RESEARCH ON THE CONSTRUCTION OF AI COMPOSITION SYSTEM BASED ON HMM

Year 2024, , 216 - 240, 23.09.2024

Weijia Yang , Inho Lee

https://doi.org/10.51576/ymd.1536267

Abstract

The Markov chain is an automatic accompaniment algorithm for intelligent computer systems, belonging to the interdisciplinary research field of musicology and computer science. Currently, there are many methods for AI music generation, but research on AI music generation based on the Hidden Markov Model (HMM) is relatively scarce. This paper proposes a method for constructing an AI composition system based on the HMM. This system achieves the goal of automatically generating accompaniment music from score data. The proposed system has achieved relatively stable results in the generation of musical elements such as form and harmony, accompaniment texture, and instrumentation, and has scored well in evaluation experiments.

Keywords

Automatic accompaniment algorithm, Artificial Intelligence, Composition, Popular music, Hidden Markov Model.

HMMS TEMELLİ YAPAY ZEKA BESTECİLİĞİ SİSTEMİ İNŞASI ÜZERİNE BİR ARAŞTIRMA

Abstract

Yapay Zeka (AI) çağı geldi ve önemli bir konu olan yapay zeka ile besteleme büyük ilgi görmektedir. Şu anda, müzikoloji ve bilgisayar bilimi disiplinler arası araştırma alanında birçok otomatik besteleme algoritması bulunmaktadır ve Markov zinciri, zeki bilgisayar sistemleri için temsil edici bir otomatik eşlik algoritmasıdır. Büyük veri çağının gelmesiyle birlikte, olasılık teorisine dayalı bir otomatik besteleme yöntemi olan Markov zinciri yavaş yavaş göz ardı edilmeye başlanmıştır. Ancak, Gizli Markov Modeli (HMM) temelli yapay zeka müzik üretimi üzerine yapılan araştırmalar hala çok değerlidir. Bu makale, popüler müzik tarzı için HMM'ye dayalı bir yapay zeka beste sistemi inşa etme yöntemini önermektedir. Bu sistem, nota verilerinden otomatik olarak eşlik müziği üretme hedefini gerçekleştirmektedir. Önerilen sistem, form ve uyum, eşlik dokusu ve enstrümantasyon gibi müzikal unsurların üretilmesinde görece istikrarlı sonuçlar elde etmiş ve değerlendirme deneylerinde iyi notlar almıştır. Bu çalışma, yapay zeka çağında algoritmik besteleme mühendisliği örneklerinin inşası yoluyla müzikoloji araştırmalarının teknik sınırlarını deneysel bir şekilde keşfetmeyi amaçlamaktadır.

Keywords

Otomatik eşlik algoritması, Yapay Zeka, Beste, Popüler müzik, Hidden Markov Model.

