WinkTalk: a demonstration of a multimodal speech synthesis platform linking facial expressions to expressive synthetic voices

摘要

This paper describes a demonstration of the WinkTalk system, which is a speech synthesis platform using expressive synthetic voices. With the help of a webcamera and facial expression analysis, the system allows the user to control the expressive features of the synthetic speech for a particular utterance with their facial expressions. Based on a personalised mapping between three expressive synthetic voices and the users facial expressions, the system selects a voice that matches their face at the moment of sending a message. The WinkTalk system is an early research prototype that aims to demonstrate that facial expressions can be used as a more intuitive control over expressive speech synthesis than manual selection of voice types, thereby contributing to an improved communication experience for users of speech generating devices.