Spandan Kumar Barthakur; Parismita Sarma; Maharshi Nath; Daiyaan Ahmed; Hirak Jyoti Hazarika; Bikash Baruah

Hybrid Deep Learning-Based Automated Genre Classification of Assamese Regional Songs

PDF (887KB), PP.394-411

Views: 0 Downloads: 0

Author(s)

Spandan Kumar Barthakur ^1,2 Parismita Sarma ¹ Maharshi Nath ³ Daiyaan Ahmed ⁴ Hirak Jyoti Hazarika ⁵ Bikash Baruah ^1,*

1. Department of Information Technology, Gauhati University, India

2. Department of Computer Science and Engineering, The Assam Royal Global University, India

3. Software Developer, MARLN Corporation, India

4. Software Developer, National Informatics Centre(NIC), Dispur, Assam, India

5. Department of Library Sciences, The Assam Royal Global University, India

* Corresponding author.

DOI: https://doi.org/10.5815/ijem.2026.03.24

Received: 24 Feb. 2026 / Revised: 13 Apr. 2026 / Accepted: 20 May 2026 / Published: 8 Jun. 2026

Index Terms

Assamese Regional Songs, Convolutional Neural Networks, ResNet50, VGG16, LSTM, Bihu, Kamrupiya Lokageet, Goalporiya Lokageet, Borgeet, Naam

Abstract

This work aims to preserve and promote the rich musical heritage of Assam by developing an automated classification system for Assamese regional songs using a hybrid deep learning approach. This method not only modernizes the preservation of traditional music but also enhances its accessibility to a global audience for integrating AI with cultural conservation. Five genres of Assamese songs—Bihu, Kamrupiya Lokageet, Goalporiya Lokageet, Borgeet, and Naam—are considered in this study. By leveraging Convolutional Neural Networks (CNNs) and advanced audio feature extraction techniques such as Mel-Frequency Cepstral Coefficients (MFCCs) and spectrograms, a hybrid model combining VGG16 and ResNet50 is developed. This fusion utilizes the strengths of both architectures, enhancing the model’s performance and accuracy. Following the process, it is observed that two distinctly different genres, Bihu and Borgeet, are accurately categorized by the proposed model, while the remaining three show slight labeling inconsistencies.

Cite This Paper

Spandan Kumar Barthakur, Parismita Sarma, Maharshi Nath, Daiyaan Ahmed, Hirak Jyoti Hazarika, Bikash Baruah, "Hybrid Deep Learning-Based Automated Genre Classification of Assamese Regional Songs", International Journal of Engineering and Manufacturing (IJEM), Vol.16, No.3, pp.394-411, 2026. DOI:10.5815/ijem.2026.03.24

