Music Genre Classification using Machine Learning on FMA Dataset

Sathvik Reddy B P; Nikitha R; Shilpa T U; Prof. Shankar N. B

doi:10.32628/IJSRCSEIT

Authors

Sathvik Reddy B P Computer Science and Engineering, R. L Jalappa Institute of Technology, Doddaballapura, Bangaluru, India Author
Nikitha R Computer Science and Engineering, R. L Jalappa Institute of Technology, Doddaballapura, Bangaluru, India Author
Shilpa T U Computer Science and Engineering, R. L Jalappa Institute of Technology, Doddaballapura, Bangaluru, India Author
Prof. Shankar N. B Associate Professor, Computer Science and Engineering, R. L Jalappa Institute of Technology, Doddaballapura, Bangaluru, India Author

DOI:

https://doi.org/10.32628/IJSRCSEIT

Keywords:

Human Ear, Digital Platforms, AI, Alongside Naive Bayes, Quadratic Discriminant Analysis

Abstract

Music is a universal form of expression with a multitude of genres that resonate with diverse audiences. While genre classification may seem straightforward to the human ear, automating this process poses a complex challenge. This complexity stems from the subtle and intricate characteristics that differentiate one musical genre from another. Effective categorization not only has implications for how music is organized and recommended in digital platforms but can also provide insights into the underlying structure and semantics of musical compositions. To tackle this issue, we aim to utilize machine learning and deep learning techniques to automatically categorize music into genres.

Downloads

Download data is not yet available.

References

Krittika Leatpantulak, Yuttana Kitjaidure, 6-8 March 2019, “ Music Genre Classification of audio signals using Particle Swarm Optimization and Stacking Ensemble”, 2019 7th International Electrical Engineering Congress (iEECON), INSPEC Accession Number: 19228693.

Yandre M.G Costa, Luiz S. Oliveira, Alessandor L. Koericb, Fabien Gouyoun, 16-18 June 2011, “Music genre recognition using spectrograms”, Institute of Electrical and Electronics Engineers (IEEE), Print ISBN:978-1-4577-0074-3, INSPEC Accession Number: 12177876.

Chang-Hsing Lee, Jau-Ling Shih, Kyun-Min Yu, Hwai-San Lin, 28 April 2009, “Automatic Music Genre Classification Based on Modulation of Spectral and Cepstral Features”, Institute of Electrical and Electronics Engineers (IEEE), Print ISSN: 1941-0077, INSPEC Accession Number: 10664199.

Brian McFee, Python Librosa Documentation, https://librosa.org

François Chollet, Python Keras Documentation, https://keras.io

Steve Tjoa, “Notes on Music Information Retrieval”, https://musicinformationretrieval.com