Article
Classification of Music Genres based on Mel Frequency Cepstrum Coefficients using Deep Learning Models
Disruptive Technologies for Big Data and Cloud Applications: Proceedings of ICBDCC 2021
(2022)
Abstract
Genre classification is indeed a vital task today since the number of songs produced on a regular basis keeps increasing. On average, around, 60,000 tracks are being uploaded per day on Spotify. So, classifying these tracks by genre is definitely an important task for every musical streaming services and platforms. Due to the high classification performance of neural network models such as convolutional neural network (CNN), multi-layer perceptron (MLP), and long short-term memory network (LSTM) are used in this work to automatically classify music into to its genres based on Mel-frequency cepstrum coefficients (MFCCs) instead of manually entering the genre. We experimented the models with the GTZAN dataset and provided a comparative analysis on the classification efficiency of deep learning models. We achieved a classification of 70.42% for our proposed CNN model which is greater than the human accuracy and over other deep learning models.
Keywords
- multilayer perceptron,
- convulutional neural networks,
- long short-term memory,
- music genre classification
Disciplines
Publication Date
Fall August 2, 2022
DOI
10.1007/978-981-19-2177-3_83
Citation Information
Preetham, M., Panga, J.B., Andrew, J., Raimond, K., Dang, H. (2022). Classification of Music Genres Based on Mel-Frequency Cepstrum Coefficients Using Deep Learning Models. In: Peter, J.D., Fernandes, S.L., Alavi, A.H. (eds) Disruptive Technologies for Big Data and Cloud Applications. Lecture Notes in Electrical Engineering, vol 905. Springer, Singapore. https://doi.org/10.1007/978-981-19-2177-3_83