Abstract:
This paper presents our work on building an expressive facial speech synthesis system Eface, which can be used on a social or service robot. Eface aims at enabling a robot to deliver infor- mation clearly with empathetic speech and an expressive virtual face. The system is built on two open source software packages: the Festival speech synthesis system, which provides robots the capability to speak with di erent voices and emotions, and Xface{a 3D talking head, which enables the robot to display various human fa- cial expressions. This paper addresses how to express di erent speech emotions with Festi- val and how to integrate the synthesized speech with Xface. We have also implemented Eface on a physical robot and tested it with some ser- vice scenarios.