Comparison of Music Genre Classification Results Using Multilayer Perceptron With Chroma Feature and Mel Frequency Cepstral Coefficients Extraction Features

Rina Refianti, Faradilla Mahardi

Abstract


The development of digital music, especially in genre classification has helped in the ease of studying and searching for a song. There are many ways that can be used to classify the songs/music into genres. Deep Learning is one of the Machine Learning implementation methods that can be used to classify the genre of music. The author managed to create a deep learning-based program using the MLP model with two extraction features, Chroma Feature and MFCC which can classify song/ music genres. Pre-processing of the song is done to take the features of the existing value then the value will be incorporated into the model to be trained and tested. The model was trained and tested with data of 3000 songs which were divided into 10 genres. The model was also tested using the Confusion Matrix with 600 songs of the total available data. The models with Chroma Features as extraction features have an accuracy rate of 53 %, while the MFCC extraction features have an accuracy rate of 80.2 %.


Keywords


Multilayer Perceptron, Chroma Feature, MFCC, Classification, Music Genre

Full Text:

PDF

References


R. Rekha, and R.S. Tharani (2021), Speech Emotion Recognition using Multilayer Perceptron Classifier on Ravdess Dataset. ICCAP 2021, December 07-08, Chennai, India, 2021, doi: 10.4108/eai.7-12- 2021.2314726.

Sudianto, A.D. Sripamuji, I. Ramadhanti, Risa Riski Amalia, J.Saputra, B. Prihatnowo (2022), Penerapan Algoritma Support Vector Machine Dan Multi-Layer Perceptron Pada Klasifikasi Topik Berita. Jurnal Nasional Pendidikan Teknik Informatika, Volume 11, Nomor 2, pp.84-91.

M. Farooq, F. Hussain, N.K. Baloch, F.R. Raja, H. Yu, Y.B. Zikria (2020), Impact of feature selection algorithm on speech emotion recognition using deep convolutional neural network. Sensors, 20(21), 6008.

GTZAN, http://opihi.cs.uvic.ca/.

M.A. Hossan, S. Memon, and M.A. Gregory (2010), A novel approach for MFCC feature extraction. 2010 4th International Confer-ence on Signal Processing and Communication Systems, Gold Coast, QLD, Australia, pp. 1-5, 2010, doi: 10.1109/ICSPCS.2010.5709752.

P.P. Singh, P. Rani (2014), An Approach to Extract Feature using MFCC. IOSR Journal of Engineering (IOSRJEN), Vol. 04, Issue 08, pp.21-25.

A. Sithara, A. Thomas, D. Mathew (2018), Study of MFCC and IHC Feature Extraction Methods with Probabilistic Acoustic Models for Speaker Biometric Applications. Procedia Computer Science 143, pp.267-276.

N. Scaringella, G. Zoia, and D. Mlynek (2006). Automatic genre classification of music content: a survey. IEEE Signal Process. Mag., vol. 23, no. 2, pp. 133–141.

F. Pachet and D. Cazaly (2000). A taxonomy of musical genres. In Proc. Content-Based Multimedia Information Access (RIAO), Paris, France, 2000.

F. Pachet, J. Aucouturier, A. L. Burthe, A. Zils, and A. Beurive (2004), The cuidado music browser: an end-to-end electronic music distribution system. In Multimedia Tools and Applications, 2004, Special Issue on the CBMI03 Conference, Rennes, France, 2003.

D. Perrot and R. O. Gjerdigen (1999), Scanning the dial: An exploration of factors in the identification of musical style. In Proceed-ings of the 1999 Society for Music Perception and Cognition.

K. Kosina (2002), Music genre recognition, Master’s thesis. Hagenberg Technical University, Hagenberg, Germany, June 2002.




DOI: https://doi.org/10.52088/ijesty.v3i2.444

Article Metrics

Abstract view : 0 times
PDF - 0 times

Refbacks

  • There are currently no refbacks.


Copyright (c) 2023 Rina Refianti, Faradilla Mahardi

International Journal of Engineering, Science and Information Technology (IJESTY) eISSN 2775-2674