tech,4-2-H01-1055,bq |
reach . However , the improved
<term>
speech
|
recognition
|
</term>
has brought to light a new problem
|
#935
However, the improved speech 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. |
tech,26-2-N03-1001,bq |
achieved using conventional
<term>
word-trigram
|
recognition
|
</term>
requiring
<term>
manual transcription
|
#2250
The method combines domain independent acoustic models with off-the-shelf classifiers to give utterance classification performance that is surprisingly close to what can be achieved using conventional word-trigram recognition requiring manual transcription. |
tech,23-3-N03-1001,bq |
domain
</term>
; the
<term>
output
</term>
of
<term>
|
recognition
|
</term>
with this
<term>
model
</term>
is then
|
#2278
In our method, unsupervised training is first used to train a phone n-gram model for a particular domain; the output ofrecognition with this model is then passed to a phone-string classifier. |
other,10-2-N03-1012,bq |
<term>
scoring
</term>
alternative
<term>
speech
|
recognition
|
hypotheses ( SRH )
</term>
in terms of their
|
#2467
We apply our system to the task of scoring alternative speech recognition hypotheses (SRH) in terms of their semantic coherence. |
other,18-3-N03-1012,bq |
semantically coherent and incoherent
<term>
speech
|
recognition
|
hypotheses
</term>
. An evaluation of our
|
#2498
We conducted an annotation experiment and showed that human annotators can reliably differentiate between semantically coherent and incoherent speech recognition hypotheses. |
model,7-1-N03-1018,bq |
generative probabilistic optical character
|
recognition
|
( OCR ) model
</term>
that describes an end-to-end
|
#2678
In this paper, we introduce a generative probabilistic optical character recognition (OCR) model that describes an end-to-end process in the noisy channel framework, progressing from generation of true text through its transformation into the noisy output of an OCR system. |
tech,27-2-N03-2003,bq |
and/or
<term>
topic
</term>
of the target
<term>
|
recognition
|
task
</term>
, but also that it is possible
|
#3055
In this paper, we show how training data can be supplemented with text from the web filtered to match the style and/or topic of the targetrecognition task, but also that it is possible to get bigger performance gains from the data by using class-dependent interpolation of N-grams. |
tech,36-12-J05-1003,bq |
tasks
</term>
, for example ,
<term>
speech
|
recognition
|
</term>
,
<term>
machine translation
</term>
|
#8973
Although 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,5-3-P80-1004,bq |
generalized metaphor
</term>
contains a
<term>
|
recognition
|
network
</term>
, a
<term>
basic mapping
</term>
|
#12481
Each generalized metaphor contains arecognition network, a basic mapping, additional transfer mappings, and an implicit intention component. |
tech,14-4-P80-1004,bq |
from a
<term>
reconstruction
</term>
to a
<term>
|
recognition
|
task
</term>
. Implications towards automating
|
#12512
It is argued that the method reduces metaphor interpretation from a reconstruction to arecognition task. |
tech,5-4-P84-1047,bq |
addition , it facilitates
<term>
fragmentary
|
recognition
|
</term>
and the use of
<term>
multiple parsing
|
#13369
In addition, it facilitates fragmentary recognition and the use of multiple parsing strategies, and so is particularly useful for robust recognition of extra-grammatical input. |
tech,22-4-P84-1047,bq |
is particularly useful for robust
<term>
|
recognition
|
of extra-grammatical input
</term>
. Several
|
#13385
In addition, it facilitates fragmentary recognition and the use of multiple parsing strategies, and so is particularly useful for robustrecognition of extra-grammatical input. |
other,6-12-J86-3001,bq |
processing description specifies in these
<term>
|
recognition
|
tasks
</term>
the role of information from
|
#14374
This processing description specifies in theserecognition tasks the role of information from the discourse and from the participants' knowledge of the domain. |
tech,16-2-C90-3014,bq |
<term>
phonological system
</term>
:
<term>
speech
|
recognition
|
</term>
and
<term>
synthesis system
</term>
.
|
#16398
The approach of KPSG provides an explicit development model for constructing a computational phonological system: speech recognition and synthesis system. |
other,7-1-H90-1060,bq |
<term>
large vocabulary continuous speech
|
recognition
|
</term>
. First , we present a new paradigm
|
#16986
This paper reports on two contributions to large vocabulary continuous speech recognition. |
tech,6-4-H90-1060,bq |
<term>
training speakers
</term>
for
<term>
SI
|
recognition
|
</term>
, we achieved a 7.5 %
<term>
word error
|
#17077
With only 12 training speakers for SI recognition, we achieved a 7.5% word error rate on a standard grammar and test set from the DARPA Resource Management corpus. |
tech,4-3-C92-4199,bq |
mechanism includes
<term>
title-driven name
|
recognition
|
</term>
,
<term>
adaptive dynamic word formation
|
#18321
The proposed mechanism includes title-driven name recognition, adaptive dynamic word formation, identification of 2-character and 3-character Chinese names without title. |
measure(ment),16-3-H92-1016,bq |
modifications combined to reduce the
<term>
speech
|
recognition
|
word and sentence error rates
</term>
by
|
#18754
Together with the use of a larger training set, these modifications combined to reduce the speech recognition word and sentence error rates by a factor of 2.5 and 1.6, respectively, on the October '91 test set. |
tech,17-3-H92-1036,bq |
approach for the following four
<term>
speech
|
recognition
|
</term>
applications , namely
<term>
parameter
|
#19117
Because of its adaptive nature, Bayesian learning serves as a unified approach for the following four speech recognition applications, namely parameter smoothing, speaker adaptation, speaker group modeling and corrective training. |
tool,11-1-H92-1074,bq |
</term>
represents a new
<term>
DARPA speech
|
recognition
|
technology
</term>
development initiative
|
#19539
The CSR (Connected Speech Recognition) corpus represents a new DARPA speech recognition technology development initiative to advance the state of the art in CSR. |