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.
Work supported by SNF project 21-49144.96
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
J. J. Bharucha and P. M. Todd. Modeling the perception of tonal structure with neural nets. Computer Music Journal, 13(4):44–53, 1989.
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.
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.
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.
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.
Sepp Hochreiter and Juergen Schmidhuber. Long Short-Term Memory. Neural Computation, 9(8):1735–1780, 1997.
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.
Michael C. Mozer. Neural network composition by prediction: Exploring the benefits of psychophysical constraints and multiscale processing. Cognitive Science, 6:247–280, 1994.
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.
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.
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.
Peter M. Todd. A connectionist approach to algorithmic composition. Computer Music Journal, 13(4):27–43, 1989.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Eck, D., Schmidhuber, J. (2002). Learning the Long-Term Structure of the Blues. In: Dorronsoro, J.R. (eds) Artificial Neural Networks — ICANN 2002. ICANN 2002. Lecture Notes in Computer Science, vol 2415. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-46084-5_47
Download citation
DOI: https://doi.org/10.1007/3-540-46084-5_47
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-44074-1
Online ISBN: 978-3-540-46084-8
eBook Packages: Springer Book Archive