Reference

[1]M. Sharma, P. K. Jha, and P. K. Das, "Music Genre Classification using a Hybrid CNN-LSTM Model with MFCC Input," Journal of Signal Processing Systems, vol. 2478, 25 July. 2025. DOI: https://doi.org/10.1007/978-3-031-93703-3_14
[2]T. Li, "Optimizing the configuration of deep learning models for music genre classification," Heliyon, vol. 10, no. 2, 2024. DOI: https://doi.org/10.1016/j.heliyon.2024.e24892
[3]M. Altayeb, A. Al- Ghraibah, Classification of three pathological voices based on specific features groups using support vector machine, International Journal of Electrical and Computer Engineering, 12 (1), pp. 946-956, 2022. DOI: https://doi.org/10.11591/ijece.v12i1.
[4]Samia Bouteldja, Assia Kourgli, "A comparative analysis of SVM, K-NN, and decision trees for high resolution satellite image scene classification," Proc. SPIE 11433, Twelfth International Conference on Machine Vision (ICMV 2019), 114331I (31 January 2020); DOI: 10.1117/12.2557563.
[5]Q. Ning and J. Shi, "Artificial Neural Network for Folk Music Style Classification," Mobile Information Systems, vol. 2022, no. 1, p. 9203420, 2022. DOI: https://doi.org/10.1155/2022/9203420.
[6]K. Bora, M. P. Barman, A. N. Patowary, and T. Bora, "Classification of Assamese folk songs’ melody using supervised learning techniques," Indian J. Sci. Technol., vol. 16, no. 2, pp. 89-96, Sep. 2023. DOI: https://doi.org/10.17485/IJST/v16i2.1686.
[7]V. K. Solanke and S. B. Shirude, "Machine Learning Approaches for Classification of Indian Folk Music Genres," in Power Engineering and Intelligent Systems, V. Shrivastava, J. C. Bansal, and B. K. Panigrahi, Eds., PEIS 2025, Lecture Notes in Electrical Engineering, vol. 1461, Singapore: Springer, 2026, ch. 37. DOI: https://doi.org/10.1007/978-981-96-9724-3_37.
[8]G. Ru, X. Zhang, J. Wang, N. Cheng, and J. Xiao, "Improving Music Genre Classification from Multi-Modal Properties of Music and Genre Correlations Perspective," in ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1–5, 2023. DOI: https://doi.org/10.1109/ICASSP49357.2023.
[9]S. Senthil Pandi, B. S. Murugan, S. Dhanasekaran, and P. Kumar, "Utilizing Spectrograms and Deep Learning Techniques for Improved Music Genre Classification," in 2024 7th International Conference on Circuit Power and Computing Technologies (ICCPCT), vol. 1, pp. 1723–1728, 2024. DOI: https://doi.org/10.1109/ICCPCT61902.2024.10673160.
[10]S. Jothimani and K. Premalatha, "MFF-SAug: Multi feature fusion with spectrogram augmentation of speech emotion recognition using convolution neural network," Chaos, Solitons & Fractals, vol. 162, p. 112512, Sep. 2022. DOI: https://doi.org/10.1016/j.chaos.2022.112512
[11]S. Chakrabarty, R. Islam, E. Pricop, and H. K. Sarma, "An Approach to Discover Similar Musical Patterns," IEEE Access, vol. 10, pp. 47322-39, Apr. 2022. DOI: https://doi.org/10.1109/ACCESS.2022.3169362
[12]W. Wang and M. Sohail, "Research on music style classification based on deep learning," Computational and Mathematical Methods in Medicine, vol. 2022, Jan. 18, 2022. DOI: https://doi.org/10.1155/2022/3699885
[13]A. R. Rajanna, K. Aryafar, A. Shokoufandeh, and R. Ptucha, "Deep Neural Networks: A Case Study for Music Genre Classification," in 2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA), pp. 655–660, 2015. DOI: https://doi.org/10.1109/ICMLA.2015.160.
[14]C. J. Rani and N. Devarakonda, "Indian Classical Dance Forms Classification Using Transfer Learning," in Computational Intelligence and Data Analytics, R. Buyya, S. M. Hernandez, R. M. R. Kovvur, and T. H. Sarma, Eds., Lecture Notes on Data Engineering and Communications Technologies, vol. 142, Singapore: Springer, 2023, ch. 18. DOI: https://doi.org/10.1007/978-981-19-3391-2_18.
[15]W. Wu, F. Han, G. Song, and Z. Wang, "Music Genre Classification Using Independent Recurrent Neural Network," in 2018 Chinese Automation Congress (CAC), pp. 192–195, 2018. DOI: https://doi.org/10.1109/CAC.2018.8623623.
[16]S. Shetty and S. Hegde, "Automatic classification of Carnatic music instruments using MFCC and LPC," in Data Management, Analytics and Innovation: Proceedings of ICDMAI 2019, Volume 1, Singapore: Springer, 2020, pp. 463-474. DOI: https://doi.org/10.1007/978-981-32-9949-8_32.
