|
speaker adaptation ( SA )
</term>
using the
|
new
|
<term>
SI corpus
</term>
and a small amount
|
#17134
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. |
|
small amount of
<term>
speech
</term>
from the
|
new
|
( target )
<term>
speaker
</term>
. A
<term>
|
#17145
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. |
|
technique for failed parses
</term>
, and a
|
new
|
technique called
<term>
terminal substring
|
#17481
We describe three techniques for making syntactic analysis more robust---an agenda-based scheduling parser, a recovery technique for failed parses, and a new technique called terminal substring parsing. |
|
of its
<term>
search space
</term>
. As each
|
new
|
<term>
edge
</term>
is added to the
<term>
chart
|
#17602
As each new edge is added to the chart, the algorithm checks only the topmost of the edges adjacent to it, rather than all such edges as in conventional treatments. |
tech,30-2-C92-2115,bq |
pints in
<term>
MT. This paper proposes a
|
new
|
type of
</term><term>
transfer system
</term>
|
#18113
This paper proposes a new type of transfer system, called a Similarity-driven Transfer System (SimTran), for use in such case-based MT (CBMT). |
|
Language Processing
</term>
. In this paper , a
|
new
|
mechanism , based on the concept of
<term>
|
#18290
In this paper, a new mechanism, based on the concept of sublanguage, is proposed for identifying unknown words, especially personal names, in Chinese newspapers. |
|
of use . We have recently reported on two
|
new
|
<term>
word-sense disambiguation systems
</term>
|
#19180
We have recently reported on two new word-sense disambiguation systems, one trained on bilingual material (the Canadian Hansards) and the other trained on monolingual material (Roget's Thesaurus and Grolier's Encyclopedia). |
|
Recognition ) corpus
</term>
represents a
|
new
|
<term>
DARPA speech recognition technology
|
#19536
The CSR (Connected Speech Recognition) corpus represents a new DARPA speech recognition technology development initiative to advance the state of the art in CSR. |
|
</term>
development for the past 5 years . The
|
new
|
<term>
CSR corpus
</term>
supports research
|
#19581
The new CSR corpus supports research on major new problems including unlimited vocabulary, natural grammar, and spontaneous speech. |
|
corpus
</term>
supports research on major
|
new
|
problems including
<term>
unlimited vocabulary
|
#19588
The new CSR corpus supports research on major new problems including unlimited vocabulary, natural grammar, and spontaneous speech. |
|
<term>
errors
</term>
, this paper proposes
|
new
|
methods using
<term>
m-th order Markov chain
|
#20678
In order to judge three types of the errors, which are characters wrongly substituted, deleted or inserted in a Japanese bunsetsu and an English word, and to correct these errors, this paper proposes new methods using m-th order Markov chain model for Japanese kanji-kana characters and English alphabets, assuming that Markov probability of a correct chain of syllables or kanji-kana characters is greater than that of erroneous chains. |
|
</term>
and
<term>
ambiguity handling
</term>
. A
|
new
|
, flexible
<term>
inference method
</term>
|
#20879
A new, flexible inference method for Horn logic program is proposed. |