I
nte
rna
t
io
na
l J
o
urn
a
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.
9
,
No
.
2
,
A
p
r
il
201
9
,
p
p
.
1
0
3
6
~
1
0
4
4
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v9
i
2
.
pp
1
0
3
6
-
1044
1036
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e
.
co
m/
jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
I
JE
C
E
M
usic fingerpr
int
ing
bas
ed on bha
t
tacha
ry
a
distance
f
o
r so
ng
a
nd cov
er so
ng
re
co
g
nition
Riy
a
na
rt
o
Sa
rno
1
,
Dedy
Ra
h
m
a
n
Wij
a
y
a
2
,
M
uh
a
m
m
a
d
Nez
a
r
M
a
ha
rdik
a
3
1,
2,
3
I
n
f
o
rm
a
ti
c
s De
p
a
rt
m
e
n
t,
In
stit
u
t
T
e
k
n
o
lo
g
i
S
e
p
u
l
u
h
N
o
p
e
m
b
e
r
,
In
d
o
n
e
sia
2
S
c
h
o
o
l
o
f
A
p
p
li
e
d
S
c
ien
c
e
,
T
e
lk
o
m
Un
iv
e
rsit
y
,
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
J
u
l 2
4
,
2
0
1
8
R
ev
i
s
ed
No
v
2
7
,
2
0
1
8
A
cc
ep
ted
Dec
25
,
2
0
1
8
P
e
o
p
le
o
f
ten
h
a
v
e
tro
u
b
le
re
c
o
g
n
izin
g
a
so
n
g
e
sp
e
c
iall
y
,
i
f
th
e
so
n
g
is
su
n
g
b
y
a
n
o
t
o
rig
in
a
l
a
rti
st
w
h
ich
is
c
a
ll
e
d
c
o
v
e
r
so
n
g
.
He
n
c
e
,
a
n
id
e
n
ti
f
ica
ti
o
n
s
y
ste
m
m
i
g
h
t
b
e
u
se
d
t
o
h
e
lp
re
c
o
g
n
ize
a
so
n
g
o
r
t
o
d
e
tec
t
c
o
p
y
rig
h
t
v
io
latio
n
.
In
th
is
st
u
d
y
,
w
e
tr
y
to
re
c
o
g
n
ize
a
so
n
g
a
n
d
a
c
o
v
e
r
so
n
g
b
y
u
sin
g
th
e
f
in
g
e
rp
rin
t
o
f
th
e
s
o
n
g
re
p
re
s
e
n
ted
b
y
fe
a
tu
re
s
e
x
tra
c
ted
f
ro
m
M
P
EG
-
7
.
T
h
e
f
in
g
e
rp
rin
t
o
f
th
e
so
n
g
is
re
p
re
se
n
ted
b
y
A
u
d
io
S
ig
n
a
t
u
re
Ty
p
e
.
M
o
re
o
v
e
r,
th
e
f
in
g
e
rp
rin
t
o
f
t
h
e
c
o
v
e
r
so
n
g
is
re
p
re
se
n
ted
b
y
A
u
d
io
S
p
e
c
tru
m
F
latn
e
ss
a
n
d
A
u
d
io
S
p
e
c
tru
m
P
ro
jec
ti
o
n
.
F
u
rt
h
e
rm
o
re
,
w
e
p
ro
p
o
se
a
slid
in
g
a
lg
o
ri
th
m
a
n
d
k
-
Ne
a
re
st
Ne
ig
h
b
o
r
(k
-
NN
)
w
it
h
B
h
a
tt
a
c
h
a
r
y
y
a
d
istan
c
e
f
o
r
so
n
g
re
c
o
g
n
it
io
n
a
n
d
c
o
v
e
r
so
n
g
re
c
o
g
n
it
io
n
.
T
h
e
re
s
u
lt
s
o
f
th
is
e
x
p
e
ri
m
e
n
t
sh
o
w
th
a
t
t
h
e
p
ro
p
o
s
e
d
f
in
g
e
rp
rin
t
tec
h
n
i
q
u
e
h
a
s
a
n
a
c
c
u
ra
c
y
o
f
1
0
0
%
f
o
r
so
n
g
re
c
o
g
n
it
io
n
a
n
d
a
n
a
c
c
u
ra
c
y
o
f
8
5
.
3
%
f
o
r
c
o
v
e
r
so
n
g
re
c
o
g
n
it
io
n
.
K
ey
w
o
r
d
s
:
B
h
attac
h
ar
y
y
a
d
is
tan
ce
k
-
NN
Sli
d
in
g
alg
o
r
it
h
m
So
n
g
r
ec
o
g
n
itio
n
Co
p
y
rig
h
t
©
2
0
1
9
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Ded
y
R
a
h
m
a
n
W
ij
a
y
a
,
Sch
o
o
l o
f
A
p
p
lied
Scien
ce
,
T
elk
o
m
U
n
i
v
er
s
it
y
,
Jl
.
T
elek
o
m
u
n
i
k
asi T
er
u
s
an
B
u
ah
B
at
u
,
B
an
d
u
n
g
4
0
2
5
7
,
I
n
d
o
n
esia
.
E
m
ail: d
ed
y
r
w
@
tas
s
.
tel
k
o
m
u
n
iv
er
s
it
y
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
Mu
s
ic
is
a
p
o
p
u
lar
asp
ec
t
o
f
h
u
m
a
n
li
f
e.
Ma
n
y
p
eo
p
le
m
a
k
e
m
u
s
ic
o
r
lis
te
n
to
it
w
h
ile
w
o
r
k
in
g
,
s
tu
d
y
in
g
,
o
r
r
elax
in
g
.
I
n
p
u
b
l
ic
p
lace
s
,
s
o
n
g
s
ar
e
p
la
y
ed
t
o
en
ter
tain
v
is
ito
r
s
,
w
h
o
ar
e
o
f
ten
cu
r
io
u
s
ab
o
u
t
w
h
at
m
u
s
ic
t
h
e
y
ar
e
li
s
te
n
in
g
to
an
d
w
an
t
to
k
n
o
w
w
h
a
t
s
o
n
g
th
e
y
ar
e
h
ea
r
i
n
g
.
I
n
ad
d
itio
n
,
a
m
u
s
i
c
r
ec
o
g
n
itio
n
s
y
s
te
m
also
ca
n
b
e
u
s
ed
to
d
etec
t
ille
g
all
y
co
p
ied
m
u
s
ic.
O
n
e
p
r
o
b
le
m
t
h
at
is
d
if
f
ic
u
lt
to
h
a
n
d
le
i
s
d
etec
tio
n
co
v
er
s
o
n
g
.
C
o
v
er
s
o
n
g
s
ar
e
s
u
n
g
b
y
d
i
f
f
er
e
n
t
s
in
g
er
s
.
Ge
n
d
er
d
if
f
er
e
n
ce
s
i
n
s
i
n
g
er
s
,
d
if
f
er
en
t
s
o
u
n
d
co
lo
r
s
,
an
d
i
m
p
r
o
v
i
s
e
d
to
n
es
m
a
k
e
i
t
h
ar
d
er
to
d
etec
t.
Se
v
er
al
s
t
u
d
ies
h
a
v
e
b
ee
n
d
o
n
e
i
n
s
o
n
g
r
ec
o
g
n
itio
n
a
n
d
s
e
v
er
al
m
et
h
o
d
s
ar
e
ap
p
lied
in
th
i
s
f
ield
.
I
n
th
e
p
r
ev
io
u
s
s
tu
d
ies,
s
o
n
g
r
e
co
g
n
itio
n
h
as
b
ee
n
d
o
n
e
b
y
M
u
lti
-
b
an
d
S
u
m
o
f
Sp
ec
tr
o
g
r
a
m
,
w
i
th
9
1
%
ac
cu
r
ac
y
[
1
]
,
an
d
t
h
e
P
C
A
al
g
o
r
ith
m
[
2
]
.
C
o
v
er
s
o
n
g
r
ec
o
g
n
itio
n
h
as
b
ee
n
d
o
n
e
u
s
in
g
t
h
e
r
a
w
s
i
g
n
al
as
in
p
u
t
[
3
]
,
[
4
]
.
Fro
m
ea
c
h
o
f
s
e
g
m
en
t
o
f
t
h
e
s
i
g
n
al,
th
e
ch
r
o
m
a
w
ill
b
e
o
b
tain
ed
.
T
h
is
ch
r
o
m
a
ca
n
b
e
u
s
ed
to
r
ec
o
g
n
ize
a
c
o
v
er
s
o
n
g
w
it
h
6
2
%
ac
cu
r
ac
y
[
5
]
-
[
7
]
.
O
th
er
e
x
p
er
i
m
e
n
ts
u
s
ed
pi
tch
[
8
]
-
[
1
0
]
,
I
n
f
o
r
m
a
tio
n
-
T
h
eo
r
etic
Me
as
u
r
es
o
f
Si
m
ilar
it
y
[
1
1
]
,
m
u
s
ic
s
tr
u
ct
u
r
e
s
eg
m
e
n
tatio
n
[
1
2
]
an
d
2
D
F
o
u
r
ier
T
r
an
s
f
o
r
m
[
1
3
]
to
r
ec
o
g
n
ize
co
v
er
s
o
n
g
s
.
I
n
a
p
r
ev
io
u
s
ex
p
er
i
m
en
t,
f
i
n
g
er
p
r
in
t
in
g
h
as
b
ee
n
u
s
ed
t
o
id
en
ti
f
y
t
h
e
ti
tle
o
f
a
s
o
n
g
b
ased
o
n
t
h
e
r
a
w
s
i
g
n
al
o
f
t
h
e
m
u
s
ic.
I
n
an
o
t
h
er
ex
p
er
i
m
e
n
t,
t
h
e
f
i
n
g
er
p
r
in
t
w
a
s
g
ain
ed
a
n
d
p
r
o
ce
s
s
ed
i
n
s
p
ec
tr
o
g
r
a
m
f
o
r
m
.
I
n
o
u
r
e
x
p
er
i
m
e
n
t,
w
e
u
s
ed
f
ea
t
u
r
es
f
r
o
m
MP
E
G
-
7
.
T
h
e
ex
tr
ac
tio
n
o
f
m
u
s
ic
f
ea
t
u
r
es
b
a
s
ed
o
n
MP
E
G
-
7
in
t
h
e
f
o
r
m
o
f
a
t
w
o
-
d
i
m
e
n
s
io
n
al
m
atr
i
x
,
n
x
m
.
M
P
E
G
-
7
h
as
s
u
b
b
an
d
v
al
u
es
f
o
r
ea
ch
f
ea
t
u
r
e.
I
n
a
p
r
ev
io
u
s
ex
p
er
i
m
en
t,
s
o
n
g
r
ec
o
g
n
itio
n
u
s
i
n
g
f
in
g
er
p
r
in
ti
n
g
w
as
d
o
n
e
b
y
ap
p
l
y
i
n
g
a
s
lid
i
n
g
al
g
o
r
ith
m
o
n
a
o
n
e
-
d
i
m
e
n
s
io
n
al
m
atr
i
x
[
1
4
]
.
T
h
is
ex
p
er
i
m
e
n
t
k
ep
t
th
e
m
atr
i
x
o
b
tain
ed
f
r
o
m
MP
E
G
-
7
ex
tr
ac
t
io
n
.
T
h
is
ac
ti
v
it
y
is
k
n
o
w
n
a
s
MI
R
.
