I
nte
rna
t
io
na
l
J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
11
,
No
.
4
,
A
u
g
u
s
t
2021
,
p
p
.
3
3
3
8
~
3
3
4
6
I
SS
N:
2088
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
11
i
4
.
pp
3
3
3
8
-
3
3
4
6
3338
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
A new
t
echno
lo
g
y
on trans
la
ting In
do
nesia
n spo
k
e
n l
a
ng
ua
g
e
into Ind
o
nesia
n si
g
n lang
ua
g
e sy
stem
Ris
k
y
Asw
i R
a
m
a
da
ni,
I
K
et
ut
G
ede
Dha
r
m
a
P
utr
a
,
M
a
de
Su
da
r
m
a
,
I
da
Ay
u Dw
i G
iria
nta
ri
P
r
o
g
ra
m
Do
k
to
ra
l
Il
m
u
T
e
k
n
ik
,
Un
iv
e
rsitas
Ud
a
y
a
n
a
,
De
n
p
a
sa
r,
In
d
o
n
e
sia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
y
3
1
,
2
0
2
0
R
ev
i
s
ed
Dec
2
9
,
2
0
2
0
A
cc
ep
ted
J
an
1
3
,
2
0
2
1
P
e
o
p
le
w
it
h
h
e
a
rin
g
d
isa
b
i
li
ti
e
s
a
re
th
o
se
w
h
o
a
re
u
n
a
b
le
t
o
h
e
a
r,
re
su
lt
e
d
i
n
th
e
ir
d
isa
b
il
it
y
to
c
o
m
m
u
n
ica
te
u
sin
g
sp
o
k
e
n
lan
g
u
a
g
e
.
T
h
e
so
lu
ti
o
n
o
f
f
e
r
e
d
in
t
h
is
re
se
a
rc
h
is
b
y
c
re
a
ti
n
g
a
o
n
e
w
a
y
tran
sla
ti
o
n
tec
h
n
o
l
o
g
y
t
o
in
terp
re
t
sp
o
k
e
n
lan
g
u
a
g
e
to
In
d
o
n
e
sia
n
si
g
n
lan
g
u
a
g
e
s
y
st
e
m
(S
IBI).
T
h
e
m
e
c
h
a
n
is
m
a
p
p
li
e
d
h
e
re
is
b
y
c
a
t
c
h
i
n
g
th
e
se
n
ten
c
e
s
(a
u
d
io
)
sp
o
k
e
n
b
y
c
o
m
m
o
n
so
c
iety
to
b
e
c
o
n
v
e
rted
to
tex
ts,
b
y
u
sin
g
sp
e
e
c
h
re
c
o
g
n
it
io
n
.
T
h
e
tex
ts
a
re
th
e
n
p
ro
c
e
ss
e
d
in
tex
t
p
ro
c
e
ss
in
g
to
se
lec
t
th
e
in
p
u
t
tex
ts.
T
h
e
n
e
x
t
sta
g
e
is
ste
m
m
in
g
th
e
t
e
x
ts
in
to
p
re
f
ix
e
s,
b
a
sic
w
o
rd
s,
a
n
d
su
ff
ix
e
s.
Eac
h
w
o
rd
s
a
r
e
th
e
n
b
e
i
n
g
in
d
e
x
e
d
a
n
d
m
a
tch
e
d
to
S
IBI.
A
f
ter
wa
rd
s,
th
e
sy
ste
m
will
a
rra
n
g
e
th
e
w
o
rd
s
in
to
S
IBI
se
n
ten
c
e
s
b
a
se
d
o
n
th
e
o
rig
in
a
l
se
n
ten
c
e
s,
so
th
a
t
th
e
p
e
o
p
le
w
it
h
h
e
a
rin
g
d
isa
b
il
it
ies
c
a
n
g
e
t
th
e
in
f
o
r
m
a
ti
o
n
c
o
n
tain
e
d
w
it
h
in
th
e
sp
o
k
e
n
la
n
g
u
a
g
e
.
T
h
is
tec
h
n
o
l
o
g
y
su
c
c
e
ss
ra
te
w
e
re
tes
ted
u
sin
g
Co
n
f
u
sio
n
M
a
tri
x
,
w
h
ich
re
su
lt
e
d
in
p
re
c
isio
n
v
a
lu
e
o
f
7
6
%
,
a
c
c
u
ra
c
y
v
a
lu
e
o
f
7
8
%
,
a
n
d
re
c
a
ll
v
a
lu
e
o
f
7
9
%
.
T
h
is
tec
h
n
o
lo
g
y
h
a
s
b
e
e
n
tes
ted
in
S
M
P
-
L
B
K
a
r
y
a
M
u
ly
a
o
n
th
e
7
t
h
g
ra
d
e
r
stu
d
e
n
ts
w
it
h
th
e
to
t
a
l
o
f
9
stu
d
e
n
ts.
F
ro
m
th
e
tes
t,
it
is o
b
tai
n
e
d
t
h
a
t
8
6
%
o
f
stu
d
e
n
ts s
tate
d
th
a
t
t
h
is t
e
c
h
n
o
l
o
g
y
ru
n
s v
e
r
y
we
ll
.
K
ey
w
o
r
d
s
:
Hea
r
in
g
d
i
s
ab
ilit
ies
SIB
I
Sp
ee
ch
r
ec
o
g
n
i
tio
n
Sp
o
k
en
la
n
g
u
a
g
e
T
r
an
s
lato
r
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
I
Ketu
t G
ed
e
Dh
ar
m
a
P
u
tr
a
P
r
o
g
r
am
Do
k
to
r
al
I
l
m
u
T
ek
n
i
k
(
P
DI
T
)
Un
i
v
er
s
ita
s
Ud
a
y
a
n
a
Den
p
asar
,
B
ali,
8
0
2
3
4
,
I
n
d
o
n
e
s
ia
E
m
ail:
i
k
g
d
ar
m
ap
u
tr
a
@
u
n
u
d
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
Dea
f
p
eo
p
le
r
ef
er
s
to
th
at
w
h
o
h
as
d
is
ab
ilit
ie
s
in
h
ea
r
in
g
f
u
n
ct
io
n
.
T
h
is
co
n
d
itio
n
m
i
g
h
t
b
e
eith
er
te
m
p
o
r
ar
y
o
r
p
er
m
a
n
e
n
t.
Fo
r
th
o
s
e
liv
in
g
ar
o
u
n
d
p
eo
p
le
w
i
th
h
ea
r
i
n
g
d
is
ab
ilit
ie
s
,
a
s
p
ec
ial
co
m
m
u
n
ica
tio
n
f
o
r
m
is
h
i
g
h
l
y
n
ee
d
ed
in
o
r
d
er
to
p
r
o
p
er
ly
d
eliv
er
th
e
m
ess
a
g
e
in
a
co
n
v
er
s
atio
n
[1
-
3
]
.
I
n
d
o
n
esian
s
i
g
n
lan
g
u
a
g
e
s
y
s
te
m
o
r
s
is
te
m
is
y
a
r
a
t
B
a
h
a
s
a
I
n
d
o
n
esia
(
S
I
B
I
)
is
a
s
i
g
n
la
n
g
u
a
g
e
s
y
s
te
m
s
p
e
cif
icall
y
d
ev
elo
p
ed
f
o
r
p
eo
p
le
w
i
th
h
ea
r
in
g
d
is
ab
ilit
ies
.
I
n
d
o
n
es
ian
s
ig
n
la
n
g
u
a
g
e
s
y
s
te
m
f
o
llo
w
s
I
n
d
o
n
esia
n
g
r
a
m
m
atica
l
s
tr
u
ct
u
r
e,
an
d
th
e
m
o
r
p
h
o
lo
g
y
is
also
b
ased
o
n
B
a
h
a
s
a
I
n
d
o
n
esia
[4
-
6
]
.
T
h
e
I
n
d
o
n
esian
s
i
g
n
la
n
g
u
a
g
e
s
y
s
te
m
also
in
cl
u
d
es p
r
ef
i
x
es,
b
asic
wo
r
d
s
,
an
d
s
u
f
f
i
x
es [
7
]
.
W
ith
in
th
e
i
n
f
o
r
m
atio
n
tech
n
o
lo
g
y
f
ie
ld
,
esp
ec
iall
y
i
n
I
n
d
o
n
esia,
t
h
er
e
ar
e
s
till
v
er
y
li
m
ited
r
esear
ch
er
s
d
ev
elo
p
in
g
tec
h
n
o
lo
g
y
o
n
tr
an
s
lati
n
g
la
n
g
u
a
g
e
s
p
ec
if
ic
f
o
r
p
eo
p
le
w
it
h
h
ea
r
in
g
d
i
s
ab
ilit
ies.
T
ec
h
n
o
lo
g
ies
w
h
ic
h
h
av
e
b
e
en
d
ev
elo
p
ed
cu
r
r
en
t
l
y
f
o
r
p
eo
p
le
w
ith
h
ea
r
i
n
g
d
is
ab
i
lit
ies
ar
e
I
n
d
o
n
es
ian
v
o
ca
b
u
lar
ies d
ictio
n
ar
y
,
an
d
I
n
d
o
n
esia
n
s
i
g
n
lan
g
u
ag
e
m
o
r
p
h
o
lo
g
y
[
8
,
9]
C
r
ea
tin
g
s
p
ec
ial
f
ac
ilit
ies
f
o
r
p
eo
p
le
w
it
h
h
ea
r
in
g
d
i
s
ab
ilit
ies
is
a
h
ea
v
y
ta
s
k
.
I
n
2
0
0
1
,
th
e
I
n
d
o
n
esia
n
g
o
v
er
n
m
e
n
t
h
ad
j
u
s
t
estab
li
s
h
ed
th
e
d
ictio
n
ar
y
o
f
I
n
d
o
n
e
s
ia
n
s
i
g
n
lan
g
u
ag
e
s
y
s
te
m
,
o
f
w
h
ic
h
d
u
r
in
g
th
at
ti
m
e
th
er
e
w
er
e
o
n
l
y
a
f
e
w
tec
h
n
o
lo
g
y
d
ev
el
o
p
m
e
n
ts
o
n
t
h
e
f
ield
.
