<?xml version="1.0" standalone="yes"?>
<Paper uid="A97-1005">
  <Title>QuickSet: Multimodal Interaction for Simulation Set-up and Control</Title>
  <Section position="7" start_page="22" end_page="22" type="concl">
    <SectionTitle>
7. CONCLUDING REMARKS
</SectionTitle>
    <Paragraph position="0"> QuickSet has been delivered to the US Navy (NRaD) and US Marine Corps. for use at 29 Palms, California, where it is primarily used to set up training scenarios and to control the virtual environment. It is also installed at NRaD's Command Center of the Future. The system was used by the US Army's 82nd Airborne Corps. at Ft. Bragg during the Royal Dragon Exercise. There, QuickSet was deployed in a tent, where it was subjected to an extreme noise environment, including explosions, low-flying jet aircraft, generators, and the like. Not surprisingly, spoken interaction with QuickSet was not feasible, although users gestured successfully. Instead, users wanted to gesture.</Paragraph>
    <Paragraph position="1"> Although we had provided a multimodal interface for use in less hostile conditions, nevertheless we needed to provide,and in fact have provided, a complete overlap in functionality, such that any task can be accomplished just with pen or just with speech when necessary. Finally, QuickSet is now being extended for use in the Exlnit simulation initialization system for DARPA's STOW-97 Advanced Concept Demonstration that is intended for creation of division-sized exercises.</Paragraph>
    <Paragraph position="2"> Regarding the multimodal interface itself, QuickSet has undergone a &amp;quot;proactive&amp;quot; interface evaluation in that the studies that were performed in advance of building the system predicted the utility of multimodal over unimodal speech as an input to map-based systems \[17, 18\]. In particular, it was discovered in this research that multimodal interaction generates simpler language than unimodal spoken commands to maps. For example, to create a &amp;quot;phase line&amp;quot; between two three-digit &lt;x,y&gt; grid coordinates, a user would have to say: &amp;quot;create a line from nine four three nine six one to nine five seven nine six eight and call it phase line green&amp;quot; \[14\]. In contrast, a QuickSet user would say &amp;quot;phase line green&amp;quot; while drawing a line. Creation of area features with unimodal speech would be more complex still, if not infeasible. Given that numerous difficult-to-process linguistic phenomena (such as utterance disfluencies) are known to be elevated in lengthy utterances, and also to be elevated when people speak locative constituents \[17, 18\], multimodal interaction that permits pen input to specify locations and that results in brevity offers the possibility of more robust recognition.</Paragraph>
    <Paragraph position="3"> Further development of QuickSet's spoken, gestural, and multimodal integration capabilites are continuing. Research is also ongoing to examine and quantify the benefits of multimodal interaction in general, and our architecture in particular.</Paragraph>
  </Section>
class="xml-element"></Paper>