Cookies Policy

This site uses cookies. By continuing to browse the site you are agreeing to our use of cookies.

I accept this policy

Find out more here

Handling Disfluencies in Spontaneous Language Models

Brill’s MyBook program is exclusively available on BrillOnline Books and Journals. Students and scholars affiliated with an institution that has purchased a Brill E-Book on the BrillOnline platform automatically have access to the MyBook option for the title(s) acquired by the Library. Brill MyBook is a print-on-demand paperback copy which is sold at a favorably uniform low price.

Access this chapter

+ Tax (if applicable)

Chapter Summary

In automatic speech recognition, a stochastic language model (LM) predicts the probability of the next word on the basis of previously recognized words. For the recognition of dictated speech this method works reasonably well since sentences are typically well-formed and reliable estimation of the probabilities is possible on the basis of large amounts of written text material. However, for spontaneous speech the situation is quite different: disfluencies distort the normal flow of sentences and written transcripts of spontaneous speech are too scarce to train good stochastic LMs. Both factors contribute to the poor performance of automatic speech recognizers on spontaneous input. In this paper we investigate how one specific approach to disfluencies in spontaneous language modeling influences recognition performance.



Can't access your account?
  • Tools

  • Add to Favorites
  • Printable version
  • Email this page
  • Recommend to your library

    You must fill out fields marked with: *

    Librarian details
    Your details
    Why are you recommending this title?
    Select reason:
    Computational Linguistics in the Netherlands 2002 — Recommend this title to your library
  • Export citations
  • Key

  • Full access
  • Open Access
  • Partial/No accessInformation