Me
an
w
h
ile,
th
e
h
ea
r
in
g
d
is
ab
led
p
eo
p
le
w
er
e
i
n
h
i
g
h
n
ee
d
s
o
f
co
m
m
u
n
icatio
n
to
o
ls
t
o
b
e
u
s
ed
i
n
r
ec
ei
v
i
n
g
i
n
f
o
r
m
a
tio
n
i
n
t
h
e
f
o
r
m
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
A
n
ew tec
h
n
o
lo
g
y
o
n
tr
a
n
s
la
tin
g
I
n
d
o
n
esia
n
s
p
o
k
en
l
a
n
g
u
a
g
e
in
to
.
.
.
(
R
is
ky
A
s
w
i R
a
ma
d
a
n
i)
3339
au
d
io
[
1
0
]
.
T
h
e
s
o
lu
tio
n
o
f
th
is
p
r
o
b
le
m
is
to
d
ev
elo
p
a
o
n
e
-
w
a
y
tr
a
n
s
latio
n
tech
n
o
lo
g
y
f
r
o
m
s
p
o
k
e
n
lan
g
u
a
g
e
to
I
n
d
o
n
esia
n
s
i
g
n
la
n
g
u
a
g
e
s
y
s
te
m
.
I
n
2
0
1
8
,
w
e
d
ev
elo
p
ed
a
d
ata
s
et
o
n
I
n
d
o
n
e
s
ian
s
i
g
n
la
n
g
u
ag
e
s
y
s
te
m
ac
co
r
d
in
g
to
th
e
m
o
r
p
h
o
lo
g
y
in
B
a
h
a
s
a
I
n
d
o
n
esia
.
T
h
e
d
a
ta
s
et
i
n
cl
u
d
es
p
r
ef
i
x
es,
b
as
ic
w
o
r
d
s
,
an
d
s
u
f
f
i
x
es.
T
h
e
r
es
ea
r
ch
w
as
e
n
tit
led
“Da
ta
b
a
s
e
o
f
I
n
d
o
n
esia
n
S
ig
n
S
ystem”
[
1
1
]
.
T
h
is
r
esear
ch
is
th
e
co
n
ti
n
u
atio
n
f
r
o
m
t
h
e
p
r
ec
ed
in
g
r
esear
ch
i
n
2
0
1
8
.
I
n
th
i
s
r
esear
ch
a
tec
h
n
o
lo
g
y
w
o
u
ld
b
e
d
ev
elo
p
ed
to
co
n
d
u
ct
o
n
e
w
a
y
tr
a
n
s
latio
n
f
r
o
m
s
p
o
k
e
n
lan
g
u
a
g
e
to
I
n
d
o
n
esia
n
s
ig
n
la
n
g
u
a
g
e
s
y
s
te
m
[
1
2
]
.
I
n
d
o
n
esia
n
o
v
elt
y
o
f
t
h
is
r
esear
c
h
is
b
ei
n
g
ab
le
to
m
a
k
e
a
n
in
ter
p
r
eter
o
f
s
p
o
k
en
la
n
g
u
a
g
e
in
to
I
n
d
o
n
esia
n
s
i
g
n
lan
g
u
ag
e
,
b
y
f
o
llo
w
in
g
t
h
e
m
o
r
p
h
o
lo
g
y
o
f
I
n
d
o
n
esia
n
.
I
n
p
u
t
u
s
ed
in
t
h
is
r
esear
ch
co
n
s
i
s
ts
o
f
s
en
te
n
ce
s
d
eli
v
er
ed
o
r
ally
(
a
u
d
io
)
,
w
h
ic
h
t
h
en
w
a
s
r
ec
o
r
d
ed
u
s
i
n
g
m
icr
o
p
h
o
n
es
i
n
lap
to
p
s
o
r
m
o
b
ile
p
h
o
n
e
s
.
T
h
e
v
o
ice
w
o
u
ld
s
u
b
s
eq
u
en
tl
y
b
e
co
n
v
er
ted
in
to
tex
t
s
u
s
i
n
g
s
p
ee
ch
r
ec
o
g
n
i
tio
n
tec
h
n
o
lo
g
y
[
1
3
-
1
5
]
.
T
h
e
tex
ts
w
o
u
ld
la
ter
en
ter
th
e
p
r
o
ce
s
s
i
n
g
s
tag
e.
T
ex
t
p
r
o
ce
s
s
in
g
is
u
s
ed
to
s
elec
t
i
n
p
u
t
s
en
ten
ce
s
[
1
6
,
1
7
]
.
T
ex
t
p
r
o
ce
s
s
in
g
co
n
s
is
ts
o
f
s
ev
er
al
s
tag
e
s
s
u
ch
as
ca
s
e
f
o
ld
in
g
,
to
k
en
izi
n
g
,
an
d
s
te
m
m
in
g
.
C
ase
f
o
ld
in
g
i
s
co
n
d
u
cted
t
o
h
o
m
o
g
e
n
ize
t
h
e
le
tter
s
to
lo
w
er
ca
s
e
letter
s
.
T
o
k
en
izin
g
is
u
s
ed
to
tr
i
m
t
h
e
s
en
te
n
ce
s
to
w
o
r
d
s
.
T
h
e
last
s
tag
e
i
s
s
te
m
m
i
n
g
w
h
ich
is
u
s
ed
to
s
ep
ar
ate
w
o
r
d
ele
m
e
n
ts
to
p
r
ef
i
x
es,
b
asic
w
o
r
d
s
,
an
d
s
u
f
f
i
x
e
s
[
1
8
,
1
9
]
.
T
h
e
w
o
r
d
s
w
h
ic
h
h
a
v
e
b
ee
n
i
d
en
tifie
d
i
n
to
a
n
u
m
b
er
o
f
p
r
ef
i
x
es,
b
as
ic
w
o
r
d
s
,
a
n
d
s
u
f
f
i
x
es
w
o
u
ld
th
en
g
o
th
r
o
u
g
h
i
n
d
ex
i
n
g
p
r
o
ce
s
s
w
it
h
th
e
p
r
ep
ar
ed
d
atab
ase
[
2
0
]
.
Fin
all
y
,
th
e
w
o
r
d
s
w
o
u
l
d
b
e
co
n
v
er
ted
to
a
w
o
r
d
in
I
n
d
o
n
esia
n
s
i
g
n
lan
g
u
a
g
e
s
y
s
te
m
(
I
m
a
g
es).
I
n
o
r
d
er
n
o
t
to
ch
an
g
e
th
e
i
n
f
o
r
m
atio
n
co
n
tain
ed
i
n
I
n
d
o
n
esia
n
s
ig
n
la
n
g
u
a
g
e
s
y
s
t
e
m
,
t
h
e
p
i
ct
u
r
es
w
i
ll
b
e
ar
r
an
g
ed
in
t
h
e
f
o
r
m
at
io
n
b
ased
o
n
t
h
e
i
n
p
u
t
s
e
n
te
n
ce
s
.
T
h
is
tr
an
s
latio
n
tec
h
n
o
lo
g
y
h
as
g
o
n
e
th
r
o
u
g
h
t
w
o
s
ta
g
es
o
f
test
s
.
T
h
e
f
ir
s
t
test
w
as
u
s
i
n
g
co
n
f
u
s
io
n
m
atr
i
x
ai
m
ed
to
id
en
ti
f
y
ac
c
u
r
ac
y
,
p
r
ec
is
io
n
,
an
d
r
ec
all
[
2
1
,
2
2
]
.
T
h
e
s
ec
o
n
d
test
w
a
s
co
n
d
u
c
t
ed
to
u
n
d
er
s
tan
d
to
w
h
at
ex
ten
t t
h
e
s
tu
d
e
n
ts
o
f
S
MP
-
L
B
Kar
y
a
M
u
l
y
a
ar
e
ab
le
to
u
s
e
th
is
tec
h
n
o
lo
g
y
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
is
r
esear
ch
f
o
c
u
s
e
s
o
n
tec
h
n
o
lo
g
y
o
n
tr
an
s
lati
n
g
s
p
o
k
e
n
B
a
h
a
s
a
I
n
d
o
n
esia
to
I
n
d
o
n
esian
s
i
g
n
lan
g
u
a
g
e
s
y
s
te
m
.
T
o
i
m
p
le
m
e
n
t
t
h
i
s
tec
h
n
o
lo
g
y
,
a
lo
n
g
p
r
o
ce
s
s
s
h
o
u
ld
b
e
co
n
d
u
cted
.
T
h
e
p
r
o
ce
s
s
s
p
an
s
f
r
o
m
in
s
er
ti
n
g
i
n
p
u
t
i
n
t
h
e
f
o
r
m
o
f
s
e
n
ten
ce
s
w
h
ic
h
ar
e
n
o
r
m
al
l
y
u
s
ed
b
y
I
n
d
o
n
esia
n
p
eo
p
le
in
r
eg
u
lar
co
n
v
er
s
atio
n
to
p
r
o
d
u
ce
o
u
t
p
u
t
in
t
h
e
f
o
r
m
o
f
s
i
g
n
lan
g
u
a
g
e
to
b
e
r
ec
ei
v
ed
b
y
p
e
o
p
l
e
w
it
h
h
ea
r
in
g
d
is
ab
ilit
ies.
T
h
is
ap
p
licatio
n
w
a
s
b
u
ilt
in
w
eb
s
ite
b
ase
s
o
th
at
it
is
ac
ce
s
s
ib
le
in
all
k
in
d
s
o
f
p
latf
o
r
m
s
[
23
]
.
