Second International Conference on Spoken Language Processing (ICSLP'92)

Banff, Alberta, Canada
October 13-16, 1992

The Effect of Information Feedback on the Performance of a Phoneme Recognizer Using Kohonen Map

Takuya Koizumi, Jyoji Urata, Shuji Taniguchi

Dept of Information Science, Fukui University, Fukui, Japan

This paper deals with a new phoneme recognition system with information feedback comprising a learning vector quantizer (LVQ) and hidden Markov models (HMMs). This system aims at achieving higher phoneme recognition rates than conventional LVQ-HMM systems, incorporating a feedback of information on the classification of input phoneme which is obtained from the out-put of the LVQ. 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 are higher than those accomplished with conventional LVQ-HMM phoneme recognizers which have no information feedback.

Full Paper

Bibliographic reference.  Koizumi, Takuya / Urata, Jyoji / Taniguchi, Shuji (1992): "The effect of information feedback on the performance of a phoneme recognizer using kohonen map", In ICSLP-1992, 1363-1366.