Approaches to emotional expressivity in synthetic speech

Marc Schröder

In: Krzysztof Izdebski (Hrsg.). Emotions in the Human Voice: Culture and Perception. Seiten 307-321 III Plural Publishing San Diego, CA 2008.


Attempts to add emotion effects to synthesised speech have existed since the beginning of the 1990s, and have recently gained popularity to the extent that the first commercial synthesisers include emotional or otherwise expressive capabilities. Over the years, several prototypes and fully operational systems have been built based on different synthesis techniques, and quite a number of smaller studies have been conducted. This chapter aims to give an overview of what has been done in this field, pointing out the inherent properties of the various synthesis techniques used, summarising the prosody rules employed, and taking a look at the evaluation paradigms. Finally, some potentially interesting directions for future development are discussed.


Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence