계층적 인공신경망을 이용한 구성을 갖춘 곡의 자동생성

Automatic Generation of a Configured Song with Hierarchical Artificial Neural Networks

  • 김경환 (한성대학교 전자정보공학과) ;
  • 정성훈 (한성대학교 기계전자공학부)
  • Kim, Kyung-Hwan (Department of Electronics and Information Engineering, Hansung University) ;
  • Jung, Sung Hoon (School of Mechanical and Electronic Engineering, Hansung University)
  • 투고 : 2017.07.10
  • 심사 : 2017.07.28
  • 발행 : 2017.07.31


본 논문에서는 자동작곡에서 계층적 인공신경망을 이용하여 전/중/후 별로 곡의 멜로디가 전개되는 구성을 갖춘 곡을 자동으로 생성하는 방법을 제안한다. 첫 번째 계층에서는 하나의 인공신경망을 사용하여 기존의 곡을 학습시키거나 혹은 무작위 멜로디를 학습시키고 박자후처리를 하여 곡을 출력한다. 두 번째 계층에서는 첫 번째 인공신경망이 만든 멜로디를 전/중/후별로 세 개의 인공신경망에 학습한 후 곡을 출력한다. 두 번째 계층의 세 개의 인공신경망에서는 반복을 만들기 위하여 전/중/후 별로 마디구분을 이용한 반복을 적용하며 이후 박자/화성/조성후처리를 수행하여 곡을 완성한다. 실험결과 구성을 갖춘 곡이 생성됨을 확인하였다.

In this paper, we propose a method to automatically generate a configured song with melodies composed of front/middle/last parts by using hierarchical artificial neural networks in automatic composition. In the first layer, an artificial neural network is used to learn an existing song or a random melody and outputs a song after performing rhythm post-processing. In the second layer, the melody created by the artificial neural network in the first layer is learned by three artificial neural networks of front/middle/last parts in the second layer in order to make a configured song. In the artificial neural network of the second layer, we applied a method to generate repeatability using measure identity in order to make song with repeatability and after that the song is completed after rhythm, chord, tonality post-processing. It was confirmed from experiments that our proposed method produced configured songs well.



연구 과제 주관 기관 : 한성대학교


  1. B. Johanson and R. Poli, "GP-Music: An Interactive Genetic Programming System for Music Generation with Automated Fitness Raters" Proceedings of the Third Annual Conference, pp. 181-186, 1998.
  2. N. Tokui and H. Iba, "Music Composition with Interactive Evolutionary Computation," Proceedings of the Third International Conference on Generative Art, pp. 215-226, 2000.
  3. A. Santos, B. Arcay, J. Dorado, J. Romero, and J. Rodriguez, "Evolutionary Computation Systems for Musical Composition," Proceedings of the International Conference Acoustic and Music: Theory and Applications, pp. 97-102, 2000.
  4. C. Chen and R. Miikkulainen, "Creating Melodies with Evolving Recurrent Neural Networks," Proceedings of the 2001 International Joint Conference on Neural Networks, pp. 2241-2246, 2001.
  5. Debora C. Correa, Alexandre L. M. Levada, Jose H. Saito, and Joao F. Mari, "Neural network based systems for computer-aided musical composition: supervised x unsupervised learning," Proceeding SAC '08 Proceedings of the 2008 ACM symposium on Applied computing, pp. 1738-1742, 2008.
  6. T. Oliwa and M. Wagner, "Composing Music with Neural Networks and Probabilistic Finite-State Machines," Applications of Evolutionary Computing: EvoWorkshops 2008, pp. 503-508, 2008
  7. H. Kim, B. Kim, and B. Zhang, "Learning music and generation of crossover music using evolutionary hypernetworks," Proceedings of Korea Computer Congress 2009, pp. 134-138, 2009.
  8. G. Bickerman, S. Bosley, P. Swire, and Rober M. Keller, "Learning to Create Jazz Melodies Using Deep Belief Nets," Proceedings of the International Conference on Computational Creativity, pp. 228-237, 2010.
  9. Andres E. Coca, Roseli A. F. Romero, and Liang Zhao, "Generation of composed musical structures through recurrent neural networks based on chaotic inspiration," Proceedings of International Joint Conference on Neural Networks," pp. 3220-3226, 2011.
  10. J. D. Fernandez and F. Vico, "AI Methods in Algorithmic Composition: A Comprehensive Survey," Journal of Artificial Intelligence Research," vol. 48, pp. 513-582, 2013.
  11. J. Cho, E. M. Ryu, J. Oh, and S. H. Jung, "Training Method of Artificial Neural Networks for Implementation of Automatic Composition Systems," KIPS Transactions on Software and Data Engineering, vol. 3, no. 8, pp. 315-320, Aug. 2014.
  12. J. Oh, J. Song, K. Kim, and S. H. Jung, "Automatic Composition Using Training Capability of Artificial Neural Networks and Chord Progression," Journal of Korea Multimedia Society, vol. 18, no. 11, pp. 1358-1366, Nov. 2015
  13. K. Kim, and S. H. Jung, "Postprocessing for Tonality and Repeatability, and Average Neural Networks for Training Multiple Songs in Automatic Composition," Journal of Korean Institute of Intelligent Systems, vol. 26, no. 6, pp. 445-451, Dec. 2016
  14. K. Kim, and S. H. Jung, "Adoption of Artificial Neural Network for Rest, Enhanced Postprocessing of Beats and Initial Melody Processing for Automatic Composition System," Journal of Korea Digital Contents Society, vol. 17, no. 6, pp. 449-459, Dec. 2016
  15. A Configured Song Composed by Hierarchical Artificial Neural Networks, download from the URL
  16. A Configured Song Composed by Hierarchical Artificial Neural Networks, download from the URL