H94-1077 |
speech recognition system for
|
telephone directory assistance
|
. We have developed a two-stage
|
H94-1077 |
technique was evaluated by the
|
telephone directory assistance
|
system , using the 56 context-independent
|
H94-1077 |
analyzing 300 sentences in simulated
|
telephone directory assistance
|
dialogs . Figure 3 gives an example
|
H94-1077 |
their likelihood scores . The
|
telephone directory assistance
|
database constraint is not usually
|
N06-4002 |
By the year 2000 , commercial
|
telephone directory assistance
|
systems started appearing as
|
E03-1055 |
is derived from the domain of a
|
telephone directory assistance
|
. Along with the bilingual annotation
|
P00-1049 |
originally made for an automatic
|
telephone directory assistance
|
system ( Higashida , 1994 ) .
|
H94-1077 |
likelihood score . system for
|
telephone directory assistance
|
. Error Correction If there is
|
H94-1077 |
Experimental System We developed a
|
telephone directory assistance
|
system that covers two cities
|
H94-1077 |
R ~ = log Rb 1 - ~ z ~ . m for
|
telephone directory assistance
|
. crowd noise ( nonstationary
|
H94-1077 |
algorithm and applied it to a
|
telephone directory assistance
|
system including 70,000 subscriber
|
H94-1077 |
multi-modal speech dialog system for
|
telephone directory assistance
|
with three input devices ( mi
|
H94-1077 |
satisfies the constraint in the
|
telephone directory assistance
|
database , because there is a
|
H94-1077 |
ITS APPLICATION TO A MULTI-MODAL
|
TELEPHONE DIRECTORY ASSISTANCE
|
SYSTEM 1 . INTRODUCTION One of
|
H94-1077 |
ITS APPLICATION TO A MULTI-MODAL
|
TELEPHONE DIRECTORY ASSISTANCE
|
SYSTEM </title> Yasuhiro Minami
|
H94-1077 |
resistant to noise . 5 . MULTI-MODAL
|
TELEPHONE DIRECTORY ASSISTANCE
|
SYSTEM 5.1 . System Structure
|