Skip to main content
SpringerLink
Log in

Statistical Approach to Automatic Expressive Rendition of Polyphonic Piano Music

  • Chapter
  • First Online:
Book cover Guide to Computing for Expressive Music Performance

Abstract

In this chapter, we discuss how to render expressive polyphonic piano music through a statistical approach. Generating polyphonic expression is an important element in achieving automatic expressive piano performance since the piano is a polyphonic instrument. We will start by discussing the features of polyphonic piano expression and present a method for modeling it based on an approximation involving melodies and harmonies. An experimental evaluation indicates that performances generated with the proposed method achieved polyphonic expression and created an impression of expressiveness. In addition, performances generated with models trained on different performances were perceptually distinguishable by human listeners. Finally, we introduce an automatic expressive piano system called Polyhymnia that won the first place in the autonomous section of Performance Rendering Contest for Computer Systems (RenCon) 2010.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 54.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    Six nonmusicians, 17 hobbyist musicians, and 2 professional musicians participated in the experiment.

  2. 2.

    Differences in the average scores were tested using analysis of variance and its post-hoc test using TukeyHSD algorithm implemented in GNU R.

  3. 3.

    Polyhymnia is one of the nine muses in Greek mythology, and it also means choral poetry or multiple hymns.

  4. 4.

    Two professional musicians, 13 hobbyist musicians, and 2 nonmusicians participated in the listening experiments.

  5. 5.

    F. Chopin, Prelude No. ~ 1, 4, 7, 15, 20, Etude Op. ~ 10-3, 10–4, 25–11, Waltz Op. ~ 18, 34–2, 64–2, 69–1, 69–2, Nocturne No. ~ 2 and 10.

  6. 6.

    W. A. Mozart, Piano Sonata KV279-1, 279–2, 279–3, 331–1, 545–1, 545–2 and 545-3.

  7. 7.

    W. A. Mozart, Klavierstück, KV. 33, W. A. Mozart, Sonatina No. 41, KV. 439, F. Chopin, Mazurka No. 19, Op. 30.

References

  1. Berger AL (1997) The improved iterative scaling algorithm: a gentle introduction, Carnegie Mellon University

    Google Scholar 

  2. Bottou L (1991) Stochastic gradient learning in neural networks. In Proceedings of Neuro-Nimes 91

    Google Scholar 

  3. Darroch J, Ratcliff D (1972) Generalized iterative scaling for log-linear models. Ann Math Stat 43:1470–1480

    Article  MathSciNet  MATH  Google Scholar 

  4. Flossmann S, Grachten M, Widmer G (2009) Expressive performance rendering: introducing performance context. In Proceedings of the SMC, pp 155–160

    Google Scholar 

  5. Friberg A, Bresin R, Sundberg J (2006) Overview of the KTH rule system for musical performance. Adv Cogn Psychol 2(2):145–161

    Article  Google Scholar 

  6. Gabrielsson A (1985) Interplay between analysis and synthesis in studies of music performance and music experience. Music Percept 3:59–86

    Article  Google Scholar 

  7. Gieseking A, Leimer K (1972) Piano technique. Dover, New York

    Google Scholar 

  8. Grindlay G, Helmhold D (2006) Modeling, analyzing, and synthesizing expressive piano performance with graphical models. Mach Learn 65:361–387

    Article  Google Scholar 

  9. Hashida M, Matsui T, Katayose H (2008) A new database describing deviation information of performance expressions. In Proceedings of the ISMIR, pp 489–494

    Google Scholar 

  10. Huron D, Fantini D (1989) The avoidance of inner-voice entries: perceptual evidence and musical practice. Music Percept 7(1):43–48

    Article  Google Scholar 

  11. Lafferty J, McCallum A, Pereira F (2011) Conditional random fields: probabilistic models for segmenting and labeling sequence data. In Proceedings of the ML, pp 282–289

    Google Scholar 

  12. Lehvinne J (1972) Basic principle in pianoforte playing. Dover, New York

    Google Scholar 

  13. Lerdahl F, Jackendoff R (1983) A generative theory of tonal music. MIT Press, Cambridge, MA

    Google Scholar 

  14. Mazzola G (2002) The topos of music – geometric logic of concept, theory, and performance. Birkenhäuser, Basel/Boston

    Google Scholar 

  15. MusicXML, Recordare llc., http://www.recordare.com/musicxml

  16. Palmer C (1997) Music performance. Ann Rev Psychol 48:115–138

    Article  Google Scholar 

  17. Pancutt R (2003) Accents and expression in piano performance. In: Niemöller KW (ed) Perspektiven und Methoden einer Systemischen Musikwissenschaft, Systemische Musikwissenschaft. Peter Lang, Frankfurt am Main, pp 163–185

