4th International Conference on Spoken Language Processing

Philadelphia, PA, USA
October 3-6, 1996

Recurrent Neural Networks for Phoneme Recognition

Takuya Koizumi, Mikio Mori, Shuji Taniguchi, Mitsutoshi Maruya

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

This paper deals with recurrent neural networks of multi-layer perceptron type which are well-suited for speech recognition, specially for phoneme recognition. The ability of these networks has been investigated by phoneme recognition experiments using a number of Japanese words uttered by a native male speaker in a quiet environment. Results of the experiments show that recognition rates achieved with these networks are higher than those obtained with conventional non-recurrent neural networks.

Full Paper

Bibliographic reference.  Koizumi, Takuya / Mori, Mikio / Taniguchi, Shuji / Maruya, Mitsutoshi (1996): "Recurrent neural networks for phoneme recognition", In ICSLP-1996, 326-329.