MI
R
m
ea
n
s
p
r
o
ce
s
s
in
g
th
e
m
u
s
ic
s
p
ec
tr
o
g
r
a
m
to
o
b
tai
n
u
s
e
f
u
l
in
f
o
r
m
atio
n
[
1
5
]
.
So
n
g
r
ec
o
g
n
itio
n
(
f
in
g
er
p
r
in
ti
n
g
)
an
d
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:
2
0
8
8
-
8708
Mu
s
ic
fin
g
erp
r
in
tin
g
b
a
s
ed
o
n
b
h
a
tta
c
h
a
r
ya
d
is
ta
n
ce
f
o
r
s
o
n
g
a
n
d
co
ve
r
s
o
n
g
r
ec
o
g
n
itio
n
(
R
iya
n
a
r
to
S
a
r
n
o
)
1037
co
v
er
s
o
n
g
d
etec
tio
n
is
p
ar
t
o
f
MI
R
.
Fo
r
ex
a
m
p
le,
m
u
s
ic
r
ec
o
m
m
e
n
d
atio
n
s
y
s
te
m
u
s
in
g
co
llab
o
r
ativ
e
f
ilter
i
n
g
an
d
m
u
s
ic
g
en
r
e
cl
ass
i
f
icatio
n
also
h
av
e
b
ee
n
p
r
o
p
o
s
ed
[
1
6
]
,
[
1
7
]
.
A
f
i
n
g
er
p
r
in
t
o
f
s
o
n
g
i
s
ch
ar
ac
ter
is
tic
f
o
r
ce
r
tai
n
t
y
p
es
o
f
m
u
s
ic.
T
h
er
e
ar
e
m
an
y
w
a
y
s
to
g
et
t
h
e
f
i
n
g
er
p
r
in
t
o
f
a
m
u
s
ic
p
iece
,
s
u
ch
as
u
s
i
n
g
s
ci
k
it
-
lear
n
lib
r
ar
y
o
r
an
al
y
zi
n
g
it
s
s
p
ec
tr
o
g
r
a
m
.
I
n
t
h
i
s
p
ap
er
,
w
e
p
r
o
p
o
s
e
an
au
d
io
f
in
g
er
p
r
in
ti
n
g
tec
h
n
iq
u
e
f
o
r
s
o
n
g
an
d
co
v
er
s
o
n
g
r
ec
o
g
n
itio
n
b
ased
o
n
MP
E
G
-
7
f
ea
t
u
r
es.
Mo
r
eo
v
er
,
MP
E
G
-
7
h
as
b
ee
n
r
ep
o
r
ted
to
s
u
cc
ess
f
u
ll
y
d
etec
t
th
e
m
o
o
d
o
f
m
u
s
ic
[
1
8
]
,
[
1
9
]
an
d
te
m
p
o
cl
ass
i
f
icatio
n
[
3
]
.
A
co
v
er
s
o
n
g
m
ea
n
s
t
h
at
th
e
s
i
n
g
er
p
er
f
o
r
m
s
a
s
o
n
g
o
r
ig
i
n
all
y
p
er
f
o
r
m
ed
b
y
an
o
t
h
er
ar
tis
t
[
2
0
]
.
B
esid
es
th
e
ex
tr
ac
tio
n
p
r
o
ce
s
s
,
th
e
d
if
f
er
en
ce
b
et
w
ee
n
t
h
is
ex
p
er
i
m
e
n
t
an
d
p
r
ev
io
u
s
ex
p
er
i
m
en
ts
is
i
n
h
o
w
th
e
f
i
n
g
er
p
r
in
t
o
f
th
e
m
u
s
ic
w
a
s
o
b
tain
ed
.
W
e
u
s
ed
MP
E
G
-
7
ex
tr
ac
tio
n
b
ec
au
s
e
th
e
r
es
u
lt
o
f
th
e
e
x
tr
ac
tio
n
p
r
o
ce
s
s
is
a
n
u
m
b
e
r
o
f
f
ea
tu
r
es
t
h
at
ca
n
b
e
u
s
ef
u
l
f
o
r
o
b
tain
in
g
in
f
o
r
m
atio
n
f
r
o
m
a
m
u
s
ic
p
ie
ce
.
B
y
MP
E
G
-
7
e
x
tr
ac
tio
n
,
1
7
f
ea
t
u
r
es
ca
n
b
e
o
b
tai
n
ed
[
2
1
]
.
Ho
w
ev
er
,
i
n
th
i
s
ex
p
er
i
m
e
n
t,
w
e
u
s
ed
o
n
l
y
3
o
u
t
t
h
ese
1
7
f
ea
t
u
r
es.
Fo
r
s
o
n
g
r
ec
o
g
n
itio
n
w
e
u
s
ed
A
u
d
io
Si
g
n
at
u
r
e
T
y
p
e,
w
h
ile
w
e
u
s
ed
A
u
d
io
P
r
o
j
ec
tio
n
an
d
A
u
d
io
Sp
ec
tr
u
m
Fla
tn
e
s
s
f
o
r
co
v
er
s
o
n
g
r
ec
o
g
n
it
io
n
.
MP
E
G
-
7
ex
tr
ac
tio
n
p
r
o
d
u
ce
s
an
XM
L
f
ile
co
n
ta
i
n
in
g
t
h
e
1
7
f
ea
t
u
r
es
f
r
o
m
t
h
e
MP
E
G
-
7
DDL
s
ch
e
m
e.
T
o
g
et
th
e
f
ea
t
u
r
es
t
h
at
ex
is
t
i
n
th
e
XM
L
f
ile
f
o
r
m
at,
XQu
er
y
n
ee
d
s
to
b
e
ap
p
lied
.
T
h
e
s
elec
ted
f
ea
tu
r
es
ar
e
th
e
n
tr
ea
ted
b
y
a
s
lid
in
g
alg
o
r
ith
m
a
n
d
k
-
NN
alg
o
r
it
h
m
w
it
h
B
h
attac
h
ar
y
y
a
d
is
ta
n
ce
.
T
h
e
r
em
ai
n
o
f
t
h
is
p
ap
er
is
ar
r
an
g
ed
as
f
o
llo
w
s
:
Sect
io
n
2
ex
p
lain
s
th
e
r
esear
c
h
m
eth
o
d
s
as
w
e
ll
a
s
MP
E
G
-
7
,
B
h
attac
h
ar
y
y
a
d
is
ta
n
ce
,
th
e
s
lid
i
n
g
al
g
o
r
ith
m
,
k
-
NN,
d
is
cr
ete
w
av
ele
t
tr
an
s
f
o
r
m
,
s
o
n
g
r
ec
o
g
n
itio
n
m
et
h
o
d
,
co
v
er
s
o
n
g
r
ec
o
g
n
iti
o
n
m
et
h
o
d
,
th
e
s
y
s
te
m
ar
ch
it
ec
tu
r
e,
an
d
th
e
d
ataset.
Sect
i
o
n
3
d
escr
ib
es
th
e
r
esu
lt t
h
at
w
as
g
o
tte
n
f
r
o
m
t
h
e
ex
p
e
r
i
m
e
n
t.
Sectio
n
4
is
t
h
e
c
o
n
clu
s
io
n
o
f
t
h
i
s
p
ap
er
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
is
s
ec
tio
n
e
x
p
lain
s
t
h
e
MP
E
G
-
7
a
n
d
r
eq
u
ir
ed
f
ea
tu
r
e
s
f
o
r
th
is
ex
p
er
i
m
en
t.
F
u
r
th
er
m
o
r
e,
it
also
d
escr
ib
es
th
e
p
r
o
p
o
s
ed
k
-
NN
co
m
b
in
ed
w
it
h
s
lid
i
n
g
al
g
o
r
ith
m
,
B
h
attac
h
ar
y
y
a
d
is
ta
n
c
e,
d
is
c
r
ete
w
a
v
elet
tr
an
s
f
o
r
m
,
an
d
t
h
e
d
ataset.
2
.
1
.
So
ng
re
co
g
nitio
n
m
et
ho
d
T
h
e
g
o
al
o
f
th
is
m
et
h
o
d
is
to
r
ec
o
g
n
ize
th
e
titl
e
o
f
a
s
o
n
g
.
T
h
e
s
o
n
g
s
a
v
ed
in
“
w
a
v
”
f
o
r
m
at
i
s
ex
tr
ac
ted
u
s
i
n
g
MP
E
G
-
7
f
ea
t
u
r
e
ex
tr
ac
to
r
.
T
h
e
ex
tr
ac
tio
n
r
esu
lt
i
s
t
h
e
A
u
d
io
Si
g
n
a
tu
r
e
T
y
p
e
f
ea
t
u
r
e.
Au
d
io
Sig
n
at
u
r
e
T
y
p
e
f
r
o
m
t
h
e
ex
tr
ac
tio
n
p
r
o
ce
s
s
is
th
e
n
ap
p
lied
in
th
e
s
lid
in
g
alg
o
r
it
h
m
an
d
k
-
N
N
u
s
in
g
B
h
attac
h
ar
y
y
a
d
is
ta
n
ce
.
I
n
t
h
is
e
x
p
er
i
m
e
n
t,
k
-
NN
w
as
u
s
e
d
b
ec
au
s
e
i
t
h
as
b
ee
n
s
u
cc
es
s
f
u
ll
y
r
ep
o
r
ted
f
o
r
f
av
o
r
ab
le
p
er
f
o
r
m
an
ce
i
n
n
o
n
-
s
tat
io
n
ar
y
s
ig
n
al
p
r
o
ce
s
s
in
g
[
1
7
]
,
[
2
2
]
,
[
2
3
]
.
T
h
e
d
etails
o
f
th
is
p
r
o
ce
s
s
ar
e
d
ep
icted
in
Fig
u
r
e
1
.
Fig
u
r
e
1
.
Deta
ils
o
f
s
o
n
g
r
ec
o
g
n
i
tio
n
2
.
2
.
Co
v
er
s
o
ng
re
co
g
nitio
n m
et
ho
d
T
h
e
g
o
al
o
f
th
is
m
et
h
o
d
is
to
id
en
tify
th
e
ti
tle
o
f
a
co
v
er
s
o
n
g
.
C
o
v
er
s
o
n
g
r
ec
o
g
n
i
tio
n
is
a
n
ex
ten
s
io
n
o
f
t
h
e
s
o
n
g
r
ec
o
g
n
i
tio
n
m
e
th
o
d
.
T
h
e
s
o
n
g
s
av
ed
in
.
w
av
f
o
r
m
a
t
is
e
x
tr
ac
ted
u
s
in
g
MP
E
G
-
7
.
T
h
e
d
if
f
er
e
n
ce
w
it
h
s
o
n
g
r
ec
o
g
n
i
ti
o
n
i
s
t
h
e
n
u
m
b
er
o
f
r
eq
u
ir
ed
f
ea
tu
r
es.
T
h
e
ex
tr
ac
tio
n
p
r
o
ce
s
s
o
f
t
h
e
co
v
er
s
o
n
g
r
ec
o
g
n
itio
n
m
et
h
o
d
p
r
o
d
u
ce
s
Au
d
io
Sp
ec
tr
u
m
Fla
tn
e
s
s
an
d
A
u
d
io
Sp
ec
tr
u
m
P
r
o
j
ec
tio
n
.
T
h
ese
f
ea
tu
r
es
ar
e
th
en
p
r
o
ce
s
s
ed
b
y
2
D
d
is
cr
ete
w
a
v
elet
tr
a
n
s
f
o
r
m
.
