Symbolic vs. acoustics-based style control for expressive unit selection

Ingmar Steiner; Marc Schröder; Marcela Charfuelan Oliva; Annette Klepp

In: Seventh ISCA Tutorial and Research Workshop on Speech Synthesis (SSW7). ISCA Tutorial and Research Workshop on Speech Synthesis (SSW-7), located at Interspeech, September 22-24, Kyoto, Japan, ISCA, 2010.


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.


vq_unitselection.pdf (pdf, 323 KB )

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence