lr,12-4-H92-1016,bq |
The weighted error for the entire
<term>
spoken language system
</term>
on the same
<term>
test set
</term>
is 49.3 % .
|
#18789
The weighted error for the entire spoken language system on the sametest set is 49.3%. |
lr,26-2-H92-1016,bq |
These include
<term>
context-dependent phonetic modelling
</term>
, the use of a
<term>
bigram language model
</term>
in conjunction with a
<term>
probabilistic LR parser
</term>
, and refinements made to the
<term>
lexicon
</term>
.
|
#18735
These include context-dependent phonetic modelling, the use of a bigram language model in conjunction with a probabilistic LR parser, and refinements made to thelexicon. |
lr,7-3-H92-1016,bq |
Together with the use of a larger
<term>
training set
</term>
, these modifications combined to reduce the
<term>
speech recognition word and sentence error rates
</term>
by a factor of 2.5 and 1.6 , respectively , on the
<term>
October '91 test set
</term>
.
|
#18744
Together with the use of a largertraining 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. |
lr-prod,35-3-H92-1016,bq |
Together with the use of a larger
<term>
training set
</term>
, these modifications combined to reduce the
<term>
speech recognition word and sentence error rates
</term>
by a factor of 2.5 and 1.6 , respectively , on the
<term>
October '91 test set
</term>
.
|
#18772
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 theOctober '91 test set. |
lr-prod,7-5-H92-1016,bq |
Similar results were also obtained on the
<term>
February '92 benchmark evaluation
</term>
.
|
#18802
Similar results were also obtained on theFebruary '92 benchmark evaluation. |
measure(ment),16-3-H92-1016,bq |
Together with the use of a larger
<term>
training set
</term>
, these modifications combined to reduce the
<term>
speech recognition word and sentence error rates
</term>
by a factor of 2.5 and 1.6 , respectively , on the
<term>
October '91 test set
</term>
.
|
#18753
Together with the use of a larger training set, these modifications combined to reduce thespeech recognition word and sentence error rates by a factor of 2.5 and 1.6, respectively, on the October '91 test set. |
model,10-2-H92-1016,bq |
These include
<term>
context-dependent phonetic modelling
</term>
, the use of a
<term>
bigram language model
</term>
in conjunction with a
<term>
probabilistic LR parser
</term>
, and refinements made to the
<term>
lexicon
</term>
.
|
#18719
These include context-dependent phonetic modelling, the use of abigram language model in conjunction with a probabilistic LR parser, and refinements made to the lexicon. |
tech,17-2-H92-1016,bq |
These include
<term>
context-dependent phonetic modelling
</term>
, the use of a
<term>
bigram language model
</term>
in conjunction with a
<term>
probabilistic LR parser
</term>
, and refinements made to the
<term>
lexicon
</term>
.
|
#18726
These include context-dependent phonetic modelling, the use of a bigram language model in conjunction with aprobabilistic LR parser, and refinements made to the lexicon. |
tech,2-2-H92-1016,bq |
These include
<term>
context-dependent phonetic modelling
</term>
, the use of a
<term>
bigram language model
</term>
in conjunction with a
<term>
probabilistic LR parser
</term>
, and refinements made to the
<term>
lexicon
</term>
.
|
#18711
These includecontext-dependent phonetic modelling, the use of a bigram language model in conjunction with a probabilistic LR parser, and refinements made to the lexicon. |
tech,6-4-H92-1016,bq |
The weighted error for the entire
<term>
spoken language system
</term>
on the same
<term>
test set
</term>
is 49.3 % .
|
#18783
The weighted error for the entirespoken language system on the same test set is 49.3%. |
tool,23-1-H92-1016,bq |
This paper describes the status of the
<term>
MIT ATIS system
</term>
as of February 1992 , focusing especially on the changes made to the
<term>
SUMMIT recognizer
</term>
.
|
#18706
This paper describes the status of the MIT ATIS system as of February 1992, focusing especially on the changes made to theSUMMIT recognizer. |
tool,7-1-H92-1016,bq |
This paper describes the status of the
<term>
MIT ATIS system
</term>
as of February 1992 , focusing especially on the changes made to the
<term>
SUMMIT recognizer
</term>
.
|
#18690
This paper describes the status of theMIT ATIS system as of February 1992, focusing especially on the changes made to the SUMMIT recognizer. |