T
h
e
2
D
d
is
cr
ete
w
av
ele
t
tr
an
s
f
o
r
m
r
e
s
u
lt
is
ap
p
lied
in
t
h
e
s
lid
in
g
al
g
o
r
ith
m
an
d
k
-
N
N
with
B
h
attac
h
ar
y
y
a
d
is
ta
n
ce
.
T
h
e
s
p
ec
if
ics o
f
th
i
s
p
r
o
ce
s
s
ar
e
s
h
o
w
n
in
F
ig
u
r
e
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.
9
,
No
.
2
,
A
p
r
il 2
0
1
9
:
1
0
3
6
-
1044
1038
Fig
u
r
e
2
.
De
tails
o
f
co
v
er
s
o
n
g
r
ec
o
g
n
i
tio
n
2
.
3
.
Fe
a
t
ure
e
x
t
ra
ct
io
n
MP
E
G
-
7
is
a
s
tan
d
ar
d
d
es
cr
ip
tio
n
o
f
m
u
l
ti
m
ed
ia
co
n
ten
t
ac
co
r
d
in
g
to
th
e
I
SO/IE
C
1
5
9
3
8
s
tan
d
ar
d
[
2
4
]
.
T
h
e
m
u
lt
i
m
ed
ia
co
n
ten
t
s
in
cl
u
d
e
i
m
a
g
es,
m
u
s
ic
(
s
o
u
n
d
)
,
an
d
v
id
eo
.
Ho
w
e
v
er
,
th
is
s
t
u
d
y
f
o
cu
s
ed
o
n
l
y
o
n
m
u
l
ti
m
ed
ia
co
n
ten
t
i
n
th
e
f
o
r
m
o
f
m
u
s
ic.
I
n
p
er
f
o
r
m
in
g
f
ea
tu
r
e
e
x
tr
ac
tio
n
,
MP
E
G
-
7
p
r
o
d
u
ce
s
a
n
u
m
b
er
o
f
f
ea
t
u
r
e
s
ca
lled
lo
w
le
v
el
d
escr
ip
to
r
s
.
T
h
e
ex
tr
ac
ted
m
u
s
ic
f
ea
t
u
r
es
b
ased
o
n
MP
E
G
-
7
ar
e
in
th
e
f
o
r
m
o
f
m
etad
ata
wh
ich
i
s
s
to
r
ed
in
m
atr
ix
f
o
r
m
.
T
h
e
m
atr
i
x
h
a
s
a
s
ize
o
f
n
×
m
.
An
ex
a
m
p
le
o
f
s
u
c
h
a
m
a
tr
ix
ca
n
b
e
s
ee
n
i
n
Fig
u
r
e
3
.
T
h
e
m
v
alu
e
i
s
ca
lled
th
e
s
u
b
b
an
d
m
e
tad
ata
o
f
th
e
m
u
s
ic.
T
h
e
s
u
b
b
an
d
m
etad
ata
d
ep
en
d
o
n
t
h
e
f
ea
t
u
r
es
u
s
ed
.
T
h
e
v
a
lu
e
o
f
n
d
ep
en
d
s
o
n
t
h
e
d
u
r
atio
n
an
d
s
ize
o
f
th
e
s
o
u
n
d
s
o
u
r
ce
.
Hen
ce
,
th
e
lo
n
g
er
a
s
o
u
n
d
i
m
p
lies
th
e
g
r
ea
ter
v
al
u
e
o
f
n
o
b
tain
ed
b
y
ex
tr
ac
tio
n
o
f
MP
E
G
-
7
f
ea
tu
r
e
s
.
Fig
u
r
e
3
.
E
x
a
m
p
le
o
f
a
n
MP
E
G
-
7
m
atr
i
x
T
h
e
co
llectio
n
o
f
all
M
P
E
G
-
7
f
ea
tu
r
es
is
s
to
r
ed
in
an
XM
L
d
o
cu
m
en
t
w
ith
a
s
p
ec
if
ic
s
ch
e
m
e,
ca
lled
th
e
MP
E
G
-
7
DD
L
s
c
h
e
m
e.
I
n
o
r
d
er
to
g
et
f
ea
t
u
r
es
f
r
o
m
t
h
e
MP
E
G
-
7
e
x
tr
ac
tio
n
p
r
o
ce
s
s
,
XQu
er
y
h
as
to
b
e
ap
p
lied
to
th
e
XM
L
-
d
o
cu
m
e
n
t.
MP
E
G
-
7
h
as
1
7
f
ea
t
u
r
es
b
u
t
w
e
o
n
l
y
u
s
ed
t
h
r
ee
o
f
th
e
m
in
t
h
is
e
x
p
er
i
m
e
n
t.
Fo
r
s
o
n
g
r
ec
o
g
n
it
io
n
,
w
e
u
s
ed
Au
d
io
Sig
n
at
u
r
e
T
y
p
e,
wh
ile
f
o
r
co
v
er
s
o
n
g
r
ec
o
g
n
iti
o
n
w
e
u
s
ed
A
u
d
io
Sp
ec
tr
u
m
P
r
o
j
ec
tio
n
an
d
Au
d
io
Sp
ec
tr
u
m
Flat
n
e
s
s
.
Au
d
i
o
Sig
n
at
u
r
e
T
y
p
e
r
ep
r
esen
t
s
th
e
„
id
e
n
tit
y
‟
o
f
an
au
d
io
s
ig
n
al.
B
ased
o
n
MP
E
G
-
7
ex
tr
ac
tio
n
,
th
i
s
f
ea
t
u
r
e
is
th
e
f
i
n
g
er
p
r
in
t
o
f
a
p
iece
o
f
m
u
s
ic.
T
h
e
Au
d
io
S
ig
n
at
u
r
e
T
y
p
e
n
u
m
b
er
,
m
,
i
s
1
6
b
ased
o
n
F
ig
u
r
e
1
.
Au
d
io
Sig
n
at
u
r
e
T
y
p
e
is
g
ai
n
ed
f
r
o
m
th
e
au
d
io
f
il
e
s
av
ed
in
“
wa
v
”
f
o
r
m
at.
T
h
e
au
d
io
f
iles
i
n
“
w
a
v
”
f
o
r
m
a
t
ar
e
ex
tr
ac
ted
u
s
i
n
g
MP
E
G
-
7
f
ea
t
u
r
e
ex
tr
ac
to
r
.
Au
d
io
Sig
n
at
u
r
e
T
y
p
e
i
s
i
n
t
h
e
f
o
r
m
o
f
a
m
atr
ix
.
T
h
e
v
al
u
es
i
n
t
h
e
Au
d
io
Si
g
n
atu
r
e
T
y
p
e
m
a
tr
ix
ar
e
i
n
t
h
e
r
an
g
e
[
-
1
,
1
]
.
I
t
is
th
is
m
atr
ix
t
h
at
r
e
p
r
esen
ts
t
h
e
ch
a
r
ac
ter
is
t
ics
o
f
th
e
m
u
s
ic
a
n
d
it
h
as
to
b
e
p
r
o
ce
s
s
ed
to
p
er
f
o
r
m
s
o
n
g
r
ec
o
g
n
itio
n
.
I
n
t
h
e
co
v
er
s
o
n
g
r
ec
o
g
n
itio
n
e
x
p
er
i
m
e
n
t
w
e
u
s
ed
t
w
o
f
ea
tu
r
es
f
r
o
m
MP
E
G
-
7
.
Au
d
i
o
Sp
ec
tr
u
m
P
r
o
j
ec
tio
n
(
A
SP
)
is
a
f
ea
t
u
r
e
d
er
iv
ed
f
r
o
m
i
n
d
ep
en
d
en
t
co
m
p
o
n
en
t
an
al
y
s
is
(
I
C
A
)
an
d
s
i
n
g
u
lar
v
al
u
e
d
ec
o
m
p
o
s
itio
n
(
SVD)
.
Au
d
io
Sp
ec
tr
u
m
P
r
o
j
ec
tio
n
is
u
s
ed
to
s
y
m
b
o
lize
a
lo
w
-
d
i
m
e
n
s
i
o
n
al
f
ea
t
u
r
e
o
f
t
h
e
s
p
ec
tr
u
m
a
f
ter
p
r
o
j
ec
tio
n
.
A
u
d
io
Sp
ec
tr
u
m
P
r
o
j
ec
tio
n
is
a
s
p
ec
tr
o
g
r
a
m
th
a
t
is
u
s
ed
f
o
r
s
o
u
n
d
class
i
f
ica
tio
n
f
r
o
m
v
ar
io
u
s
s
o
u
r
ce
s
.
T
o
g
et
th
e
v
al
u
e
o
f
Au
d
io
Sp
ec
tr
u
m
P
r
o
j
ec
tio
n
,
s
ev
er
al
ar
e
s
tep
s
r
eq
u
ir
ed
.
A
p
p
l
y
(
1
)
to
th
e
Au
d
io
Sp
ec
tr
u
m
E
n
v
elo
p
e
f
ea
t
u
r
e,
w
h
er
e
l
i
s
t
h
e
i
n
d
ex
o
f
an
A
E
lo
g
ar
it
h
m
ic
f
r
eq
u
e
n
c
y
r
an
g
e
(
〖
AE
〗
_
cb
(
k
,
l)
)
,
an
d
k
is
th
e
f
r
a
m
e
i
n
d
ex
.
Af
ter
th
at,
ap
p
l
y
(
2
)
a
n
d
(
3
)
,
th
e
g
o
al
o
f
w
h
ic
h
i
s
to
n
o
r
m
alize
ea
c
h
d
ec
ib
el
-
s
ca
le
s
p
ec
tr
al
v
ec
to
r
w
i
th
r
o
o
t
m
ea
n
s
q
u
ar
e
(
R
MS)
,
w
h
er
e
L
is
t
h
e
n
u
m
b
er
o
f
A
E
s
p
ec
tr
al
co
ef
f
icie
n
t
s
an
d
K
is
t
h
e
to
tal
n
u
m
b
er
o
f
f
r
a
m
es.
(
)
(
(
)
)
(
1
)
√
(
(
)
)
(
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:
2
0
8
8
-
8708
Mu
s
ic
fin
g
erp
r
in
tin
g
b
a
s
ed
o
n
b
h
a
tta
c
h
a
r
ya
d
is
ta
n
ce
f
o
r
s
o
n
g
a
n
d
co
ve
r
s
o
n
g
r
ec
o
g
n
itio
n
(
R
iya
n
a
r
to
S
a
r
n
o
)
1039
(
)
(
)
(
3
)
Au
d
io
Sp
ec
tr
u
m
Fla
tn
e
s
s
is
th
e
s
ec
o
n
d
MP
E
G
-
7
f
ea
t
u
r
e
u
s
ed
in
co
v
er
s
o
n
g
r
ec
o
g
n
i
ti
o
n
.
Au
d
io
Sp
ec
tr
u
m
F
latn
e
s
s
(
A
S
F)
r
ef
l
ec
ts
th
e
f
latn
e
s
s
p
r
o
p
er
ties
o
f
a
s
ig
n
al.
T
h
e
f
latn
e
s
s
p
r
o
p
er
ti
es
ar
e
d
e
f
in
ed
b
y
a
s
p
ec
if
ied
n
u
m
b
er
o
f
f
r
eq
u
e
n
c
y
b
an
d
s
.
