Research Article
BibTex RIS Cite
Year 2024, , 25 - 35, 07.06.2024
https://doi.org/10.38088/jise.1406162

Abstract

References

  • [1] Briot, J. P., & Pachet, F. (2020). Deep learning for music generation: challenges and directions. Neural Computing and Applications, 32(4), 981-993.
  • [2] Bozkurt, B., Gedik, A. C., & Karaosmanoglu, M. K. (2009, April). Music information retrieval for Turkish music: problems, solutions and tools. In 2009 IEEE 17th Signal Processing and Communications Applications Conference (pp. 804-807). IEEE.
  • [3] Kızrak, M. A., & Bolat, B. (2017). A musical information retrieval system for Classical Turkish Music makams. Simulation, 93(9), 749-757.
  • [4] Karaosmanoğlu, M. K. (2012). A Turkish makam music symbolic database for music information retrieval: SymbTr. In Proceedings of 13th International Society for Music Information Retrieval Conference; 2012 October 8-12; Porto, Portugal. Porto: ISMIR, 2012. p. 223–228. International Society for Music Information Retrieval (ISMIR).
  • [5] Krueger, B. Classical piano midi page (2016). URl: http://www.piano-midi.de/(Last accessed 28/11/2023).
  • [6] Ay, G., & Akkal, L. B. (2009). İTÜ Türk Musikisi Devlet Konservatuarı Türk müziğinde uygulama-Kuram sorunları ve çözümleri. Uluslararası çağrılı kongre bildiriler kitabı.
  • [7] Öztürk, Ö., Özacar, T., & Abidin, D. (2018, September). KORAL: Türk Müziği için Makam Tabanlı Öneri Motoru Tasarımı. In 2018 International Conference on Artificial Intelligence and Data Processing (IDAP) (pp. 1-4). IEEE.
  • [8] Abidin, D., Öztürk, Ö., & Öztürk, T. Ö. (2017). Klasik Türk müziğinde makam tanıma için veri madenciliği kullanımı. Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi, 32(4), 1221-1232.
  • [9] Mangal, S., Modak, R., & Joshi, P. (2019). LSTM based music generation system. arXiv preprint arXiv:1908.01080.
  • [10] Shah, F., Naik, T., & Vyas, N. (2019, December). LSTM based music generation. In 2019 International Conference on Machine Learning and Data Engineering (iCMLDE) (pp. 48-53). IEEE.
  • [11] Wu, J., Hu, C., Wang, Y., Hu, X., & Zhu, J. (2019). A hierarchical recurrent neural network for symbolic melody generation. IEEE transactions on cybernetics, 50(6), 2749-2757.
  • [12] Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... & Polosukhin, I. (2017). Attention is all you need. Advances in neural information processing systems, 30.
  • [13] Niu, Z., Zhong, G., & Yu, H. (2021). A review on the attention mechanism of deep learning. Neurocomputing, 452, 48-62.
  • [14] Wu, J., Liu, X., Hu, X., & Zhu, J. (2020). PopMNet: Generating structured pop music melodies using neural networks. Artificial Intelligence, 286, 103303.
  • [15] Muhamed, A., Li, L., Shi, X., Yaddanapudi, S., Chi, W., Jackson, D., ... & Smola, A. J. (2021, May). Symbolic music generation with transformer-gans. In Proceedings of the AAAI conference on artificial intelligence (Vol. 35, No. 1, pp. 408-417).
  • [16] Tanberk, S., & Tükel, D. B. (2021, January). Style-specific Turkish pop music composition with CNN and LSTM network. In 2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI) (pp. 000181-000185). IEEE.
  • [17] Aydıngün, A., Baglu, D., Canbaz, B., & Kökbıyık, A. Derin Ögrenme ile Türkçe Sarkı Besteleme Turkish Music Generation using Deep Learning.
  • [18] Cuthbert MS, Ariza C (2010) music21: A toolkit for computer-aided musicology and symbolic music data. Proceedings of the 11th International Society for Music Information Retrieval Conference (ISMIR 2010).
  • [19] Cuthbert, M. S., & Ariza, C. (2010). music21: A toolkit for computer-aided musicology and symbolic music data.
  • [20] Patro, S.G.K, & Sahu, K. K. (2015). Normalization: A preprocessing stage. arXiv preprint arXiv:1503.06462.
  • [21] Hochreiter, S. (1998). The vanishing gradient problem during learning recurrent neural nets and problem solutions. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 6(02), 107-116.
  • [22] Lin, T., Wang, Y., Liu, X., & Qiu, X. (2022). A survey of transformers. AI Open.