Mo
r
e
d
etailed
ex
p
lan
atio
n
an
d
s
ch
e
m
e
ar
e
d
ep
icted
in
th
e
f
o
l
lo
w
i
n
g
f
lo
w
c
h
ar
t
as s
h
o
w
n
i
n
Fig
u
r
e
1
.
Fig
u
r
e
1
.
Flo
w
c
h
ar
t o
f
t
h
e
n
e
w
tec
h
n
o
lo
g
y
o
n
t
r
an
s
la
tin
g
s
p
o
k
en
l
a
n
g
u
a
g
e
to
I
n
d
o
n
esia
n
s
ig
n
l
a
n
g
u
a
g
e
s
y
s
te
m
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
4
,
A
u
g
u
s
t
2021
:
3
3
3
8
-
334
6
3340
2
.
1
.
Sp
ee
ch
re
co
g
nitio
n
Sp
ee
ch
R
ec
o
g
n
itio
n
is
t
h
e
p
r
o
ce
s
s
o
f
co
n
v
er
ti
n
g
a
u
d
io
to
te
x
ts
.
Au
d
io
s
ar
e
s
o
u
r
ce
d
f
r
o
m
t
h
e
s
o
ciet
y
w
h
o
ar
e
n
o
t
f
a
m
iliar
w
i
th
s
i
g
n
la
n
g
u
a
g
e
s
y
s
te
m
b
u
t
ar
e
ai
m
i
n
g
to
d
eliv
er
m
es
s
ag
e
to
war
d
s
th
eir
h
ea
r
in
g
-
i
m
p
air
ed
co
u
n
ter
p
ar
ts
.
I
n
f
o
r
m
atio
n
co
n
v
e
y
ed
b
y
th
e
s
o
ciet
y
is
i
n
th
e
f
o
r
m
o
f
s
p
o
k
en
s
e
n
te
n
ce
s
(
a
u
d
io
)
.
T
h
en
,
th
e
a
u
d
io
in
p
u
t
w
o
u
ld
b
e
co
n
v
er
ted
i
n
to
te
x
ts
b
y
u
s
i
n
g
s
p
ee
ch
r
ec
o
g
n
i
tio
n
[
24,
25
]
.
T
h
e
o
u
tp
u
t
p
r
o
d
u
ce
d
f
r
o
m
s
p
ee
ch
r
ec
o
g
n
itio
n
p
r
o
ce
s
s
ar
e
s
e
n
ten
ce
s
(
te
x
ts
)
.
T
h
e
F
ig
u
r
e
2
is
a
s
i
m
p
li
f
ied
f
ig
u
r
e
s
h
o
w
in
g
th
e
s
p
ee
c
h
r
ec
o
g
n
itio
n
p
r
o
ce
s
s
.
Sp
ee
ch
r
ec
o
g
n
itio
n
i
s
b
io
m
etr
ic
r
ec
o
g
n
itio
n
,
w
h
ich
is
t
h
e
p
r
o
ce
s
s
o
f
a
co
m
p
u
ter
r
ec
o
g
n
i
zin
g
w
h
a
t
s
o
m
eo
n
e
i
s
s
a
y
in
g
b
ased
o
n
t
h
e
to
n
e
o
f
v
o
ice
t
h
at
is
co
n
v
er
t
ed
in
to
d
ig
ital
te
x
t.
T
h
is
s
y
s
te
m
is
v
er
y
g
o
o
d
if
it
is
u
s
ed
to
d
ev
elo
p
co
m
m
u
n
ic
atio
n
ap
p
licatio
n
s
f
o
r
th
e
g
e
n
er
al
p
u
b
lic
w
ith
h
ea
r
in
g
i
m
p
ai
r
er
s
.
T
h
e
p
r
o
ce
s
s
is
to
co
n
v
er
t
s
o
u
n
d
s
p
ec
tr
u
m
d
a
ta
in
to
d
ig
it
al
f
o
r
m
an
d
co
n
v
e
r
t
it
to
tex
t
.
Sp
ee
ch
r
ec
o
g
n
it
io
n
h
a
s
s
ev
er
al
s
tep
s
th
at
ar
e
i
m
p
o
r
tan
t
f
o
r
r
ec
o
g
n
izi
n
g
s
o
u
n
d
s
.
T
h
e
f
o
llo
w
i
n
g
ar
e
t
h
e
s
tep
s
t
h
at
s
p
ee
ch
r
ec
o
g
n
i
tio
n
u
s
es
to
r
ec
o
g
n
ize
s
o
u
n
d
.
R
ec
eiv
in
g
i
n
p
u
t d
ata
E
x
tr
ac
tio
n
,
i.e
.
in
p
u
t d
ata
s
to
r
ag
e
as
w
ell
a
s
d
atab
ase
cr
ea
tio
n
B
en
ch
m
ar
k
i
n
g
/
m
atch
in
g
,
w
h
i
ch
is
th
e
s
ta
g
e
o
f
m
a
tch
i
n
g
n
e
w
d
ata
w
it
h
v
o
ice
d
ata
(
m
a
tc
h
in
g
g
r
a
m
m
ar
)
in
th
e
d
atab
ase
User
id
en
tit
y
v
al
id
atio
n
Af
ter
t
h
e
d
ata
is
v
al
id
ated
,
th
e
u
s
er
(
g
e
n
er
al
p
u
b
lic)
ca
n
s
u
b
m
it
i
n
f
o
r
m
atio
n
t
h
at
w
il
l
b
e
co
n
v
e
y
ed
to
th
e
d
ea
f
th
r
o
u
g
h
m
icr
o
p
h
o
n
e
Af
ter
th
e
s
o
u
n
d
is
s
a
v
ed
,
th
e
s
y
s
te
m
w
il
l c
o
n
v
er
t t
h
e
d
ata
in
t
o
tex
t
.
Fig
u
r
e
2
.
P
r
o
ce
s
s
in
g
au
d
io
to
t
ex
ts
2
.
2
.
T
ex
t
pro
ce
s
s
ing
T
h
e
tex
ts
p
r
o
d
u
ce
d
in
th
e
p
r
e
v
io
u
s
s
tag
e
w
er
e
n
o
t
ar
r
an
g
ed
y
et,
t
h
er
ef
o
r
e
tex
t
p
r
o
ce
s
s
in
g
is
n
ee
d
ed
to
ar
r
an
g
e
an
d
to
s
p
lit th
e
te
x
t
s
b
ased
o
n
th
eir
s
y
llab
les
[
26,
27
]
.
T
h
e
f
o
llo
w
i
n
g
ar
e
s
ta
g
es i
n
tex
t p
r
o
ce
s
s
i
n
g
.
2
.
2
.
1
.
Ca
s
e
f
o
ldi
ng
C
ase
f
o
ld
in
g
i
s
t
h
e
s
ta
g
e
w
h
er
e
tex
t
s
w
er
e
h
o
m
o
g
e
n
ized
to
l
o
w
er
ca
s
e
s
.
Fi
g
u
r
e
3
i
s
t
h
e
ca
s
e
f
o
ld
i
n
g
p
r
o
ce
s
s
f
ig
u
r
e.
Fig
u
r
e
3
.
C
ase
f
o
ld
i
n
g
p
r
o
ce
s
s
2
.
2
.
2
.
T
o
k
eniz
ing
T
o
k
en
izin
g
is
s
p
litt
i
n
g
th
e
p
r
ev
io
u
s
l
y
h
o
m
o
g
en
ized
te
x
ts
i
n
to
w
o
r
d
s
.
T
h
e
w
o
r
d
s
ar
e
r
ec
o
g
n
ized
b
y
s
p
ac
e,
en
ter
,
an
d
tab
u
latio
n
.
T
h
e
Fi
g
u
r
e
4
is
a
n
illu
s
tr
atio
n
o
f
t
h
e
to
k
en
izin
g
p
r
o
ce
s
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
A
n
ew tec
h
n
o
lo
g
y
o
n
tr
a
n
s
la
tin
g
I
n
d
o
n
esia
n
s
p
o
k
en
l
a
n
g
u
a
g
e
in
to
.
.
.
(
R
is
ky
A
s
w
i R
a
ma
d
a
n
i)
3341
Fig
u
r
e
4
.
T
o
k
en
izi
n
g
p
r
o
ce
s
s
2
.
2
.
3
.
Ste
m
m
i
ng
Fu
r
t
h
er
m
o
r
e,
s
te
m
m
i
n
g
is
t
h
e
p
r
o
ce
s
s
to
s
ep
ar
ate
p
r
ef
ix
es,
b
asic
w
o
r
d
s
,
an
d
s
u
f
f
i
x
e
s
[
2
8
,
2
9
]
s
te
m
m
i
n
g
is
m
ad
e
f
r
o
m
B
a
h
a
s
a
I
n
d
o
n
esia
m
o
r
p
h
o
lo
g
y
s
t
r
u
c
tu
r
e,
w
h
ic
h
is
d
ep
icted
as
:
+
+
Af
f
i
x
atio
n
i
s
th
e
p
r
o
ce
s
s
o
f
ad
d
in
g
/ a
f
f
ix
i
n
g
o
r
af
f
ix
i
n
g
.
A
f
f
ix
atio
n
co
n
s
i
s
ts
o
f
:
p
r
ef
ix
(
p
r
ef
i
x
)
: b
er
-
,
b
e
-
,
P
E
R
-
,
p
er
-
,
d
i
-
,
ter
-
,
k
e,
s
e
s
u
f
f
ix
(
s
u
f
f
ix
)
:
-
k
an
,
-
an
,
-
i
T
h
e
u
s
e
o
f
w
o
r
d
s
i
n
I
n
d
o
n
e
s
i
an
u
s
u
a
l
l
y
g
et
s
a
p
r
ef
i
x
o
r
s
u
f
f
i
x
,
f
o
r
ex
a
m
p
le
t
h
e
w
o
r
d
ea
ts
,
th
e
w
o
r
d
g
ets
a
p
r
ef
i
x
o
f
t
h
e
w
o
r
d
an
d
t
h
e
w
o
r
d
(
ma
ka
n
)
ea
t b
asicall
y
.
