Stochastic automata for language modeling

  title={Stochastic automata for language modeling},
  author={Giuseppe Riccardi and Roberto Pieraccini and Enrico Bocchieri},
  journal={Computer Speech & Language},
Stochastic language models are widely used in spoken language understanding to recognize and interpret the speech signal: the speech samples are decoded into word transcriptions by means of acoustic and syntactic models and then interpreted according to a semantic model. Both for speech recognition and understanding, search algorithms use stochastic models to extract the most likely uttered sentence and its correspondent interpretation. The design of the language models has to be effective in… CONTINUE READING
72 Citations
25 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 72 extracted citations


Publications referenced by this paper.
Showing 1-10 of 25 references

Interpolated estimation of Markov source parameters from sparse data

  • F. Jelinek, R. L. Mercer
  • In Pattern Recognition in Practice,
  • 1980
Highly Influential
4 Excerpts

CHRONUS, the new generation

  • R. Pieraccini, E. Levin
  • In Proceedings of the Worshop on Spoken Language
  • 1995
1 Excerpt

Similar Papers

Loading similar papers…