Skip to main content

Machine Improvisation in Music: Information-Theoretical Approach

  • 2014 Accesses

Abstract

This chapter introduces the methods and techniques of machine improvisation based on information-theoretical modeling of music, starting from the first 1998 universal classification modeling of music as an information source, style mixing using joint information source, variable-length motif dictionary improvisation based on universal prediction, and use of information dynamics for symbolic approximation in the factor oracle machine improvisation algorithm. Later developments include query-guided machine improvisation, free-energy modeling of music cognition, and reformulating of variational generative neural music models in terms of rate-distortion theory. This information-theoretical framework offers a novel view of man–machine creative music interaction as a communication problem between an artificial agent and a musician, seeking optimal trade-off between novelty and stylistic imitation under scarcity constraints.

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-030-72116-9_14
  • Chapter length: 32 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   269.00
Price excludes VAT (USA)
  • ISBN: 978-3-030-72116-9
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   349.99
Price excludes VAT (USA)
Hardcover Book
USD   349.99
Price excludes VAT (USA)
Fig. 14.1
Fig. 14.2
Fig. 14.3
Fig. 14.4
Fig. 14.5
Fig. 14.6
Fig. 14.7
Fig. 14.8
Fig. 14.9
Fig. 14.10
Fig. 14.11
Fig. 14.12
Fig. 14.13

Notes

  1. 1.

    The latent states do not correspond specifically to any music-theoretical notions such as harmony or rhythm, but are a rather generic formulation for any underlying cause that governs musical structure.

References

  1. Abdallah, S., & Plumbley, M. (2009). Information dynamics: Patterns of expectation and surprise in the perception of music. Connection Science, 21(2–3), 89–117. ISSN: 0954-0091.

    Google Scholar 

  2. Allauzen, C., Crochemore, M., & Raffinot, M. (1999). Factor oracle: A new structure for pattern matching. In SOFSEMÕ99: Theory and practice of informatics (pp. 295–310). Springer.

    Google Scholar 

  3. Assayag, G., et al. (1999). Computer-assisted composition at IRCAM: From PatchWork to OpenMusic. Computer Music Journal, 23(3), 59–72.

    CrossRef  Google Scholar 

  4. Barlow, H. B. (1961). Possible principles underlying the transformations of sensory messages. Sensory Communication, 217–234.

    Google Scholar 

  5. Berger, T. (1971). Rate distortion theory; a mathematical basis for data compression (Vol. xiii, 311 pp.). English. Englewood Cliffs, NJ: Prentice-Hall. ISSN: 0137531036.

    Google Scholar 

  6. Cover, T. M., & Thomas, J. (1991). Elements of information theory. Wiley.

    Google Scholar 

  7. Delerue , O., Assayag, G., & Dubnov, S. (1999). Guessing the composer’s mind: Applying universal prediction to musical style. In Proceedings of the International Computer Music Conference, ICMC98.

    Google Scholar 

  8. Dubnov, S. (1999). Stylistic randomness: About composing NTrope Suite. Organised Sound,4(2), 87–92.

    Google Scholar 

  9. Dubnov, S. (2011). Musical information dynamics as models of auditory anticipation. In W. Wang (Ed.), Machine audition: Principles, algorithms and systems (pp. 371–397). IGI Global.

    Google Scholar 

  10. Dubnov, S. (2019). Query-based deep improvisation. In International Conference on Computational Creativity, ICCC2019, Workshop on Musical Meta-Creation. Charlotte: University of North Carolina.

    Google Scholar 

  11. Dubnov, S., & Assayag, G. (2008). Memex and composer duets: Computer aided composition using style modeling and mixing. In Collection Musique Sciences ircam Delatour et al. (Eds.), Open music composers book 2. cote interne IRCAM.

    Google Scholar 

  12. Dubnov, S., Assayag, G., & Cont, A. (2011). Audio oracle analysis of musical information rate. In 2011 Fifth IEEE International Conference on Semantic Computing (ICSC) (pp. 567– 571). IEEE.

    Google Scholar 

  13. Dubnov, S., Koh, E. S., & Wright, D. (2018). Rethinking recurrent latent variable model for music composition. In IEEE 20th International Workshop on Multimedia Signal Processing (MMSP) (pp. 1–6). Vancouver, BC.

