Time-first search for large vocabulary speech recognition

@inproceedings{Robinson1998TimefirstSF,
  title={Time-first search for large vocabulary speech recognition},
  author={Tony Robinson and James Christie},
  booktitle={ICASSP},
  year={1998}
}
This paper describes a new search technique for large vocabu lary speech recognition based on a stack decoder. Considerable m emory savings are achieved with the combination of a tree based lexicon and a new search technique. The search proceeds time-fir st, that is partial path hypotheses are extended into the future in the inner loop and a tree walk over the lexicon is performed as an outer loop. Partial word hypotheses are grouped based on lan guage model state. The stack maintains… CONTINUE READING
Highly Cited
This paper has 54 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 29 extracted citations

54 Citations

01020'98'02'07'12'17
Citations per Year
Semantic Scholar estimates that this publication has 54 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-9 of 9 references

Apparatus and method for determining a likely word sequence from labels generated by an acoustic processor

  • L. R. Bahl, F. Jelinek
  • US Patent 4,748,670,
  • 1988
Highly Influential
4 Excerpts

Efficient Algorithms for Speech Recognition

  • Mosur K. Ravishankar
  • PhD thesis, Carnegie Mellon University,
  • 1996
2 Excerpts

The Use of Context in Large Vocabulary Speech Recognition

  • Julian James Odell
  • PhD thesis,
  • 1995
3 Excerpts

tilingual large vocabulary speech recognition : the European SQALE project

  • S. J. Young, M. Adda-Dekker, +8 authors H. J. M. Steeneken
  • Computer Speech and Language

Similar Papers

Loading similar papers…