Third International Conference on Spoken Language Processing (ICSLP 94)

Yokohama, Japan
September 18-22, 1994

Phonetic Visualization for Speech Training System by Using Neural Network

Itaru Nagayama, Norio Akamatsu, Toshiki Yoshino

Faculty of Engineering, University of Tokushima, Tokushima, Japan

This paper describes an attempt to develop a new phonetic visualization method of speech training system for the speech impairment. A problem associated with the conventional speech training system is briefly reviewed. Reasons for attempting to develop the new method are given. The proposed method uses neural network approach to visualize phonetic patterns. The method and its display capabilities are described. Also the experimental result of visualizing five Japanese vowels /A/,/I/,/U/,/E/,/O/ by using the proposed method is described.

Full Paper

Bibliographic reference.  Nagayama, Itaru / Akamatsu, Norio / Yoshino, Toshiki (1994): "Phonetic visualization for speech training system by using neural network", In ICSLP-1994, 2027-2030.