T
h
e
T
ab
le
1
is
a
lis
t o
f
w
o
r
d
s
th
at
g
et
p
r
ef
i
x
a
n
d
s
u
f
f
ix
.
Ste
m
m
i
n
g
i
n
th
i
s
r
es
ea
r
ch
is
s
p
ec
i
f
icall
y
d
esi
g
n
e
d
to
b
u
ild
tr
an
s
lato
r
tech
n
o
lo
g
y
f
o
r
p
eo
p
le
w
i
t
h
h
ea
r
in
g
d
is
ab
ilit
ies.
T
h
e
i
m
ag
es
o
f
s
ig
n
la
n
g
u
a
g
e
s
y
s
te
m
o
r
s
is
tem
b
a
h
a
s
a
is
ya
r
a
t
(
SB
I
)
ar
e
s
o
u
r
ce
d
f
r
o
m
d
ictio
n
ar
y
o
f
s
i
g
n
la
n
g
u
a
g
es
p
u
b
lis
h
ed
i
n
2
0
0
1
b
y
th
e
De
p
ar
tm
e
n
t
o
f
E
d
u
ca
tio
n
.
T
h
e
t
o
tal
d
ata
o
f
w
o
r
d
s
tak
en
is
3
3
4
0
w
o
r
d
s
c
o
n
s
i
s
t
o
f
b
asic
w
o
r
d
s
,
p
r
ef
ix
e
s
,
an
d
s
u
f
f
i
x
es.
T
o
d
ev
elo
p
th
is
tec
h
n
o
lo
g
y
,
a
d
ata
s
e
t
i
s
n
ee
d
ed
to
s
to
r
e
t
h
e
w
o
r
d
s
/
te
x
t
s
.
T
h
e
tex
ts
w
o
u
ld
la
ter
b
e
s
to
r
ed
in
d
atab
ase,
a
n
d
ar
e
ca
lled
as
b
asic
w
o
r
d
s
i
n
th
is
r
esear
c
h
.
T
ex
ts
(
SIB
I
)
w
e
r
e
s
to
r
ed
in
r
ep
o
s
ito
r
y
o
r
s
p
ec
if
ied
f
o
ld
er
en
tit
led
“
I
m
ag
e
o
f
SIB
I
”.
T
h
e
p
u
r
p
o
s
e
o
f
s
ep
ar
atin
g
b
asic
w
o
r
d
s
a
n
d
i
m
a
g
es o
f
SIB
I
is
to
ac
ce
ler
ate
th
e
d
ata
co
llectio
n
p
r
o
ce
s
s
.
B
y
s
p
litt
i
n
g
t
h
e
p
r
ef
i
x
es
a
n
d
s
u
f
f
i
x
es,
s
te
m
m
i
n
g
p
r
o
ce
s
s
w
il
l
id
en
ti
f
y
t
h
e
b
asic
w
o
r
d
s
.
T
h
e
id
en
tifie
d
b
asic
w
o
r
d
s
ar
e
later
tr
ac
ed
f
o
r
its
I
d
.
E
v
er
y
w
o
r
d
g
o
i
n
g
th
r
o
u
g
h
th
i
s
tr
an
s
lato
r
tech
n
o
lo
g
y
s
h
o
u
ld
p
as
s
s
te
m
m
i
n
g
p
r
o
ce
s
s
,
i
n
th
e
Fi
g
u
r
e
5
s
h
o
w
t
h
e
e
x
a
m
p
le
o
f
s
en
ten
ce
in
p
u
t
a
n
d
t
h
e
s
te
m
m
in
g
p
r
o
ce
s
s
.
T
h
e
p
r
o
ce
s
s
ed
b
asic
w
o
r
d
s
w
er
e
th
en
s
h
o
w
n
b
ased
o
n
th
e
ir
I
d
s
,
th
e
I
d
s
w
er
e
s
u
b
s
eq
u
en
tl
y
m
atc
h
ed
w
ith
t
h
e
i
m
a
g
es o
f
w
o
r
d
s
(
SIB
I
)
s
to
r
ed
in
th
e
r
ep
o
s
ito
r
y
.
T
ab
le
1
.
L
is
t o
f
s
e
n
te
n
ce
s
to
t
e
s
t
N
u
mb
e
r
W
o
r
d
P
r
e
f
i
x
B
a
si
c
W
o
r
d
S
u
f
f
i
x
1.
M
e
mak
a
n
(
e
a
t
)
Me
-
M
a
k
a
n
(
e
a
t
)
2.
M
e
mb
a
c
a
(
r
e
a
d
)
M
e
m
-
B
a
c
a
(
r
e
a
d
)
3.
B
e
r
si
h
k
a
n
(
c
l
e
a
n
i
n
g
)
B
e
r
si
h
(
c
l
e
a
n
i
n
g
)
-
k
a
n
4.
M
e
n
u
l
i
s
(
w
r
i
t
e
)
Me
-
T
u
l
i
s
(
w
r
i
t
e
)
5.
M
a
n
d
i
k
a
n
(
b
a
t
h
e
)
M
a
n
d
i
(
b
a
t
h
e
)
-
k
a
n
Fig
u
r
e
5
.
Ste
m
m
i
n
g
p
r
o
ce
s
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
4
,
A
u
g
u
s
t
2021
:
3
3
3
8
-
334
6
3342
2
.
2
.
4
.
T
ex
t
t
o
i
m
a
g
e
T
h
e
p
r
o
ce
s
s
o
f
co
n
v
er
t
in
g
te
x
t
to
i
m
a
g
es
(
SIB
I
)
u
s
e
s
a
n
I
d
as
a
li
n
k
b
et
w
ee
n
te
x
t
a
n
d
i
m
a
g
e
te
x
t
(
SIB
I
)
.
T
ex
t
i
m
ag
e
s
(
SIB
I
)
a
r
e
s
to
r
ed
in
a
s
p
ec
if
ic
r
ep
o
s
i
to
r
y
,
to
allo
w
f
aster
ac
ce
s
s
an
d
lig
h
ten
s
y
s
te
m
p
er
f
o
r
m
a
n
ce
.
Fi
g
u
r
e
6
is
a
s
i
m
p
le
i
m
a
g
e
s
h
o
w
i
n
g
t
h
e
p
r
o
ce
s
s
o
f
co
n
v
er
ti
n
g
te
x
t
to
te
x
t
i
m
ag
e
(
SIB
I
)
.
I
n
t
h
i
s
r
esear
ch
,
I
n
d
ex
i
n
g
i
s
co
n
d
u
c
t
ed
to
m
atc
h
th
e
te
x
t
s
w
it
h
i
m
ag
e
s
(
SIB
I
)
.
T
h
e
f
o
llo
w
i
n
g
ch
ar
t
illu
s
tr
ates
t
h
e
m
atc
h
in
g
p
r
o
ce
s
s
as s
h
o
w
n
in
Fig
u
r
e
7
.
Fig
u
r
e
6
.
Flo
w
c
h
ar
t o
f
i
n
d
ex
i
n
g
tex
t
s
w
it
h
i
m
ag
e
s
Fig
u
r
e
7
.
I
llu
s
tr
atio
n
o
n
m
atc
h
in
g
t
e
x
t I
d
to
i
m
a
g
e
I
d
2
.
2
.
5
.
Sente
nces in sig
n la
ng
ua
g
e
I
m
ag
e
s
o
f
w
o
r
d
s
(
SIB
I
)
w
h
ic
h
w
er
e
p
r
ev
io
u
s
l
y
s
ep
ar
ated
t
h
en
b
ei
n
g
ar
r
an
g
ed
i
n
a
s
en
te
n
ce
(
SIB
I
)
.
I
m
ag
e
s
o
f
s
e
n
te
n
ce
s
(
SIB
I
)
c
an
b
e
ea
s
il
y
s
ee
n
b
y
t
h
e
p
eo
p
le
w
it
h
h
ea
r
i
n
g
d
is
ab
il
ities
.
T
h
e
d
is
p
lay
i
n
th
i
s
o
u
tp
u
t
is
s
ti
ll
in
b
lack
an
d
wh
ite
b
ased
o
n
its
s
o
u
r
ce
s
in
t
h
e
d
ictio
n
ar
y
w
h
ic
h
w
er
e
o
b
tain
ed
th
r
o
u
g
h
i
m
ag
e
s
ca
n
n
i
n
g
.
T
h
e
Fig
u
r
e
8
is
th
e
i
m
ag
e
o
f
s
e
n
ten
ce
(
SIB
I
)
o
u
tp
u
t.
Fig
u
r
e
8
.
Sen
te
n
ce
s
i
n
th
e
f
o
r
m
o
f
I
n
d
o
n
e
s
ia
n
s
i
g
n
l
a
n
g
u
a
g
e
s
y
s
te
m
(
SIB
I
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
A
n
ew tec
h
n
o
lo
g
y
o
n
tr
a
n
s
la
tin
g
I
n
d
o
n
esia
n
s
p
o
k
en
l
a
n
g
u
a
g
e
in
to
.
.
.
(
R
is
ky
A
s
w
i R
a
ma
d
a
n
i)
3343
3.
RE
SU
L
T
S
A
ND
D
I
SCU
SS
I
O
N
3
.
1
.
P
re
cisi
o
n a
nd
re
ca
ll
a
cc
ura
cy
a
na
ly
s
is
Mo
d
el
test
in
g
i
s
an
e
s
s
e
n
tial
s
tep
,
co
n
s
id
er
in
g
t
h
e
ap
p
licati
o
n
w
ill
b
e
d
ir
ec
tl
y
r
elate
d
to
th
e
p
eo
p
le
w
it
h
h
ea
r
in
g
d
is
ab
ilit
y
[
3
0
-
32]
.
T
o
an
aly
ze
ac
c
u
r
ac
y
,
p
r
ec
is
io
n
,
an
d
r
ec
all
test
o
f
t
h
i
s
ap
p
licatio
n
,
co
n
f
u
s
io
n
m
atr
i
x
i
s
u
s
ed
.
