Enhancing Music Genres Classification withMFCC and CNN

Enhancing Music Genres Classification withMFCC and CNN

Music Genre, Classification,MFCC,CNN

Music genre classification aims to group music genres with a high degree of accuracy. Music genre classification is a critical challenge in pattern recognition anddigital signal processing. In this paper, we introduce music genres classificationusingMel-Frequency Cepstral Coefficient (MFCC) as an extraction feature andusing the algorithmConvolutional Neural Network (CNN) as a classification model. The MFCC feature was chosen because of its ability to represent the frequency characteristics of audio signals that correspond to human auditory perception, where the music genre dataset was processed into an MFCC representation before being trained on a CNN model. In this study, we compare threedifferent CNN model to determine the best architecture. The results showed that model architecture 1 obtained the best accuracy during training at 97.15%, while model architecture 2 obtained a training accuracy of 95.74% andmodel architecture 3 obtained a training accuracy of 95.18%. In testing with new data, model architecture 3 obtained the highest accuracy compared to the other 2 models, with 81%, whichindicates good generalization ability. This study proves that the combination of MFCC andCNN is effective for music genre classificationwith high accuracy.

Bulkis Kanata1, Sudi M. Al Sasongko2, Mujni Ahmad Ali

https://ijicom.respati.ac.id/index.php/ijicom/article/view/180/124

International Journal of Informatics and Computation (IJICOM)

2025

Fajar bagus W

PDF

English

Text