Sixth International Conference on Spoken Language Processing
(ICSLP 2000)

Beijing, China
October 16-20, 2000

Speech Recognition based on Estimation of Mutual Information

Yibiao Yu, Heming Zhao

Department of Communication and Electronic Engineering, Soochow University, Suzhou, China

This paper proposed a pattern matching algorithm based on estimation of mutual information for speech recognition. The preliminary experiments on connected Chinese digits recognition show 97% of test digits were recognized correctly with 4 times much less time consume than DTW or HMM, and it was 6% higher than which gotten by conventional DTW with same experiments data and condition. According to our experiments, the proposed algorithm can be considered as an applicable effective matching method for speech recognition especially for monosyllable word recognition.


Full Paper

Bibliographic reference.  Yu, Yibiao / Zhao, Heming (2000): "Speech recognition based on estimation of mutual information", In ICSLP-2000, vol.2, 1046-1049.