A
S
F
s
h
o
w
s
h
o
w
t
h
e
p
o
w
er
s
p
ec
tr
u
m
o
f
a
s
i
g
n
a
l
d
ev
iates
f
r
o
m
th
e
f
r
eq
u
en
c
ies
o
f
a
f
lat
s
h
ap
e.
T
h
e
ter
m
„
f
lat
s
h
ap
e
‟
d
escr
ib
es
th
e
n
o
is
e
o
r
i
m
p
u
ls
e
in
a
s
i
g
n
al.
T
h
is
f
ea
t
u
r
e
is
u
s
ed
to
m
ea
s
u
r
e
th
e
s
i
m
ilar
it
y
b
et
w
ee
n
o
n
e
au
d
io
s
ig
n
al
an
d
an
o
t
h
er
.
T
h
e
f
ir
s
t
s
tep
o
f
Au
d
io
Sp
ec
tr
u
m
Flatn
e
s
s
e
x
tr
ac
tio
n
is
ca
lc
u
lat
in
g
th
e
p
o
w
er
s
p
ec
tr
u
m
o
f
t
h
e
s
ig
n
al
[
2
1
]
.
T
h
en
,
it
is
d
i
v
i
d
ed
in
to
lo
Sig
n
a
n
d
h
iSi
g
n
.
T
h
e
v
alu
e
o
f
lo
S
ig
n
a
n
d
h
i
Si
g
n
ar
e
d
eter
m
i
n
ed
b
y
(
4
)
an
d
(
5
)
,
r
esp
ec
ti
v
el
y
,
w
h
er
e
t
h
e
v
alu
e
o
f
Y
d
eter
m
in
e
s
th
e
lo
w
er
b
an
d
ed
g
e.
T
h
e
m
in
i
m
u
m
v
al
u
e
f
o
r
lo
Sig
n
is
r
ec
o
m
m
e
n
d
ed
to
b
e
2
5
0
Hz,
s
o
n
=
-
8
,
an
d
D
is
th
e
d
esire
d
n
u
m
b
er
o
f
f
r
eq
u
en
c
y
b
a
n
d
s
.
Def
i
n
i
n
g
t
h
e
f
r
eq
u
en
c
y
b
an
d
s
w
it
h
h
i
Sig
n
an
d
lo
Sig
n
m
a
k
es
Au
d
io
Sp
ec
tr
u
m
Flat
n
es
s
to
o
s
en
s
iti
v
e
to
th
e
s
a
m
p
li
n
g
f
r
eq
u
en
c
y
.
He
n
ce
,
it
n
ee
d
s
to
b
e
m
o
d
i
f
ied
s
o
t
h
at
all
b
an
d
s
s
li
g
h
t
l
y
o
v
er
lap
ea
ch
o
t
h
er
.
T
h
e
m
o
d
if
ica
tio
n
o
f
h
iSi
g
n
an
d
lo
Sig
n
ca
n
b
e
s
ee
n
in
(
6
)
an
d
(
7
)
.
T
h
en
f
o
r
ea
ch
f
r
eq
u
e
n
c
y
b
a
n
d
d
,
A
u
d
io
Sp
ec
tr
u
m
Flat
n
ess
ca
n
b
e
ca
lcu
lat
ed
w
it
h
(
8
)
.
(
4
)
(
5
)
(
)
(
6
)
(
7
)
√
∏
(
)
(
)
(
)
(
8
)
2
.
4
.
B
ha
t
t
a
cha
r
y
y
a
dis
t
a
nce
B
h
attac
h
ar
y
y
a
d
is
ta
n
ce
d
o
es
n
o
t
r
ea
lly
lo
o
k
f
o
r
th
e
d
is
ta
n
ce
o
f
an
y
th
i
n
g
.
Un
li
k
e
E
u
clid
ea
n
d
is
tan
ce
,
B
h
attac
h
ar
y
y
a
d
is
tan
ce
i
s
m
o
r
e
lik
e
f
i
n
d
in
g
t
h
e
s
i
m
ilar
it
y
b
et
w
ee
n
t
w
o
d
i
s
tr
ib
u
tio
n
s
[
2
5
]
.
T
h
e
d
is
tr
ib
u
tio
n
r
ef
er
s
to
t
h
e
B
h
attac
h
ar
y
y
a
c
o
ef
f
icie
n
t.
T
h
i
s
co
ef
f
icie
n
t
is
u
s
u
all
y
u
s
ed
to
d
i
s
co
v
er
t
h
e
r
elativ
e
c
lo
s
en
e
s
s
o
f
t
w
o
v
ec
to
r
s
.
T
h
e
f
o
r
m
u
la
o
f
B
h
attac
h
ar
y
y
a
d
is
ta
n
ce
ca
n
b
e
s
ee
n
in
(
9
)
,
w
h
er
e
D_
B
(
r
,
s
)
is
th
e
d
is
tan
c
e
b
et
w
ee
n
r
a
n
d
s
d
is
tr
ib
u
tio
n
s
o
r
class
es.
(
)
(
(
)
)
(
9
)
W
h
er
e
(
)
√
(
)
(
)
(
1
0
)
2
.
5
.
Dis
cr
et
e
w
a
v
elet
t
ra
ns
f
o
r
m
(
DWT
)
Dis
cr
ete
w
a
v
elet
tr
an
s
f
o
r
m
(
D
W
T
)
is
g
e
n
er
all
y
u
s
ed
i
n
s
i
g
n
al
p
r
o
ce
s
s
in
g
.
DW
T
is
a
m
eth
o
d
u
s
ed
t
o
r
ec
o
n
s
tr
u
ct
a
s
i
g
n
al
b
u
t
s
ti
ll
r
etain
s
t
h
e
o
r
ig
in
a
l
s
i
g
n
al.
I
t
w
a
s
also
s
u
cc
e
s
s
f
u
ll
y
ap
p
lied
to
p
r
o
ce
s
s
s
ig
n
als
elec
tr
o
n
ic
n
o
s
e
[
2
2
]
,
[
2
6
]
,
[
2
7
]
.
Sig
n
a
ls
t
h
at
w
a
v
elet
tr
an
s
f
o
r
m
h
a
s
b
ee
n
ap
p
lied
to
h
a
v
e
a
s
h
o
r
ter
len
g
t
h
t
h
an
th
e
o
r
ig
in
a
l.
T
h
er
e
a
r
e
tw
o
f
i
l
ter
s
th
at
ca
n
b
e
tak
en
w
h
e
n
a
p
p
ly
i
n
g
w
a
v
elet
tr
an
s
f
o
r
m
to
an
au
d
io
s
ig
n
al,
i.e
.
lo
w
-
p
ass
f
il
ter
an
d
h
ig
h
-
p
ass
f
ilter
.
T
h
e
lo
w
-
p
as
s
f
ilter
y
iel
d
s
ap
p
r
o
x
i
m
ate
co
e
f
f
icie
n
t
wh
ich
r
ep
r
esen
ts
th
e
v
o
ice
o
f
th
e
s
i
n
g
er
o
f
t
h
e
s
o
n
g
(
i
n
th
i
s
ca
s
e
w
o
m
en
a
n
d
m
en
h
av
e
al
m
o
s
t
t
h
e
s
a
m
e
v
alu
es)
an
d
th
e
d
etail
co
ef
f
icie
n
t
w
h
ich
r
ep
r
esen
t
s
t
h
e
s
o
u
n
d
o
f
th
e
in
s
tr
u
m
e
n
t
s
o
f
th
e
s
o
n
g
.
I
n
t
h
i
s
s
tu
d
y
,
t
h
e
v
a
lu
es
tak
e
n
f
r
o
m
t
h
e
DW
T
w
er
e
t
h
e
ap
p
r
o
x
i
m
ate
c
o
ef
f
icie
n
t
o
n
l
y
.
DW
T
is
h
ig
h
l
y
d
ep
en
d
e
n
t
o
n
th
e
le
v
el
o
f
d
ec
o
m
p
o
s
i
tio
n
t
h
at
is
u
s
ed
.
T
h
e
h
i
g
h
er
t
h
e
le
v
el
o
f
d
ec
o
m
p
o
s
itio
n
i
n
d
icate
s
t
h
e
h
ig
h
er
t
h
e
r
is
k
t
h
at
t
h
e
s
ig
n
al
w
i
ll
b
e
d
a
m
a
g
ed
.
C
o
n
v
er
s
el
y
,
t
h
e
lo
w
er
th
e
le
v
e
l
o
f
d
ec
o
m
p
o
s
itio
n
,
th
e
m
o
r
e
s
u
s
ce
p
tib
le
th
e
s
i
g
n
al
w
ill
b
e
to
n
o
is
e
[
2
8
]
.
L
ev
el
d
ec
o
m
p
o
s
itio
n
u
p
to
4
w
it
h
wav
elet
f
a
m
il
y
h
aa
r
w
er
e
u
s
ed
i
n
th
i
s
ex
p
er
i
m
e
n
t.
A
ll
le
v
els
a
r
e
g
ath
er
ed
b
y
t
h
e
lo
w
-
p
ass
f
ilter
,
s
o
t
h
e
y
ca
n
b
e
class
i
f
ied
.
2
-
D
DW
T
is
ap
p
lied
to
ea
ch
f
ea
t
u
r
e,
w
h
ic
h
is
s
t
ill
in
a
m
atr
i
x
f
o
r
m
.
Fig
u
r
e
4
d
en
o
tes an
ex
a
m
p
le
o
f
au
d
io
s
i
g
n
al
th
at
r
ec
o
n
s
tr
u
c
t
ed
b
y
DW
T
.
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.
9
,
No
.
2
,
A
p
r
il 2
0
1
9
:
1
0
3
6
-
1044
1040
(
a)
(
b
)
Fig
u
r
e
4
.
T
h
e
ex
a
m
p
le
o
f
au
d
i
o
s
ig
n
a
l f
r
o
m
MP
E
G
-
7
ex
tr
ac
t
io
n
,
(
a)
Or
ig
in
al
s
ig
n
al
(
b
)
R
e
co
n
s
tr
u
cted
s
ig
n
al
2
.
6
.
k
-
NN
co
m
b
ine
d w
it
h sl
idi
ng
a
lg
o
rit
h
m
As
m
en
t
io
n
ed
ab
o
v
e,
th
e
f
ea
t
u
r
es
o
f
MP
E
G
-
7
ar
e
in
t
h
e
f
o
r
m
o
f
a
m
atr
i
x
.
Mo
r
eo
v
er
,
k
-
NN
is
u
s
ed
as
a
clas
s
if
icatio
n
m
et
h
o
d
.
C
o
m
m
o
n
k
-
NN
m
et
h
o
d
s
an
al
y
ze
tr
ain
i
n
g
d
ata
a
n
d
test
i
n
g
d
ata
th
e
n
m
ea
s
u
r
e
t
h
e
d
is
tan
ce
b
et
w
ee
n
t
h
e
m
u
s
i
n
g
E
u
clid
ea
n
d
is
tan
ce
.
Ho
w
ev
er
,
in
th
is
ex
p
er
i
m
e
n
t,
w
e
u
s
ed
B
h
attac
h
ar
y
y
a
d
is
tan
ce
to
m
ea
s
u
r
e
d
is
tan
ce
.
B
o
th
tr
ain
in
g
d
ata
an
d
test
in
g
d
ata
ar
e
in
th
e
f
o
r
m
o
f
a
v
ec
to
r
,
b
u
t
th
e
f
ea
tu
r
e
ex
tr
ac
tio
n
r
esu
lt
o
f
MP
E
G
-
7
i
s
i
n
t
h
e
f
o
r
m
o
f
a
t
w
o
-
d
i
m
e
n
s
io
n
al
m
atr
i
x
.
