Title :
N-best speech hypothesis reordering based on comprehensive information theory
Author :
Liu, Jianyi ; Zhong, Yixin
Author_Institution :
Res. Center of Intelligence, Beijing Univ. of Posts & Telecommun., China
Abstract :
This paper proposes a hypothesis reordering technique, based on a newly established theory, namely comprehensive information theory, to improve the accuracy of speech recognition in a man-machine dialog system. For each hypothesis, we calculate the amount of comprehensive information that hypothesis provided and then reorder N-best hypothesis according to the amount of comprehensive information. Results of experiments have shown its effectiveness.
Keywords :
heuristic programming; information theory; interactive systems; speech recognition; N-best speech hypothesis reordering; comprehensive information theory; man-machine dialog system; speech recognition; Error analysis; Humans; Information resources; Information theory; Intelligent systems; Man machine systems; Natural language processing; Natural languages; Speech processing; Speech recognition;
Conference_Titel :
Natural Language Processing and Knowledge Engineering, 2003. Proceedings. 2003 International Conference on
Conference_Location :
Beijing, China
Print_ISBN :
0-7803-7902-0
DOI :
10.1109/NLPKE.2003.1275865
