The Seventh ISCA Tutorial and Research Workshop on Speech Synthesis Kyoto, Japan September 22-24, 2010

Symbolic vs. Acoustics-Based Style Control for Expressive Unit Selection

Ingmar Steiner (1,2), Marc Schröder (1), Marcela Charfuelan (1), Annette Klepp (1,2)

(1) DFKI GmbH, Saarbrücken, Germany
(2) Department of Computational Linguistics & Phonetics, Saarland University, Germany

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

Full Paper

Bibliographic reference.  Steiner, Ingmar / Schröder, Marc / Charfuelan, Marcela / Klepp, Annette (2010): "Symbolic vs. acoustics-based style control for expressive unit selection", In SSW7-2010, 114-119.