IJSDIP Logo

International Journal of System Design and Information Processing

psnajournals.org.in
Sign Up Login

Deep Learning-Based Genre Classification of Irish Traditional Music Using Latent Audio Representations

Paper ID:
IJSDIP_2025_VOLUME 13_ISSUE 3_14-21
Author's Name:
Tamilarasi K, Vignesh Kumar S, Vetrivel K, and Thameem Ansari H
Volume:
13
Issue:
Issue 3
Year:
2025
Pages:
14-21

Abstract

Irish traditional music has a rich diversity of genres such as reels, jigs, hornpipes, and airs. Automatic identification of these genres is still a challenge because of shared rhythmic patterns and melodic similarities. In this work, by investigating the application of latent audio representations learned from deep learning models for Irish traditional music genre classification. By utilizing unsupervised feature learning, we are able to capture inherent musical patterns that go beyond traditional handcrafted features. A collection of Irish traditional music is processed with spectrogram-based embeddings and self-supervised learning methods. Experiments show that latent representations enhance classification performance over conventional signal processing techniques. This work contributes to computational ethnomusicology by offering a strong framework for genre classification, benefiting musicologists, digital archiving, and folk music enthusiasts. Future directions involve increasing the dataset and optimizing models for real-time use.

Keywords

Irish Traditional Music, Genre Classification, Deep Learning, Spectrogram Embeddings, Self-Supervised Learning, Computational Ethnomusicology, Music Information Retrieval.

References

[1] L. Moysis et al., "Music Deep Learning: Deep Learning Methods for Music Signal Processing—A Review of the State-of-the-Art," in IEEE Access, vol. 11, pp. 17031-17052, 2023, doi: 10.1109/ACCESS.2023.3244620. [2] W. Seo, S. -H. Cho, P. Teisseyre and J. Lee, "A Short Survey and Comparison of CNN-Based Music Genre Classification Using Multiple Spectral Features," in IEEE Access, vol. 12, pp. 245-257, 2024, doi: 10.1109/ACCESS.2023.3346883. [3] J. Shen and G. Xiao, "Music Genre Classification Based on Functional Data Analysis," in IEEE Access, vol. 12, pp. 185482-185491, 2024, doi: 10.1109/ACCESS.2024.3512874. [4] Y. Chen and Y. Sun, "The Usage of Artificial Intelligence Technology in Music Education System Under Deep Learning," in IEEE Access, vol. 12, pp. 130546-130556, 2024, doi: 10.1109/ACCESS.2024.3459791. [5] J. Gu et al., "Music Intervention in Human Life, Work, and Disease: A Survey," in International Journal of Crowd Science, vol. 7, no. 3, pp. 97-105, September 2023, doi: 10.26599/IJCS.2023.9100003. [6] T. Łukaszewicz and D. Kania, "A Music Classification Approach Based on the Trajectory of Fifths," in IEEE Access, vol. 10, pp. 73494-73502, 2022, doi: 10.1109/ACCESS.2022.3190016. [7] K. M. Hasib, A. Tanzim, J. Shin, K. O. Faruk, J. A. Mahmud and M. F. Mridha, "BMNet-5: A Novel Approach of Neural Network to Classify the Genre of Bengali Music Based on Audio Features," in IEEE Access, vol. 10, pp. 108545-108563, 2022, doi: 10.1109/ACCESS.2022.3213818. [8] T. Lukaszewicz and D. Kania, "Trajectory of Fifths Based on Chroma Subbands Extraction–A New Approach to Music Representation, Analysis, and Classification," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 47, no. 3, pp. 2157-2169, March 2025, doi: 10.1109/TPAMI.2024.3519420. [9] L. Zheng and C. Li, "Real-Time Emotion-Based Piano Music Generation Using Generative Adversarial Network (GAN)," in IEEE Access, vol. 12, pp. 87489-87500, 2024, doi: 10.1109/ACCESS.2024.3414673. [10] A. Kumar Bairwa, S. Bhat, T. Sawant and R. Manoj, "MGU-V: A Deep Learning Approach for Lo-Fi Music Generation Using Variational Autoencoders With State-of-the-Art Performance on Combined MIDI Datasets," in IEEE Access, vol. 12, pp. 143237-143251, 2024, doi: 10.1109/ACCESS.2024.3471918. [11] M. Ahmed, U. Rozario, M. M. Kabir, Z. Aung, J. Shin and M. F. Mridha, "Musical Genre Classification Using Advanced Audio Analysis and Deep Learning Techniques," in IEEE Open Journal of the Computer Society, vol. 5, pp. 457-467, 2024, doi: 10.1109/OJCS.2024.3431229. [12] O. E. Oguike and M. Primus, "Multimodal Music Genre Classification of Sotho-Tswana Musical Videos," in IEEE Access, doi: 10.1109/ACCESS.2025.3536026. [13] J. Liu, "Aggregating Contextual Information for Multi-Criteria Online Music Recommendations," in IEEE Access, vol. 13, pp. 8790-8805, 2025, doi: 10.1109/ACCESS.2025.3527512. [14] A. Simon, G. Loquet, J. Østergaard and S. Bech, "Cortical Auditory Attention Decoding During Music and Speech Listening," in IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 31, pp. 2903-2911, 2023, doi: 10.1109/TNSRE.2023.3291239. [15] S. Kim and K. Lee, "Music-Driven Synchronous Dance Generation Considering K-Pop Musical and Choreographical Characteristics," in IEEE Access, vol. 12, pp. 94152-94163, 2024, doi: 10.1109/ACCESS.2024.3420433. [16] X. Gao, C. Gupta and H. Li, "Automatic Lyrics Transcription of Polyphonic Music With Lyrics-Chord Multi-Task Learning," in IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 30, pp. 2280-2294, 2022, doi: 10.1109/TASLP.2022.3190742. [17] X. Gao, C. Gupta and H. Li, "PoLyScriber: Integrated Fine-Tuning of Extractor and Lyrics Transcriber for Polyphonic Music," in IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 31, pp. 1968-1981, 2023, doi: 10.1109/TASLP.2023.3275036. [18] M. Tomasetti and L. Turchet, "Playing With Others Using Headphones: Musicians Prefer Binaural Audio With Head Tracking Over Stereo," in IEEE Transactions on Human-Machine Systems, vol. 53, no. 3, pp. 501-511, June 2023, doi: 10.1109/THMS.2023.3270703. [19] S. -L. Wu, C. Donahue, S. Watanabe and N. J. Bryan, "Music ControlNet: Multiple Time-Varying Controls for Music Generation," in IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 32, pp. 2692-2703, 2024, doi: 10.1109/TASLP.2024.3399026. [20] Z. Xu et al., "The Classification and Judgment of Abnormal Problems in Music Song Interpretation Based on Deep Learning," in IEEE Access, vol. 11, pp. 68706-68716, 2023, doi: 10.1109/ACCESS.2023.3280606.