The present paper addresses the issue of flexibility in expressive unit selection speech synthesis by using different style selection techniques. We select units from a mixed-style unit selection database, using either forced style switching, no control, symbolic target cost, or acoustic target cost as a style selection criterion. We assess the effect of selection technique, feature weight and relative weight of target vs. join costs on a set of objective measures for style specificity and smoothness.
Index Terms: expressive speech synthesis, unit selection, style control, voice quality, acoustic target cost
Cite as: Steiner, I., Schröder, M., Charfuelan, M., Klepp, A. (2010) Symbolic vs. acoustics-based style control for expressive unit selection. Proc. 7th ISCA Workshop on Speech Synthesis (SSW 7), 114-119
@inproceedings{steiner10_ssw,
author={Ingmar Steiner and Marc Schröder and Marcela Charfuelan and Annette Klepp},
title={{Symbolic vs. acoustics-based style control for expressive unit selection}},
year=2010,
booktitle={Proc. 7th ISCA Workshop on Speech Synthesis (SSW 7)},
pages={114--119}
}