<?xml version="1.0" standalone="yes"?>
<Paper uid="W04-2305">
  <Title>Combining Acoustic Confidences and Pragmatic Plausibility for Classifying Spoken Chess Move Instructions</Title>
  <Section position="7" start_page="0" end_page="0" type="concl">
    <SectionTitle>
6 Conclusions
</SectionTitle>
    <Paragraph position="0"> We presented a machine learning approach that combines acoustic confidence scores with automatic move evaluations for selecting from the n-best speech recognition hypotheses in a chess playing scenario and compared the results to two different baselines.</Paragraph>
    <Paragraph position="1"> The chess scenario is well suited for our experiments because it allowed us to filter out impossible moves and to use a computer chess program to assess the plausibility of legal moves. However, the methodology underlying Experiment 1 can be applied to other spoken dialogue systems to choose interpretation(s) from a recogniser's n-best output. We have successfully used this setup for classifying hypotheses in a command and control spoken dialogue system (Gabsdil and Lemon, subm). Experiment 2 exploits the fact that the number of possible interpretations is finite in the chess scenario. Although this obviously does not hold for many dialogue tasks, there are applications such as call routing (e.g. (Walker et al., 2000)) where the number of possible interpretations is limited in a similar way. Instead of selecting correct interpretations, we imagine that one could also use the proposed setup to decide which of a finite set of dialogue moves was performed by a speaker.</Paragraph>
  </Section>
class="xml-element"></Paper>