Abstract—Guitar has been played since the 15th century until now. The traditional method used in transcribing guitar chords from a song is through determining the chords while listening to it. Through the use of modern technology in the field of Computer Science, transcribing guitar chords from acoustic audio can be attainable through classification method. Musical features were extracted by J48 decision from an audio file. The mean percentages of success using the prototype and Weka are 33.81% and 47.79% respectively. Further data analysis through t-test shows Weka selection of musical features is more relevant than the prototype.
 

Index Terms—guitar, chords recognition, J48 decision trees, classification method, data mining, musical feature extraction

Cite: Darrell A. Talavera, Erika Svetlana C. Nase, Leonard D. Pancho, and Adomar L. Ilao, "Transcription of Guitar Chords from Acoustic Audio," Journal of Advances in Information Technology, Vol. 11, No. 3, pp. 149-154, August 2020. doi: 10.12720/jait.11.3.149-154

Copyright © 2020 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.