A voxicon is a lexicon of “visual object concepts” or voxemes. A voxeme is a visual instantiation of a lexical item, used for procedurally generating multimodal simulations of motion events in a three-dimensional environment.

The voxicon framework is based on the modeling language VoxML, which is used to convert natural language expressions into real time visualizations using real-world semantic knowledge of objects and events. Our approach adds a focus on motion and dynamics to the world of scene generation from natural language.