Towards the Optimal Minimization of a Pronunciation Dictionary Model

  • Simon Dobrišek
  • Janez Žibert
  • France Mihelič
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6231)


This paper presents the results of our efforts to obtain the minimum possible finite-state representation of a pronunciation dictionary. Finite-state transducers are widely used to encode word pronunciations and our experiments revealed that the conventional redundancy-reduction algorithms developed within this framework yield suboptimal solutions. We found that the incremental construction and redundancy reduction of acyclic finite-state transducers creates considerably smaller models (up to 60%) than the conventional, non-incremental (batch) algorithms implemented in the OpenFST toolkit.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Mohri, M., Pereira, F., Riley, M.: Weighted Finite-state Transducers in Speech Recognition. Computer Speech and Language 16, 69–88 (2002)CrossRefGoogle Scholar
  2. 2.
    Jelinek, F.: Statistical Methods for Speech Recognition. The MIT Press, Cambridge (1998)Google Scholar
  3. 3.
    Mohri, M., Pereira, F.C.N., Riley, M.: Speech Recognition with Weighted Finite-State Transducers. In: Rabiner, L., Juang, F. (eds.) Handbook on Speech Processing and Speech Communication, Part E: Speech recognition. Springer, Heidelberg (2008)Google Scholar
  4. 4.
    Allauzen, C., Riley, M., Schalkwyk, J., Skut, W., Mohri, M.: OpenFst: A General and Efficient Weighted Finite-State Transducer Library. In: Holub, J., Žďárek, J. (eds.) CIAA 2007. LNCS, vol. 4783, pp. 11–23. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  5. 5.
    Dobrišek, S., Vesnicer, B., Mihelič, F.: A Sequential Minimization Algorithm for Finite-State Pronounciation Lexicon Models. In: Proceedings of Interspeech 2009, International Speech Communication Association, Brighton, UK, pp. 720–723 (2009)Google Scholar
  6. 6.
    Aho, A.V., Sethi, R., Ullman, J.D.: Compilers, Principles, Techniques and Tools. Addison Wesley, Reading (1986)Google Scholar
  7. 7.
    Revuz, D.: Minimisation of Acyclic Deterministic Automata in Linear Time. Theoretical Computer Science 92, 181–189 (1992)MATHCrossRefMathSciNetGoogle Scholar
  8. 8.
    Spider – The Demonstration Implementation of the Algorithm for the Incremental Construction and Redundancy Reduction of Unweighted Acyclic FSTs,
  9. 9.
    Young, S., Evermann, G., Gales, M., Hain, T., Kershaw, D., Moore, G., Odell, J., Ollason, D., Povey, D., Valtchev, V., Woodland, P.: The HTK Book (for HTK Version 3.4). Cambridge University Engineering Department, Cambridge (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Simon Dobrišek
    • 1
  • Janez Žibert
    • 2
  • France Mihelič
    • 1
  1. 1.Faculty of Electrical EngineeringUniversity of LjubljanaLjubljanaSlovenia
  2. 2.Primorska Institute of Natural Sciences and TechnologyUniversity of PrimorskaKoperSlovenia

Personalised recommendations