The possibility to vary speaker type and speaking style will be a feature of the next gen- eration text-to-speech systems. Already today, the need for these possibilities are appar- ent, in dialogue systems and when speech synthesis is used as prostheses for persons with a communication handicap. Much of the information needed is not yet available. In this contribution we argue that speech synthesis itself is an efficient tool to study and understand variability in speech. Some different methods are reviewed, representing both analysis/synthesis techniques and signal manipulations as well as text-to-speech. The main emphasis is on the work at KTH to study the variation of speaker and speak- ing styles in the context of our text-to-speech system.
Cite as: Granström, B. (1991) The use of speech synthesis in exploring different speaking styles. Proc. ESCA Workshop on Phonetics and Phonology of Speaking Styles, paper 003
@inproceedings{granstrom91_ppst,
author={Björn Granström},
title={{The use of speech synthesis in exploring different speaking styles}},
year=1991,
booktitle={Proc. ESCA Workshop on Phonetics and Phonology of Speaking Styles},
pages={paper 003}
}