Advertisement

Concurrent Constraint Programming and Tree–Based Acoustic Modelling

  • Moritz Neugebauer
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3132)

Abstract

The design of acoustic models is key to a reliable connection between acoustic waveform and linguistic message in terms of individual speech units. We present an original application of concurrent constraint programming in this important area of spoken language processing. The application presented here employs concurrent constraint programming – represented by Mozart/Oz [1] – to overcome the problem of sparse training data in order to provide context-dependent acoustic models for automatic speech recognition.

References

  1. 1.
    Smolka, G.: The Oz programming model. In: van Leeuwen, J. (ed.) Computer Science Today. LNCS, vol. 1000, pp. 324–343. Springer, Heidelberg (1995)CrossRefGoogle Scholar
  2. 2.
    Young, S.J., Odell, J.J., Woodland, P.C.: Tree-based state tying for high accuracy acoustic modelling. In: Proceedings of the ARPA Human Language Technology Workshop, Plainsboro, NJ, pp. 307–312 (1994)Google Scholar
  3. 3.
    Neugebauer, M.: Constraint Programming and Subphonetic Acoustic Modelling. PhD thesis, Department of Computer Science, University College Dublin (in preparation)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Moritz Neugebauer
    • 1
  1. 1.Department of Computer ScienceUniversity College DublinDublin 4Ireland

Personalised recommendations