Expressive Speech for a Virtual Talking Head

摘要

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 information 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 different voices and emotions, and Xface–a 3D talking head, which enables the robot to display various human facial expressions. This paper addresses how to express different speech emotions with Festival and how to integrate the synthesized speech with Xface. We have also implemented Eface on a physical robot and tested it with some service scenarios. 1