    Google Scholar 

  14. Feder, M., Merhav, N., & Gutman, M. (1992). Universal prediction of individual sequences. IEEE Transactions on Information Theory, 38, 1258–1270.

    MathSciNet  CrossRef  Google Scholar 

  15. Friston, K. (2012). The history of the future of the Bayesian brain. Neuroimage, 62(2), 1230–1233.

    CrossRef  Google Scholar 

  16. Harte, C., Sandler, M., & Gasser, M. (2006). Detecting harmonic change in musical audio. In Proceedings of Audio and Music Computing for Multimedia Workshop.

    Google Scholar 

  17. Higgins, I., et al. (2017). \(\beta \)-VAE: Learning basic visual concepts with a constrained variational framework. In ICLR.

    Google Scholar 

  18. Kingma, D. P., & Welling, M. (2013). Auto-encoding variational Bayes. In Proceedings of the 2nd International Conference on Learning Representations (ICLR).

    Google Scholar 

  19. Lefebvre, A., & Lecroq, T. (2002). Compror: On-line lossless data compression with a factor oracle. Information Processing Letters,83(1), 1–6.

    Google Scholar 

  20. Lefebvre, A., Lecroq, T., & Alexandre, J. (2003). An improved algorithm for finding longest repeats with a modified factor oracle. Journal of Automata, Languages and Combinatorics, 8(4), 647–657.

    MathSciNet  MATH  Google Scholar 

  21. Ron, D., Singer, Y., & Tishby, N. (1994). The power of amnesia. In J. D. Cowan, G. Tesauro, & J. Alspector (Eds.), Advances in neural information processing systems (Vol. 6, pp. 176–183). Morgan-Kaufmann.

    Google Scholar 

  22. Roy, P., Ghedini, F., & Pachet, F. (2016). Creating music and texts with flow machines. Multidisciplinary contributions to the science of creative thinking. Creativity in the twenty first century. Singapore: Springer.

    Google Scholar 

  23. Wainwright, M. J., & Jordan, M. I. (2008). Graphical models, exponential families, and variational inference. In Foundations and Trends in Machine Learning 1.1-2 (pp. 1–305).

    Google Scholar 

  24. Wang, C., & Dubnov, S. (2014). Guided music synthesis with variable Markov Oracle. In The 3rd International Workshop on Musical Metacreation, 10th Artificial Intelligence and Interactive Digital Entertainment Conference.

    Google Scholar 

  25. Wang, C., & Dubnov, S. (2014). Variable Markov Oracle: A novel sequential data points clustering algorithm with application to 3D gesture query-matching. In International Symposium on Multimedia (pp. 215–222). IEEE.

    Google Scholar 

  26. Wang, C., & Dubnov, S. (2015). Pattern discovery from audio recordings by Variable Markov Oracle: A music information dynamics approach. In Proceedings of 40th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

    Google Scholar 

  27. Wang, C., & Dubnov, S. (2015). Pattern discovery from audio recordings by variable Markov Oracle: A music information dynamics approach. In: 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP). IEEE.

    Google Scholar 

  28. Wang, C., & Dubnov, S. (2015). The variable Markov Oracle: Algorithms for human gesture applications. IEEE MultiMedia, 22(04), 52–67. ISSN: 1070-986X.

    Google Scholar 

  29. Ziv, J., & Lempel, A. (1977, May). A universal algorithm for sequential data compression. IEEE Transactions on Information Theory, 23(3), 337–343.

    Google Scholar 

  30. Ziv, J., & Lempel, A. (1978). Compression of individual sequences via variable-rate coding. IEEE Transactions on Information Theory,24(5), 530–536.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Shlomo Dubnov .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this chapter

Verify currency and authenticity via CrossMark

Cite this chapter

Dubnov, S. (2021). Machine Improvisation in Music: Information-Theoretical Approach. In: Miranda, E.R. (eds) Handbook of Artificial Intelligence for Music. Springer, Cham. https://doi.org/10.1007/978-3-030-72116-9_14

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-72116-9_14

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-72115-2

  • Online ISBN: 978-3-030-72116-9

  • eBook Packages: Computer ScienceComputer Science (R0)