I
n
o
r
d
er
to
k
ee
p
th
e
m
atr
i
x
f
o
r
m
,
k
-
NN
is
co
m
b
i
n
ed
w
i
th
a
m
o
d
i
f
i
ed
s
lid
in
g
al
g
o
r
ith
m
.
I
n
t
h
is
ex
p
er
i
m
e
n
t,
w
e
d
id
n
o
t
„
s
lid
e‟
ea
ch
s
u
b
b
an
d
(
r
o
w
)
.
B
h
attac
h
ar
y
y
a
d
is
ta
n
ce
al
l
o
w
s
u
s
t
o
ca
lcu
late
t
h
e
a
v
er
ag
e
v
al
u
e
o
f
ea
ch
m
a
tr
ix
b
ec
a
u
s
e
B
h
at
ta
ch
ar
y
y
a
d
is
ta
n
ce
m
ea
s
u
r
es
t
h
e
d
is
tan
ce
b
et
w
ee
n
v
ec
to
r
s
,
n
o
t
b
et
w
ee
n
p
o
in
ts
.
T
h
e
av
er
ag
e
v
al
u
e
o
f
ea
c
h
o
f
t
h
e
m
atr
ice
s
is
„
s
lid
ed
‟
an
d
th
e
B
h
attac
h
ar
y
y
a
d
is
tan
ce
is
ca
lc
u
lated
.
T
h
is
m
et
h
o
d
is
u
s
ed
b
o
th
f
o
r
s
o
n
g
r
ec
o
g
n
itio
n
an
d
co
v
er
s
o
n
g
r
ec
o
g
n
it
io
n
.
I
n
t
h
is
ex
p
er
i
m
e
n
t,
th
e
k
p
ar
a
m
eter
o
f
k
-
NN
i
s
5
.
T
h
e
d
if
f
er
en
ce
b
et
w
ee
n
s
o
n
g
r
ec
o
g
n
itio
n
an
d
co
v
er
s
o
n
g
r
ec
o
g
n
itio
n
w
as t
h
e
t
y
p
e
an
d
n
u
m
b
er
o
f
f
ea
t
u
r
es u
s
ed
.
2
.
7
.
Sy
s
t
e
m
a
rc
h
it
ec
t
ure
Fig
u
r
e
5
illu
s
tr
ates t
h
e
d
etails
o
f
th
e
s
y
s
te
m
ar
c
h
itect
u
r
e
u
s
e
d
in
th
i
s
ex
p
er
i
m
e
n
t.
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:
2
0
8
8
-
8708
Mu
s
ic
fin
g
erp
r
in
tin
g
b
a
s
ed
o
n
b
h
a
tta
c
h
a
r
ya
d
is
ta
n
ce
f
o
r
s
o
n
g
a
n
d
co
ve
r
s
o
n
g
r
ec
o
g
n
itio
n
(
R
iya
n
a
r
to
S
a
r
n
o
)
1041
P
r
o
c
e
s
s
i
n
g
F
e
a
t
u
r
e
E
x
t
r
a
c
t
i
o
n
S
o
n
g
T
i
t
l
e
4
5
3
2
6
1
7
Fig
u
r
e
5
.
S
y
s
te
m
ar
ch
itect
u
r
e
T
h
e
ex
p
lan
atio
n
o
f
t
h
e
p
r
o
ce
s
s
f
lo
w
is
as
f
o
llo
w
s
:
1.
A
s
o
n
g
i
s
r
ec
o
r
d
ed
th
r
o
u
g
h
a
m
o
b
ile
d
e
v
ice
ap
p
licatio
n
.
T
h
e
r
ec
o
r
d
e
d
s
o
n
g
s
h
o
u
ld
b
e
in
“
w
a
v
”
f
o
r
m
at
2.
T
h
e
r
e
co
r
d
ed
s
o
n
g
is
s
e
n
t to
a
s
er
v
er
3.
T
h
e
r
ec
o
r
d
ed
s
o
n
g
is
ex
tr
ac
ted
u
s
i
n
g
MP
E
G
-
7
4.
T
h
e
r
esu
lt o
f
th
e
e
x
tr
ac
tio
n
p
r
o
ce
s
s
is
an
X
ML
d
o
cu
m
e
n
t t
h
at
co
n
tain
s
s
e
v
er
al
f
ea
t
u
r
es.
T
h
en
X
Qu
er
y
is
u
s
ed
to
o
b
tain
th
e
r
eq
u
i
r
ed
f
ea
tu
r
es
5.
T
h
e
r
eq
u
ir
ed
f
ea
tu
r
es a
r
e
ap
p
l
ied
in
th
e
p
r
ep
r
o
ce
s
s
in
g
m
et
h
o
d
6.
T
h
e
r
esu
lt f
r
o
m
t
h
e
p
r
ep
r
o
ce
s
s
in
g
s
ta
g
e
is
u
s
ed
ac
co
r
d
in
g
to
th
e
m
e
th
o
d
b
ein
g
ex
ec
u
ted
in
th
e
class
i
f
icatio
n
s
ta
g
e
7.
T
h
e
r
esu
lt f
r
o
m
p
r
o
ce
s
s
i
n
g
w
il
l b
e
s
h
o
w
n
i
n
m
o
b
ile
d
ev
ice
a
p
p
li
ca
tio
n
as a
r
esu
lt
2
.
8
.
Da
t
a
s
et
T
h
e
au
d
io
d
ataset
w
a
s
o
b
tain
ed
f
r
o
m
Yo
u
T
u
b
e.
T
h
e
au
d
io
d
ataset
h
as
to
b
e
in
“
wav
”
f
o
r
m
at
.
T
h
e
d
ataset
th
at
w
as
u
s
ed
a
s
tr
ain
i
n
g
d
ata
f
o
r
s
o
n
g
r
ec
o
g
n
i
tio
n
an
d
co
v
er
s
o
n
g
r
ec
o
g
n
iti
o
n
w
as
o
n
e
w
h
o
l
e
s
o
n
g
.
T
h
e
tr
ain
in
g
d
ata
h
ad
d
u
r
atio
n
o
f
3
-
4
m
in
u
te
s
.
Af
t
er
ex
tr
ac
tio
n
th
e
s
i
g
n
al
h
ad
a
len
g
t
h
o
f
3
0
0
-
4
0
0
s
u
b
b
an
d
s
(
r
o
w
s
)
.
T
h
e
d
ata
s
et
f
o
r
test
i
n
g
d
at
a
w
as
r
a
n
d
o
m
l
y
cu
t
to
a
le
n
g
t
h
o
f
3
0
s
ec
o
n
d
s
.
Af
ter
e
x
tr
ac
tio
n
,
th
e
s
i
g
n
al
h
ad
a
len
g
t
h
o
f
2
0
-
3
0
s
u
b
b
an
d
s
(
r
o
w
s
)
.
T
h
e
s
u
b
b
an
d
s
o
f
all
tr
ai
n
i
n
g
d
ata
w
er
e
th
en
„
s
lid
ed
‟
alo
n
g
th
e
s
u
b
b
an
d
s
o
f
t
h
e
te
s
ti
n
g
d
a
ta.
T
h
e
r
esu
lt
o
f
t
h
is
„
s
lid
i
n
g
‟
is
t
h
e
d
is
ta
n
ce
b
et
w
ee
n
t
h
e
t
est
in
g
d
ata
a
n
d
t
h
e
tr
ain
i
n
g
d
ata.
T
h
en
,
th
e
s
h
o
r
te
s
t
d
is
tan
ce
is
s
ea
r
c
h
ed
.
T
h
e
tr
ain
i
n
g
d
ata
an
d
test
i
n
g
d
ata
s
ch
e
m
e
i
s
s
h
o
w
n
in
Fig
u
r
e
6
.
Fo
r
th
e
s
o
n
g
r
ec
o
g
n
i
tio
n
ex
p
er
i
m
en
t,
t
h
ir
t
y
t
h
r
ee
s
o
n
g
s
wer
e
u
s
ed
to
r
ec
o
g
n
ize.
E
ac
h
s
o
n
g
w
a
s
r
an
d
o
m
l
y
s
e
lecte
d
.
C
o
v
er
s
o
n
g
r
ec
o
g
n
itio
n
u
s
ed
f
i
f
t
y
s
o
n
g
s
w
ith
f
iv
e
u
n
iq
u
e
s
o
n
g
titl
e
s
.
Fo
r
ea
ch
s
o
n
g
t
h
er
e
w
er
e
f
iv
e
co
v
er
s
o
n
g
s
w
it
h
a
m
ale
s
i
n
g
er
an
d
f
i
v
e
co
v
er
s
o
n
g
s
w
it
h
a
f
e
m
ale
s
i
n
g
er
.
Fig
u
r
e
6
.
I
llu
s
tr
atio
n
o
f
th
e
d
at
aset in
t
h
is
e
x
p
er
i
m
e
n
t
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.
9
,
No
.
2
,
A
p
r
il 2
0
1
9
:
1
0
3
6
-
1044
1
042
3.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
T
h
is
s
ec
tio
n
d
is
c
u
s
s
es t
h
e
r
esu
lt o
f
ex
p
er
i
m
e
n
t i
n
cl
u
d
in
g
s
o
n
g
an
d
co
v
er
s
o
n
g
r
ec
o
g
n
itio
n
.
3
.
1
.
So
ng
re
c
o
g
nitio
n r
esu
lt
T
h
e
tr
ain
in
g
d
ata
f
o
r
f
in
g
er
p
r
in
t
p
r
o
ce
s
s
i
n
g
co
n
s
i
s
ted
o
f
3
3
s
o
n
g
s
.
T
h
e
s
o
n
g
s
w
er
e
r
ec
o
r
d
ed
u
s
i
n
g
a
m
o
b
ile
d
e
v
ice.
T
h
e
A
u
d
io
Si
g
n
at
u
r
e
T
y
p
e
f
ea
t
u
r
e
o
f
ea
c
h
s
o
n
g
n
ee
d
s
to
b
e
s
a
v
ed
in
a
d
atab
ase.
I
n
th
i
s
ex
p
er
i
m
e
n
t,
w
e
u
s
ed
a
w
h
o
le
s
o
n
g
a
s
tr
ai
n
i
n
g
d
ata.
T
h
e
tes
tin
g
d
ata
u
s
ed
w
er
e
3
0
s
ec
o
n
d
s
o
f
r
an
d
o
m
l
y
c
u
t
tr
ain
i
n
g
d
ata.
T
h
e
ac
cu
r
ac
y
o
f
th
e
s
o
n
g
r
ec
o
g
n
itio
n
m
et
h
o
d
w
a
s
ca
lcu
la
ted
u
s
i
n
g
(
1
1
)
.
(
1
1
)
W
h
er
e
T
R
UE
is
th
e
to
tal
o
f
v
alid
p
r
ed
ictio
n
s
an
d
D
A
T
A
is
th
e
to
tal
n
u
m
b
er
o
f
test
in
g
d
ata.
T
h
e
r
esu
lt
o
f
s
o
n
g
r
ec
o
g
n
itio
n
tes
tin
g
u
s
in
g
B
h
a
ttach
ar
y
y
a
d
is
ta
n
ce
i
s
s
h
o
w
n
in
T
ab
le
1
.
