Advances in healthcare information systems and administration book series,
Journal Year:
2024,
Volume and Issue:
unknown, P. 313 - 330
Published: Nov. 22, 2024
Speech
disorders
are
the
conditions
in
people
which
affect
their
ability
to
speak
properly
i.e.,
different
from
normal
fluency
speaking.
These
speech
issues
usually
generated
due
a
variety
of
neurological
issues.
The
proper
and
correct
analysis
these
is
always
required
for
recommendation
treatment.
signals
may
provide
deep
insight
into
type
speech-related
In
this
paper,
thorough
performed
signals-based
disorder
analysis.
Various
types
discussed
here,
along
with
treatments
diagnosis
methods.
Furthermore,
various
steps
involved
thoroughly
examined.
traditional
models
as
well
novel
learning
further
applicability
detecting
disorders.
such
Dysarthria,
stuttering,
voice
disorders,
etc.
considered
here
Journal of Artificial Intelligence and Capsule Networks,
Journal Year:
2024,
Volume and Issue:
6(3), P. 340 - 362
Published: Sept. 1, 2024
Vocal
disorders
present
significant
challenges
for
patients
and
clinicians,
impacting
communication
quality
of
life.
The
development
artificial
intelligence
(AI)
technologies
offers
promising
possibilities
improving
the
assessment
management
vocal
disorders.
This
study
aims
to
evaluate
effectiveness
applicability
different
AI
approaches
in
this
field
through
a
comparative
AI-enabled
medical
assistance
Various
techniques,
including
machine
learning
algorithms,
deep
models,
natural
language
processing
methods,
are
explored
context
diagnosing
disorders,
planning
treatments,
managing
patients.
insights
gained
from
contribute
understanding
role
transforming
healthcare
delivery
highlighting
opportunities,
challenges,
future
directions
utilizing
enhance
specialized
field.
Journal of Machine and Computing,
Journal Year:
2024,
Volume and Issue:
unknown, P. 463 - 471
Published: April 5, 2024
With
the
demand
for
better,
more
user-friendly
HMIs,
voice
recognition
systems
have
risen
in
prominence
recent
years.
The
use
of
computer-assisted
vocal
pathology
categorization
tools
allows
accurate
detection
diseases.
By
using
these
methods,
disorders
may
be
diagnosed
early
on
and
treated
accordingly.
An
effective
Deep
Learning-based
tool
feature
extraction-based
identification
is
goal
this
project.
This
research
presents
results
EfficientNet,
a
pre-trained
Convolutional
Neural
Network
(CNN),
speech
dataset
order
to
achieve
highest
possible
classification
accuracy.
Artificial
Rabbit
Optimization
Algorithm
(AROA)-tuned
set
parameters
complements
model's
mobNet
building
elements,
which
include
linear
stack
divisible
convolution
max-pooling
layers
activated
by
Swish.
In
make
suggested
approach
applicable
broad
variety
disorder
problems,
study
also
suggests
unique
training
method
along
with
several
methodologies.
One
database,
Saarbrücken
database
(SVD),
has
been
used
test
proposed
technology.
Using
up
96%
accuracy,
experimental
findings
demonstrate
that
CNN
capable
detecting
pathologies.
demonstrates
great
potential
real-world
clinical
settings,
where
it
provide
classifications
as
little
three
seconds
expedite
automated
diagnosis
treatment.
Computer Methods in Biomechanics & Biomedical Engineering,
Journal Year:
2024,
Volume and Issue:
unknown, P. 1 - 11
Published: Oct. 18, 2024
Post-stroke
Dysarthria
(PSD)
is
one
of
the
common
sequelae
stroke.
PSD
can
harm
patients'
quality
life
and,
in
severe
cases,
be
life-threatening.
Most
existing
methods
use
frequency
domain
features
to
recognize
pathological
voice,
which
makes
it
hard
completely
represent
characteristics
voice.
Although
some
results
have
been
achieved,
there
still
a
long
way
go
for
practical
applications.
Therefore,
an
improved
deep
learning-based
model
proposed
classify
between
voice
and
normal
using
novel
fusion
feature
(MSA)
1D
ResNet
network
hybrid
bi-directional
LSTM
with
dilated
convolution
(named
DRN-biLSTM).
The
experimental
show
that
our
bring
greater
improvement
speech
recognition
than
method
only
analyzes
MFCC
features,
better
synthesize
hidden
characterize
speech.
In
terms
structure,
introduction
further
improve
performance
Resnet
network,
compared
ordinary
networks
such
as
CNN
LSTM.
accuracy
this
reaches
82.41%
100%
at
syllable
level
speaker
level,
respectively.
Our
scheme
outperforms
other
learning
capability
rate,
will
help
play
important
role
assessment
diagnosis
China.
Advances in healthcare information systems and administration book series,
Journal Year:
2024,
Volume and Issue:
unknown, P. 313 - 330
Published: Nov. 22, 2024
Speech
disorders
are
the
conditions
in
people
which
affect
their
ability
to
speak
properly
i.e.,
different
from
normal
fluency
speaking.
These
speech
issues
usually
generated
due
a
variety
of
neurological
issues.
The
proper
and
correct
analysis
these
is
always
required
for
recommendation
treatment.
signals
may
provide
deep
insight
into
type
speech-related
In
this
paper,
thorough
performed
signals-based
disorder
analysis.
Various
types
discussed
here,
along
with
treatments
diagnosis
methods.
Furthermore,
various
steps
involved
thoroughly
examined.
traditional
models
as
well
novel
learning
further
applicability
detecting
disorders.
such
Dysarthria,
stuttering,
voice
disorders,
etc.
considered
here
