The Journal of Korean Institute of Communications and Information Sciences (한국통신학회논문지)

The Korean Institute of Commucations and Information Sciences (한국통신학회)
권호 표지
DOI QR코드

DOI QR Code

Rule-Based Generation of Four-Part Chorus Applied With Chord Progression Learning Model

화성 진행 학습 모델을 적용한 규칙 기반의 4성부 합창 음악 생성

  • Cho, Won Ik (Seoul National University Department of Electrical and Computer Engineering and Institute of New Media and Communications) ;
  • Kim, Jeung Hun (Seoul National University Department of Electrical and Computer Engineering and Institute of New Media and Communications) ;
  • Cheon, Sung Jun (Seoul National University Department of Electrical and Computer Engineering and Institute of New Media and Communications) ;
  • Kim, Nam Soo (Seoul National University Department of Electrical and Computer Engineering and Institute of New Media and Communications)
  • Received : 2016.09.09
  • Accepted : 2016.11.18
  • Published : 2016.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we apply a chord progression learning model to a rule-based generation of a four-part chorus. The proposed system is given a 32-note melody line and completes the four-part chorus based on the rule of harmonics, predicting the chord progression with the CRBM model. The data for the training model was collected from various harmony textbooks, and chord progressions were extracted with key-independent features so as to utilize the given data effectively. It was shown that the output piece obtained with the proposed learning model had a more natural progression than the piece that used only the rule-based approach.

본 논문에서는 규칙 기반의 4성부 합창 음악 생성 과정에 화성 진행 학습 모델을 적용해 보고자 한다. 제안하는 시스템은 32음의 멜로디를 입력으로 받아 다른 세 성부를 화성학의 규칙에 맞게 완성시켜 주며, 그 과정에서 사용하는 화성 진행을 CRBM 모델을 이용하여 예측한다. 학습 데이터는 화성학 교육 자료집에서 다수 발췌하였으며, 화성 진행을 조성에 독립적으로 추출하여 주어진 데이터를 효과적으로 활용할 수 있도록 하였다. 학습 모델을 적용한 결과물이 기존의 규칙 기반 4성부 합창 음악에 비해 보다 자연스러운 진행을 보임이 확인되었다.

Keywords

References

  1. G. Nierhaus, Algorithmic composition : Paradigms of automated music generation, Springer Wien New York, 2010.
  2. D. Patrick and J. Sheppard, "Evolving four-part harmony using genetic algorithms," Eur. Conf. Appl. Evolutionary Computation, Springer Berlin Heidelberg, 2011.
  3. M. Allan and C. KI Williams, "Harmonising chorales by probabilistic inference," Advances in Neural Inf. Process. Syst., vol. 17, pp. 25-32, 2005.
  4. D. Johnson, Hexadria : Composing music with recurrent neural network(2015), Retrieved Sept., 08, 2016, from http://www.hexahedria.com/2015/08/03/composing-music-with-recurrent-neural-networks/
  5. L. Yi and J. Goldsmith, "Automatic generation of four-part harmony," BMA 268, 2007.
  6. W. I. Cho, C. M. Lee, H. Y. Kim, S. Y. Jang, and N. S. Kim, "Rule-based generation of 4-part chorus," in Proc. KICS Int. Conf. Commun., pp. 1492-1494, 2016.
  7. G. Bickerman, S. Bosley, P. Swire, and R. M. Keller, "Learning to create jazz melodies using deep belief nets," in Proc. Int. Conf. Computational Creativity, 2010.
  8. B. D. Baek, Harmonics, Sumundang, 2008.
  9. G. W. Taylor, G. E. Hinton, and S. Roweis, "Modeling human motion using binary latent variables," in Proc. 19th Neural Inf. Process. Syst., pp. 1345-1352, 2007.
  10. D. Temperley, A statistical analysis of tonal harmony(2009), Retrieved Etp., 12, 2016, from http://theory.esm.rochester.edu/temperley/kp-stats/index.html
  11. G. Montufar, N. Ay, and K. Ghazi-Zahedi, "Geometry and expressive power of conditional restricted Boltzmann machines," J. Machine Learning Res., vol. 16, pp. 2405-2436, 2015.
  12. G. W. Taylor, L. Sigal, D. J. Fleet, and G. E. Hinton, "Dynamical binary latent variable models for 3d human pose tracking," CVPR, pp. 631-638, Jun. 2010.
  13. G. Taylor, Implicit mixture of conditional restricted boltzmann machine : Code Version 1.000(2010), Retrieved Apr., 21, 2016, from http://www.uoguelph.ca/-gwtaylor/publications/cvpr2010/
  14. ITU-T, Recommendation P.800 : Methods for subjective determination of transmission quality(1996), Retrieved Sep., 09, 2016, from https://www.itu.int/rec/T-REC-P.800-199608-I/en
  15. O. Lartillot, P. Toiviainen, and T. Eerola, "A MATLAB toolbox for music information retrieval," in Data Anal., Machine Learning and Appl., Springer Berlin Heidelberg, pp.261-268, 2008.
  16. K. S. Kwon, H. Y. Kim, and N. S. Kim, "Speech basis matrix using noise data and NMF-based speech enhancement scheme," J. KICS, vol. 40, no. 4, pp. 619-627, 2015. https://doi.org/10.7840/kics.2015.40.4.619
  17. C. M. Lee, S. H. Bae, J. H. Kim, and N. S. Kim, "Spectro-temporal filtering based on soft decision for stereophonic acoustic echo suppression," J. KICS, vol. 39, no. 12, pp.1346-1351, 2014.