Prediction of Notes from Vocal Time Series: An Overview

  • Claus Weihs
  • Uwe Ligges
  • Ursula Garczarek
Part of the Studies in Classification, Data Analysis, and Knowledge Organization book series (STUDIES CLASS)


This paper deals with the prediction of notes from vocal time series. Different kinds of classification algorithms using different amounts of background information are described and compared. The results of the methods are presented by an transcription algorithm into musical notes.


Independent Component Analysis Radial Basis Function Kernel Misclassification Rate Quadratic Loss Function Note Classification 
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. VON AMELN, F. (2001): Blind source separation in der Praxis. Diploma Thesis, Fachbereich Statistik, Universität Dortmund, Germany.Google Scholar
  2. CANO, P., LOSCOS, A., and BONADA, J. (1999): Score-Performance Matching using HMMs. In: Proceedings of the International Computer Music Conference. Beijing, China.Google Scholar
  3. CEMGIL, T., DESAIN, P., and KAPPEN, B. (2000): Rhythm Quantization for Transcription. Computer Music Journal 24(2), 60–76.CrossRefGoogle Scholar
  4. CHAPELLE, O., VAPNIK, V., BOUSQUET, O., and MUKHERJEE, S. (2001): Choosing Multiple Parameters for Support Vector Machines. Machine Learning, 46, 131.CrossRefGoogle Scholar
  5. DIXON, S. (1996): Multiphonic Note Identification. Australian Computer Science Communications, 17(1), 318–323.Google Scholar
  6. GARCZAREK, U., WEIHS, C., and LIGGES, U. (2003): Prediction of Notes from Vocal Time Series. Technical Report 1/2003, SFB475, Department of Statistics, University of Dortmund. Scholar
  7. HYVÄRINEN, A., KARHUNEN, J., and OJA, E. (2001): Independent Component Analysis. Wiley, New York.Google Scholar
  8. IHAKA, R. and GENTLEMAN, R. (1996): R: A Language for Data Analysis and Graphics. Journal of Computational and Graphical Statistics, 5(3), 299–314.CrossRefGoogle Scholar
  9. LIGGES, U., WEIHS, C., and HASSE-BECKER, P. (2002): Detection of Locally Stationary Segments in Time Series. In: W. Härdle and B. Rönz (Eds.): Comp-Stat2002 — Proceedings in Computational Statistics — 15th Symposium held in Berlin, Germany. Physika Verlag, Heidelberg, 285–290.Google Scholar
  10. NIENHUYS, H.-W., NIEUWENHUIZEN, J., et al. (2002): GNU LilyPond — The Music Typesetter. Free Software Foundation,, Version 1.6.5.Google Scholar
  11. PREUSSER, A., LIGGES, U., and WEIHS, C. (2002): Ein R Exportfilter für das Notations-und Midi-Programm LilyPond. Arbeitsbericht 35, Fachbereich Statistik, Universität Dortmund, Germany. Scholar
  12. ROSSIGNOL, S., DEPALLE, P., SOUMAGNE, J., RODET, X., and COLLETTE, J.-L. (1999): Vibrato: Detection, Estimation, Extractiom, Modification. In: Proceedings 99 Digital Audio Effects Workshop.Google Scholar
  13. SCHOLKOPF, B. (1998): Support-Vektor-Lernen. In: G. Hotz et al. (Eds.): Ausgezeichnete Informatikdissertationen. Teubner, Stuttgart, 135–150.Google Scholar
  14. SCHWAIGHOFER, A. (2002): SVM toolbox for Matlab. Scholar
  15. SEIDNER, W. and WENDLER, J. (1997): Die Sängerstimme. Henschel, Berlin.Google Scholar
  16. VAPNIK, V. (1995): The Nature of Statistical Learning Theory. Springer, New York.Google Scholar
  17. WEIHS, C., BERGHOFF, S., HASSE-BECKER, P., and LIGGES, U. (2001): Assessment of Purity of Intonation in Singing Presentations by Discriminant Analysis. In: J. Kunert and G. Trenkler (Eds.): Mathematical Statistics and Biometrical Applications. Josef Eul, Bergisch-Gladbach, Köln, 395–410.Google Scholar
  18. WEIHS, C. and LIGGES, U. (2003): Automatic Transcription of Singing Performances. Research Report 03/1, Department of Statistics, University of Dortmund. Scholar

Copyright information

© Springer-Verlag Berlin · Heidelberg 2005

Authors and Affiliations

  • Claus Weihs
    • 1
  • Uwe Ligges
    • 1
  • Ursula Garczarek
    • 1
  1. 1.Fachbereich StatistikUniversität DortmundDortmundGermany

Personalised recommendations