Data
is
u
s
ed
t
o
test
1
0
0
s
e
n
te
n
ce
s
(
a
u
d
io
)
t
o
b
e
co
n
v
er
ted
to
i
m
a
g
es
o
f
t
ex
ts
(
SIB
I
)
.
Data
in
T
ab
le
2
is
d
ata
u
s
ed
in
s
y
s
te
m
test
i
n
g
.
B
y
u
s
i
n
g
co
n
f
u
s
io
n
m
atr
i
x
,
r
esear
ch
er
ca
n
as
s
ess
s
y
s
te
m
s
u
cc
es
s
r
ate,
b
y
ca
lc
u
lati
n
g
ac
c
u
r
ac
y
,
p
r
ec
is
io
n
,
an
d
r
ec
all
as
s
u
cc
es
s
p
ar
a
m
eter
.
T
h
e
Fig
u
r
e
9
s
h
o
w
s
ac
cu
r
ac
y
,
p
r
ec
is
io
n
an
d
r
ec
all
ca
lcu
latio
n
.
T
ab
le
2
.
L
is
t o
f
s
e
n
te
n
ce
s
to
t
e
s
t
N
u
mb
e
r
S
e
n
t
e
n
c
e
1
sa
y
a
m
e
m
b
a
c
a
b
u
k
u
se
t
i
a
p
so
re
2
st
o
p
,
a
p
a
y
a
n
g
k
a
m
u
l
a
k
u
k
a
n
3
a
y
o
s
i
l
a
h
k
a
n
a
i
rn
y
a
d
i
m
i
n
u
m
Fig
u
r
e
9
.
R
esear
ch
r
es
u
lt
a
n
al
y
s
i
s
u
s
in
g
c
o
n
f
u
s
io
n
m
atr
i
x
T
h
e
d
ata
is
o
b
tain
ed
f
r
o
m
t
h
e
ap
p
licatio
n
test
in
g
r
es
u
lt
s
.
Fro
m
th
e
d
ata,
r
esear
ch
er
is
allo
w
ed
to
ac
q
u
ir
e
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
an
d
r
ec
all
v
alu
es
o
f
t
h
e
ap
p
licatio
n
.
T
h
e
d
et
ailed
ca
lcu
latio
n
is
s
h
o
w
n
i
n
(
1
)
-
(
3
)
.
T
h
e
ca
lcu
la
tio
n
h
a
s
r
es
u
lted
i
n
t
h
e
v
a
lu
e
s
o
f
p
r
ec
is
io
n
i
s
7
6
%,
ac
cu
r
ac
y
is
7
8
%,
a
n
d
r
ec
all
is
7
9
%.
I
t
ca
n
b
e
co
n
clu
d
ed
f
r
o
m
t
h
e
v
a
lu
e
s
th
a
t th
is
tec
h
n
o
lo
g
y
r
u
n
w
e
ll.
=
(
+
)
+
+
+
(
1
)
=
(
38
+
40
)
38
+
40
+
12
+
10
=
0
,
78
=
+
(
2
)
=
38
38
+
12
=
0
,
76
=
+
(
3
)
=
38
38
+
10
=
0
,
79
3
.
2
.
T
esting
o
f
t
ra
ns
la
t
o
r
t
ec
hn
o
lo
g
y
in s
t
ud
ent
s
o
f
SM
P
-
LB
K
a
ry
a
M
uli
a
Su
ra
ba
y
a
T
esti
n
g
o
f
tr
a
n
s
la
to
r
tech
n
o
l
o
g
y
i
n
S
u
r
ab
a
y
a
Mu
l
y
a
J
u
n
i
o
r
Hig
h
Sc
h
o
o
l
-
L
B
s
t
u
d
en
t
s
is
n
ee
d
ed
,
co
n
s
id
er
in
g
t
h
at
t
h
is
tr
an
s
lato
r
tech
n
o
lo
g
y
w
i
ll
b
e
u
s
ed
b
y
d
ea
f
p
eo
p
le.
T
r
an
s
lato
r
tech
n
o
lo
g
y
w
a
s
test
ed
o
n
1
st
g
r
ad
e
s
tu
d
e
n
ts
o
f
SMP
-
L
B
Su
r
ab
a
y
a,
t
h
ese
s
t
u
d
en
ts
w
er
e
ag
ed
1
2
-
1
3
y
ea
r
s
.
T
h
e
s
y
s
te
m
w
as
test
ed
o
n
9
s
tu
d
e
n
ts
.
T
h
e
Fi
g
u
r
e
1
0
is
a
p
h
o
to
o
f
t
h
e
tr
ial
ac
ti
v
itie
s
ca
r
r
ied
o
u
t
at
SMP
-
L
B
Kar
y
a
Mu
l
y
a
S
u
r
ab
a
y
a.
I
n
s
tr
u
m
e
n
t
is
n
ee
d
ed
to
m
ea
s
u
r
e
th
e
s
u
cc
e
s
s
o
f
tr
an
s
lato
r
tech
n
o
lo
g
y
,
in
t
h
e
p
ilo
t
p
h
ase
a
q
u
esti
o
n
n
air
e
i
s
u
s
ed
.
T
o
an
aly
ze
t
h
e
n
u
m
b
er
o
f
s
tu
d
e
n
ts
f
r
o
m
SMP
-
L
B
K
ar
y
a
Mu
l
y
a
S
u
r
ab
a
y
a
w
h
o
r
ate
t
h
is
a
p
p
licatio
n
it
i
s
g
o
o
d
to
u
s
e
(
4
)
.
Ind
e
x
for
m
ul
a
%
=
t
o
t
al
s
co
r
e
Y
∗
100
(
4
)
Fro
m
(
4
)
,
it
is
f
o
u
n
d
th
at
t
h
e
p
er
ce
n
tag
e
o
f
s
t
u
d
en
t
s
w
h
o
g
av
e
ex
ce
lle
n
t
g
r
ad
es,
c
an
b
e
s
ee
n
m
o
r
e
clea
r
l
y
in
t
h
e
T
ab
le
3.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
4
,
A
u
g
u
s
t
2021
:
3
3
3
8
-
334
6
3344
Fig
u
r
e
1
0
.
T
r
ial
tr
an
s
lato
r
s
y
s
t
e
m
t
r
an
s
lati
n
g
I
n
d
o
n
esia
n
s
p
o
k
en
l
a
n
g
u
a
g
e
i
n
to
I
n
d
o
n
esia
n
s
ig
n
l
a
n
g
u
a
g
e
s
y
s
te
m
(
SIB
I
)
T
ab
le
3
.
R
esu
lts
o
f
th
e
as
s
es
s
m
en
t b
y
q
u
es
tio
n
n
air
e
N
u
mb
e
r
A
ss
e
ssm
e
n
t
p
a
r
a
me
t
e
r
s
T
h
e
r
e
su
l
t
s t
h
a
t
s
h
o
w
a
r
e
v
e
r
y
g
o
o
d
1.
I
n
t
e
r
f
a
c
e
8
7
%
2.
N
a
v
i
g
a
t
i
o
n
me
n
u
7
1
%
3.
T
r
a
n
sl
a
t
i
o
n
r
e
su
l
t
s
9
8
%
4.
U
se
r
G
u
i
d
e
7
3
%
5.
I
n
f
o
r
mat
i
v
e
9
8
%
6.
R
e
c
o
r
d
i
n
g
se
n
si
t
i
v
i
t
y
8
7
%
A
v
e
r
a
g
e
8
6
%
Fro
m
t
h
e
r
es
u
lt
s
i
n
Fig
u
r
e
3
i
t
ca
n
b
e
co
n
cl
u
d
ed
th
at
8
6
%
o
f
r
esp
o
n
d
en
ts
r
ated
tr
an
s
lato
r
t
ec
h
n
o
lo
g
y
as
v
er
y
g
o
o
d
.
T
h
is
r
esear
ch
a
ls
o
g
et
s
s
o
m
e
ad
v
ice
f
r
o
m
p
e
o
p
le
w
it
h
h
ea
r
in
g
i
m
p
a
ir
m
e
n
t
s
u
c
h
as
i
m
p
r
o
v
i
n
g
ac
cu
r
ac
y
,
i
n
cr
ea
s
i
n
g
v
o
ca
b
u
l
ar
y
,
a
n
d
i
m
p
r
o
v
in
g
ap
p
ea
r
an
ce
.
A
n
d
n
ee
d
s
to
b
e
m
ad
e
an
An
d
r
o
id
-
b
ased
ap
p
licatio
n
.
4.
CO
NCLU
SI
O
N
T
h
is
n
e
w
tech
n
o
lo
g
y
o
n
tr
an
s
latin
g
s
p
o
k
e
n
lan
g
u
ag
e
(
au
d
io
)
to
I
n
d
o
n
esian
s
i
g
n
la
n
g
u
a
g
e
s
y
s
te
m
i
s
ca
p
ab
le
to
tr
an
s
late
s
p
o
k
en
l
an
g
u
a
g
e
to
SIB
I
lan
g
u
a
g
e.
T
h
e
s
tag
es
i
n
co
n
d
u
ctin
g
tr
a
n
s
lat
io
n
ar
e
s
p
ee
ch
r
ec
o
g
n
itio
n
,
tex
t
p
r
o
ce
s
s
i
n
g
,
b
asic
w
o
r
d
s
,
i
m
a
g
es
o
f
SIB
I
,
s
te
m
m
i
n
g
,
in
d
ex
in
g
,
s
e
n
ten
ce
s
in
s
i
g
n
lan
g
u
a
g
e,
an
d
v
id
eo
in
SIB
I
.
Vid
eo
is
u
s
ed
to
allo
w
t
h
e
p
eo
p
le
w
ith
h
ea
r
in
g
d
is
ab
ilit
ies
to
r
ec
eiv
e
o
u
tp
u
t
ea
s
il
y
.