Classical Turkish Music Composition with LSTM Self-Attention

Year 2024, , 25 - 35, 07.06.2024
https://doi.org/10.38088/jise.1406162

Abstract

Synthetic symbolic music generation, the process of creating new musical pieces using symbolic representations, has gained significant traction in the field of music informatics and computational creativity. It holds immense potential for various applications, ranging from music education and composition assistance to music therapy and personalized music recommendation systems. Classical Turkish music (CTM) exhibit distinct characteristics regarding Western Tonal Classical Music (WCM) such as melodic organization, formation of rhythmic structure or melodic expressions. This study tackles the challenge of symbolic music composition, focusing on CTM. Unlike WCM, CTM incorporates microtonal intervals. These intervals are smaller than the semitones in Western music, allowing for a more nuanced expression of pitch. This leads to a more diverse set of pitch ranges. The proposed method employs a combination of self-attention and long-short term memory (LSTM) networks to capture long-term relational information and generate realistic CTM compositions. LSTMs effectively model sequential dependencies and improve local relations within musical structures and self-attention improves the context vector, allowing the model to attend to different aspects of the musical context simultaneously. This combination enables the proposed method to generate compositions that are both musically coherent and stylistically consistent with distinct features of CTM. The proposed method was evaluated on two datasets, the CTM dataset and Classical Music Piano (CPM) dataset. The assessment of musical contents is evaluated through melodic similarity and stylistic consistency metrics. The results demonstrate that the proposed method is able to generate musical content that is coherent and produce music that is pleasing-to-hear. Overall, the article presents a novel and effective approach to symbolic music composition, focusing on CTM.

Thanks

The hyperparameter optimization has been conducted at the B.T.U. High-Performance Clustering Laboratory (HPCLAB).

References

  • [1] Briot, J. P., & Pachet, F. (2020). Deep learning for music generation: challenges and directions. Neural Computing and Applications, 32(4), 981-993.
  • [2] Bozkurt, B., Gedik, A. C., & Karaosmanoglu, M. K. (2009, April). Music information retrieval for Turkish music: problems, solutions and tools. In 2009 IEEE 17th Signal Processing and Communications Applications Conference (pp. 804-807). IEEE.
  • [3] Kızrak, M. A., & Bolat, B. (2017). A musical information retrieval system for Classical Turkish Music makams. Simulation, 93(9), 749-757.
  • [4] Karaosmanoğlu, M. K. (2012). A Turkish makam music symbolic database for music information retrieval: SymbTr. In Proceedings of 13th International Society for Music Information Retrieval Conference; 2012 October 8-12; Porto, Portugal. Porto: ISMIR, 2012. p. 223–228. International Society for Music Information Retrieval (ISMIR).
  • [5] Krueger, B. Classical piano midi page (2016). URl: http://www.piano-midi.de/(Last accessed 28/11/2023).
  • [6] Ay, G., & Akkal, L. B. (2009). İTÜ Türk Musikisi Devlet Konservatuarı Türk müziğinde uygulama-Kuram sorunları ve çözümleri. Uluslararası çağrılı kongre bildiriler kitabı.
  • [7] Öztürk, Ö., Özacar, T., & Abidin, D. (2018, September). KORAL: Türk Müziği için Makam Tabanlı Öneri Motoru Tasarımı. In 2018 International Conference on Artificial Intelligence and Data Processing (IDAP) (pp. 1-4). IEEE.
  • [8] Abidin, D., Öztürk, Ö., & Öztürk, T. Ö. (2017). Klasik Türk müziğinde makam tanıma için veri madenciliği kullanımı. Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi, 32(4), 1221-1232.
  • [9] Mangal, S., Modak, R., & Joshi, P. (2019). LSTM based music generation system. arXiv preprint arXiv:1908.01080.
  • [10] Shah, F., Naik, T., & Vyas, N. (2019, December). LSTM based music generation. In 2019 International Conference on Machine Learning and Data Engineering (iCMLDE) (pp. 48-53). IEEE.
  • [11] Wu, J., Hu, C., Wang, Y., Hu, X., & Zhu, J. (2019). A hierarchical recurrent neural network for symbolic melody generation. IEEE transactions on cybernetics, 50(6), 2749-2757.
  • [12] Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... & Polosukhin, I. (2017). Attention is all you need. Advances in neural information processing systems, 30.
  • [13] Niu, Z., Zhong, G., & Yu, H. (2021). A review on the attention mechanism of deep learning. Neurocomputing, 452, 48-62.
  • [14] Wu, J., Liu, X., Hu, X., & Zhu, J. (2020). PopMNet: Generating structured pop music melodies using neural networks. Artificial Intelligence, 286, 103303.
  • [15] Muhamed, A., Li, L., Shi, X., Yaddanapudi, S., Chi, W., Jackson, D., ... & Smola, A. J. (2021, May). Symbolic music generation with transformer-gans. In Proceedings of the AAAI conference on artificial intelligence (Vol. 35, No. 1, pp. 408-417).
  • [16] Tanberk, S., & Tükel, D. B. (2021, January). Style-specific Turkish pop music composition with CNN and LSTM network. In 2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI) (pp. 000181-000185). IEEE.
  • [17] Aydıngün, A., Baglu, D., Canbaz, B., & Kökbıyık, A. Derin Ögrenme ile Türkçe Sarkı Besteleme Turkish Music Generation using Deep Learning.
  • [18] Cuthbert MS, Ariza C (2010) music21: A toolkit for computer-aided musicology and symbolic music data. Proceedings of the 11th International Society for Music Information Retrieval Conference (ISMIR 2010).
  • [19] Cuthbert, M. S., & Ariza, C. (2010). music21: A toolkit for computer-aided musicology and symbolic music data.
  • [20] Patro, S.G.K, & Sahu, K. K. (2015). Normalization: A preprocessing stage. arXiv preprint arXiv:1503.06462.
  • [21] Hochreiter, S. (1998). The vanishing gradient problem during learning recurrent neural nets and problem solutions. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 6(02), 107-116.
  • [22] Lin, T., Wang, Y., Liu, X., & Qiu, X. (2022). A survey of transformers. AI Open.
There are 22 citations in total.

