A General Strategy for Hidden Markov Chain Parameterisation in Composite Feature-Spaces

  • David Windridge
  • Richard Bowden
  • Josef Kittler
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3138)

Abstract

A general technique for the construction of hidden Markov models (HMMs) from multiple-variable time-series observations in noisy experimental environments is set out. The proposed methodology provides an ICA-based feature-selection technique for determining the number, and the transition sequence, of underlying hidden states, along with the statistics of the observed-state emission characteristics. In retaining correlation information between features, the method is potentially far more general than Gaussian mixture model HMM parameterisation methods such as Baum-Welch re-estimation, to which we demonstrate our method reduces when an arbitrary separation of features, or an experimentally-limited feature-space is imposed.

Keywords

Hide Markov Model Independent Component Analysis Gaussian Mixture Model Independent Component Analysis Hide State 
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.

References

  1. 1.
    Baum, L., Eagon, J.: American Mathematical Society Bulletin, vol. 73, pp. 360–363 (1967)Google Scholar
  2. 2.
    Young, S., Odell, J., Ollason, D., Valtchev, V., Woodland, P.: The HTK Book for HTK Version 2.1. Cambridge University, Cambridge (1997)Google Scholar
  3. 3.
    Hyvärinen, A., Oja, E.: Independent Component Analysis: Algorithms and Applic ations. Neural Networks 13(4-5), 411–430 (2000)CrossRefGoogle Scholar
  4. 4.
    Comon, P.: Independent component analysis, A new concept? IEEE Signal Processing Mag. 36(3) (1994)Google Scholar
  5. 5.
    Devijver, P.A., Kittler, J.: ’Pattern Recognition: A Statistical Approach. Prentice-Hall, Englewood Cliffs (1982)MATHGoogle Scholar
  6. 6.
    Diaconis, P., Freedman, D.: Asymptotics of graphical projection pursuit. Ann. Stat. 12, 793–815 Google Scholar
  7. 7.
    Windridge, D., Bowden, R., Kittler, J. (Univ. of Surrey Technical Report: VSSP-TR- 3/2004), UNIS, UKGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • David Windridge
    • 1
  • Richard Bowden
    • 1
  • Josef Kittler
    • 1
  1. 1.Centre for Vision, Speech and Signal Processing, Dept. of Electronic & Electrical EngineeringUniversity of SurreyGuildfordUK

Personalised recommendations