<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-1301">
  <Title>Adaptive Help for Speech Dialogue Systems Based on Learning and Forgetting of Speech Commands</Title>
  <Section position="3" start_page="0" end_page="1" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Modern premium class vehicles contain a large number of driver information and driving assistance systems. Therefore the need for enhanced display and control concepts arose. BMW's iDrive is one of these concepts, allowing the driver to choose functions by a visual-haptic interface (see Fig. 1) (Haller, 2003). In Addition to the visual-haptic interface, iDrive includes a speech dialogue system (SDS) as well. The SDS allows the driver to use a large number of functions via speech commands (Hagen et al., 2004). The system offers a context specific help function that can be activated by uttering the keyword 'options'. The options provide help in the form of a list, containing speech commands available in the current context (see dialogue 1). Currently neither the driver's preferences nor his knowledge is taken  timize the options by adaption that takes preferences and knowledge into account.</Paragraph>
    <Paragraph position="1"> Our basic concern was to reduce the driver's memory load by reducing irrelevant information.</Paragraph>
    <Paragraph position="2"> An adaptive help system based upon an individual user model could overcome this disadvantage. In (Komatani et al., 2003) and (Libuda and Kraiss, 2003), several adaptive components can be included to improve dialogue systems, e.g. user and content adaption, situation adaption and task adaption. Hassel (2006) uses adaption to apply different dialogue strategies according to the user's experience with the SDS. In our system we concentrate on user modeling and content adaption.</Paragraph>
    <Paragraph position="3"> In this paper, we present studies concerning learning and forgetting of speech commands in automotive environments. The results are used to develop a model describing the driver's knowledge in our SDS domain. This model is used to adapt the content of the options lists.</Paragraph>
    <Paragraph position="4">  Dialogue 1 User: &amp;quot;Phone.&amp;quot; System: &amp;quot;Phone. Say dial name, dial number or name a list.&amp;quot; User: &amp;quot;Options.&amp;quot; System: &amp;quot;Options. Say dial followed by a name, for example 'dial Alex', or say dial name, dial number, save number, phone book, speed dialing list, top eight, last eight, accepted calls, missed calls, active calls and or or off.&amp;quot;</Paragraph>
  </Section>
class="xml-element"></Paper>