This paper discusses the need for an enhanced model of Swedish prosody for use in dialogue systems. A description is given of the components of the model which is being developed as part of the project Prosodic Segmentation and Structuring of Dialogue. The model is based on parameters derived from observations of both man-man and man-machine dialogues. The main extension in relation to our previous model lies in the introduction of continuous parameters which affect the phonetic realization of the discrete parameters of our original model. These continuous parameters are related in complex ways to features of the discourse situation.
Cite as: Bruce, G., Granström, B., Gustafson, K., Horne, M., House, D., Touati, P. (1995) Towards an enhanced prosodic model adapted to dialogue applications. Proc. ESCA Workshop on Spoken Dialogue Systems, 201-204
@inproceedings{bruce95_sds,
author={Gösta Bruce and Björn Granström and Kjell Gustafson and Merle Horne and David House and Paul Touati},
title={{Towards an enhanced prosodic model adapted to dialogue applications}},
year=1995,
booktitle={Proc. ESCA Workshop on Spoken Dialogue Systems},
pages={201--204}
}