T
h
e
titl
e
o
f
t
h
e
s
o
n
g
d
e
n
o
tes
tr
ain
i
n
g
d
ata
an
d
test
i
n
g
d
ata
u
s
ed
in
t
h
is
ex
p
er
i
m
e
n
t.
I
n
th
i
s
ex
p
er
i
m
e
n
t,
all
s
o
n
g
s
w
er
e
r
ec
o
g
n
ized
co
r
r
ec
tl
y
.
A
cc
o
r
d
in
g
to
T
ab
le
2
.
an
d
(
1
1
)
,
th
e
test
i
n
g
s
ce
n
ar
io
f
o
r
s
o
n
g
r
ec
o
g
n
itio
n
u
s
in
g
B
h
at
tach
a
r
y
y
a
d
is
tan
ce
h
ad
a
r
ec
o
g
n
itio
n
ac
cu
r
ac
y
o
f
1
0
0
%.
T
ab
le
1
.
R
esu
lts
o
f
Fi
n
g
er
p
r
in
t P
r
ed
ictio
n
No
T
i
t
l
e
o
f
t
h
e
S
o
n
g
R
e
su
l
t
No
T
i
t
l
e
o
f
t
h
e
S
o
n
g
R
e
su
l
t
1
M
i
d
d
l
e
√
18
Je
r
a
√
2
T
r
e
mo
r
√
19
K
e
r
e
t
a
M
a
l
a
m K
o
p
√
3
F
a
d
e
d
√
20
K
e
r
e
t
a
M
a
l
a
m O
r
i
√
4
T
u
r
n
U
p
T
h
e
S
p
e
a
k
e
r
√
21
K
i
mci
l
K
e
p
o
l
e
n
√
5
S
a
x
o
b
e
a
t
s
√
22
K
l
e
p
e
k
K
l
e
p
e
k
√
6
L
i
v
i
n
O
n
A
P
r
a
y
e
r
√
23
B
i
z
a
r
r
e
L
o
v
e
T
r
i
a
n
g
l
e
√
7
C
a
r
e
l
e
ss W
h
i
sp
e
r
√
24
A
sal
K
a
u
B
a
h
a
g
i
a
√
8
I
t
‟
s M
y
L
i
f
e
√
25
B
i
a
r
K
u
S
e
n
d
i
r
i
√
9
T
h
i
n
g
W
i
l
l
G
e
t
B
e
t
t
e
r
√
26
B
a
g
a
i
ma
n
a
K
u
T
a
h
u
√
10
Ev
e
r
y
b
o
d
y
K
n
e
w
√
27
B
e
r
d
i
st
r
a
k
s
i
√
11
G
e
t
L
o
w
√
28
S
a
y
a
n
g
√
12
Ju
d
i
√
29
B
e
r
d
u
a
S
a
j
a
√
13
B
e
g
a
d
a
n
g
√
30
R
a
h
a
s
i
a
√
14
B
e
n
a
n
g
B
i
r
u
√
31
H
o
w
D
e
e
p
i
s Yo
u
r
L
o
v
e
√
15
G
o
y
a
n
g
D
u
man
g
√
32
S
a
l
a
mk
u
U
n
t
u
k
K
e
k
a
si
h
m
u
y
a
n
g
B
a
r
u
√
16
Jan
j
i
P
a
l
su
√
33
S
h
o
w
M
e
t
h
e
M
e
a
n
i
n
g
o
f
B
e
i
n
g
L
o
n
e
l
y
√
17
Jaran
g
o
y
a
n
g
√
T
ab
le
2
.
C
o
n
f
u
s
io
n
Ma
tr
i
x
f
o
r
Fin
g
er
p
r
in
t T
esti
n
g
Scen
ar
io
S
y
st
e
m Pr
e
d
i
c
t
T
r
u
e
F
a
l
s
e
L
a
b
e
l
T
r
u
e
33
0
F
a
l
s
e
0
0
3
.
2
.
Co
v
er
s
o
ng
re
co
g
nitio
n r
esu
lt
T
o
ca
lcu
late
th
e
ac
c
u
r
ac
y
o
f
c
o
v
er
s
o
n
g
r
ec
o
g
n
itio
n
,
w
e
u
s
e
d
cr
o
s
s
v
alid
atio
n
.
T
h
e
cr
o
s
s
v
alid
atio
n
m
et
h
o
d
u
s
ed
in
th
i
s
ex
p
er
i
m
en
t
w
as
k
-
f
o
ld
cr
o
s
s
v
alid
ati
o
n
.
I
n
k
-
f
o
ld
cr
o
s
s
v
alid
atio
n
,
all
en
tr
ies
i
n
th
e
o
r
ig
in
al
tr
ain
i
n
g
d
ata
s
et
ar
e
u
s
ed
f
o
r
b
o
th
tr
ain
in
g
a
s
well
as
v
alid
atio
n
.
A
l
s
o
,
ea
ch
en
tr
y
i
s
u
s
ed
f
o
r
v
alid
atio
n
j
u
s
t
o
n
ce
.
K
-
f
o
ld
esti
m
ates
t
h
e
ac
cu
r
ac
y
o
f
t
h
e
m
ac
h
in
e
lear
n
in
g
m
o
d
el,
in
t
h
is
ca
s
e
k
-
N
N,
b
y
av
er
ag
i
n
g
th
e
ac
c
u
r
ac
ies d
er
iv
ed
f
r
o
m
al
l k
ca
s
e
s
o
f
cr
o
s
s
v
a
lid
atio
n
.
I
n
th
is
e
x
p
er
i
m
e
n
t,
th
e
v
alu
e
o
f
k
u
s
ed
w
as
3
.
Hen
ce
,
th
er
e
w
er
e
ten
iter
atio
n
s
to
ca
lcu
la
te
th
e
ac
cu
r
ac
y
o
f
o
u
r
m
o
d
el.
T
h
e
r
esu
lt
o
f
cr
o
s
s
v
al
id
atio
n
f
o
r
co
v
er
s
o
n
g
r
ec
o
g
n
i
tio
n
is
s
h
o
wn
in
T
ab
le
3
.
Fro
m
th
e
T
ab
le
3
.
,
w
e
ca
n
s
ee
th
a
t
th
e
ac
cu
r
ac
y
o
f
co
v
er
s
o
n
g
r
ec
o
g
n
itio
n
w
as
8
5
.
3
%.
T
h
e
s
tan
d
ar
d
d
ev
iatio
n
o
f
co
v
er
s
o
n
g
r
ec
o
g
n
itio
n
w
as 8
.
1
8
%,
w
h
ic
h
i
n
d
icate
s
t
h
at
t
h
e
class
i
f
icatio
n
w
as q
u
i
te
s
tab
le.
T
ab
le
3
.
C
r
o
s
s
Valid
atio
n
R
es
u
lt
K
A
c
c
u
r
a
c
y
(
%)
1
8
6
.
6
2
7
5
.
5
3
8
1
.
1
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:
2
0
8
8
-
8708
Mu
s
ic
fin
g
erp
r
in
tin
g
b
a
s
ed
o
n
b
h
a
tta
c
h
a
r
ya
d
is
ta
n
ce
f
o
r
s
o
n
g
a
n
d
co
ve
r
s
o
n
g
r
ec
o
g
n
itio
n
(
R
iya
n
a
r
to
S
a
r
n
o
)
1043
K
A
c
c
u
r
a
c
y
(
%)
4
8
1
.
1
5
9
7
.
7
6
7
5
.
5
7
9
0
.
5
8
9
6
.
4
9
9
0
.
5
10
7
8
.
8
A
v
e
r
a
g
e
8
5
.
3
4.
CO
NCLU
SI
O
N
I
n
o
r
d
er
to
r
ec
o
g
n
ize
a
s
o
n
g
,
th
e
MP
E
G
-
7
f
ea
t
u
r
e
Au
d
io
S
i
g
n
at
u
r
e
T
y
p
e
w
a
s
u
s
ed
a
s
f
i
n
g
er
p
r
in
t
o
r
„
id
en
t
it
y
‟
o
f
a
s
o
n
g
.
I
n
co
v
er
s
o
n
g
r
ec
o
g
n
it
io
n
,
t
h
e
MP
E
G
-
7
f
ea
tu
r
es
Au
d
io
Sp
ec
tr
u
m
P
r
o
j
ec
tio
n
an
d
Au
d
io
Sp
ec
tr
u
m
Flat
n
ess
f
ea
t
u
r
es
w
er
e
u
s
ed
.
Fo
r
b
o
th
s
o
n
g
r
ec
o
g
n
itio
n
an
d
co
v
er
s
o
n
g
r
ec
o
g
n
itio
n
a
k
-
NN
class
i
f
ier
w
a
s
u
s
ed
.
B
ec
au
s
e
t
h
e
d
ata
ar
e
o
r
ig
i
n
all
y
i
n
m
atr
i
x
f
o
r
m
,
t
h
e
y
w
er
e
m
o
d
i
f
ied
b
y
co
m
b
i
n
i
n
g
th
e
m
w
it
h
a
s
l
id
in
g
al
g
o
r
ith
m
a
n
d
B
h
attac
h
ar
y
y
a
d
is
ta
n
ce
.
A
cc
u
r
ac
y
f
o
r
s
o
n
g
r
ec
o
g
n
itio
n
o
f
t
h
is
ex
p
er
i
m
en
t
w
as
1
0
0
%.
A
f
ter
ca
lc
u
lati
n
g
t
h
e
a
cc
u
r
ac
y
u
s
i
n
g
cr
o
s
s
v
alid
atio
n
th
e
r
ec
o
g
n
itio
n
ac
c
u
r
ac
y
is
8
5
.
3
%.
T
h
ese
r
esu
lts
in
d
icate
th
a
t th
e
p
r
o
p
o
s
ed
m
et
h
o
d
ca
n
o
b
tain
f
a
v
o
r
ab
le
p
er
f
o
r
m
an
ce
to
r
ec
o
g
n
ize
s
o
n
g
an
d
co
v
er
s
o
n
g
.
RE
F
E
R
E
NC
E
S
[1
]
S
.
S
.
Ra
n
ja
n
i,
K.
Ka
rth
ik
,
P
.
K
.
Bo
ra
,
a
n
d
V.
A
b
d
u
lk
a
re
e
m
,
“
M
u
lt
i
-
b
a
n
d
S
u
m
o
f
S
p
e
c
tro
g
ra
m
B
a
se
d
A
u
d
io
F
in
g
e
rp
rin
ti
n
g
o
f
In
d
ian
F
il
m
S
o
n
g
s
f
o
r
M
u
lt
i
-
L
in
g
u
a
l
S
o
n
g
Re
tri
e
v
a
l
,
”
2
0
1
5
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Ad
v
a
n
c
e
s i
n
Co
m
p
u
ti
n
g
,
Co
mm
u
n
ica
ti
o
n
s
a
n
d
In
fo
rm
a
t
ics
,
ICAC
CI
2
0
1
5
,
p
p
.
1
4
1
4
-
1
4
2
0
,
2
0
1
5
.
[2
]
I.
M
u
e
ll
e
r
a
n
d
R.
W
e
lt
e
r,
“
Ro
b
u
st
A
u
d
io
F
i
n
g
e
rp
rin
ti
n
g
f
o
r
S
o
n
g
Id
e
n
ti
f
ica
ti
o
n
,
”
in
2
0
0
4
1
2
t
h
Eu
ro
p
e
a
n
S
ig
n
a
l
Pro
c
e
ss
in
g
Co
n
fer
e
n
c
e
,
2
0
0
4
,
p
p
.
