This paper describes the voice output subsystem of a speech dialogue system, as this relates to prosody generation, and in particular, prosodic marking of focus. We demonstrate how focal domain values are assigned within the text generation component at the intentional, attentional and surface-linguistic levels, and how realisation of the pitch contour is achieved.
Cite as: NickYoud, N., House, J. (1991) Generating intonation in a voice dialogue system. Proc. 2nd European Conference on Speech Communication and Technology (Eurospeech 1991), 1287-1290, doi: 10.21437/Eurospeech.1991-295
@inproceedings{nickyoud91_eurospeech,
author={NickYoud NickYoud and Jill House},
title={{Generating intonation in a voice dialogue system}},
year=1991,
booktitle={Proc. 2nd European Conference on Speech Communication and Technology (Eurospeech 1991)},
pages={1287--1290},
doi={10.21437/Eurospeech.1991-295}
}