Next: Parsing wordgraphs
Up: Robust parsing of wordgraphs
Previous: Robust parsing of wordgraphs
The input to the NLP module consists of wordgraphs produced by the
speech recogniser [33]. A wordgraph is a compact
representation for all sequences of words that the speech recogniser
hypothesises for a spoken utterance. The states of the graph represent
points in time, and a transition between two states represents a word that
may have been uttered between the corresponding points in time. Each
transition is associated with an acoustic score representing a measure
of confidence that the word perceived there was
actually uttered. These scores are negative logarithms of
probabilities and therefore require addition as opposed to
multiplication when two scores are combined. An example of a typical
wordgraph is given as the first graph in figure 19.
At an early stage, the wordgraph is normalised to eliminate the
pause transitions. Such transitions represent periods of time for
which the speech recogniser hypothesises that no words are uttered.
After this optimisation, the wordgraph contains exactly one start
state and one or more final states, associated with a score,
representing a measure of confidence that the utterance ends at that
point. The wordgraphs in figure 19 provide an example.
From now on, we will assume wordgraphs
are normalised in this sense. Below, we refer to transitions in the
wordgraph using the notation
for a
transition from state v_{i} to v_{j} with symbol w and acoustic
score a. Let
refer to a final state v_{i} with
acoustic score a.
Figure 19:
Wordgraph and normalized wordgraph
for the utterance Zondag vier
februari (Sunday Februari fourth). The special label #
in the first graph indicates a pause transition. These transitions
are eliminated in the second graph.

Next: Parsing wordgraphs
Up: Robust parsing of wordgraphs
Previous: Robust parsing of wordgraphs
20000710