Multi-modal telephony services in hometalk

HomeTalk platform is a multi-modal interaction framework. It uses speech recognition and computer vision to model new generation of interfaces in the residential environment. In this paper we focus particularly on telephony aspect of the overall multimodal platform. We discuss vision of future telephony applications in home environment. The vision is based on the use of simple visual clues and speech interaction. We suggest the method of how to implement such applications using general platform. We provide short description of the platform and we demonstrate platform use on several telephony applications. The applications have been developed for trials and used by several groups of people in real life situations. The trials provided valuable feedback both to application and platform design.