4th International Conference on Spoken Language Processing
Philadelphia, PA, USA
This paper deals with a new phoneme recognition system based on a model of human auditory system. This system is made up of a model of human cochlea and a simple multi-layer recurrent neural network which has feedback connections of self-loop type. 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. The result of the experiment shows that recognition accuracies achieved with this system in the presence of noise are higher than those obtained by a combination of frequency spectral analysis by DFT and conventional feedforward neural network and that the cochlea model effectively prevents the deterioration due to noise of recognition accuracy.
Bibliographic reference. Koizumi, Takuya / Mori, Mikio / Taniguchi, Shuji (1996): "Speech recognition based on a model of human auditory system", In ICSLP-1996, 937-940.