2
0
9
5
-
2
0
9
8
,
2
0
0
4
.
[3
]
A
.
L
a
z
a
ro
,
R.
S
a
rn
o
,
J.
A
.
R,
a
n
d
M
.
N.
M
a
h
a
rd
ik
a
,
“
M
u
sic
T
e
m
p
o
Clas
sif
ic
a
ti
o
n
Us
in
g
A
u
d
io
S
p
e
c
tru
m
Ce
n
tro
id
,
A
u
d
io
S
p
e
c
tru
m
F
latn
e
ss
,
a
n
d
Au
d
i
o
S
p
e
c
tru
m
S
p
re
a
d
b
a
se
d
o
n
M
P
EG
-
7
A
u
d
io
F
e
a
tu
re
s,”
in
3
r
d
In
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
o
n
S
c
ien
c
e
i
n
In
fo
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
(
ICS
IT
e
c
h
)
,
p
p
.
4
1
-
4
6
,
2
0
1
7
.
[4
]
J.
-
T
.
F
a
n
g
,
Y.
-
R.
Ch
a
n
g
,
a
n
d
P
.
-
C.
Ch
a
n
g
,
“
De
e
p
L
e
a
rn
in
g
o
f
Ch
ro
m
a
Re
p
re
s
e
n
tatio
n
f
o
r
Co
v
e
r
S
o
n
g
Id
e
n
ti
f
ica
ti
o
n
i
n
C
o
m
p
re
ss
io
n
Do
m
a
in
,
”
M
u
lt
id
ime
n
si
o
n
a
l
S
y
ste
ms
a
n
d
S
ig
n
a
l
Pro
c
e
ss
in
g
,
p
p
.
1
-
1
6
,
F
e
b
.
2
0
1
7
.
[5
]
T
.
M
.
Ch
a
n
g
,
E.
T
.
C
h
e
n
,
C
.
B.
Hs
ieh
,
a
n
d
P
.
C.
C
h
a
n
g
,
“
Co
v
e
r
S
o
n
g
I
d
e
n
ti
f
ica
ti
o
n
w
it
h
Di
re
c
t
Ch
ro
m
a
F
e
a
tu
re
Ex
trac
ti
o
n
F
ro
m
AA
C
F
il
e
s,”
in
2
0
1
3
IEE
E
2
n
d
Gl
o
b
a
l
Co
n
fer
e
n
c
e
o
n
Co
n
su
me
r
El
e
c
tro
n
ics
(
GC
CE)
,
p
p
.
5
5
-
5
6
,
2
0
1
3
.
[6
]
A
.
Ca
m
a
re
n
a
-
Ib
a
rro
la,
K.
F
ig
u
e
ro
a
,
a
n
d
H.
T
e
jed
a
-
V
i
ll
e
la,
“
En
tr
o
p
y
P
e
r
Ch
r
o
m
a
f
o
r
Co
v
e
r
S
o
n
g
Id
e
n
ti
f
ica
ti
o
n
,
”
in
2
0
1
6
IE
EE
In
ter
n
a
ti
o
n
a
l
Au
t
u
mn
M
e
e
ti
n
g
o
n
Po
we
r,
El
e
c
tro
n
ic
s a
n
d
Co
m
p
u
ti
n
g
(
ROPE
C)
,
p
p
.
1
-
6
,
2
0
1
6
.
[7
]
T
.
Be
rti
n
-
M
a
h
ieu
x
a
n
d
D.
P
.
W
.
El
li
s,
“
L
a
rg
e
-
S
c
a
l
e
Co
v
e
r
S
o
n
g
Re
c
o
g
n
it
io
n
Us
in
g
Ha
sh
e
d
Ch
r
o
m
a
L
a
n
d
m
a
r
k
s
,”
in
2
0
1
1
IEE
E
W
o
rk
sh
o
p
o
n
A
p
p
li
c
a
ti
o
n
s
o
f
S
ig
n
a
l
Pro
c
e
ss
in
g
t
o
Au
d
i
o
a
n
d
Aco
u
stics
(
W
AS
PA
A
)
,
p
p
.
1
1
7
-
1
2
0
,
2
0
1
1
.
[8
]
N.
Ch
e
n
,
J.
S
.
Do
w
n
ie,
H.
X
ia
o
,
a
n
d
Y.
Zh
u
,
“
Co
c
h
lea
r
P
it
c
h
Clas
s
P
r
o
f
il
e
f
o
r
Co
v
e
r
S
o
n
g
I
d
e
n
ti
f
ica
ti
o
n
,
”
A
p
p
li
e
d
Aco
u
stics
,
v
o
l.
9
9
,
p
p
.
9
2
-
9
6
,
De
c
.
2
0
1
5
.
[9
]
N.
Ch
e
n
,
W
.
L
i,
a
n
d
H.
X
iao
,
“
F
u
sin
g
S
im
il
a
rit
y
F
u
n
c
ti
o
n
s
f
o
r
Co
v
e
r
S
o
n
g
Id
e
n
ti
f
ica
ti
o
n
,
”
M
u
lt
i
me
d
ia
T
o
o
ls
a
n
d
Ap
p
li
c
a
ti
o
n
s
,
p
p
.
1
-
2
4
,
F
e
b
.
2
0
1
7
.
[1
0
]
A
.
De
g
a
n
i,
M
.
Da
lai,
R
.
L
e
o
n
a
rd
i,
a
n
d
P
.
M
ig
li
o
ra
ti
,
“
A
He
u
risti
c
f
o
r
Dista
n
c
e
F
u
sio
n
i
n
Co
v
e
r
S
o
n
g
Id
e
n
ti
f
ica
ti
o
n
,
”
in
2
0
1
3
1
4
t
h
In
ter
n
a
ti
o
n
a
l
W
o
rk
sh
o
p
o
n
Ima
g
e
An
a
lys
is
fo
r
M
u
lt
ime
d
ia
In
ter
a
c
ti
v
e
S
e
rv
ice
s
(
W
IA
M
IS
)
,
p
p
.
1
-
4
,
2
0
1
3
.
[1
1
]
P
.
F
o
ste
r,
S
.
Dix
o
n
,
a
n
d
A
.
Kla
p
u
ri,
“
Id
e
n
ti
fy
in
g
Co
v
e
r
S
o
n
g
s
Us
in
g
In
f
o
r
m
a
ti
o
n
-
th
e
o
re
ti
c
M
e
a
su
re
s
o
f
S
im
il
a
rit
y
,
”
IEE
E/
ACM
T
ra
n
s.
A
u
d
i
o
,
S
p
e
e
c
h
a
n
d
L
a
n
g
.
Pr
o
c
.
,
v
o
l
.
2
3
,
n
o
.
6
,
p
p
.
9
9
3
-
1
0
0
5
,
Ju
n
.
2
0
1
5
.
[1
2
]
K.
Ca
i,
D.
Ya
n
g
,
a
n
d
X
.
Ch
e
n
,
“
Tw
o
-
La
y
e
r
L
a
r
g
e
-
S
c
a
le
Co
v
e
r
S
o
n
g
Id
e
n
ti
f
ica
ti
o
n
S
y
ste
m
Ba
se
d
o
n
M
u
sic
S
tru
c
tu
re
S
e
g
m
e
n
tatio
n
,
”
in
2
0
1
6
IEE
E
1
8
t
h
I
n
ter
n
a
ti
o
n
a
l
W
o
rk
sh
o
p
o
n
M
u
l
ti
me
d
ia
S
ig
n
a
l
Pro
c
e
ss
in
g
(
M
M
S
P)
,
p
p
.
1
-
6
,
2
0
1
6
.
[1
3
]
P
.
S
e
e
th
a
ra
m
a
n
,
“
Co
v
e
r
S
o
n
g
I
d
e
n
ti
f
ica
ti
o
n
W
it
h
2
d
F
o
u
rier
T
ra
n
sf
o
rm
S
e
q
u
e
n
c
e
s
,
”
in
2
0
1
7
IE
E
E
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
Pr
o
c
e
ss
in
g
(
ICAS
S
P)
,
2
0
1
7
.
[1
4
]
S
.
D.
Yo
u
,
W
.
-
H.
C
h
e
n
,
a
n
d
W
.
-
K.
Ch
e
n
,
“
M
u
sic
I
d
e
n
ti
f
ica
ti
o
n
S
y
ste
m
Us
in
g
M
P
EG
-
7
A
u
d
i
o
S
ig
n
a
tu
re
De
sc
rip
to
rs,”
T
h
e
S
c
ien
ti
fi
c
W
o
rl
d
J
o
u
r
n
a
l
,
v
o
l.
2
0
1
3
,
p
.
e
7
5
2
4
6
4
,
M
a
r.
2
0
1
3
.
[1
5
]
“
W
h
a
t
is
M
u
sic
In
f
o
rm
a
ti
o
n
Re
tri
e
v
a
l?
”
[
On
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
s:/
/m
u
sic
in
f
o
r
m
a
ti
o
n
re
tri
e
v
a
l.
c
o
m
/
w
h
y
_
m
ir.
h
tm
l.
[1
6
]
M
.
S
u
n
it
h
a
a
n
d
T
.
A
d
il
a
k
sh
m
i,
“
M
u
sic
Re
c
o
m
m
e
n
d
a
ti
o
n
S
y
ste
m
w
it
h
Us
e
r
-
Ba
s
e
d
a
n
d
Item
-
Ba
s
e
d
Co
ll
a
b
o
ra
ti
v
e
F
il
terin
g
T
e
c
h
n
iq
u
e
,
”
In
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
En
g
in
e
e
rin
g
a
n
d
I
n
fo
rm
a
t
ics
,
v
o
l.
5
,
n
o
.
1
,
p
p
.
5
9
-
6
8
,
2
0
1
7
.
[1
7
]
M
.
S
u
d
a
rm
a
a
n
d
I.
G
.
H
a
rse
m
a
d
i,
“
De
sig
n
a
n
d
A
n
a
l
y
sis
S
y
ste
m
o
f
KN
N
a
n
d
ID3
A
lg
o
rit
h
m
f
o
r
M
u
sic
Clas
sif
ic
a
ti
o
n
Ba
se
d
o
n
M
o
o
d
F
e
a
tu
re
Ex
trac
ti
o
n
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
E
lec
trica
l
a
n
d
Co
mp
u
t
e
r
En
g
in
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
7
,
n
o
.
1
,
p
p
.
4
8
6
-
4
9
5
,
2
0
1
7
.
[1
8
]
R.
S
a
rn
o
,
J.
A
.
Rid
o
e
a
n
,
D.
S
u
n
a
ry
o
n
o
,
a
n
d
D.
R
.
W
ij
a
y
a
,
“
Clas
si
f
ic
a
ti
o
n
o
f
M
u
sic
M
o
o
d
Us
i
n
g
M
P
EG
-
7
A
u
d
io
F
e
a
tu
re
s
a
n
d
S
V
M
w
it
h
Co
n
f
id
e
n
c
e
In
terv
a
l,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
n
Arti
fi
c
i
a
l
In
telli
g
e
n
c
e
T
o
o
ls
,
v
o
l.
2
7
,
n
o
.
5
,
2
0
1
8
.
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.
9
,
No
.
2
,
A
p
r
il 2
0
1
9
:
1
0
3
6
-
1044
1044
[1
9
]
J.
A
.
Rid
o
e
a
n
,
R.
S
a
rn
o
,
D.
S
u
n
a
r
y
o
,
a
n
d
D.