T
h
i
s
tr
an
s
lati
n
g
tec
h
n
o
lo
g
y
h
as
b
e
en
te
s
ted
t
h
r
o
u
g
h
co
n
v
er
tin
g
s
p
o
k
e
n
s
e
n
te
n
ce
s
.
T
h
e
to
tal
n
u
m
b
er
o
f
s
p
o
k
en
s
en
te
n
ce
s
i
s
1
0
0
s
en
ten
ce
s
.
Fro
m
th
e
tes
t,
it
w
a
s
o
b
tain
e
d
th
e
d
ata
s
u
ch
as
:
p
r
ec
is
io
n
v
alu
e
o
f
7
6
%
an
d
ac
cu
r
ac
y
v
al
u
e
o
f
7
8
%.
T
h
e
r
ec
all
v
al
u
e
in
th
i
s
s
y
s
te
m
i
s
a
lr
ea
d
y
g
o
o
d
in
th
e
n
u
m
b
er
o
f
7
9
%.
Fro
m
t
h
at,
i
t
ca
n
b
e
co
n
c
lu
d
ed
t
h
at
t
h
e
s
y
s
te
m
h
a
s
b
ee
n
ab
le
to
tr
a
n
s
la
te
s
p
o
k
e
n
s
e
n
te
n
ce
s
to
p
ict
u
r
ed
s
en
te
n
ce
s
i
n
t
h
e
f
o
r
m
o
f
SIB
I
i
m
a
g
es.
W
h
er
e
as
f
o
r
in
ter
f
ac
e
ass
e
s
s
m
e
n
t,
n
av
i
g
atio
n
m
e
n
u
,
tr
an
s
la
tio
n
r
esu
lt
s
,
u
s
er
g
u
id
e,
in
f
o
r
m
ati
v
e,
an
d
r
ec
o
r
d
in
g
s
e
n
s
iti
v
it
y
.
Va
lu
e
b
y
r
esp
o
n
d
e
n
ts
is
v
er
y
g
o
o
d
,
w
it
h
an
a
v
er
ag
e
v
alu
e
o
f
8
6
%.
RE
F
E
R
E
NC
E
S
[1
]
T
o
b
a
,
Y.,
Ho
riu
c
h
i,
H.,
M
a
tsu
m
o
t
o
,
S
.
,
S
a
ik
i,
S
.
,
Na
k
a
m
u
ra
,
M
.
,
Uc
h
in
o
,
T
e
t
a
l
.,
“
Co
n
sid
e
ri
n
g
m
u
lt
i
-
m
o
d
a
l
sp
e
e
c
h
v
isu
a
li
z
a
ti
o
n
f
o
r
d
e
a
f
a
n
d
h
a
rd
o
f
h
e
a
rin
g
p
e
o
p
le,
”
2
0
1
5
1
0
t
h
Asia
-
P
a
c
if
ic
S
y
mp
o
si
u
m
o
n
In
fo
rm
a
t
io
n
a
n
d
T
e
lec
o
mm
u
n
ica
ti
o
n
T
e
c
h
n
o
l
o
g
ies
(
AP
S
IT
T
)
,
C
o
lo
m
b
o
,
2
0
1
5
,
p
p
.
1
–
3
,
d
o
i:
1
0
.
1
1
0
9
/A
P
S
IT
T
.
2
0
1
5
.
7
2
1
7
1
0
2
.
[2
]
V
.
E
Ne
w
to
n
a
n
d
S
.
R
.
S
h
a
h
,
“
I
m
p
ro
v
in
g
c
o
m
m
u
n
ica
ti
o
n
w
it
h
p
a
ti
e
n
ts
w
it
h
a
h
e
a
rin
g
im
p
a
ir
m
e
n
t,
”
Co
mm
u
n
i
ty
Eye
He
a
lt
h
,
v
o
l
.
26
,
p
p
.
6
–
7
,
2
0
1
3
.
[3
]
U
.
L
e
m
k
e
a
n
d
S
.
S
c
h
e
r
p
iet,
“
Ora
l
c
o
m
m
u
n
ica
ti
o
n
in
in
d
iv
id
u
a
ls
w
it
h
h
e
a
rin
g
im
p
a
irme
n
t
-
c
o
n
sid
e
ra
ti
o
n
s
re
g
a
rd
in
g
a
tt
e
n
ti
o
n
a
l,
”
Fro
n
t
Psy
c
h
o
l
.
,
v
o
l
.
1
7
,
p
p
.
8
–
1
5
,
2
0
1
5
.
[4
]
S
.
D
L
a
ra
sa
ti
,
V
.
Ku
b
o
ň
,
a
n
d
D.
Zem
a
n
,
“
In
d
o
n
e
sia
n
M
o
rp
h
o
lo
g
y
T
o
o
l
(M
o
rp
h
In
d
):
T
o
w
a
rd
s
a
n
In
d
o
n
e
sia
n
Co
rp
u
s
,
”
In
ter
n
a
ti
o
n
a
l
W
o
rk
sh
o
p
o
n
S
y
ste
ms
a
n
d
Fr
a
me
wo
rk
s
fo
r
Co
mp
u
ta
t
io
n
a
l
M
o
rp
h
o
lo
g
y
,
2
0
1
1
,
v
o
l
.
4
,
pp
.
1
1
9
–
1
9
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
A
n
ew tec
h
n
o
lo
g
y
o
n
tr
a
n
s
la
tin
g
I
n
d
o
n
esia
n
s
p
o
k
en
l
a
n
g
u
a
g
e
in
to
.
.
.
(
R
is
ky
A
s
w
i R
a
ma
d
a
n
i)
3345
[5
]
F
.
P
isc
e
ld
o
,
R.
M
a
h
e
n
d
ra
,
R.
M
a
n
u
r
u
n
g
,
a
n
d
I
.
W
.
A
r
k
a
,
“
A
Tw
o
-
L
e
v
e
l
M
o
rp
h
o
lo
g
ica
l
A
n
a
l
y
se
r
f
o
r
th
e
In
d
o
n
e
sia
n
L
a
n
g
u
a
g
e
,
”
Asso
c
ia
ti
o
n
fo
r C
o
mp
u
ta
ti
o
n
a
l
L
in
g
u
ist
ics
,
v
o
l.
5
,
p
p
.
1
–
6
,
2
0
1
4
.
[6
]
H.
A
l
w
i,
S.
A
rd
jo
w
id
jo
jo
,
a
n
d
H
.
L
a
p
o
li
w
a
,
“
In
d
o
n
e
sia
n
L
a
n
g
u
a
g
e
S
tan
d
a
rd
G
ra
m
m
a
r
,
”
(in
In
d
o
n
e
sia
),
P
u
sa
t
d
a
n
Ba
lai
P
u
sta
k
a
,
Ja
k
a
rta,
2
0
0
3
.
[7
]
De
p
a
rter
m
e
n
P
e
n
d
i
d
ik
a
n
Na
sio
n
a
l
In
d
o
n
e
sia
,
“
In
d
o
n
e
sia
n
S
ig
n
S
y
ste
m
,
”
(in
In
d
o
n
e
sia
)
,
P
u
sa
t
d
a
n
Ba
lai
P
u
sta
k
a
,
Ja
k
a
rta,
2
0
0
2
.
[8
]
A
.
W
.
Ya
n
u
a
rd
i,
S
.
P
ra
se
ti
o
,
a
n
d
P
.
P
.
J.
A
d
i,
“
In
d
o
n
e
sia
n
S
ig
n
L
a
n
g
u
a
g
e
Co
m
p
u
ter
A
p
p
li
c
a
ti
o
n
f
o
r
t
h
e
De
a
f
,
”
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
E
d
u
c
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
a
n
d
Co
m
p
u
ter
,
S
h
a
n
g
h
a
i
,
2
0
1
0
,
v
ol
.
2
,
p
p
.
57
–
6
5
.
[9
]
M
.
N.
Ba
e
h
a
q
i,
M
.
Irz
a
l
,
a
n
d
F
.
H.
In
d
iy
a
h
,
“
M
o
rp
h
o
l
o
g
ica
l
A
n
a
l
y
sis
o
f
S
p
e
e
c
h
T
ra
n
sla
ti
o
n
in
t
o
I
n
d
o
n
e
sia
n
S
ig
n
L
a
n
g
u
a
g
e
S
y
ste
m
(S
IBI)
o
n
A
n
d
ro
i
d
P
latf
o
rm
,
”
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
Ad
v
a
n
c
e
d
Co
m
p
u
t
e
r
S
c
ien
c
e
a
n
d
in
fo
rm
a
ti
o
n
S
y
ste
ms
(
ICACS
IS
)
,
Ba
li
,
2
0
1
5
,
p
p
.
2
0
5
–
21
0
.
[1
0
]
W
.
K.
M
p
ra
h
,
“
S
o
u
rc
e
s
a
n
d
Us
e
o
f
S
e
x
u
a
l
a
n
d
Re
p
ro
d
u
c
ti
v
e
He
a
l
th
In
f
o
rm
a
ti
o
n
Am
o
n
g
De
a
f
P
e
o
p
le
in
G
h
a
n
a
,
”
In
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
Disa
b
il
it
y
S
tu
d
ies
,
v
o
l.
1
,
pp
.
1
–
1
1
,
2
0
1
4
.
[1
1
]
R.
A
.
Ra
m
a
d
h
a
n
i,
I.
D.
P
u
tra,
M
.
S
u
d
a
rm
a
,
a
n
d
I.
A
.
G
iri
a
n
tari,
“
Da
tab
a
se
o
f
In
d
o
n
e
sia
n
S
ig
n
S
y
ste
m
,
”
in
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
S
ma
rt Gre
e
n
T
e
c
h
n
o
lo
g
y
in
El
e
c
trica
l
a
n
d
I
n
f
o
rm
a
ti
o
n
S
y
ste
ms
,
Ba
li
,
I
n
d
o
n
e
sia
,
2
0
1
8
,
vo
l.
