Language modelling using a hidden Markov chain with application to automatic transcription of French stenotypy

  • Anne-Marie Derouault
  • Bernard Merialdo


Two kinds of problems arise in speech recognition: at the acoustic level (phonetic recognition), and at the linguistic level (lexical ambiguity).


Speech Recognition Language Modelling Speech Recognition System Lexical Ambiguity Linguistic Level 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Bahl, L.R., R. L. Mercer, F. Jelinek, A. Nadas, D. Nahamoo, M. Pitcheny (1983). Recognition of isolated words sentences from a 5000 word vocabulary office correspondence task. Proceedings of the ICASSP, Boston, 1065-1067.Google Scholar
  2. Baum, L.E. (1972). An inequality and associated maximization technique in statistical estimation of probabilistic functions of Markov process. Inequalities, vol.3, 1-8.Google Scholar
  3. Derouault, A.-M. and B. Merialdo (1984). Language modelling at the syntactic level. Proceedings of ICPR, Montreal.Google Scholar
  4. Jelinek, F. (1976). Continuous speech recognition by statistical methods. Proc IEEE 64, no 4, 532–556.CrossRefGoogle Scholar
  5. Merialdo, B. and A.-M. Derouault (1984). Recognition complexity with large vocabulary. Proceedings of ICCASP, San Diego.Google Scholar

Copyright information

© Springer Science+Business Media New York 1986

Authors and Affiliations

  • Anne-Marie Derouault
    • 1
  • Bernard Merialdo
    • 1
  1. 1.IBM-France Scientific CenterParisFrance

Personalised recommendations