system
</term>
,
<term>
features
</term>
and
<term>
decision strategies
</term>
are discovered and trained automatically
#19499In our system, features anddecision strategies are discovered and trained automatically, using a large body of speech data.
model,4-3-H89-1027,ak
</term>
. In our
<term>
system
</term>
,
<term>
features
</term>
and
<term>
decision strategies
</term>
#19497In our system,features and decision strategies are discovered and trained automatically, using a large body of speech data.
model,12-2-H89-1027,ak
the past efforts that make use of
<term>
heuristic rules
</term>
whose development requires intense
#19467In contrast to many of the past efforts that make use ofheuristic rules whose development requires intense knowledge engineering, our approach attempts to express the speech knowledge within a formal framework using well-defined mathematical tools.
tech,18-2-H89-1027,ak
whose development requires intense
<term>
knowledge engineering
</term>
, our approach attempts to express
#19473In contrast to many of the past efforts that make use of heuristic rules whose development requires intenseknowledge engineering, our approach attempts to express the speech knowledge within a formal framework using well-defined mathematical tools.
tech,9-1-H89-1027,ak
we initiated a project to develop a
<term>
phonetically-based spoken language understanding system
</term>
called
<term>
SUMMIT
</term>
. In contrast
#19447Recently, we initiated a project to develop aphonetically-based spoken language understanding system called SUMMIT.
lr,19-3-H89-1027,ak
automatically , using a large body of
<term>
speech data
</term>
. This paper describes the
<term>
system
#19512In our system, features and decision strategies are discovered and trained automatically, using a large body ofspeech data.
other,27-2-H89-1027,ak
our approach attempts to express the
<term>
speech knowledge
</term>
within a formal framework using
<term>
#19482In contrast to many of the past efforts that make use of heuristic rules whose development requires intense knowledge engineering, our approach attempts to express thespeech knowledge within a formal framework using well-defined mathematical tools.
tool,15-1-H89-1027,ak
understanding system
</term>
called
<term>
SUMMIT
</term>
. In contrast to many of the past
#19453Recently, we initiated a project to develop a phonetically-based spoken language understanding system calledSUMMIT.
tech,2-3-H89-1027,ak
mathematical tools
</term>
. In our
<term>
system
</term>
,
<term>
features
</term>
and
<term>
decision
#19495In oursystem, features and decision strategies are discovered and trained automatically, using a large body of speech data.
tech,4-4-H89-1027,ak
data
</term>
. This paper describes the
<term>
system
</term>
, and documents its current performance
#19519This paper describes thesystem, and documents its current performance.
other,34-2-H89-1027,ak
</term>
within a formal framework using
<term>
well-defined mathematical tools
</term>
. In our
<term>
system
</term>
,
<term>
#19489In contrast to many of the past efforts that make use of heuristic rules whose development requires intense knowledge engineering, our approach attempts to express the speech knowledge within a formal framework usingwell-defined mathematical tools.