#21151With only 12 training speakers for SI recognition, we achieved a 7.5% word error rate on a standard grammar andtest set from the DARPA Resource Management corpus.
lr,23-6-H90-1060,ak
corpus
</term>
and a small amount of
<term>
speech
</term>
from the
<term>
new ( target ) speaker
#21201Second, we show a significant improvement for speaker adaptation (SA) using the new SI corpus and a small amount ofspeech from the new (target) speaker.
other,3-9-H90-1060,ak
combined by averaging . Using only 40
<term>
utterances
</term>
from the
<term>
target speaker
</term>
#21249Using only 40utterances from the target speaker for adaptation, the error rate dropped to 4.1% --- a 45% reduction in error compared to the SI result.
other,31-2-H90-1060,ak
amount of
<term>
speech
</term>
from a few
<term>
speakers
</term>
instead of the traditional practice
#21079First, we present a new paradigm for speaker-independent (SI) training of hidden Markov models (HMM), which uses a large amount of speech from a fewspeakers instead of the traditional practice of using a little speech from many speakers.
other,6-3-H90-1060,ak
. In addition , combination of the
<term>
training speakers
</term>
is done by averaging the statistics
#21100In 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.
model,1-7-H90-1060,ak
<term>
new ( target ) speaker
</term>
. A
<term>
probabilistic spectral mapping
</term>
is estimated independently for each
#21211Aprobabilistic spectral mapping is estimated independently for each training (reference) speaker and the target speaker.
model,1-8-H90-1060,ak
the
<term>
target speaker
</term>
. Each
<term>
reference model
</term>
is transformed to the space of the
#21230Eachreference model is transformed to the space of the target speaker and combined by averaging.
tech,22-3-H90-1060,ak
models
</term>
rather than the usual
<term>
pooling
</term>
of all the
<term>
speech data
</term>
#21116In addition, combination of the training speakers is done by averaging the statistics of independently trained models rather than the usualpooling of all the speech data from many speakers prior to training.
tech,8-2-H90-1060,ak
First , we present a new paradigm for
<term>
speaker-independent ( SI ) training
</term>
of
<term>
hidden Markov models ( HMM
#21056First, 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.
measure(ment),14-4-H90-1060,ak
recognition
</term>
, we achieved a 7.5 %
<term>
word error rate
</term>
on a standard
<term>
grammar
</term>
#21143With 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.
other,30-3-H90-1060,ak
the
<term>
speech data
</term>
from many
<term>
speakers
</term>
prior to
<term>
training
</term>
. With
#21124In 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 manyspeakers prior to training.
model,17-3-H90-1060,ak
statistics of independently trained
<term>
models
</term>
rather than the usual
<term>
pooling
#21111In addition, combination of the training speakers is done by averaging the statistics of independently trainedmodels rather than the usual pooling of all the speech data from many speakers prior to training.
tech,8-6-H90-1060,ak
show a significant improvement for
<term>
speaker adaptation ( SA )
</term>
using the new
<term>
SI corpus
</term>
#21186Second, we show a significant improvement forspeaker adaptation ( SA ) using the new SI corpus and a small amount of speech from the new (target) speaker.