tech,9-9-H90-1060,bq |
the
<term>
target speaker
</term>
for
<term>
|
adaptation
|
</term>
, the
<term>
error rate
</term>
dropped
|
#17196
Using only 40 utterances from the target speaker foradaptation, the error rate dropped to 4.1% --- a 45% reduction in error compared to the SI result. |
tech,6-4-H90-1060,bq |
12
<term>
training speakers
</term>
for
<term>
|
SI recognition
|
</term>
, we achieved a 7.5 %
<term>
word error
|
#17076
With only 12 training speakers forSI recognition, we achieved a 7.5% word error rate on a standard grammar and test set from the DARPA Resource Management corpus. |
tech,14-2-H90-1060,bq |
speaker-independent ( SI ) training
</term>
of
<term>
|
hidden Markov models ( HMM )
|
</term>
, which uses a large amount of
<term>
|
#17002
First, we present a new paradigm for speaker-independent (SI) training ofhidden Markov models ( HMM ), which uses a large amount of speech from a few speakers instead of the traditional practice of using a little speech from many speakers. |
other,30-6-H90-1060,bq |
speech
</term>
from the new ( target )
<term>
|
speaker
|
</term>
. A
<term>
probabilistic spectral mapping
|
#17149
Second, we show a significant improvement for speaker adaptation (SA) using the new SI corpus and a small amount of speech from the new (target)speaker. |
other,16-7-H90-1060,bq |
reference ) speaker
</term>
and the
<term>
|
target speaker
|
</term>
. Each
<term>
reference model
</term>
|
#17167
A probabilistic spectral mapping is estimated independently for each training (reference) speaker and thetarget speaker. |
other,7-1-H90-1060,bq |
paper reports on two contributions to
<term>
|
large vocabulary continuous speech recognition
|
</term>
. First , we present a new paradigm
|
#16982
This paper reports on two contributions tolarge vocabulary continuous speech recognition. |
other,44-2-H90-1060,bq |
little
<term>
speech
</term>
from many
<term>
|
speakers
|
</term>
. In addition , combination of the
|
#17032
First, we present a new paradigm for speaker-independent (SI) training of hidden Markov models (HMM), which uses a large amount of speech from a few speakers instead of the traditional practice of using a little speech from manyspeakers. |
other,15-5-H90-1060,bq |
condition for this test suite , using 109
<term>
|
training speakers
|
</term>
. Second , we show a significant
|
#17116
This performance is comparable to our best condition for this test suite, using 109training speakers. |
lr-prod,26-4-H90-1060,bq |
</term>
and
<term>
test set
</term>
from the
<term>
|
DARPA Resource Management corpus
|
</term>
. This
<term>
performance
</term>
is
|
#17096
With only 12 training speakers for SI recognition, we achieved a 7.5% word error rate on a standard grammar and test set from theDARPA Resource Management corpus. |
tech,15-8-H90-1060,bq |
target speaker
</term>
and combined by
<term>
|
averaging
|
</term>
. Using only 40
<term>
utterances
</term>
|
#17185
Each reference model is transformed to the space of the target speaker and combined byaveraging. |
tech,34-3-H90-1060,bq |
many
<term>
speakers
</term>
prior to
<term>
|
training
|
</term>
. With only 12
<term>
training speakers
|
#17068
In addition, combination of the training speakers is done by averaging the statistics> of independently trained models rather than the usual pooling of all the speech data from many speakers prior totraining. |
lr,16-6-H90-1060,bq |
adaptation ( SA )
</term>
using the new
<term>
|
SI corpus
|
</term>
and a small amount of
<term>
speech
|
#17135
Second, we show a significant improvement for speaker adaptation (SA) using the newSI corpus and a small amount of speech from the new (target) speaker. |
other,10-8-H90-1060,bq |
transformed to the
<term>
space
</term>
of the
<term>
|
target speaker
|
</term>
and combined by
<term>
averaging
</term>
|
#17180
Each reference model is transformed to the space of thetarget speaker and combined by averaging. |
lr,20-4-H90-1060,bq |
word error rate
</term>
on a standard
<term>
|
grammar
|
</term>
and
<term>
test set
</term>
from the
<term>
|
#17090
With only 12 training speakers for SI recognition, we achieved a 7.5% word error rate on a standardgrammar and test set from the DARPA Resource Management corpus. |
other,9-7-H90-1060,bq |
is estimated independently for each
<term>
|
training ( reference ) speaker
|
</term>
and the
<term>
target speaker
</term>
|
#17160
A probabilistic spectral mapping is estimated independently for eachtraining ( reference ) speaker and the target speaker. |
other,24-9-H90-1060,bq |
dropped to 4.1 % --- a 45 % reduction in
<term>
|
error
|
</term>
compared to the
<term>
SI
</term>
result
|
#17211
Using only 40 utterances from the target speaker for adaptation, the error rate dropped to 4.1% --- a 45% reduction inerror compared to the SI result. |
measure(ment),12-9-H90-1060,bq |
</term>
for
<term>
adaptation
</term>
, the
<term>
|
error rate
|
</term>
dropped to 4.1 % --- a 45 % reduction
|
#17199
Using only 40 utterances from the target speaker for adaptation, theerror rate dropped to 4.1% --- a 45% reduction in error compared to the SI result. |
other,6-9-H90-1060,bq |
40
<term>
utterances
</term>
from the
<term>
|
target speaker
|
</term>
for
<term>
adaptation
</term>
, the
<term>
|
#17193
Using only 40 utterances from thetarget speaker for adaptation, the error rate dropped to 4.1% --- a 45% reduction in error compared to the SI result. |
other,3-4-H90-1060,bq |
<term>
training
</term>
. With only 12
<term>
|
training speakers
|
</term>
for
<term>
SI recognition
</term>
, we
|
#17073
With only 12training 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. |
lr,27-2-H90-1060,bq |
</term>
, which uses a large amount of
<term>
|
speech
|
</term>
from a few
<term>
speakers
</term>
instead
|
#17015
First, we present a new paradigm for speaker-independent (SI) training of hidden Markov models (HMM), which uses a large amount ofspeech from a few speakers instead of the traditional practice of using a little speech from many speakers. |