Advertisement

Learning the Long-Term Structure of the Blues

  • Douglas Eck
  • Jürgen Schmidhuber
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2415)

Abstract

In general music composed by recurrent neural networks (RNNs) suffers from a lack of global structure. Though networks can learn note-by-note transition probabilities and even reproduce phrases, they have been unable to learn an entire musical form and use that knowledge to guide composition. In this study, we describe model details and present experimental results showing that LSTM successfully learns a form of blues music and is able to compose novel (and some listeners believe pleasing) melodies in that style. Remarkably, once the network has found the relevant structure it does not drift from it: LSTM is able to play the blues with good timing and proper structure as long as one is willing to listen.

Keywords

Recurrent Neural Network Cell Block Music Composition Musical Form Sheet Music 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    J. J. Bharucha and P. M. Todd. Modeling the perception of tonal structure with neural nets. Computer Music Journal, 13(4):44–53, 1989.CrossRefGoogle Scholar
  2. 2.
    F. A. Gers, J.A. Perez-Ortiz, D. Eck, and J. Schmidhuber. DEKF-LSTM. In Proc. 10th European Symposium on Artifical Neural Networks, ESANN 2002, 2002.Google Scholar
  3. 3.
    F. A. Gers and J. Schmidhuber. Recurrent nets that time and count. In Proc. IJCNN’2000, Int. Joint Conf. on Neural Networks, Como, Italy, 2000.Google Scholar
  4. 4.
    F. A. Gers and J. Schmidhuber. LSTM recurrent networks learn simple context free and context sensitive languages. IEEE Transactions on Neural Networks, 12(6):1333–1340, 2001.CrossRefGoogle Scholar
  5. 5.
    S. Hochreiter, Y. Bengio, P. Frasconi, and J. Schmidhuber. Gradient flow in recurrent nets: the difficulty of learning long-term dependencies. In S. C. Kremer and J. F. Kolen, editors, A Field Guide to Dynamical Recurrent Neural Networks. IEEE Press, 2001.Google Scholar
  6. 6.
    Sepp Hochreiter and Juergen Schmidhuber. Long Short-Term Memory. Neural Computation, 9(8):1735–1780, 1997.CrossRefGoogle Scholar
  7. 7.
    Michael C. Mozer. Induction of multiscale temporal structure. In D. S. Lippman, J. E. Moody, and D. S. Touretzky, editors, Advances in Neural Information Processing Systems 4, pages 275–282. San Mateo, CA: Morgan Kaufmann, 1992.Google Scholar
  8. 8.
    Michael C. Mozer. Neural network composition by prediction: Exploring the benefits of psychophysical constraints and multiscale processing. Cognitive Science, 6:247–280, 1994.Google Scholar
  9. 9.
    Juan Antonio Pérez-Ortiz, Juergen Schmidhuber, Felix A. Gers, and Douglas Eck. Improving long-term online prediction with decoupled extended kalman filters. In Artificial Neural Networks — ICANN 2002 (Proceedings), 2002.Google Scholar
  10. 10.
    A. J. Robinson and F. Fallside. The utility driven dynamic error propagation network. Technical Report CUED/F-INFENG/TR.1, Cambridge University Engineering Department, 1987.Google Scholar
  11. 11.
    C. Stevens and J. Wiles. Representations of tonal music: A case study in the development of temporal relationship. In M.C. Mozer, P. Smolensky, D.S. Touretsky, J.L Elman, and A. S. Weigend, editors, Proceedings of the 1993 Connectionist Models Summer School, pages 228–235. Erlbaum, Hillsdale, NJ, 1994.Google Scholar
  12. 12.
    Peter M. Todd. A connectionist approach to algorithmic composition. Computer Music Journal, 13(4):27–43, 1989.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Douglas Eck
    • 1
  • Jürgen Schmidhuber
    • 1
  1. 1.Istituto Dalle Molle di Studi sull’Intelligenza Artificiale (IDSIA)MannoSwitzerland

Personalised recommendations