DocumentCode :
2780248
Title :
A mandarin speech recognition result evaluation algorithm on mixed words
Author :
Liu, Gang ; Chen, Wei ; Guo, Yujing ; Guo, Jun
Author_Institution :
Pattern Recognition & Intell. Syst. Lab., Beijing Univ. of Posts & Telecommun., Beijing, China
fYear :
2009
fDate :
6-8 Nov. 2009
Firstpage :
695
Lastpage :
700
Abstract :
Speech recognition result is always evaluated by dynamic programming algorithm which can find the best match between recognized results and references. And the match unit could be word, syllable, phone and so on. However, in mandarin speech recognition, this traditional algorithm is not accurate because of the unique characteristics of Chinese word-formation. In order to improve evaluation performance on Chinese, we proposed a mandarin speech recognition evaluation algorithm based on mixed words. Our experiments show that our proposed algorithm can effectively reduce the false error caused by traditional evaluation algorithm.
Keywords :
dynamic programming; performance evaluation; speech recognition; Chinese word-formation; dynamic programming algorithm; evaluation performance; mandarin speech recognition; mixed words; Dynamic programming; Heuristic algorithms; Hidden Markov models; Intelligent systems; Laboratories; Natural languages; Pattern matching; Pattern recognition; Speech recognition; Testing; Dynamic Programming; Mixed Words; Result Evaluation; Speech Recognition;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Network Infrastructure and Digital Content, 2009. IC-NIDC 2009. IEEE International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-4898-2
Electronic_ISBN :
978-1-4244-4900-6
Type :
conf
DOI :
10.1109/ICNIDC.2009.5360786
Filename :
5360786
Link To Document :
بازگشت