Synthesis of nonverbal listener vocalizations

Sathish Chandra Pammi

In: In Proceedings Doctorial consortium at ACII 2009. IEEE International Conference on Affective Computation and Intelligent Interaction (ACII-09) September 10-12 Amsterdam Netherlands 2009.


Listener vocalizations play an important role in communicating listener intentions while the interlocutor is talking. Synthesis of listener vocalizations is one of the focused research areas to improve emotionally colored conversational speech synthesis. The major objective of the work presented in this paper is providing a new functionality to text-to-speech synthesis system that can synthesize nonverbal listener vocalizations. As synthesis of listener vocalizations is a new topic in conversational speech synthesis, many research questions are raised. A methodology is proposed to conduct research on those questions which can provide solutions to build a system to generate nonverbal listener vocalizations. We discuss the work done so far according to proposed working strategy and tentative plans for future work.

Projekte (pdf, 56 KB ) pammi2009a.pdf (pdf, 160 KB )

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence