This paper deals with the need for speech synthesis in dialogue systems to incorporate tone of voice for cueing in the listener feelings concerning the attitude of the computer-speaker. Dialogue systems intended for different purposes require different global tones of voice to sound completely convincing. But in addition the synthetic speech needs local tones of voice to signify changing and adapting attitudes during the course of the dialogue with the human user of the system. We discuss the format of a tone of voice model and provide an example using intonation declination.
Keywords: dialogue systems, speech synthesis, pragmatics, intonation, declination.
Cite as: Morton, K., Tatham, M. (1993) Speech synthesis in dialogue systems. Proc. 3rd European Conference on Speech Communication and Technology (Eurospeech 1993), 905-908, doi: 10.21437/Eurospeech.1993-208
@inproceedings{morton93_eurospeech,
author={Katherine Morton and Marcel Tatham},
title={{Speech synthesis in dialogue systems}},
year=1993,
booktitle={Proc. 3rd European Conference on Speech Communication and Technology (Eurospeech 1993)},
pages={905--908},
doi={10.21437/Eurospeech.1993-208}
}