Music Genre Classification Using 1D Convolution Neural Network
Abstract
Music genre classification system is a system that is important to the users for effectiveness in the digital music industry. One of the effective ways of genre classification is in music recommendation and access to users. With accurate classification system built, songs can be readily accessed by the users when the genre of the song is known and recommendation of songs to the users is made easy. Also, automatic classification of genre is important to solve problems such as tracking down related songs, discovering societies that will like specific songs and also for survey purposes.
In recent times, deep learning techniques have proven to be effective in several classification tasks including music genre classification. This paper therefore examines the application of 1D Convolutional Neural Network for music genre classification. A new dataset consisting of 1000 Nigerian traditional songs with seven genres was used for this work. As features extraction is crucial to audio analysis, seven low level features also known as content based features were extracted from the songs in the dataset which served as input into the classifier. Our results showed that the accuracy level of the system is 92.5% with a precision of 92.7%, recall of 92.5% and f1 score of 92.5%.
References
Weibin Zhang, Wenkang Lei, XiangminXu, Xiaofeng Xing (2016). Improved Music Genre Classification with Convolutional Neural Network. Interspeech 2016 .http://dx.doi.org/10.21437/Interspeech.2016-1236. pp. 3304-3308
N. Auguin, S. Huang, and P. Fung (2013) “Identification of live or studio versions of a song via supervised learning,” in Signal and Information Processing Association Annual Summit and Conference(APSIPA), 2013 Asia-Pacific. IEEE, 2013, pp. 1–4.
J. Bergstra, N. Casagrande, D. Erhan, D. Eck, and B. K´egl (2006) “Aggregate features and adaboost for music classification,” Machine learning, vol. 65, no. 2-3, pp. 473–484, 2006.
S. Sigtia and S. Dixon (2014).“Improved music feature learning with deep neural networks,” in Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on.IEEE, 2014, pp. 6959–6963.
JiaDai, Wenju Liu, HaoZheng, Wei Xue, and Chongjia Ni (2016). Semi-supervised Learning of Bottleneck Feature for Music Genre Classification, T. Tan et al. (Eds.): CCPR 2016, Part II, CCIS 663, pp. 552–562.
SerkanKiranyaz, OnurAvci, Osama Abdeljaber, TurkerInce, MoncefGabbouj, Daniel J. Inman (2020). 1D convolutional neural networks and applications: A survey. Mechanical Systems and Signal Processing 151 (2021) 107398, Elsevier, pp. 1-21
Nils (2018). Introduction to 1D Convolutional Neural Network, blog.goodaudience.com/.
A. Elbir✉ and N. Aydin.Music genre classification and music recommendation by using deep learning (2020).Electronics Letters. Vol. 56, No. 12, pp. 627–629
SoumyaSuvraGhosal and IndranilSarkar.Novel Approach to Music Genre Classification using Clustering Augmented Learning Method (CALM).Proceedings of the AAAI 2020 Spring Symposium on CombiningMachine Learning and Knowledge Engineering in Practice (AAAI-MAKE 2020).Vol 2600
SnigdhaChillara, Kavitha A S, Shwetha A Neginhal, ShreyaHaldia and Vidyullatha K S. (2019). Music Genre Classification using Machine Learning Algorithms: A comparison. International Research Journal of Engineering and Technology (IRJET). Volume: 06 Issue: 05, pp. 851-858
HareeshBahuleyan (2018). Music Genre Classification using Machine Learning Techniques. arXIV: 1804.01149v1[cs.sd], https://www.researchgate.net/publication/324218667. Accesed in October 2020
Vishnupriya S, K. Meenakshi (2018). Automatic Music Genre Classification using Convolution Neural Network.2018 International Conference on Computer Communication and Informatics (ICCCI -2017), Coimbatore, INDIA.IEEE
Nikki Pelchat, Craig M Gelowitz. Neural Network Music Genre Classification (2019). 2019 IEEE Canadian Conference of Electrical and Computer Engineering (CCECE)
Vinicius D. Valerio, Rodolfo M. Pereira, Yandre M. G. Costa, Diego Bertolini and Carlos N. Silla Jr. (2018).A Resampling Approach for Imbalanceness on Music Genre Classification Using Spectrograms. Association for the Advancement of Artificial Intelligence (www.aaai.org).pp 500-505.
George Tzanetakis and Perry Cook (2002).Musical Genre Classification of Audio Signals, IEEE Transactions on speech and audio processing, VOL. 10, NO. 5, pp. 293-302
Carlos N. Silla Jr., Celso A. A. Kaestner, Alessandro L. Koerich (2007), Automatic Music Genre Classification Using Ensemble of Classifiers. XXXIII Seminario Integrado de Software e Hardware.DOI: 10.1109/ICSMC.2007.4414136
Nicolas Scaringella, Giorgio Zoia, and Daniel Mlynek (2006). IEEE Signal Processing Magazine,pp. 133-141
Carmine-EmanueleCella (2015).An Introduction to Audio Features.Coservatorio di Padova. www.carminecella.com. Accessed October, 2019.