3
,
pp
.
2
2
5
–
2
2
8
.
[1
2
]
R.
M
.
M
c
G
u
i
re
,
J.
He
rn
a
n
d
e
z
-
Re
b
o
ll
a
r,
T
.
S
tarn
e
r,
V.
He
n
d
e
rso
n
,
H.
Bra
sh
e
a
r
,
a
n
d
D.
S
.
Ro
ss
,
“
T
o
w
a
rd
s
a
o
n
e
-
w
a
y
Am
e
rica
n
si
g
n
lan
g
u
a
g
e
tr
a
n
sla
to
r,
”
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Au
t
o
ma
ti
c
Fa
c
e
a
n
d
Ge
stu
re
Rec
o
g
n
it
i
o
n
,
S
e
o
u
l,
2
0
0
4
,
v
o
l
.
6
,
p
p
.
6
2
0
–
6
2
5
.
[1
3
]
T
.
S
h
im
a
d
a
,
R.
Ni
sh
im
u
ra
,
M
.
T
a
n
a
k
a
,
H.
Ka
wa
h
a
ra
,
a
n
d
T
.
Irin
o
,
“
De
v
e
lo
p
in
g
a
m
e
th
o
d
t
o
b
u
i
ld
Ja
p
a
n
e
se
sp
e
e
c
h
re
c
o
g
n
it
io
n
sy
ste
m
,
”
Co
n
fer
e
n
c
e
An
th
o
lo
g
y
,
C
h
in
a
,
Ja
n
.
2
0
1
3
,
p
p
.
1
2
0
–
1
2
5
.
[1
4
]
A
.
N
.
d
e
A
n
d
ra
d
e
,
C.
M
a
ria
,
a
n
d
Da
n
iela
G.
,
“
S
p
e
e
c
h
re
c
o
g
n
it
io
n
in
i
n
d
iv
i
d
u
a
ls
w
it
h
se
n
so
ri
n
e
u
ra
l
h
e
a
rin
g
lo
ss
,
”
Bra
zili
a
n
J
o
u
rn
a
l
o
f
Oto
r
h
in
o
la
ry
n
g
o
lo
g
y
,
v
o
l.
2
8
,
p
p
.
1
–
5
,
2
0
1
6
.
[1
5
]
C.
Bro
o
k
e
s,
“
S
p
e
e
c
h
-
to
-
tex
t
sy
ste
m
s
f
o
r
d
e
a
f
,
d
e
a
f
e
n
e
d
a
n
d
h
a
rd
-
of
-
h
e
a
rin
g
p
e
o
p
le,”
in
S
e
mi
n
a
r
o
n
S
p
e
e
c
h
a
n
d
L
a
n
g
u
a
g
e
Pr
o
c
e
ss
in
g
f
o
r Disa
b
le
d
a
n
d
El
d
e
rly
Peo
p
le
,
L
o
n
d
o
n
,
2
0
0
0
,
v
o
l.
4
,
p
p
.
5
/
1
–
5
/4
.
[1
6
]
X
.
L
in
,
J.
Ya
n
g
,
a
n
d
J.
Z
h
a
o
,
“
T
h
e
tex
t
a
n
a
l
y
sis a
n
d
p
ro
c
e
ss
in
g
o
f
T
h
a
i
lan
g
u
a
g
e
te
x
t
to
sp
e
e
c
h
c
o
n
v
e
rsio
n
s
y
ste
m
,
”
in
In
ter
n
a
ti
o
n
a
l
S
y
mp
o
si
u
m o
n
C
h
in
e
se
S
p
o
k
e
n
L
a
n
g
u
a
g
e
Pro
c
e
ss
in
g
,
S
in
g
a
p
o
re
,
2
0
1
4
,
v
o
l.
9
,
p
p
.
4
3
6
–
4
3
6
.
[1
7
]
R.
F
o
rg
á
č
a
n
d
R.
Kra
k
o
v
sk
ý
,
“
T
e
x
t
p
ro
c
e
ss
in
g
b
y
u
sin
g
p
ro
jec
ti
v
e
A
R
T
n
e
u
ra
l
n
e
tw
o
rk
s,
”
in
Ne
w
T
re
n
d
s
in
S
ig
n
a
l
Pro
c
e
ss
in
g
(
NT
S
P)
,
De
m
a
n
o
v
sk
a
Do
li
n
a
,
v
o
l.
6
,
p
p
.
1
–
5,
2
0
1
6
.
[1
8
]
A
.
G
h
a
z
v
in
i
a
n
d
M
.
J.
A
b
A
z
i
z
,
“
S
tem
m
in
g
a
l
g
o
rit
h
m
f
o
r
d
if
fe
re
n
t
ten
se
s
to
im
p
ro
v
e
P
e
rsia
n
d
icti
o
n
a
ry
,
”
in
S
y
mp
o
si
u
m o
n
In
d
u
stri
a
l
E
lec
tro
n
ics
a
n
d
A
p
p
li
c
a
ti
o
n
s
,
Ba
n
d
u
n
g
,
2
0
1
2
,
p
p
.
5
0
–
5
3
.
[1
9
]
F.
S
.
A
lo
taib
i
a
nd
V
.
G
u
p
ta,
“
A
c
o
g
n
it
iv
e
in
sp
ired
u
n
su
p
e
rv
ise
d
lan
g
u
a
g
e
-
in
d
e
p
e
n
d
e
n
t
tex
t
ste
m
m
e
r
f
o
r
In
f
o
rm
a
ti
o
n
re
tri
e
v
a
l,
”
Co
g
n
it
ive
S
y
ste
ms
Res
e
a
rc
h
,
v
o
l.
58
,
p
p
.
291
–
3
0
0
,
2
0
0
0
.
[2
0
]
T
.
Ne
u
g
e
b
a
u
e
r,
“
I
m
a
g
e
in
d
e
x
in
g
,
”
T
h
e
In
d
e
x
e
r
,
v
o
l.
2
8
,
p
p
.
9
8
–
1
0
3
,
2
0
1
0
.
[2
1
]
S
.
Ru
u
sk
a
,
W
.
Hä
m
ä
l
ä
in
e
n
,
S
.
K
a
jav
a
,
M
.
M
u
g
h
a
l,
P
.
M
a
ti
lain
e
n
,
J
.
M
o
n
o
n
e
n
,
a
n
d
M
.
J
o
li
a
t,
“
A
E
v
a
lu
a
ti
o
n
o
f
th
e
c
o
n
f
u
sio
n
m
a
tri
x
m
e
th
o
d
i
n
th
e
v
a
li
d
a
ti
o
n
o
f
a
n
a
u
to
m
a
ted
s
y
ste
m
f
o
r
m
e
a
su
rin
g
f
e
e
d
in
g
b
e
h
a
v
io
u
r
o
f
c
a
tt
le,
”
Beh
a
v
io
u
ra
l
Pro
c
e
ss
e
s
,
v
ol
.
1
4
8
,
p
p
.
5
6
–
6
2
,
2
0
1
8
.
[2
2
]
P
.
T
ra
jd
o
s
a
n
d
M
.
K
u
rz
y
n
sk
i,
“
Weig
h
ti
n
g
sc
h
e
m
e
f
o
r
a
p
a
ir
w
ise
m
u
lt
i
-
lab
e
l
c
las
sif
ier
b
a
se
d
o
n
th
e
f
u
z
z
y
c
o
n
f
u
sio
n
m
a
tri
x
,
”
Pa
tt
e
rn
Rec
o
g
n
it
i
o
n
L
e
tt
e
rs
,
v
o
l.
1
0
3
,
p
p
.
60
–
6
7
,
2
0
1
8
.
[2
3
]
K.
P
.
Di
p
in
,
J.
Bo
se
,
a
n
d
S
.
P
a
l,
“
Us
e
r
F
rien
d
ly
T
a
b
M
a
n
a
g
e
m
e
n
t
in
W
e
b
Br
o
w
se
rs,
”
in
An
n
u
a
l
Co
n
su
me
r
Co
mm
u
n
ica
ti
o
n
s &
N
e
two
rk
in
g
C
o
n
fer
e
n
c
e
(
CCNC)
,
L
a
s V
e
g
a
s
,
v
o
l.
1
6
,
p
p
.
1
–
4
,
2
0
1
9
.
[2
4
]
V
.
M
it
ra
,
H.
F
ra
n
c
o
,
M
.
G
ra
c
ia
re
n
a
,
a
n
d
D.
V
e
rg
y
ri,
“
M
e
d
iu
m
-
d
u
ra
ti
o
n
m
o
d
u
latio
n
c
e
p
stra
l
f
e
a
tu
re
f
o
r
ro
b
u
st
sp
e
e
c
h
re
c
o
g
n
it
io
n
,
”
in
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Aco
u
stics
,
S
p
e
e
c
h
a
n
d
S
i
g
n
a
l
Pro
c
e
ss
in
g
(
ICAS
S
P)
,
2
0
1
4
,
p
p
.
1
7
4
9
–
1
7
5
3
.
[2
5
]
T
.
A
th
a
n
a
se
li
s,
S
.
Ba
k
a
m
id
is,
G
.
G
ian
n
o
p
o
u
lo
s,
I
.
Do
l
o
g
lo
u
,
a
n
d
E.
F
o
t
in
e
a
,
“
Ro
b
u
st
sp
e
e
c
h
re
c
o
g
n
it
io
n
i
n
th
e
p
re
se
n
c
e
o
f
n
o
ise
u
sin
g
m
e
d
ica
l
d
a
ta,”
In
ter
n
a
ti
o
n
a
l
W
o
rk
sh
o
p
o
n
Ima
g
i
n
g
S
y
ste
ms
a
n
d
T
e
c
h
n
i
q
u
e
s
,
Cre
te,
2
0
0
8
,
p
p
.
3
4
9
–
3
5
2
.
