<?xml version="1.0" standalone="yes"?>
<Paper uid="H01-1049">
  <Title>Listen-Communicate-Show (LCS): Spoken Language Command of Agent-based Remote Information Access</Title>
  <Section position="6" start_page="0" end_page="0" type="evalu">
    <SectionTitle>
4. OPERATIONAL EVALUATION
</SectionTitle>
    <Paragraph position="0"> To measure the effectiveness of the LCS paradigm under operational conditionsreal users placing real requests, accessing a live database, and using existing communications linkswe conducted a series of Integrated Feasibility Experiments (IFE). The IFEs ranged from a pilot study that featured scripted dialogue, replicated databases, and testing in the lab with prior military personnel, to field experiments where active duty Marines used the system operationally over a series of days as their sole means of interaction with the logistics system for rapid requests. We tested the systems support of placing and checking on requests for ammunition (Class V), fuels (Class III), and subsistence (Class I) supplies. More on the experimentation protocols can be found in [1] and  Over the course of the IFE process we were able to experiment with differing server configurations as well as varying communications linkages between servers. The most recent IFE (December 2000) used the server layout shown in Figure 4.</Paragraph>
    <Paragraph position="1">  Channel Ground and Airborne Radio System (SINCGARS), can create a large amount of channel noise, which alters or distorts the acoustic signal. Current recognizers can not yet compensate for this distortion, although there is active research into solving this problem.</Paragraph>
    <Paragraph position="2"> We used a second operational layout to test the system and get operator feedback on using a spoken language understanding interface. This layout is depicted in Figure 6. In this layout, we required the user to beat the same location as the entire SLS system and the agents migrated over the SINCGARS data link  to reach the logistics database. The recognizer still had to contend with the issue of a noisy and dynamic background, but the acoustic distortion was eliminated.</Paragraph>
  </Section>
class="xml-element"></Paper>