[17]H. C. Das and U. Bhattacharjee, "Machine Learning Approach for Assamese Dialect Identification," in Artificial Intelligence and Sustainable Computing, M. Pandit, M. K. Gaur, and S. Kumar, Eds., ICSISCET 2023, Algorithms for Intelligent Systems, Singapore: Springer, 2024, ch. 5. DOI: https://doi.org/10.1007/978-981-97-0327-2_5.
[18]S. Shubham and D. Banerjee, "Hybrid CNN and Logistic Regression Approach for Folk Song Classification," in 2024 First International Conference on Innovations in Communications, Electrical and Computer Engineering (ICICEC), Davangere, India, pp. 1–7, 2024. DOI: https://doi.org/10.1109/ICICEC62498.2024.10808284.
[19]N. Karunakaran and A. Arya, "A Scalable Hybrid Classifier for Music Genre Classification using Machine Learning Concepts and Spark," in 2018 International Conference on Intelligent Autonomous Systems (ICoIAS), Singapore, pp. 128–135, 2018. DOI: https://doi.org/10.1109/ICoIAS.2018.8494161.
[20]A. Kumar, A. Rajpal, and D. Rathore, "Genre Classification using Feature Extraction and Deep Learning Techniques," in 2018 10th International Conference on Knowledge and Systems Engineering (KSE), pp. 175–180, 2018. DOI: https://doi.org/10.1109/KSE.2018.8573325.
[21]N. Ndou, R. Ajoodha and A. Jadhav, "Music Genre Classification: A Review of Deep-Learning and Traditional Machine-Learning Approaches," 2021 IEEE International IOT, Electronics and Mechatronics Conference (IEMTRONICS), Toronto, ON, Canada, 2021, pp. 1-6, DOI: 10.1109/IEMTRONICS52119.2021.9422487.
[22]P. Fulzele, R. Singh, N. Kaushik and K. Pandey, "A Hybrid Model for Music Genre Classification Using LSTM and SVM," 2018 Eleventh International Conference on Contemporary Computing (IC3), Noida, India, 2018, pp. 1-3, DOI: https://doi.org/10.1109/IC3.2018.8530557.
[23]D. Bisharad and R. H. Laskar, "Music genre recognition using convolutional recurrent neural network architecture," Expert Systems, vol. 36, no. 4, p. e12429, 2019. DOI: https://doi.org/10.1111/exsy.12429.
[24]D. Peri, “Applying Natural Language Processing and Deep Learning Techniques for Raga Recognition in Indian Classical Music,” Ph.D. dissertation, Virginia Tech, 2020. DOI: https://doi.org/10.25773/v5-w5hb-0k82
[25]M. Bhattacharjee, S. R. M. Prasanna and P. Guha, "Speech/Music Classification Using Features From Spectral Peaks," in IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 28, pp. 1549-1559, 2020, DOI: https://doi.org/10.1109/TASLP.2020.2993152.
[26]M. Serwach and B. Stasiak, “GA-based parameterization and feature selection for automatic music genre recognition,” in 2016 17th International Conference Computational Problems of Electrical Engineering (CPEE), 2016, pp. 1–4. DOI: https://doi.org/10.1109/CPEE.2016.7738724
[27]B. Rajesh and D. G. Bhalke, "Automatic genre classification of Indian Tamil and western music using fractional MFCC," International Journal of Speech Technology, vol. 19, pp. 551–563, 2016. DOI: https://doi.org/10.1007/s10772-016-9347-3.
[28]A. K. Sharma et al., "Classification of Indian Classical Music With Time-Series Matching Deep Learning Approach," in IEEE Access, vol. 9, pp. 102041-102052, 2021, DOI: https://doi.org/10.1109/ACCESS.2021.3093911
[29]G. N. Baruah, B. Bora, and P. Sarma, "Deep Learning-Based Acoustic Analysis of Assamese Traditional Songs with Specific Reference to Brajavali Language Present in Borgeet," in Proceedings of the International Conference on Smart Systems and Social Management (ICSSSM 2025), Atlantis Press, pp. 500–512, Dec. 2025. DOI: https://doi.org/10.2991/978-94-6463-950-6_33
[30]M. Neog and N. Baruah, "A Multi-Layer Hybrid Deep Learning Model for Toxic Comment Detection in Assamese," IEEE Access, vol. 13, pp. 165718–165737, 2025. DOI: https://doi.org/10.1109/ACCESS.2025.3612497
[31]N. S. Ujgare, R. Bhamare, A. Patil, Y. Rajput, P. Patil, and P. Pachorkar, "A Comprehensive Survey on Machine and Deep Learning Techniques for Genre Prediction in Folk Songs," in 2025 International Conference on Future Technologies (ICFT), pp. 1–6, 2025. DOI: https://doi.org/10.1109/ICFT66708.2025.11336726.
[32]H. P. Baral, "AI-Based Genre Classification and Recommendation System for Nepali Music," OODBODHAN, vol. 8, no. 1, pp. 152–160, 2025. DOI: https://doi.org/10.3126/oodbodhan.v8i1.81262

International Journal of Engineering and Manufacturing (IJEM)