R.
W
ij
a
y
a
,
“
M
u
sic
M
o
o
d
Clas
sif
ica
ti
o
n
Us
in
g
A
u
d
io
P
ow
e
r
A
n
d
A
u
d
io
Ha
rm
o
n
icit
y
Ba
s
e
d
o
n
M
P
EG
-
7
A
u
d
io
F
e
a
tu
re
s
A
n
d
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
i
n
e
,
”
in
Pro
c
e
e
d
in
g
-
2
0
1
7
3
rd
In
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
o
n
S
c
i
e
n
c
e
in
In
fo
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
:
T
h
e
o
ry
a
n
d
A
p
p
li
c
a
ti
o
n
o
f
IT
fo
r
Ed
u
c
a
t
io
n
,
In
d
u
stry
a
n
d
S
o
c
iety
in
Bi
g
Da
t
a
Era
,
I
CS
IT
e
c
h
2
0
1
7
,
v
o
l.
2
0
1
8
,
Ja
n
u
a
,
2
0
1
8
.
[2
0
]
J.
S
e
rrà
,
E.
G
ó
m
e
z
,
P
.
He
rre
ra
,
a
n
d
X.
S
e
rra
,
“
Ch
ro
m
a
Bin
a
r
y
S
im
il
a
rit
y
a
n
d
L
o
c
a
l
A
li
g
n
m
e
n
t
Ap
p
li
e
d
t
o
Co
v
e
r
S
o
n
g
I
d
e
n
ti
f
ica
ti
o
n
,
”
IE
EE
T
r
a
n
sa
c
ti
o
n
s
o
n
Au
d
io
,
S
p
e
e
c
h
a
n
d
L
a
n
g
u
a
g
e
Pr
o
c
e
ss
in
g
,
v
o
l.
1
6
,
n
o
.
6
,
p
p
.
1
1
3
8
-
1
1
5
1
,
2
0
0
8
.
[2
1
]
H.
-
G
.
Ki
m
,
N.
M
o
re
a
u
,
a
n
d
T
.
S
ik
o
ra
,
M
P
EG
-
7
A
u
d
i
o
a
n
d
Be
y
o
n
d
:
A
u
d
io
Co
n
ten
t
I
n
d
e
x
in
g
a
n
d
Re
tri
e
v
a
l.
Jo
h
n
W
il
e
y
&
S
o
n
s,
2
0
0
5
.
[2
2
]
D.
R.
W
ij
a
y
a
,
R.
S
a
rn
o
,
E.
Zu
lai
k
a
,
a
n
d
S
.
I.
S
a
b
il
a
,
“
De
v
e
lo
p
m
e
n
t
o
f
M
o
b
il
e
El
e
c
tro
n
ic
N
o
se
f
o
r
Be
e
f
Qu
a
li
t
y
M
o
n
i
to
ri
n
g
,
”
in
4
t
h
I
n
fo
rm
a
ti
o
n
S
y
ste
ms
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
2
0
1
7
,
I
S
ICO
2
0
1
7
,
Pro
c
e
d
ia
Co
mp
u
ter
S
c
ien
c
e
,
v
o
l.
1
2
4
,
n
o
.
No
v
e
m
b
e
r,
p
p
.
7
2
8
-
7
3
5
,
2
0
1
7
.
[2
3
]
Ha
ri
y
a
n
to
,
R.
S
a
rn
o
,
a
n
d
D.
R.
W
ij
a
y
a
,
“
D
e
tec
ti
o
n
o
f
Dia
b
e
te
s
F
ro
m
Ga
s
A
n
a
l
y
sis
o
f
Hu
m
a
n
Bre
a
th
Us
in
g
e
-
No
se
,
”
in
2
0
1
7
1
1
th
I
n
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
In
f
o
rm
a
ti
o
n
&
Co
mm
u
n
ic
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
a
n
d
S
y
ste
m
(
ICT
S
)
,
v
o
l.
0
,
p
p
.
2
4
1
-
2
4
6
,
2
0
1
7
.
[2
4
]
“
IS
O/IEC
1
5
9
3
8
-
1
:2
0
0
2
-
In
f
o
rm
a
ti
o
n
tec
h
n
o
lo
g
y
--
M
u
lt
ime
d
ia
c
o
n
ten
t
d
e
sc
rip
ti
o
n
in
ter
f
a
c
e
--
P
a
rt
1
:
S
y
ste
m
s,”
IS
O.
[2
5
]
T
.
Ka
il
a
th
,
“
T
h
e
Div
e
r
g
e
n
c
e
a
n
d
Bh
a
tt
a
c
h
a
ry
y
a
Dista
n
c
e
M
e
a
su
re
s
in
S
ig
n
a
l
S
e
lec
ti
o
n
,
”
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Co
m
m
u
n
ica
ti
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l.
1
5
,
n
o
.
1
,
p
p
.
5
2
-
6
0
,
1
9
6
7
.
[2
6
]
D.
R.
W
ij
a
y
a
,
R.
S
a
rn
o
,
a
n
d
E.
Z
u
laik
a
,
“
S
e
n
so
r
A
rra
y
Op
ti
m
iz
a
ti
o
n
f
o
r
M
o
b
i
le
El
e
c
tro
n
ic
No
se
:
W
a
v
e
let
T
ra
n
s
f
o
r
m
a
n
d
F
il
ter
Ba
se
d
F
e
a
tu
re
S
e
lec
ti
o
n
A
p
p
ro
a
c
h
,
”
In
te
rn
a
ti
o
n
a
l
Rev
iew
o
n
Co
mp
u
ter
s
a
n
d
S
o
ft
w
a
re
,
v
o
l.
1
1
,
n
o
.
8
,
p
p
.
6
5
9
-
6
7
1
,
2
0
1
6
.
[2
7
]
D.
R.
W
ij
a
y
a
,
R.
S
a
rn
o
,
a
n
d
E
.
Zu
laik
a
,
“
Ga
s
Co
n
c
e
n
tratio
n
A
n
a
l
y
sis
o
f
R
e
sistiv
e
Ga
s
S
e
n
so
r
A
rra
y
,
”
in
2
0
1
6
IEE
E
In
ter
n
a
ti
o
n
a
l
S
y
mp
o
si
u
m o
n
El
e
c
tro
n
ics
a
n
d
S
ma
rt De
v
ice
s
,
p
p
.
3
3
7
-
3
4
2
,
2
0
1
6
.
[2
8
]
D.
R.
W
ij
a
y
a
,
R.
S
a
rn
o
,
a
n
d
E
.
Zu
laik
a
,
“
In
f
o
rm
a
ti
o
n
Qu
a
li
ty
Ra
ti
o
a
s
a
No
v
e
l
M
e
tri
c
f
o
r
M
o
th
e
r
W
a
v
e
let
S
e
lec
ti
o
n
,
”
C
h
e
mo
me
trics
a
n
d
In
t
e
ll
ig
e
n
t
L
a
b
o
ra
to
ry
S
y
ste
ms
,
v
o
l.
1
6
0
,
n
o
.
N
o
v
e
m
b
e
r
2
0
1
6
,
p
p
.
5
9
-
7
1
,
2
0
1
6
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
Riy
a
n
a
r
to
S
a
r
n
o
is
a
P
ro
f
e
ss
o
r,
In
f
o
rm
a
ti
c
s
De
p
a
rt
m
e
n
t,
In
stit
u
t
T
e
k
n
o
lo
g
i
S
e
p
u
l
u
h
N
o
p
e
m
b
e
r,
S
u
ra
b
a
y
a
,
In
d
o
n
e
sia
.
He
re
c
e
iv
e
d
th
e
b
a
c
h
e
lo
r‟s
d
e
g
re
e
in
El
e
c
t
rica
l
En
g
in
e
e
rin
g
f
ro
m
In
stit
u
t
T
e
k
n
o
lo
g
i
Ba
n
d
u
n
g
,
Ba
n
d
u
n
g
,
In
d
o
n
e
sia
in
1
9
8
7
.
He
re
c
e
iv
e
d
M
.
S
c
a
n
d
P
h
.
D
in
C
o
m
p
u
te
r
S
c
ien
c
e
f
ro
m
th
e
Un
iv
e
rsit
y
o
f
B
ru
n
sw
ick
Ca
n
a
d
a
in
1
9
8
8
a
n
d
1
9
9
2
,
re
sp
e
c
ti
v
e
ly
.
In
2
0
0
3
h
e
w
a
s
p
ro
m
o
ted
to
a
F
u
ll
P
r
o
f
e
ss
o
r.
His
tea
c
h
in
g
a
n
d
re
se
a
rc
h
in
tere
st i
n
c
lu
d
e
In
tern
e
t
o
f
T
h
in
g
s,
P
r
o
c
e
ss
Aw
a
re
In
f
o
r
m
a
ti
o
n
S
y
ste
m
s,
In
telli
g
e
n
t
S
y
ste
m
s an
d
S
m
a
rt
G
rid
s.
De
d
y
Ra
h
m
a
n
W
ija
y
a
is
c
u
rre
n
tl
y
a
lec
tu
re
r
a
n
d
w
o
rk
in
g
to
w
a
rd
s
th
e
P
h
.
D
.
d
e
g
re
e
a
t
In
f
o
r
m
a
ti
c
s
De
p
a
rtme
n
t,
In
stit
u
t
T
e
k
n
o
lo
g
i
S
e
p
u
l
u
h
No
p
e
m
b
e
r,
S
u
ra
b
a
y
a
,
In
d
o
n
e
sia
.
He
re
c
e
iv
e
d
th
e
b
a
c
h
e
lo
r‟s
d
e
g
re
e
in
Co
m
p
u
ter
S
c
ien
c
e
f
ro
m
T
e
l
k
o
m
Un
iv
e
rsit
y
(
f
o
r
m
e
r
S
T
T
Telk
o
m
),
Ba
n
d
u
n
g
,
In
d
o
n
e
sia
in
2
0
0
6
.
He
re
c
e
iv
e
d
t
h
e
m
a
ste
r‟s
d
e
g
re
e
in
Co
m
p
u
ter
S
c
ien
c
e
f
ro
m
In
stit
u
t
T
e
k
n
o
lo
g
i
Ba
n
d
u
n
g
,
Ba
n
d
u
n
g
,
I
n
d
o
n
e
sia
in
2
0
1
0
.
His
m
a
in
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
c
y
b
e
r
-
p
h
y
sic
a
l
s
y
ste
m
,
in
telli
g
e
n
t
sy
ste
m
,
m
a
c
h
in
e
lea
rn
i
n
g
,
a
n
d
sig
n
a
l
p
r
o
c
e
ss
in
g
.
M
u
h
a
m
m
a
d
Ne
z
a
r
M
a
h
a
r
d
i
k
a
is
a
n
Ba
c
h
e
lo
r
st
u
d
e
n
t
f
ro
m
th
e
In
f
o
rm
a
ti
c
D
e
p
a
rt
m
e
n
t,
In
stit
u
t
T
e
k
n
o
lo
g
i
S
e
p
u
l
u
h
No
p
e
m
b
e
r,
In
d
o
n
e
sia
.
His
re
se
a
rc
h
in
tere
st
i
n
c
lu
d
e
m
a
c
h
in
e
lea
rn
in
g
,
sig
n
a
l
p
ro
c
e
ss
in
g
,
a
n
d
a
u
d
io
a
n
a
ly
sis.
Evaluation Warning : The document was created with Spire.PDF for Python.