ISCA Archive ICSLP 1994
ISCA Archive ICSLP 1994

Chinese speech understanding and spelling-word translation based on the statistics of corpus

Jun Wu, Zuoying Wang, Jiasong Sun, Jin Guo

In this paper, a new natural language processing approach based on the statistics of corpus is proposed and has been successfully applied to THED-919 Chinese speech recognition system to eliminate acoustic recognition errors and to translate spellings into Chinese words. The accuracy rate of spelling-word translation of unrestricted text is 98.4% and 2/3 of acoustic recognition errors are eliminated. Keywords: Speech Recognition, Speech Understanding, Markov Chain, N-Gram Model.


Cite as: Wu, J., Wang, Z., Sun, J., Guo, J. (1994) Chinese speech understanding and spelling-word translation based on the statistics of corpus. Proc. 3rd International Conference on Spoken Language Processing (ICSLP 1994), 207-210

@inproceedings{wu94_icslp,
  author={Jun Wu and Zuoying Wang and Jiasong Sun and Jin Guo},
  title={{Chinese speech understanding and spelling-word translation based on the statistics of corpus}},
  year=1994,
  booktitle={Proc. 3rd International Conference on Spoken Language Processing (ICSLP 1994)},
  pages={207--210}
}