Language Modeling for limited-data domains

@inproceedings{Hsu2009LanguageMF,
  title={Language Modeling for limited-data domains},
  author={Bo-June Paul Hsu},
  year={2009}
}
With the increasing focus of speech recognition and natural language processing applications on domains with limited amount of in-domain training data, enhanced system performance often relies on approaches involving model adaptation and combination. In such domains, language models are often constructed by interpolating component models trained from partially matched corpora. Instead of simple linear interpolation, we introduce a generalized linear interpolation technique that computes context… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 11 CITATIONS

Improving text recognition using optical and language model writer adaptation

Yann Soullard, Wassim Swaileh, +3 authors Chatelain
  • 2019
VIEW 1 EXCERPT
CITES METHODS

Handwriting Recognition with Multigrams

  • 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR)
  • 2017
VIEW 1 EXCERPT
CITES METHODS

Acoustic and language models adaptation for Indonesian spontaneous speech recognition

  • 2015 2nd International Conference on Advanced Informatics: Concepts, Theory and Applications (ICAICTA)
  • 2015

Toward Deep Learning Software Repositories

  • 2015 IEEE/ACM 12th Working Conference on Mining Software Repositories
  • 2015
VIEW 1 EXCERPT
CITES BACKGROUND

References

Publications referenced by this paper.
SHOWING 1-10 OF 158 REFERENCES

A probabilistic framework for segment-based speech recognition

  • Computer Speech & Language
  • 2003
VIEW 13 EXCERPTS
HIGHLY INFLUENTIAL

SRILM - an extensible language modeling toolkit

  • INTERSPEECH
  • 2002
VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

Numerical Recipes

William H. Press, Saul A. Teukolsky, William T. Vetterling, Brian P. Flannery
  • 2007
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

MAP adaptation of stochastic grammars

VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Unsupervised language model adaptation

VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

A maximum entropy approach to adaptive statistical language modelling

  • Computer Speech & Language
  • 1996
VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Similar Papers

Loading similar papers…