Evaluating Preprocessing Techniques for Unsupervised Mode Detection in Irish Traditional Music
Source abstract
Abstract
Significant computational research has been dedicated to automatic key and mode detection in Western tonal music, particularly within the major and minor modes. However, limited research has focused on identifying alternative diatonic modes in traditional and folk music contexts. This paper addresses this gap by comparing the effectiveness of various preprocessing techniques in unsupervised machine learning for diatonic mode detection. Using a dataset of Irish folk music that incorporates diatonic modes such as Ionian, Dorian, Mixolydian, and Aeolian, we assess how different preprocessing approaches influence clustering accuracy and mode distinction. By examining multiple feature transformations and reductions, this study highlights the impact of preprocessing choices on clustering performance, aiming to optimize the unsupervised classification of diatonic modes in folk music traditions.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Music and Audio Processing · Diverse Musicological Studies · Music Technology and Sound Studies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Expert Systems and Applications Lab, Faculty of Science, University of Salamanca, Plaza de los Caídos s/n, 37008 Salamanca, Spain
Funding
EA-DIGIFOLK: An European and Ibero-American approach for the digital collection, analysis and dissemination of folk music · Marie Skłodowska-Curie Actions Staff Exchanges
References (57)
Show source-provided references
1. Aspectos metodológicos en la investigación etnomusicólogica10.2307/20797473 ↗
2. Nettl, B. (1983). The Study of Ethnomusicology: Twenty-Nine Issues and Concepts, University of Illinois Press. Number 39.
3. Therapeutic Musical Scales: Theory and Practice
4. Insider or outsider? Exploring some digital challenges in ethnomusicology10.1080/03080188.2021.1872144 ↗
5. Computational ethnomusicology: Perspectives and challenges10.1080/09298215.2013.818038 ↗
6. Noll, T., Montiel, M., Gómez, F., Hamido, O.C., Besada, J.L., and Martins, J.O. (2024). Exploring Mode Identification in Irish Folk Music with Unsupervised Machine Learning and Template-Based Techniques. Mathematics and Computation in Music, Springer.10.1007/978-3-031-60638-0 ↗
7. Bertin-Mahieux, T., Ellis, D.P., Whitman, B., and Lamere, P. (2011, January 24–28). The Million Song Dataset. Proceedings of the 12th International Conference on Music Information Retrieval (ISMIR 2011), Miami, FL, USA.
8. Gajjar, P., Shah, P., and Sanghvi, H. (2021, January 16–17). E-mixup and siamese networks for musical key estimation. Proceedings of the International Conference on Ubiquitous Computing and Intelligent Information Systems 2021, Tamil Nadu, India.
9. Garg, M., Gajjar, P., Shah, P., Shukla, M., Acharya, B., Gerogiannis, V.C., and Kanavos, A. (2023). Comparative Analysis of Deep Learning Architectures and Vision Transformers for Musical Key Estimation. Information, 14.10.3390/info14100527 ↗
10. Musical genre classification of audio signals10.1109/TSA.2002.800560 ↗
11. Eerola, T., and Toiviainen, P. (2024, December 15). Suomen Kansan eSävelmät. Finnish Folk Song Database. [11.3. 2004]. Available online: http://www.jyu.fi/musica/sks/.
12. Session, T. (2024, December 15). Traditional Irish Nusic on The Session. Available online: https://thesession.org/.
13. Tracing the dynamic changes in perceived tonal organization in a spatial representation of musical keys10.1037/0033-295X.89.4.334 ↗
14. Krumhansl, C.L. (2001). Cognitive Foundations of Musical Pitch, Oxford University Press.10.1093/acprof:oso/9780195148367.001.0001 ↗
15. What’s key for key? The Krumhansl-Schmuckler key-finding algorithm reconsidered10.2307/40285812 ↗
16. Jansson, A., and Weyde, T. (2012). MIREX 2012: Key recognition with zweiklang profiles. Music Information Retrieval Evaluation eXchange (MIREX), Citeseer.
17. Development of an intelligent model for musical key estimation using machine learning techniques10.1007/s11042-022-12432-y ↗
18. Mahieu, R. (2024, December 15). Detecting Musical Key with Supervised Learning. Available online: https://api.semanticscholar.org/CorpusID:38498183.
19. Identifying Irish Traditional Music Genres Using Latent Audio Representations10.1109/ACCESS.2024.3421639 ↗
20. Fisher Discriminative Embedding Low-Rank Sparse Representation for Music Genre Classification10.1007/s00034-024-02696-0 ↗
21. Liu, X., Yang, Z., and Cheng, J. (2024). Music recommendation algorithms based on knowledge graph and multi-task feature learning. Sci. Rep., 14.10.1038/s41598-024-52463-z ↗
22. Tabaza, A., Quishawi, O., Yaghi, A., and Qawasmeh, O. (2024, January 25–26). Binding Text, Images, Graphs, and Audio for Music Representation Learning. Proceedings of the AICCONF’24: Cognitive Models and Artificial Intelligence Conference, İstanbul, Turkiye.10.1145/3660853.3660886 ↗
23. Predicting song genre with deep learning10.1108/GKMC-08-2022-0187 ↗
24. Huang, Q., Jansen, A., Lee, J., Ganti, R., Li, J.Y., and Ellis, D.P.W. (2022). MuLan: A Joint Embedding of Music Audio and Natural Language. arXiv.
25. Doh, S., Lee, J., Park, T.H., and Nam, J. (2020). Musical Word Embedding: Bridging the Gap between Listening Contexts and Music. arXiv.
