INTERACTIVE VOICE TECHNOLOGY DEVELOPMENT FOR TELECOMMUNICATIONS APPLICATIONS

This paper describes the essential speech processing techniques for in teractive voice applications in the telecommunications field. These te chniques include speech recognition and speech synthesis, both of whic h aim to make interactive speech communications between man and machin e more natural. Keyword spotting, background noise effects reduction, and speakers and/or telephone adaptation techniques are considered ess ential in speech recognition in order to allow a more natural voice in put as well as an adequate robustness against environmental variabilit ies. In the area of text-to-speech synthesis, we propose a rule-based synthesis method applicable to the Japanese language, aiming to produc e high quality speech. The commercial system ANSER of a former project is also described as an example of an interactive speech processing s ystem. Finally, a recently developed speech recognition server which i ncludes a vocabulary-flexible recognition function is described. It is meant to illustrate the concept of the techniques it employs which al low its range of applications to be easily extended and also allow it to adapt itself to the changes which are rapidly occurring in the tele communications field.