Third International Conference on Spoken Language Processing (ICSLP 94)

Yokohama, Japan
September 18-22, 1994

Simplified Sub-Neural-Networks for Accurate Phoneme Recognition

Takuya Koizumi, Shuji Taniguchi, Ken-ichi Hattori, Mikio Mori

Dept. of Information Science, Fukui University, Fukui, Japan

This paper deals with a new phoneme recognition system comprising a set of a simplified version of the sub-neural network and the hidden Markov models (HMMs). The ability of this system has been investigated by a phoneme recognition experiment using a number of Japanese words uttered by a native male speaker in a quiet environment. The result of the experiment shows that recognition rates achieved with this system is higher than those attained with the LVQ-HMM system which is known to be one of the most reliable phoneme recognizers.

Full Paper

Bibliographic reference.  Koizumi, Takuya / Taniguchi, Shuji / Hattori, Ken-ichi / Mori, Mikio (1994): "Simplified sub-neural-networks for accurate phoneme recognition", In ICSLP-1994, 1571-1574.