 1 lagu berada pada cluster yang sama.
References
Rini Wongso and Santika Diaz, "Automatic Music Classification Using Dual Tree Complex Wavelet Transform and Support Vector Machine," Journal of Theoretical and Applied Information Technology , vol. 63, 2014.
DPW Ellis, X Zeng, and McDermott JH, "Classifying Soundtracks With Audio Texture Features," ICASSP, 2011.
Tom Rzeszutek, Patrick E. Savage, and Steven Brown, "The Structure of Cross-Cultural Musical Diversity," Royal Society Publishing, 2011.
Andreas Neoclous, Maria Pantelli, Ioannou Rafaela, Petkov Nikolai, and Christos Schizas, "A Machine Learning Approach for Clustering Western and non-Western Folk Music Using Low-level And Mid-level Features.," International Workshop on Machine Learning and Music, 2013.
Theodorous Giannakopoulos and Pikrakis, Introduction to Audio Analysis: A Matlab Approach.: Elsevier, 2014.
T Ishioka, "An Expansions of x-Means For Automatically Determining The Optimal Number of Clusters," in International Conference Computational Inteligence, pp. 91-96.
Downloads
Published
Issue
Section
License
The Authors submitting a manuscript do so on the understanding that if accepted for publication, copyright of the article shall be assigned to CoreIT journal and published by Informatics Engineering Department Universitas Islam Negeri Sultan Syarif Kasim Riau as publisher of the journal.
Authors who publish with this journal agree to the following terms:
Authors automatically transfer the copyright to the journal and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlike (CC BY SA) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
Authors are able to enter into separate permission for non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
