Speech input control for networked virtual environments

Although the use of speech recognition as an input modality for users of virtual environments is in its infancy, hands-free interaction of type should provide considerable benefits for users of virtual reality systems, because the input devices they use are often unsuited to simultaneous 3-D navigation and control tasks. As part of the work carried out on behalf of GPT Limited in a UK Department of Trade and Industry collaborative project - 'Virtuosi' - GEC-Marconi Research Centre (Borehamwood) has integrated a speech recognition system with a commercial virtual reality system and developed a sophisticated vocabulary and command structure that enables users to control virtual entities. This capability has been demonstrated in the Virtuosi project's networked 'Virtual Fashion' pilot but has many potential uses in the mainstream applications of GEC-Marconi, such as control systems for virtual cockpits.