Abstract
Music Genre Classification acts as a precursor to a solid music recommendation system, as well as a music generation tool. In order to form a solid foundation to the aforementioned projects, the development of an efficient genre classification system had to be carried out. As individuals who have gained a thorough appreciation for music and its technicalities, we seek to bring about a change in the way people view music and enhance their listening experience in general by educating them about these classifications, for starters. Aural features of music have been extracted by using digital signal processing techniques and then the genre classification task has been carried out using neural networks. We use the GTZAN dataset for data analysis and modelling. The dataset uses Spectrograms generated from songs as the input into a neural net model to classify the songs into their respective musical genres. With this research work, we aim to implement deep learning techniques, specifically CNN and RNN for classifying musical genres.The proposed model outperforms the existing the state of the art model in terms of accuracy. The proposed models achieves accuracy of 76.9% and 82.25% using LSTM and CNN(with 100 epochs) respectively.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Tzanetakis G, Cook P (2002) Musical genre classification of audio signals. IEEE Trans Speech Audio Proc 10(5):293–302
Pachet F, Cazaly D (2000) A classification of musical genre. In: Proceeding of the RIAO content-based multimedia information access Conference, Paris, France
Aucouturier J, Pachet F (2003) Representing musical genre: a state of the art. J New Music Res 32(February 2015):83-93
Serwach M, Stasiak B (2016) GA-based parameterization and feature selection for automatic music genre recognition. In: Proceedings of 2016 17th international conference computational problems of electrical engineering, CPEE 2016
Choi K, Fazekas G, Sandler M (2016) Automatic tagging using deep convolutional neural networks. ISMIR
Lidy T, Rauber A (2005) Evaluation of feature extractors and psycho-acoustic transformations for music genre classification. In: IZMIR, pp 34–41
Li TLH, Chan AB, Chun AHW (2010) Automatic musical pattern feature extraction using convolutional neural network. In: (IJACSA) of the international multiconference of engineers and computer scientists (IMECS 2010), I, pp 546–550
Sturm BL (2013) Alexander lerch: an introduction to audio content analysis: applications in signal processing and music informatics. Comput Music J 37(4):90–91
Nkambule T, Ajoodha R (2021) Classification of music by genre using probabilistic graphical models and deep learning models. In: Sixth international congress on information and communication technology (6th ICICT). Springer, pp 1–6
Choi K, Fazekas G, Sandler M (2016) Explaining deep convolutional neural networks on music classification
Rajput NK, Grover BA (2022) A multi-label movie genre classification scheme based on the movie’s subtitles. Multimed Tools Appl. https://doi.org/10.1007/s11042-022-12961-6
Vinayak S, Sharma R, Singh R (2016) MOVBOK: a personalized social network based cross domain recommender system. Indian J Sci Technol 9(31):1–10
Singh RK, Singh P, Bathla G (2020) User-review oriented social recommender system for event planning. Ingénierie des Systèmes d Inf. 25(5):669–675
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Pattanaik, S.S., Jain, P., Sharma, P., Rathore, S., Kumar, A. (2023). Comparative Analysis of Music Genre Classification Framework Based on Deep Learning. In: Ramdane-Cherif, A., Singh, T.P., Tomar, R., Choudhury, T., Um, JS. (eds) Machine Intelligence and Data Science Applications. MIDAS 2022. Algorithms for Intelligent Systems. Springer, Singapore. https://doi.org/10.1007/978-981-99-1620-7_30
Download citation
DOI: https://doi.org/10.1007/978-981-99-1620-7_30
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-1619-1
Online ISBN: 978-981-99-1620-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)