[2
6
]
X
.
L
in
,
J.
Ya
n
g
,
a
n
d
J.
Z
h
a
o
,
“
T
h
e
tex
t
a
n
a
l
y
sis a
n
d
p
ro
c
e
ss
in
g
o
f
T
h
a
i
lan
g
u
a
g
e
te
x
t
to
sp
e
e
c
h
c
o
n
v
e
rsio
n
s
y
ste
m
,
”
in
In
ter
n
a
ti
o
n
a
l
S
y
mp
o
si
u
m
o
n
Ch
in
e
se
S
p
o
k
e
n
L
a
n
g
u
a
g
e
Pr
o
c
e
ss
in
g
,
S
i
n
g
a
p
o
re
,
v
o
l
.
9
,
p
p
.
4
3
6
–
4
3
6
,
2
0
1
4
,
d
o
i:
1
0
.
1
1
0
9
/IS
C
S
L
P
.
2
0
1
4
.
6
9
3
6
6
3
0
.
[2
7
]
L
.
S
k
o
v
a
jso
v
á
,
“
L
o
n
g
sh
o
rt
-
term
m
e
m
o
r
y
d
e
s
c
rip
ti
o
n
a
n
d
it
s
a
p
p
l
ica
ti
o
n
i
n
tex
t
p
ro
c
e
ss
in
g
,
”
Co
m
mu
n
ica
t
io
n
a
n
d
In
fo
rm
a
t
io
n
T
e
c
h
n
o
l
o
g
ies
,
V
y
so
k
e
T
a
tr
y
,
p
p
.
1
–
4
,
2
0
1
7
.
[2
8
]
G
.
S
e
p
ti
a
n
,
A
.
S
u
sa
n
to
,
a
n
d
G
.
F
.
S
h
i
d
ik
,
“
In
d
o
n
e
sia
n
n
e
w
s
c
la
ss
if
ic
a
ti
o
n
b
a
se
d
o
n
Na
Ba
NA
,
”
i
n
In
ter
n
a
ti
o
n
a
l
S
e
min
a
r
o
n
Ap
p
li
c
a
t
io
n
fo
r
T
e
c
h
n
o
l
o
g
y
o
f
I
n
fo
rm
a
ti
o
n
a
n
d
C
o
mm
u
n
ic
a
ti
o
n
,
S
e
m
a
ra
n
g
,
2
0
1
7
,
p
p
.
1
7
5
–
1
8
0
,
d
o
i:
1
0
.
1
1
0
9
/IS
E
M
A
NT
IC.
2
0
1
7
.
8
2
5
1
8
6
5
.
[2
9
]
D.
S
.
M
a
y
la
w
a
ti
,
W
.
B.
Zu
lf
i
k
a
r
,
C.
S
la
m
e
t,
M
.
A
.
Ra
m
d
h
a
n
i
,
a
n
d
Y.
A
.
Ge
rh
a
n
a
,
“
A
n
I
m
p
ro
v
e
d
o
f
S
te
m
m
in
g
A
l
g
o
rit
h
m
f
o
r
M
in
in
g
In
d
o
n
e
sia
n
T
e
x
t
w
it
h
S
lan
g
o
n
S
o
c
ial
M
e
d
i
a
,
”
2
0
1
8
6
th
In
ter
n
a
ti
o
n
a
l
Co
n
fe
re
n
c
e
o
n
Cy
b
e
r
a
n
d
IT
S
e
rv
ice
M
a
n
a
g
e
me
n
t
(
CIT
S
M
)
,
P
a
ra
p
a
t,
2
0
1
8
,
v
o
l.
6
,
p
p
.
1
–
6
.
[3
0
]
L
.
Ch
e
n
a
n
d
H.
L
.
T
a
n
g
,
“
I
m
p
r
o
v
e
d
c
o
m
p
u
tatio
n
o
f
b
e
li
e
f
s
b
a
se
d
o
n
c
o
n
f
u
sio
n
m
a
tri
x
f
o
r
c
o
m
b
in
i
n
g
m
u
lt
ip
le
c
las
s
i
f
iers
,
”
in
El
e
c
tro
n
ics
L
e
tt
e
rs
,
v
o
l.
4
0
,
p
p
.
2
3
8
–
2
3
9
,
2
0
0
4
.
[3
1
]
F
.
J.
A
riza
-
L
o
p
e
z
,
J.
Ro
d
rig
u
e
z
-
Av
i
,
a
n
d
M
.
V
.
A
lb
a
-
F
e
rn
a
n
d
e
z
,
“
Co
m
p
lete
Co
n
tro
l
o
f
a
n
Ob
se
rv
e
d
Co
n
f
u
sio
n
M
a
tri
x
,
”
In
ter
n
a
ti
o
n
a
l
Ge
o
sc
ien
c
e
a
n
d
Rem
o
te
S
e
n
si
n
g
S
y
mp
o
siu
m
,
V
a
len
c
ia
,
2
0
1
8
,
p
p
.
1
2
2
2
–
1
2
2
5
,
d
o
i:
1
0
.
1
1
0
9
/IG
A
RS
S
.
2
0
1
8
.
8
5
1
7
5
4
0
.
[3
2
]
D.
E.
Zo
m
a
h
o
u
n
,
“
A
S
e
m
a
n
ti
c
Co
ll
a
b
o
ra
ti
v
e
Clu
ste
rin
g
A
p
p
ro
a
c
h
Ba
se
d
o
n
Co
n
f
u
sio
n
M
a
tri
x
,”
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
S
i
g
n
a
l
-
Ima
g
e
T
e
c
h
n
o
l
o
g
y
&
In
ter
n
e
t
-
Ba
se
d
S
y
ste
ms
,
2
0
1
9
,
p
p
.
6
8
8
–
6
9
2
,
d
o
i:
1
0
.
1
1
0
9
/S
IT
IS
.
2
0
1
9
.
0
0
1
1
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
4
,
A
u
g
u
s
t
2021
:
3
3
3
8
-
334
6
3346
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
Ris
k
y
As
w
i
Ra
m
a
d
h
a
n
i
,
Bo
rn
Ap
ril
8
,
1
9
9
0
,
S
1
a
t
Nu
sa
n
tara
Un
iv
e
rsit
y
P
G
RI
Ke
d
iri
,
S
2
a
t
th
e
Yo
g
y
a
k
a
rta
Ac
a
d
e
m
y
o
f
Co
m
p
u
ter
S
c
ien
c
e
M
a
n
a
g
e
m
e
n
t,
is
c
u
rre
n
tl
y
a
P
h
D
stu
d
e
n
t
in
th
e
En
g
in
e
e
rin
g
S
tu
d
y
P
ro
g
ra
m
o
f
Do
c
to
ra
l
En
g
in
e
e
rin
g
a
t
Ud
a
y
a
n
a
Un
iv
e
rsit
y
,
Ba
li
,
th
e
f
ield
o
f
in
tere
st i
s
n
a
t
u
ra
l
lan
g
u
n
g
e
p
ro
c
e
ss
in
g
.
I
K
e
tu
t
G
e
d
e
Da
r
m
a
Pu
t
r
a
,
Bo
rn
M
e
n
g
w
it
a
n
i,
A
p
ril
2
4
,
1
9
7
4
.
Earn
in
g
a
Do
c
to
ra
te
d
e
g
re
e
a
t
G
a
j
a
h
M
a
d
a
Un
iv
e
rsit
y
,
in
th
e
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
S
tu
d
y
P
r
o
g
ra
m
,
th
e
a
re
a
o
f
in
tere
st
is
Im
a
g
e
P
ro
c
e
ss
in
g
/
Bio
m
e
tri
c
s.
Cu
rre
n
tl
y
tea
c
h
in
g
a
t
th
e
Do
c
t
o
ra
l
P
ro
g
ra
m
in
En
g
in
e
e
rin
g
,
Ud
a
y
a
n
a
Un
iv
e
rsit
y
.
M
a
d
e
S
u
d
a
r
m
a
,
Co
m
p
lete
d
Un
d
e
rg
ra
d
u
a
te
S
tu
d
y
In
1
9
9
2
a
t
th
e
Ten
No
v
e
m
b
e
r
In
stit
u
te
o
f
T
e
c
h
n
o
lo
g
y
S
u
ra
b
a
y
a
,
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
stu
d
y
,
Co
m
p
lete
d
M
a
ste
rs
in
2
0
0
0
a
t
t
h
e
S
c
h
o
o
l
o
f
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
a
n
d
En
g
in
e
e
rin
g
,
Ota
wa
Un
iv
e
rsit
y
,
C
a
n
a
d
a
,
S
3
c
o
m
p
lete
d
in
2
0
1
2
i
n
th
e
P
o
st
-
G
ra
d
u
a
te
P
ro
g
ra
m
,
Ud
a
y
a
n
a
Un
iv
e
rsit
y
,
F
ield
w
h
ich
a
re
in
tere
ste
d
in
d
a
ta
m
in
in
g
,
HCI
a
n
d
S
m
a
rt
S
y
st
e
m
s.
Id
a
Ay
u
Dw
i
G
iria
n
ta
r
i
,
Ch
a
ir
o
f
th
e
Co
re
(Ce
n
ter o
f
Ex
c
e
ll
e
n
c
e
Co
m
m
u
n
it
y
B
a
se
d
Re
n
e
w
a
b
le
En
e
rg
y
),
T
e
a
c
h
in
g
in
t
h
e
Do
c
t
o
ra
l
S
tu
d
ies
P
r
o
g
ra
m
in
En
g
in
e
e
rin
g
,
Ud
a
y
a
n
a
Un
iv
e
rsit
y
,
in
2
0
0
5
e
a
rn
e
d
a
P
h
.
D at t
h
e
U
n
iv
e
rsity
o
f
Ne
w
S
o
u
th
W
a
les
,
S
y
d
n
e
y
,
A
u
stra
li
a
.
Evaluation Warning : The document was created with Spire.PDF for Python.