#215To support engaging human users in robust, mixed-initiative speech dialogue interactions which reach beyond current capabilities in dialogue systems, the DARPA Communicator program [1] is funding the development of a distributed message-passing infrastructure for dialogue systems which all Communicator participants are using.
tech,4-2-H01-1055,ak
within reach . However , the improved
<term>
speech
recognition
</term>
has brought to light
#934However, the improvedspeech recognition has brought to light a new problem: as dialog systems understand more of what the user tells them, they need to be more sophisticated at responding to the user.
other,25-1-N01-1003,ak
syntactic structure
</term>
for
<term>
elementary
speech
acts
</term>
and the decision of how to combine
#1319Sentence planning is a set of inter-related but distinct tasks, one of which is sentence scoping, i.e. the choice of syntactic structure for elementary speech acts and the decision of how to combine them into one or more sentences.
other,10-2-N03-1012,ak
to the task of scoring alternative
<term>
speech
recognition hypotheses ( SRH )
</term>
in
#2467We apply our system to the task of scoring alternativespeech recognition hypotheses (SRH) in terms of their semantic coherence.
other,18-3-N03-1012,ak
semantically coherent and incoherent
<term>
speech
recognition hypotheses
</term>
. An evaluation
#2498We conducted an annotation experiment and showed that human annotators can reliably differentiate between semantically coherent and incoherentspeech recognition hypotheses.
other,9-1-N03-2003,ak
language modeling
</term>
of
<term>
conversational
speech
</term>
are limited . In this paper , we
#3025Sources of training data suitable for language modeling of conversational speech are limited.
tech,15-3-P03-1030,ak
enhancing techniques including
<term>
part of
speech
tagging
</term>
, new
<term>
similarity measures
#4110Motivated by these arguments, we introduce a number of new performance enhancing techniques including part of speech tagging, new similarity measures and expanded stop lists.
tech,19-3-P03-1031,ak
due to the
<term>
ambiguity
</term>
of
<term>
speech
understanding
</term>
, it is not appropriate
#4175Since multiple candidates for the understanding result can be obtained for a user utterance due to the ambiguity ofspeech understanding, it is not appropriate to decide on a single understanding result after each user utterance.
other,12-3-I05-5003,ak
<term>
PER
</term>
which leverages
<term>
part of
speech
information
</term>
of the words contributing
#7431We also introduce a novel classification method based on PER which leverages part of speech information of the words contributing to the word matches and non-matches in the sentence.
tech,36-12-J05-1003,ak
ranking tasks
</term>
, for example ,
<term>
speech
recognition
</term>
,
<term>
machine translation
#8337Although the experiments in this article are on natural language parsing (NLP), the approach should be applicable to many other NLP problems which are naturally framed as ranking tasks, for example,speech recognition, machine translation, or natural language generation.
other,4-1-P05-1056,ak
Sentence boundary detection
</term>
in
<term>
speech
</term>
is important for enriching
<term>
speech
#9426Sentence boundary detection inspeech is important for enriching speech recognition output, making it easier for humans to read and downstream modules to process.
other,9-1-P05-1056,ak
speech
</term>
is important for enriching
<term>
speech
recognition output
</term>
, making it easier
#9431Sentence boundary detection in speech is important for enrichingspeech recognition output, making it easier for humans to read and downstream modules to process.
corpora
</term>
( conversational telephone
speech
and broadcast news speech ) on both
<term>
#9518We evaluate across two corpora (conversational telephone speech and broadcast news speech) on both human transcriptions and speech recognition output.
conversational telephone speech and broadcast news
speech
) on both
<term>
human transcriptions
</term>
#9522We evaluate across two corpora (conversational telephone speech and broadcast news speech) on both human transcriptions and speech recognition output.
other,19-4-P05-1056,ak
<term>
human transcriptions
</term>
and
<term>
speech
recognition output
</term>
. In general ,
#9529We evaluate across two corpora (conversational telephone speech and broadcast news speech) on both human transcriptions andspeech recognition output.
other,25-5-P05-1056,ak
sentence boundary detection task
</term>
in
<term>
speech
</term>
, although it is interesting to note
#9558In general, our CRF model yields a lower error rate than the HMM and Maxent models on the NIST sentence boundary detection task inspeech, although it is interesting to note that the best results are achieved by three-way voting among the classifiers.
other,70-5-E06-1035,ak
<term>
cue phrases
</term>
and
<term>
overlapping
speech
</term>
, are better indicators for the
<term>
#11534Examination of the effect of features shows that predicting top-level and predicting subtopic boundaries are two distinct tasks: (1) for predicting subtopic boundaries, the lexical cohesion-based approach alone can achieve competitive results, (2) for predicting top-level boundaries, the machine learning approach that combines lexical-cohesion and conversational features performs best, and (3) conversational cues, such as cue phrases and overlapping speech, are better indicators for the top-level prediction task.
other,15-5-E89-1006,ak
temporal perspective times
</term>
, the
<term>
speech
time
</term>
and the
<term>
location time
</term>
#19198This system consists of one or more reference times and temporal perspective times, thespeech time and the location time.
other,27-2-H89-1027,ak
our approach attempts to express the
<term>
speech
knowledge
</term>
within a formal framework
#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.
lr,19-3-H89-1027,ak
automatically , using a large body of
<term>
speech
data
</term>
. This paper describes the
<term>
#19512In our system, features and decision strategies are discovered and trained automatically, using a large body ofspeech data.