lr,41-2-H90-1060,bq |
traditional practice of using a little
<term>
|
speech
|
</term>
from many
<term>
speakers
</term>
. In
|
#17029
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 littlespeech from many speakers. |
tech,8-6-H90-1060,bq |
show a significant improvement for
<term>
|
speaker adaptation ( SA )
|
</term>
using the new
<term>
SI corpus
</term>
|
#17127
Second, we show a significant improvement forspeaker adaptation ( SA ) using the new SI corpus and a small amount of speech from the new (target) speaker. |
other,6-3-H90-1060,bq |
. In addition , combination of the
<term>
|
training speakers
|
</term>
is done by averaging the
<term>
statistics
|
#17040
In addition, combination of thetraining 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 to training. |
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. |
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. |
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. |
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,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. |
lr,27-3-H90-1060,bq |
than the usual pooling of all the
<term>
|
speech data
|
</term>
from many
<term>
speakers
</term>
prior
|
#17061
In addition, combination of the training speakers is done by averaging the statistics> of independently trained models rather than the usual pooling of all thespeech data from many speakers prior to training. |
tech,8-2-H90-1060,bq |
First , we present a new paradigm for
<term>
|
speaker-independent ( SI ) training
|
</term>
of
<term>
hidden Markov models ( HMM
|
#16996
First, we present a new paradigm forspeaker-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 many speakers. |
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. |
model,16-3-H90-1060,bq |
averaging the
<term>
statistics >
</term>
of
<term>
|
independently trained models
|
</term>
rather than the usual pooling of
|
#17050
In addition, combination of the training speakers is done by averaging the statistics> ofindependently trained models rather than the usual pooling of all the speech data from many speakers prior to training. |
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. |
tech,28-9-H90-1060,bq |
in
<term>
error
</term>
compared to the
<term>
|
SI
|
</term>
result . This paper presents a specialized
|
#17215
Using only 40 utterances from the target speaker for adaptation, the error rate dropped to 4.1% --- a 45% reduction in error compared to theSI result. |
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. |
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,7-8-H90-1060,bq |
model
</term>
is transformed to the
<term>
|
space
|
</term>
of the
<term>
target speaker
</term>
|
#17177
Each reference model is transformed to thespace of the target speaker and combined by averaging. |
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. |