DocumentCode :
1932879
Title :
Boosting the accuracy of a 100000-word Japanese speech recognition system
Author :
Kimura, Shinta ; Yamazaki, Yasushi
Author_Institution :
Fujitsu Labs. Ltd., Kawasaki, Japan
fYear :
1991
fDate :
14-17 Apr 1991
Firstpage :
717
Abstract :
The authors describe some techniques for boosting the accuracy of a 100000-word Japanese speech recognition system. They review the structure and performance of the system and introduce two methods for improving the recognition accuracy. One method involves the selection of the training word set, and the other involves the number of word candidates selected by the preselection method. A method for reducing the amount of computation is also proposed. The performance of the improved system is evaluated. The top-20 recognition error rate was 1.5% for 10000 test utterances of five females and five males. The improved system could reduce top-20 recognition errors by 75% without a significant increase in computation
Keywords :
performance evaluation; speech recognition; Japanese speech recognition system; performance evaluation; preselection method; recognition accuracy; recognition error rate; reduced computation; training word set; Acoustic testing; Acoustic waves; Boosting; Dynamic programming; Error analysis; Laboratories; Loudspeakers; Speech analysis; Speech recognition; Vocabulary;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference on
Conference_Location :
Toronto, Ont.
ISSN :
1520-6149
Print_ISBN :
0-7803-0003-3
Type :
conf
DOI :
10.1109/ICASSP.1991.150440
Filename :
150440
Link To Document :
بازگشت