Lexical tree decoging with a class-based language model for Chinese speech recognition
Refereed conference paper presented and published in conference proceedings

Full Text

Times Cited

Other information
AbstractThis paper presents a method to integrate the class bigram language model effectively to the lexical tree decoder. The method reduces the memory requirement and search effort in comparison with the conventional lexical tree search with word bigram language model. The decoder is based on a timesynchronous beam search, using cross-word triphone acoustic model. To demonstrate its effectiveness, the algorithm is tested with a stock query task. Experimental results show that the lexical tree decoder based on a class bigram can reduce the search space by 11.8%. By using class-bigram look-ahead, the memory cost for storing the look-ahead probability can also achieve a saving of 73% without degradation in recognition accuracy.
All Author(s) ListChoi W.N., Wong Y.W., Lee T., Ching P.C.
Name of Conference6th International Conference on Spoken Language Processing, ICSLP 2000
Start Date of Conference16/10/2000
End Date of Conference20/10/2000
Place of ConferenceBeijing
Country/Region of ConferenceChina
LanguagesEnglish-United Kingdom

Last updated on 2020-06-09 at 01:34