Open AccessAudio fingerprint for automatic Balinese rindik music identification using gaussian mixture model
Author(s) -
A. A. R. S. Widarsa,
I Dewa Made Bayu Atmaja Darmawan
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1722/1/012101
Subject(s) - fingerprint (computing) , centroid , mel frequency cepstrum , speech recognition , computer science , mixture model , identification (biology) , feature (linguistics) , pattern recognition (psychology) , artificial intelligence , feature extraction , linguistics , philosophy , botany , biology
Rindik is a traditional gamelan instrument that has been known for a long time in which is made from bamboo. Rindik music can be identified by just hearing a little bit snippets from the music that can only be done by professional rindik players. This research assumes doing some training in the system can make the system recognize the music by just using some rindik music snippets. This research focuses on comparing some features extraction method for automatic rindik music identification by using some rindik music snippet to find out which of these features perform the best to represent rindik music. This research will use an audio fingerprint method for song identification. MFCC (Mel Frequency Cepstral Coefficient) and Spectral Subband Centroid will be used and compared as the music’s feature, and Gaussian Mixture Model will be used to model the music’s fingerprint. The result of this research show both methods give excellent results. Both features only need 10-second duration data to get over 90% overall accuracies. Both Feature gives excellent performance with GMM for automatic rindik song identification task. However, Spectral subband centroid show better result with the highest accuracies is 99.3%.