Poster: A Software Framework for Easy Integration of Speech Recognition into 3D Browsers

Abstract

In this article, we propose a software framework couples voice command definitions with existing interaction code, automating the task of creating a new grammar to be used by the recognizer engine. A new listener component for the Xj3D was created, which makes transparent to the user the integration between the 3D browser and the recognizer. The approach assumes the adoption of an independent speech recognizer, which them requires the VRML/X3D browser to be able to communicate with it. Our proposal is to hide, as much as possible, the speech implementation from the VRML/X3D programmer, keeping the additional programming to a minimum, and automating the process of updating the recognizer with successive new grammar descriptions. We believe this is a desirable feature for virtual reality system developers, and also to be used as a rapid prototyping tool when experimenting with speech technology.