Introducing statistical dependencies and structural constraints in variable-length sequence models

  • Sabine Deligne
  • François Yvon
  • Frédéric Bimbot
Session: Interference of Stochastic Models 1
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1147)

Keywords

Training Corpus Adjacent Pair IEEE Signal Processing Letter Grammatical Inference Bigram Model 
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.
    Frédéric Bimbot, Roberto Pieraccini, Esther Levin, and Bishnu Atal. Variable length sequence modeling: Multigrams. IEEE Signal Processing Letters, 2(6), 1995.Google Scholar
  2. 2.
    Sabine Deligne and Frédéric Bimbot. Language modelling by variable length sequences: theoretical formulation and evaluation of multigrams. In Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP), 1995.Google Scholar
  3. 3.
    Sabine Deligne, Frédéric Bimbot, and François Yvon. Phonetic transcription by variable length sequences: joint multigrams. In Proceedings of the European Conference on Speech Communication and Technology (Eurospeech), Madrid, Sept. 1995.Google Scholar
  4. 4.
    A. P. Dempster, N. M. Laird, and D. B. Rubin. Maximum-likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society, 39(1):1–38, 1977.Google Scholar
  5. 5.
    Guy Pérennou, Monique de Calmès, Isabelle Ferrané, and Jean-Marie Pécatte. Le projet BDLEX de base de données lexicales du français écrit et parlé. Actes du séminaire lexique, Toulouse, Janv. 1992.Google Scholar
  6. 6.
    Kari Torkolla. An efficient way to learn English grapheme-to-phoneme rules automatically. In Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP), volume 2, Minneapolis, Apr. 1993.Google Scholar
  7. 7.
    François Yvon. Grapheme-to-phoneme conversion using multiple unbounded overlapping chunks. In Proceeding of NeMLap 'II, Ankara, Turkey, 1996.Google Scholar
  8. 8.
    François Yvon. Prononcer par analogie: motivations, formalisations et évaluations. PhD thesis, École Nationale Supérieure des Télécommunications, Paris, 1996.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • Sabine Deligne
    • 1
  • François Yvon
    • 1
  • Frédéric Bimbot
    • 1
  1. 1.ENST-Dept. Signal & Dept. InformatiqueCNRS-URA 820Paris cedex 13France, European Union

Personalised recommendations