    Google Scholar 

  18. Pietra SD, Pietra VD, Lafferty J (1995) Inducing features of random fields. Technical Report, CMU-CS-95–144, Carnegie Mellon University

    Google Scholar 

  19. Repp BH (1992) Diversity and commonality in music performance: an analysis of timing microstructure in Schumann’s “Trämerei”. J Acoust Soc Am 92(5):2546–2568

    Article  Google Scholar 

  20. Sha F, Pereira F (2003) Shallow parsing with conditional random fields. In Proceedings of Human Language Technology, NAACL

    Google Scholar 

  21. Sundberg J, Askenfelt A, Frydèn L (1983) Musical performance: a synthesis-by-rule approach. Comp Music J 7(1):37–43

    Article  Google Scholar 

  22. Suzuki T, Tokunaga T, Tanaka H (1999) Case-based approach to the generation of musical expression. In Proceedings of the IJCAI, pp 642–648

    Google Scholar 

  23. Teramura K, Okuma H (2008) Gaussian process regression for rendering music performance. In Proceedings of the ICMPC

    Google Scholar 

  24. Teramura K, Maeda S (2010) Statistical learning of tempo variation for imitating piano performance (in Japanese). IPSJ Tech Rep., vol. 85, no. 12

    Google Scholar 

  25. Wallach HM (2002) Efficient training of conditional random fields. Master’s thesis, University of Edinburgh

    Google Scholar 

  26. Widmer G, Dixon S, Goebl W, Pampalk E, Tobudic A (2003) In search of the Horowitz factor. AI Mag 24(3):111–130

    Google Scholar 

Download references

Acknowledgments

This work was partially funded by CrestMuse Project of Japan Science and Technology Agency and supported by Samsung Scholarship Foundation.

Author information

Authors and Affiliations

  1. Audio Communication Group, Technische Universitat Berlin, Einsteinufer 17c, 10587, Berlin, Germany

    Tae Hun Kim

  2. Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan

    Satoru Fukayama & Shigeki Sagayama

  3. Olarbee Japan, Hiroshima, Japan

    Takuya Nishimoto

Authors
  1. Tae Hun Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Satoru Fukayama
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Takuya Nishimoto
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Shigeki Sagayama
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Tae Hun Kim .

Editor information

Editors and Affiliations

  1. ICCMR, University of Plymouth, Smeaton Building 206, Plymouth, PL4 8AA, Devon, United Kingdom

    Alexis Kirke

  2. Computing, Communication & Electronics, University of Plymouth, Plymouth, PL4 8AA, United Kingdom

    Eduardo R. Miranda

Questions

Questions

  1. 1.

    What is one of the key factors in the expressive ability of the piano?

  2. 2.

    Name three benefits of the statistical modeling approach for modeling expressive performance.

  3. 3.

    Highlight four features of musical expression in polyphonic performances.

  4. 4.

    What is the difference in the model between harmonic dependency and melodic dependency?

  5. 5.

    What dynamic programming technique can be efficiently used to calculate the musical expression?

  6. 6.

    In what forum has Polyhymnia been independently evaluated, and what was the result?

  7. 7.

    What statistical method with hidden state transition functionality is at the heart of Polyhymnia’s learning and modeling algorithm?

  8. 8.

    Why is MusicXML able to encode much better than MIDI?

  9. 9.

    In a crescendo or diminuendo, if sound intensity is changing exponentially, what is the human perception of the loudness?

  10. 10.

    In Polyhymnia, how is loudness determined for mordents, turns, trills, and grace notes?

Rights and permissions

Reprints and permissions

Copyright information

© 2013 Springer-Verlag London

About this chapter

Cite this chapter

Kim, T.H., Fukayama, S., Nishimoto, T., Sagayama, S. (2013). Statistical Approach to Automatic Expressive Rendition of Polyphonic Piano Music. In: Kirke, A., Miranda, E. (eds) Guide to Computing for Expressive Music Performance. Springer, London. https://doi.org/10.1007/978-1-4471-4123-5_6

Download citation

  • DOI: https://doi.org/10.1007/978-1-4471-4123-5_6

  • Published:

  • Publisher Name: Springer, London

  • Print ISBN: 978-1-4471-4122-8

  • Online ISBN: 978-1-4471-4123-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation