Advertisement

Comparing B-Spline and Spline Models for F0 Modelling

  • Damien Lolive
  • Nelly Barbot
  • Olivier Boëffard
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4188)

Abstract

This article describes a new approach to estimate F 0 curves using B-spline and Spline models characterized by a knot sequence and associated control points. The free parameters of the model are the number of knots and their location. The free-knot placement, which is a NP-hard problem, is done using a global MLE (Maximum Likelihood Estimation) within a simulated-annealing strategy. Experiments are conducted in a speech processing context on a 7000 syllables french corpus. We estimate the two challenging models for increasing values of the number of free parameters. We show that a B-spline model provides a slightly better improvement than the Spline model in terms of RMS error.

Keywords

Spline Function Spline Model Quadratic Spline Quadratic Distance Melodic Contour 
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.
    Raux, A., Black, A.: A unit selection approach to f0 modeling and its application to emphasis. In: Proc. ASRU Conf., pp. 700–703 (2003)Google Scholar
  2. 2.
    Hirst, D., Cristo, A.D., Espesser, R.: Levels of representation and levels of analysis for the description of intonation systems. In: Horne, M. (ed.) Prosody: Theory and Experiment, vol. 14, pp. 51–87. Kluwer Academic Pusblisher, Dordrecht (2000)Google Scholar
  3. 3.
    Taylor, P.: Analysis and synthesis of intonation using the tilt model. J. Acoust. Soc. America 107, 1697–1714 (2000)CrossRefGoogle Scholar
  4. 4.
    Sakai, S., Glass, J.: Fundamental frequency modeling for corpus-based speech synthesis based on statistical learning techniques. In: Proc. ASRU Conf., pp. 712–717 (2003)Google Scholar
  5. 5.
    Barbot, N., Boeffard, O., Lolive, D.: F0 stylisation with a free-knot b-spline model and simulated-annealing optimization. In: Proc. Eurospeech Conf., pp. 325–328 (2005)Google Scholar
  6. 6.
    Ingber, L.: Adaptive simulated annealing (asa): lessons learned. Control and Cybernetics 25, 33–54 (1996)MATHGoogle Scholar
  7. 7.
    Mouline, S., Boeffard, O., Bagshaw, P.: Automatic adaptation of the momel f 0 stylisation algorithm to new corpora. In: Proc. of ICSLP (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Damien Lolive
    • 1
  • Nelly Barbot
    • 1
  • Olivier Boëffard
    • 1
  1. 1.IRISA / Université de Rennes 1 – ENSSATLannion

Personalised recommendations