Schlieren imaging and video classification of alphabet pronunciations: exploiting phonetic flows for speech recognition and speech therapy
Visual Computing for Industry Biomedicine and Art,
Journal Year:
2024,
Volume and Issue:
7(1)
Published: May 22, 2024
Abstract
Speech
is
a
highly
coordinated
process
that
requires
precise
control
over
vocal
tract
morphology/motion
to
produce
intelligible
sounds
while
simultaneously
generating
unique
exhaled
flow
patterns.
The
schlieren
imaging
technique
visualizes
airflows
with
subtle
density
variations.
It
hypothesized
speech
flows
captured
by
schlieren,
when
analyzed
using
hybrid
of
convolutional
neural
network
(CNN)
and
long
short-term
memory
(LSTM)
network,
can
recognize
alphabet
pronunciations,
thus
facilitating
automatic
recognition
disorder
therapy.
This
study
evaluates
the
feasibility
CNN-based
video
classification
differentiate
corresponding
first
four
alphabets:
/A/,
/B/,
/C/,
/D/.
A
optical
system
was
developed,
pronunciations
were
recorded
for
two
participants
at
an
acquisition
rate
60
frames
per
second.
total
640
clips,
each
lasting
1
s,
utilized
train
test
CNN-LSTM
network.
Acoustic
analyses
conducted
understand
phonetic
differences
among
alphabets.
trained
separately
on
datasets
varying
sizes
(i.e.,
20,
30,
40,
50
videos
alphabet),
all
achieving
95%
accuracy
in
classifying
same
participant.
However,
network’s
performance
declined
tested
from
different
participant,
dropping
around
44%,
indicating
significant
inter-participant
variability
pronunciation.
Retraining
both
improved
93%
second
Analysis
misclassified
indicated
factors
such
as
low
quality
disproportional
head
size
affected
accuracy.
These
results
highlight
potential
CNN-assisted
therapy
articulation
flows,
although
challenges
remain
expanding
set
participant
cohort.
Language: Английский
Visualization and Quantification of Facemask Leakage Flows and Interpersonal Transmission with Varying Face Coverings
Xiuhua Si,
No information about this author
Jensen S. Xi,
No information about this author
H. Talaat
No information about this author
et al.
Published: June 7, 2024
Although
mask-wearing
is
now
widespread,
knowledge
of
how
to
quantify
or
improve
its
performance
remains
surprisingly
limited
and
largely
based
on
empirical
evidence.
The
objective
this
study
was
visualize
the
expiratory
airflows
from
facemasks
evaluate
aerosol
transmission
between
two
persons.
Different
visualization
methods
were
explored,
including
Schlieren
optical
system,
laser/LED-particle
imaging
thermal
camera,
vapor-SarGel
system.
leakage
flows
escaped
aerosols
quantified
using
a
hotwire
anemometer
particle
counter,
respectively.
results
show
that
reduces
exhaled
flow
velocity
2~4
m/s
(with
no
facemask)
around
0.1
m/s,
thus
decreasing
droplet
speeds.
Cloth,
surgical,
KN95
masks
showed
varying
at
nose
top,
sides,
chin.
rate
also
differed
inhalation
exhalation.
neck
gaiter
has
low
filtration
efficiency
high
fractions,
providing
protection
efficiency.
There
considerable
deposition
in
mouth-nose
area,
as
well
neck,
chin,
jaw,
which
heightened
risk
self-inoculation
through
spontaneous
face-touching.
A
face
shield
plus
surgical
mask
greatly
reduced
droplets
head,
face,
indicating
double
coverings
can
be
highly
effective
when
single
insufficient.
system
provided
practical
approach
interpersonal
under
close
contact
scenarios
with
different
coverings.
Language: Английский
Visualization and Quantification of Facemask Leakage Flows and Interpersonal Transmission with Varying Face Coverings
Xiuhua Si,
No information about this author
Jensen S. Xi,
No information about this author
H. Talaat
No information about this author
et al.
Fluids,
Journal Year:
2024,
Volume and Issue:
9(7), P. 166 - 166
Published: July 22, 2024
Although
mask-wearing
is
now
widespread,
the
knowledge
of
how
to
quantify
or
improve
their
performance
remains
surprisingly
limited
and
largely
based
on
empirical
evidence.
The
objective
this
study
was
visualize
expiratory
airflows
from
facemasks
evaluate
aerosol
transmission
between
two
persons.
Different
visualization
methods
were
explored,
including
Schlieren
optical
system,
laser/LED-particle
imaging
thermal
camera,
vapor–SarGel
system.
leakage
flows
escaped
aerosols
quantified
using
a
hotwire
anemometer
particle
counter,
respectively.
results
show
that
reduces
exhaled
flow
velocity
2~4
m/s
(with
no
facemask)
around
0.1
m/s,
thus
decreasing
droplet
speeds.
Cloth,
surgical,
KN95
masks
showed
varying
at
nose
top,
sides,
chin.
rate
also
differed
inhalation
exhalation.
neck
gaiter
has
low
filtration
efficiency
high
fractions,
providing
protection
efficiency.
There
considerable
deposition
in
mouth–nose
area,
as
well
neck,
chin,
jaw,
which
heightened
risk
self-inoculation
through
spontaneous
face-touching.
A
face
shield
plus
surgical
mask
greatly
reduced
droplets
head,
face,
indicating
double
coverings
can
be
highly
effective
when
single
insufficient.
system
provided
practical
approach
interpersonal
under
close
contact
scenarios
with
different
coverings.
Language: Английский