26. Dokania, S., and Singh, V. (2019). Graph Representation learning for Audio & Music genre Classification. arXiv.
27. Milne, A. (2013). A Computational Model of the Cognition of Tonality, Open University (United Kingdom).
28. Corpus-derived key profiles are not transpositionally equivalent10.1525/mp.2017.34.5.531 ↗
29. Are pitch-class profiles really “Key for Key”?
30. Bernardes, G., Davies, M.E., and Guedes, C. (2017, January 5–9). Automatic musical key estimation with adaptive mode bias. Proceedings of the 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), New Orleans, LA, USA.10.1109/ICASSP.2017.7952169 ↗
31. Chuan, C.H., and Chew, E. (2005, January 6). Polyphonic audio key finding using the spiral array CEG algorithm. Proceedings of the 2005 IEEE International Conference on Multimedia and Expo, Amsterdam, The Netherlands.
32. Gómez, E., and Herrera, P. (2004, January 10–14). Estimating The Tonality Of Polyphonic Audio Files: Cognitive Versus Machine Learning Modelling Strategies. Proceedings of the ISMIR 2004, Barcelona, Spain.10.1045/december2004-droettboom ↗
33. An improved model of tonality perception incorporating pitch salience and echoic memory10.1037/h0094110 ↗
34. Precise pitch profile feature extraction from musical audio for key detection10.1109/TMM.2006.870727 ↗
35. Finley, M., and Razi, A. (2019, January 7–9). Musical key estimation with unsupervised pattern recognition. Proceedings of the 2019 IEEE 9th Annual Computing and Communication Workshop and Conference (CCWC), Las Vegas, NV, USA.10.1109/CCWC.2019.8666620 ↗
36. Sturm, B., Santos, J.F., and Korshunova, I. (2015, January 26–30). Folk music style modelling by recurrent neural networks with long short term memory units. Proceedings of the 16th International Society for Music Information Retrieval Conference, Malaga, Spain.
37. Cabral, G., Briot, J.P., and Pachet, F. (2025, January 3–5). Impact of distance in pitch class profile computation. Proceedings of the Brazilian Symposium on Computer Music 2005, Belo Horizonte, Brazil.
38. Sainburg, T., McInnes, L., and Gentner, T.Q. (2020). Parametric UMAP: Learning embeddings with deep neural networks for representation and semi-supervised learning. arXiv.10.1162/neco_a_01434 ↗
39. Nonlinear Dimensionality Reduction by Locally Linear Embedding10.1126/science.290.5500.2323 ↗
40. McInnes, L., Healy, J., and Melville, J. (2018). Umap: Uniform manifold approximation and projection for dimension reduction. arXiv.10.21105/joss.00861 ↗
41. Scikit-learn: Machine Learning in Python
42. McCallum, M.C., Korzeniowski, F., Oramas, S., Gouyon, F., and Ehmann, A.F. (2022). Supervised and Unsupervised Learning of Audio Representations for Music Understanding. arXiv.
43. Dhariwal, P., Jun, H., Payne, C., Kim, J.W., Radford, A., and Sutskever, I. (2020). Jukebox: A Generative Model for Music. arXiv.
44. Li, Y., Yuan, R., Zhang, G., Ma, Y., Chen, X., Yin, H., Xiao, C., Lin, C., Ragni, A., and Benetos, E. (2023). MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training. arXiv.
45. Castellon, R., Donahue, C., and Liang, P. (2021). Codified audio language modeling learns useful representations for music information retrieval. arXiv.
46. Cao, L., Zhao, Z., and Wang, D. (2023). Clustering algorithms. Target Recognition and Tracking for Millimeter Wave Radar in Intelligent Transportation, Springer.10.1007/978-981-99-1533-0 ↗
47. Venkatkumar, I.A., and Shardaben, S.J.K. (2016, January 23–25). Comparative study of data mining clustering algorithms. Proceedings of the 2016 International Conference on Data Science and Engineering (ICDSE), Cochin, India.10.1109/ICDSE.2016.7823946 ↗
48. Carreira-Perpinán, M.A. (2015). A review of mean-shift algorithms for clustering. arXiv.
49. Arthur, D., and Vassilvitskii, S. (2007, January 7–9). k-means++: The advantages of careful seeding. Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, SODA’07, New Orleans, LA, USA.
50. Analysis of agglomerative clustering10.1007/s00453-012-9717-4 ↗
51. Ester, M., Kriegel, H.P., Sander, J., and Xu, X. (1996, January 2–4). A density-based algorithm for discovering clusters in large spatial databases with noise. Proceedings of the Second International Conference on Knowledge Discovery and Data Mining KDD’96, Portland, OR, USA.
52. Mean shift: A robust approach toward feature space analysis10.1109/34.1000236 ↗
53. The Self-Organizing Map10.1109/5.58325 ↗
54. Vettigli, G. (2024, December 15). MiniSom: Minimalistic and NumPy-Based Implementation of the Self Organizing Map. Available online: https://github.com/JustGlowing/minisom.
55. Vinh, N.X., Epps, J., and Bailey, J. (2009, January 14–18). Information theoretic measures for clusterings comparison: Is a correction for chance necessary?. Proceedings of the 26th Annual International Conference on Machine Learning, ICML’09, Montreal, QC, Canada.10.1145/1553374.1553511 ↗
56. Properties of the Hubert-Arabie Adjusted Rand Index10.1037/1082-989X.9.3.386 ↗
57. Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learning