Statistical Analysis of Left-to-Right Parser for Word-Hypothesing

  • H. Höge
  • E. Marschall
Conference paper
Part of the NATO ASI Series book series (volume 46)

Abstract

The recognition rate for fluently spoken speech achieved with beam search algorithms depend on factors as the perplexity and the recombination structure of the language model, the difficulty of the vocabulary, the quality of the acoustic phonetic decoder, and the chosen pruning strategy. In this paper a statistical model taking these factors in account is develloped. An iterative algorithm to calculate the score distribution of beam search paths and the resulting sentence error rate is presented.

Keywords

Recognition Rate Speech Segment Beam Search Successor Node Correct Path 
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.
This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. /1/.
    B. Lowere, R. Reddy: “The Harpy Speech Understanding System”, in: Trends in Speech Recognition, Prentice Hall (1980), pp. 340–360.Google Scholar
  2. /2/.
    J. Bridle et al.: “An Algorithm for Connected Word Recognition”, Proc. IEEE ASSP, Paris (1982), pp. 892–902.Google Scholar
  3. /3/.
    H. Ney: “The Use of a One-Stage Dynamic Programming Algorithm for Connected Word Recognition”, IEEE ICASSP-32 (1984), pp. 263–271.CrossRefGoogle Scholar
  4. /4/.
    H. Höge et al.: “Syllable-based Acoustic-Phonetic Decoding and Word Hypotheses Generation in Fluently Spoken Speech”, Proc. ICASSP-86, pp. 1561–1564.Google Scholar
  5. /5/.
    S.E. Levinson et al.: “An Introduction to the Application of the Theory of Probabilitic Functions of a Markov Process to Automatic Speech Recognition” BSTJ Vol. 62 (1983), pp. 1035–1074.MathSciNetMATHGoogle Scholar
  6. /6/.
    A. Adams, R. Bisiani: “The Carnegie-Mellon University Distributed Speech Recognition System”, Speech Technology (1986), pp. 14–23.Google Scholar
  7. /7/.
    H. Niemann et al.: “A System for Understanding German Speech”, Information Sciences, Vol. 3 (1984), pp. 87.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1988

Authors and Affiliations

  • H. Höge
    • 1
  • E. Marschall
    • 1
  1. 1.Zentrale Aufgaben Informationstechnik, MünchenSiemens AGMünchen 83F.R. Germany

Personalised recommendations