Details

Primary Language English
Subjects Deep Learning, Artificial Intelligence (Other)
Journal Section Research Articles
Authors

Ahmet Kaşif 0000-0003-2707-6075

Selçuk Sevgen 0000-0003-1443-1779

Early Pub Date April 19, 2024
Publication Date June 7, 2024
Submission Date December 19, 2023
Acceptance Date February 1, 2024
Published in Issue Year 2024

Cite

APA Kaşif, A., & Sevgen, S. (2024). Classical Turkish Music Composition with LSTM Self-Attention. Journal of Innovative Science and Engineering, 8(1), 25-35. https://doi.org/10.38088/jise.1406162
AMA Kaşif A, Sevgen S. Classical Turkish Music Composition with LSTM Self-Attention. JISE. June 2024;8(1):25-35. doi:10.38088/jise.1406162
Chicago Kaşif, Ahmet, and Selçuk Sevgen. “Classical Turkish Music Composition With LSTM Self-Attention”. Journal of Innovative Science and Engineering 8, no. 1 (June 2024): 25-35. https://doi.org/10.38088/jise.1406162.
EndNote Kaşif A, Sevgen S (June 1, 2024) Classical Turkish Music Composition with LSTM Self-Attention. Journal of Innovative Science and Engineering 8 1 25–35.
IEEE A. Kaşif and S. Sevgen, “Classical Turkish Music Composition with LSTM Self-Attention”, JISE, vol. 8, no. 1, pp. 25–35, 2024, doi: 10.38088/jise.1406162.
ISNAD Kaşif, Ahmet - Sevgen, Selçuk. “Classical Turkish Music Composition With LSTM Self-Attention”. Journal of Innovative Science and Engineering 8/1 (June 2024), 25-35. https://doi.org/10.38088/jise.1406162.
JAMA Kaşif A, Sevgen S. Classical Turkish Music Composition with LSTM Self-Attention. JISE. 2024;8:25–35.
MLA Kaşif, Ahmet and Selçuk Sevgen. “Classical Turkish Music Composition With LSTM Self-Attention”. Journal of Innovative Science and Engineering, vol. 8, no. 1, 2024, pp. 25-35, doi:10.38088/jise.1406162.
Vancouver Kaşif A, Sevgen S. Classical Turkish Music Composition with LSTM Self-Attention. JISE. 2024;8(1):25-3.


Creative Commons License

The works published in Journal of Innovative Science and Engineering (JISE) are licensed under a  Creative Commons Attribution-NonCommercial 4.0 International License.