 |
ESCA Workshop on Spoken Dialogue SystemsVigsų, Denmark |
 |
|
ESCA Workshop on Spoken Dialogue SystemsVigsų, Denmark |
|
This paper describes prospects of spoken dialogue systems focusing on their integration with a multimedia environment in future application areas and services. It tries to forecast where progress will be achieved in the near future and what applications will become commonplace as a result of the increased capabilities. It also describes the most important research problems to be solved in order to achieve useful systems. The problems for speech synthesis include natural and intelligible voice production, prosody control based on meaning, the control of synthesized voice quality and choice of individual speaking styles, multi-lingual synthesis, choice of application-oriented speaking styles, and synthesis from concepts. The problems for speech recognition include robust recognition against speech variations, adaptation/normalization to variations due to environmental conditions and speakers, automatic knowledge acquisition for acoustic and linguistic modeling, spontaneous speech recognition, and naturalness and ease of human/machine interaction. It is also important to establish evaluation methods for measuring the quality of technology and systems in a multimedia environment.
Bibliographic reference. Furui, Sadaoki (1995): "Prospects for spoken dialogue systems in a multimedia environment", In SDS-1995, 9-16.