A Neural Network for Bass Functional Harmonization

  • Roberto De Prisco
  • Antonio Eletto
  • Antonio Torre
  • Rocco Zaccagnino
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6025)


This paper presents the design, implementation and testing of a neural network for the functional harmonization of a bass line. The overall network consists of three base networks that are used in parallel under the control of an additional network that, at each step, chooses the best output from the three base networks.

All the neural networks have been trained using J.S. Bach’s chorales. In order to evaluate the networks, a metric measuring the distance of the output from the original J.S. Bach’s harmonization is defined.


Neural Network Current Tonality Quarter Note Inversion Number Bass Line 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Website on Bach’s chorales. A list with BWV numbers can be found here,,
  2. 2.
    Cope, D.: Experiments in Musical Intelligence, A-R edn. (1996)Google Scholar
  3. 3.
    De Prisco, R., Zaccagnino, R.: An Evolutionary Music Composer Algorithm for Bass Harmonization. In: Giacobini, M., et al. (eds.) EvoWorkshops 2008. LNCS, vol. 5484, pp. 567–572. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  4. 4.
    Ebcioglu, K.: An expert system for harmonizing four-part chorales. In: Machine models of music, pp. 385–401. MIT Press, Cambridge (1992)Google Scholar
  5. 5.
    Hild, H., Feulner, J., Menzel, W.: Harmonet, a neural net for harmonizing chorales in the style of J. S. Bach. In: Advances in Neural Information Processing Systems, vol. 4, pp. 267–274. Morgan Kaufmann, San Mateo (1992)Google Scholar
  6. 6.
    Lehmann, D.: Harmonizing melodies in real time: the connectionist approach. In: Proceedings of the International Computer Music Conference, Thessaloniki (1997)Google Scholar
  7. 7.
    Lehmann, D., Gang, D., Wagner, N.: Tuning neural network for harmonizing melodies in real-time. In: International Computer Music Conference, Ann-Arbor, Michigan (1998)Google Scholar
  8. 8.
    McIntyre, R.A.: Bach in a box: The evolution of four-part baroque harmony using a genetic algorithm. In: First IEEE Conference on Evolutionary Computation, pp. 852–857 (1994)Google Scholar
  9. 9.
    Miranda, E.R.: Composing Music with Computers. Focal Press (2001)Google Scholar
  10. 10.
    Phon-Amnuaisuk, S.: Composing Using Heterogeneous Cellular Automata. In: Giacobini, M., et al. (eds.) EvoWorkshops 2008. LNCS, vol. 5484, pp. 547–556. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  11. 11.
    Piston, W., DeVoto, M.: Harmony. W.W. Norton, New York (1987)Google Scholar
  12. 12.
    Schottstaedt, B.: Automatic species counterpoint. Tech Rep. STAN-M-19, Stanford University CCRMA. A short report appeared in Current Directions in Computer Music Research, Mathews, Pierce (eds.). MIT Press, Cambridge (1989)Google Scholar
  13. 13.
    Wiggins, G., Papadopoulos, G., Phon-Amnuaisuk, S., Tuson, A.: Evolutionary methods for musical composition. International Journal of Computing Anticipatory Systems (1999)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Roberto De Prisco
    • 1
  • Antonio Eletto
    • 1
  • Antonio Torre
    • 1
  • Rocco Zaccagnino
    • 1
  1. 1.Dipartimento di Informatica ed ApplicazioniUniversity of SalernoItaly

Personalised recommendations