References

• Allan, M., & Williams, C. (2004). Harmonising chorales by probabilistic inference. Advances in Neural Information Processing Systems, 17.
• Bäckman, K. (2009). Automatic jazz harmony evolution. Proceedings of the 6th Sound and Music Computing Conference (SMC), 349–354. Band-in-a-Box. (2024, Feb. 6). https://www.pgmusic.com
• Bell, C. (2011). Algorithmic music composition using dynamic Markov chains and genetic algorithms. Journal of Computing Sciences in Colleges, 27(2), 99– 107.
• Chong, E. K. M., & Ding, Q. (2014). Symbolic representation of chords for rulebased evaluation of tonal progressions.
• Dannenberg, R. B., & Grubb, L. (1994). Automating ensemble performance. Procs of ICMC94, 63–69.
• Dannenberg, R. B., & Hu, N. (2003). Polyphonic audio matching for score following and intelligent audio editors.
• De Prisco, R., Zaccagnino, G., & Zaccagnino, R. (2010). Evobasscomposer: A multiobjective genetic algorithm for 4-voice compositions. Proceedings of the 12th Annual Conference on Genetic and Evolutionary Computation, 817–818.
• Doush, I. A., & Sawalha, A. (2020). Automatic music composition using genetic algorithm and artificial neural networks. Malaysian Journal of Computer Science, 33(1), 35–51.
• Eason Chan. (2013). Love Transfer. https://youtu.be/jouvNcQOm7Q?si=X5ELaq2TI76bNxO8
• Farbood, M., & Schöner, B. (2001). Analysis and synthesis of Palestrina-style counterpoint using Markov chains. ICMC.
• Fernández, J. D., & Vico, F. (2013). AI methods in algorithmic composition: A comprehensive survey. Journal of Artificial Intelligence Research, 48, 513–582.
• Gurkaynak, G., Yilmaz, I., & Haksever, G. (2016). Stifling artificial intelligence: Human perils. Computer Law & Security Review, 32(5), 749–758.
• Herremans, D., Chuan, C.-H., & Chew, E. (2017). A functional taxonomy of music generation systems. ACM Computing Surveys (CSUR), 50(5), 1–30.
• Jay Chou. (2013). Rice Field. https://youtu.be/kC2bkbMC6Zs?si=kNk971D1PEseDxUe
• Jordanous, A., & Smaill, A. (2008). Artificially intelligent accompaniment using Hidden Markov Models to model musical structure.
• Linson, A., Dobbyn, C., & Laney, R. (2012). Improvisation without representation: Artificial intelligence and music.
• Luque, S. (2009). The stochastic synthesis of iannis xenakis. Leonardo Music Journal, 19, 77–84.
• Minsky, M. (2007). The emotion machine: Commonsense thinking, artificial intelligence, and the future of the human mind. Simon and Schuster.
• Music Memos. (2024, Feb. 6). https://www.chordai.net/musicmemos/
• Oliwa, T. M. (2008). Genetic algorithms and the abc music notation language for rock music composition. Proceedings of the 10th Annual Conference on Genetic and Evolutionary Computation, 1603–1610.
• Orio, N. (2001). An automatic accompanist based on hidden markov models. Congress of the Italian Association for Artificial Intelligence, 64–69.
• Rohrmeier, M., & Graepel, T. (2012). Comparing feature-based models of harmony. Proceedings of the 9th International Symposium on Computer Music Modelling and Retrieval, 357–370.
• Sako, S., Yamamoto, R., & Kitamura, T. (2014). Ryry: A real-time score-following automatic accompaniment playback system capable of real performances with errors, repeats and jumps. Active Media Technology: 10th International Conference, AMT 2014, Warsaw, Poland, August 11-14, 2014. Proceedings 10, 134–145.
• Shan, M., & Chiu, S. (2010). Algorithmic compositions based on discovered musical patterns. MULTIMEDIA TOOLS AND APPLICATIONS, 46(1), 1–23.
• Simon, I., Morris, D., & Basu, S. (2008). MySong: Automatic accompaniment generation for vocal melodies. Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, 725–734.
• Tang, F. (2021). Analysis on the construction of english language and culture teaching system based on artificial intelligence. Big Data Analytics for Cyber-Physical System in Smart City: BDCPS 2020, 28-29
• December 2020, Shanghai, China, 1464–1469.
• TFBOYS. (2021). Glory. https://youtu.be/8CookdwavLo?si=NQE9REIBPMMXAmOA Thom, B. (2000). Artificial intelligence and real-time interactive improvisation. Proceedings from the AAAI-2000 Music and AI Workshop, 35–39.
• Wright, R., Younker, B. A., Beynon, C., Hutchison, J., Linton, L., Beynon, S., Davidson, B., & Duarte, N. (2012). Tuning into the future: Sharing initial insights about the 2012 Musical Futures pilot project in Ontario. The Canadian Music Educator, 53(4), 14.
• Xia, G., & Dannenberg, R. B. (2015). Duet interaction: Learning musicianship for automatic accompaniment. NIME, 259–264.
• Zarro, R. D., & Anwer, M. A. (2017). Recognition-based online Kurdish character recognition using hidden Markov model and harmony search. Engineering Science and Technology, an International Journal, 20(2), 783–794.
• Zhu, D. (2017). Analysis of the application of artificial intelligence in college English teaching. 2017 2nd International Conference on Control, Automation and Artificial Intelligence (CAAI 2017), 235–237.