Modelling prominence and emphasis improves unit-selection synthesis

Strom, V., Nenkova, A., Clark, R., Vazquez-Alvarez, Y., Brenier, J., King, S. and Jurafsky, D. (2007) Modelling prominence and emphasis improves unit-selection synthesis. In: Interspeech 2007, Antwerp, Belgium, 27-31 Aug 2007, pp. 1282-1285.

Full text not currently available from Enlighten.

Publisher's URL: http://www.informatik.uni-trier.de/~ley/db/conf/interspeech/interspeech2007.html

Abstract

We describe the results of large scale perception experiments showing improvements in synthesising two distinct kinds of prominence: standard pitch-accent and strong emphatic accents. Previously prominence assignment has been mainly evaluated by computing accuracy on a prominence-labelled test set. By contrast we integrated an automatic pitch-accent classifier into the unit selection target cost and showed that listeners preferred these synthesised sentences. We also describe an improved recording script for collecting emphatic accents, and show that generating emphatic accents leads to further improvements in the fiction genre over incorporating pitch accent only. Finally, we show differences in the effects of prominence between child-directed speech and news and fiction genres.

Item Type:Conference Proceedings
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Vazquez-Alvarez, Dr Yolanda
Authors: Strom, V., Nenkova, A., Clark, R., Vazquez-Alvarez, Y., Brenier, J., King, S., and Jurafsky, D.
College/School:College of Science and Engineering > School of Computing Science

University Staff: Request a correction | Enlighten Editors: Update this record