ISCA Archive ICSLP 2000
ISCA Archive ICSLP 2000

An efficient lexical tree search for large vocabulary continuous speech recognition

Jun Ogata, Yasuo Ariki

This paper describes an efficient search algorithm for a high speed and high accuracy LVCSR system. A conventionally used lexical tree search is an efficient method, but has a problem in incorporating the language probability. To solve this problem, we propose in this paper a newefficient search algorithm incorporating the language model structure. In our developed LVCSR, 2-pass search algorithm is adopted to produce a word graph as an intermediate expression. The experimental results on the 20,000-word Japanese dictation task showed that the proposed method can reduce approximately half of the processing time without increasing any errors.


Cite as: Ogata, J., Ariki, Y. (2000) An efficient lexical tree search for large vocabulary continuous speech recognition. Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000), vol. 2, 967-970

@inproceedings{ogata00_icslp,
  author={Jun Ogata and Yasuo Ariki},
  title={{An efficient lexical tree search for large vocabulary continuous speech recognition}},
  year=2000,
  booktitle={Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)},
  pages={vol. 2, 967-970}
}