• An interactive speech interface for virtual characters in dynamic environments

      Mehdi, Qasim; Zeng, Xin; Gough, Norman (2004)
      In this paper, we propose a new improvement to our 3D Virtual Story Environment System (3DVSE) by adding a real-time animation with voice synthesis. The new system offers a flexible and easy way to generate an interactive 3D virtual Environment (3DVE) as compared to traditional 3D packages. It enables the user to control and interact with the virtual characters via speech instructions so that the characters can respond to the commands in real time. This system has the potential, if combined with artificial intelligence, to act as a dialogue interface for believable agents that have many applications such as computer games, and intelligent multimedia applications. In this system, the agent can talk and listen to fellow agents and human users.
    • From visual semantic parameterization to graphic visualization

      Zeng, Xin; Mehdi, Qasim; Gough, Norman (Institute of Electrical and Electronics Engineers (IEEE), 2005)
      Visualizing natural language description is a difficult and complex task. When dealing with the process of generating images from natural language descriptions, we firstly should consider the real world and find out what key visual information can be extracted from the sentences which represents the most fundament concepts in both virtual and real environments. In this paper, we present the result of a prototype system called 3DSV (3D Story Visualiser) that generates a virtual scene by using simplified story-based descriptions. In particular, we describe the methodology used to parameterize the visual and describable words into XML formatted data structure. Then we discuss how to interpret the parameterized data and create an interactive real-time 3D virtual environment.
    • Shape of the story: Story visualization techniques

      Zeng, Xin; Mehdi, Qasim; Gough, Norman (YLEM, 2005)
      The article explores the potential of incorporating knowledge of human-to-human interaction to story visualization technology by using natural language processing and 3D computer graphic techniques. This approach generates an interactive 3D Virtual Story Environment (3DVSE) based on simplified story-based natural language input allowing the manipulation and modification of properties of the environment in real time. This paper proposes a system that would enable non-technical creative writers to render characters and scenes that are normally created by graphics specialists. i.e. allowing artists to interact with science and computer technology with ease.