Zhouyu Fu, Guojun Lu, Kai Ming Ting, and Dengsheng Zhang (2011).A Survey of Audio-Based Music Classification and Annotation. IEEE Transactions on Multimedia 13(2):pp: 303 - 319
Juan Pablo Bello (2007). Low-level features and timbre. EL9173 Selected Topics in Signal Processing: Audio Content Analysis, NYU Poly, https://s18798.pcdn.co/. Accessed January, 2020.
Markus Schedl, Arthur Flexer, JuliánUrbano (2013).The neglected user in music information retrieval research. Journal of Intelligent Information, volume 41, pp. 523–539
Li D, Sethi I, Dimitrova N, McGee T (2001) Classification of general audio data for Content based retrieval. Pattern Recognition Letters 22:533–544
Claus Weihs, UweLigges, Fabian M¨orchen and Daniel M¨ullensiefen (2007). Classification in Music Research, Article in Advances in Data Analysis and Classification, pp. 1-36
Dan Ellis. 2007. Chroma feature analysis and synthesis. Resources of Laboratory for the Recognition and Organization of Speech and Audio LabROSA. https://www.ee.columbia.edu/~dpwe/resources/matlab/chroma-ansyn/. Accessed October, 2019
Signal Analysis and Feature Extraction, https://www.musicinformationretrieval.com/, Accessed November, 2019
Steve Tjoa. 2017. Music information retrieval. https://musicinformationretrieval.com/mfcc.html. Accessed February, 2020
Fabien Guoyon, FranchoisPachet and Olivier Delerue (2000). On The Use of Zero-Crossing Rate For Application of Classification of Percussive Sounds. Proceedings of the COST G-6 Conference on Digital Audio Effects (DAFX-00), Verona, Italy, December 7-9, 2000.
Yangqiu Song, Changshui Zhang and Shiming Xiang (2007).Semi-Supervised Music Genre Classification.ICASSP 2007. pp. 729-732.
Music Structure Analysis,h ttps://www.musicinformationretrieval.com/,Accessed December, 2019
ArchitRathore and MargauxDorido (2015).Music Genre Classification. Department of Computer Science and Engineering. Indian Institute of Technology, Kanpur.www.semanticsscholar.org/paper/MusicGenreClassificationRathore/AccessedJanuary,2020.
W. Chai (2006). “Semantic segmentation and summarization of music,” IEEE Signal Processing Mag., vol. 23, no. 2, pp. 124–132,
YI-Hsuan Yang and Homer H. Chen (2012). Machine Recognition of Music Emotion: A Review. ACM Transactions on Intelligent Systems and Technology, Vol 3, No 3, Article40, pp: 1-40.
LU, L., L IU, D., AND Z HANG, H. 2006. Automatic Mood Detection And Tracking Of Music Audio Signals. IEEE Trans. Audio, Speech Lang. Process. 14, 1, 5–18.
Klapuri, A. (1999). Sound Onset Detection By Applying Psychoacoustic Knowledge. In Proc. IEEE International Conference on Acoustics, Speech and Signal Processing
Olivier Lartillot, Petri Toivainen (2007). A Matlab toolbox for musical feature extraction from audio.International conference on digital audi effects. pp. 237-244
Roy (2020). All about feature scaling, https:towardsdatascience.com/, Accessed April, 2020
MinMax Scaling, https://rajeshmahajan.com/.Accessed December, 2019
ZakariaJaadi (2019).Everything You Need To Know About Interpreting Correlations, https://towardsdatascience.com/Accessed June, 2019.
Jason Brownlee, (2019). How To Calculate Correlation Between Variables in Python. https://machinelearningmastery.com/how-to-use-correlation-to-understand-the-relationship-between-variables/. Accessed January, 2020.
Nils (2018). Introduction to 1D Convolutional Neural Network, blog.goodaudience.com/.
Convolutional Neural Network, https://en.m.wikipedia.org/. Accessed December, 2019
RavisuthaSakrepatnaSrinivasamurthy (2018). Understanding 1D Convolutional Neural Network Using Multiclass Time-Varying Signals.All Theses 2911. https://tigerprints.clemson.edu/all_theses/2911
Max-pooling/Pooling, http://www.computersciencewiki.org/. Accessed November, 2019
Jason Brownlee, (2019). A gentle introduction to pooling layers for convolutional neural networks, https://machinelearningmastery.com/pooling-layers-for-convolutional-neural-networks/. Accessed January,2020
Activation Functions, www.365datascience.com. Accessed April, 2020
SanketDoshi (2019). Various Optimization Algorithms For Training Neural Network. https://towardsdatascience.com/. Accessed March,2020
Sagar Sharma (2017). Epoch vs Batch Size vsIterations. https://towardsdatascience.com/. Accessed March,2020
Vinita (2019). How to interpret loss and accuracy for a machine learning model, https://intellipaat.com/. Accessed December, 2020
