Flexible and Interpretable Soundscape Analysis for Biodiversity Assessment and Ecosystem Health for Domain Experts
Published: March 18, 2025
Language: Английский
EcoScape Analyzer: A Tool for Performing Soundscape Analysis With Flexible Pipeline for Biodiversity Assessment
Published: March 18, 2025
Language: Английский
Exploring the relationship between the soundscape and the environment: A systematic review
Ecological Indicators,
Journal Year:
2024,
Volume and Issue:
166, P. 112388 - 112388
Published: July 26, 2024
Language: Английский
Characterization of soundscapes with acoustic indices and clustering reveals phenology patterns in a subtropical rainforest
Yen‐Chun Lai,
No information about this author
Sheng-Shan Lu,
No information about this author
Ming‐Tang Shiao
No information about this author
et al.
Ecological Indicators,
Journal Year:
2025,
Volume and Issue:
171, P. 113126 - 113126
Published: Jan. 27, 2025
Language: Английский
An Exploration of Ecoacoustics and its Applications in Conservation Ecology
Almo Farina,
No information about this author
Benjamin Krause,
No information about this author
Tim C. Mullet
No information about this author
et al.
Biosystems,
Journal Year:
2024,
Volume and Issue:
245, P. 105296 - 105296
Published: Aug. 15, 2024
Language: Английский
Interpretable and Robust Machine Learning for Exploring and Classifying Soundscape Data
bioRxiv (Cold Spring Harbor Laboratory),
Journal Year:
2024,
Volume and Issue:
unknown
Published: Nov. 8, 2024
Abstract
The
adoption
of
machine
learning
in
Passive
Acoustic
Monitoring
(PAM)
has
improved
prediction
accuracy
for
tasks
like
species-specific
call
detection
and
habitat
quality
estimation.
However,
these
models
often
lack
interpretability,
PAM
generates
vast
amounts
non-informative
data,
as
soundscapes
are
typically
information
sparse.
Here,
we
developed
ecologically
interpretable
methods
that
accurately
predict
land
use
from
audio
while
filtering
unwanted
data.
Audio
habitats
Southern
India
(evergreen
forests,
deciduous
scrublands,
grasslands)
was
collected
categorised
by
(reference,
disturbed,
agriculture).
We
used
Gaussian
Mixture
Models
(GMMs)
on
top
a
Convolutional
Neural
Network
(CNN)-based
feature
extractor
to
use.
Thresholding
based
likelihood
values
GMMs
model
excluding
uninformative
enabling
our
method
outperform
such
Random
Forests
Support
Vector
Machines.
By
analysing
areas
acoustic
space
driving
predictions,
identified
“keystone”
soundscape
elements
each
use,
including
both
biotic
anthropogenic
sources.
Our
approach
provides
novel
meaningful
interpretation
exploration
large
datasets
independent
specific
extractors.
study
paves
the
way
monitoring
deliver
robust
trustworthy
assessments
scales
would
not
otherwise
be
possible.
Language: Английский
Paisaje Sonoro: Creatividad Interdisciplinaria y Tecnologías Aplicadas para el Registro del Canto de las Aves
Deleted Journal,
Journal Year:
2024,
Volume and Issue:
8(2), P. 170 - 183
Published: Dec. 3, 2024
El
artículo
introduce
al
paisaje
sonoro
como
herramienta
interdisciplinaria
directamente
vinculada
uso
de
distintas
tecnologías
las
cuales
permiten
observar
cómo
el
humano
interactúa
con
entorno
acústico.
Este
trabajo
aborda
desarrollos
tecnológicos
contrastantes
que
expanden
estudio
y
desarrollo
del
sonoro,
además
presentar
algunas
consideraciones,
la
locación
seleccionada
tecnología
grabación
empleada,
lo
cual
no
sólo
configura
composición
acústica
los
elementos
integran,
sino
también
su
potencial
aplicación
científica.
Se
tomó
en
cuenta
avance
tecnológico
ha
permitido
obtener
mejores
estrategias
captura
acústica,
así
ejemplos
entre
sí,
posibilitan
ampliar
nuestro
catalogación
análisis
canto
aves.
observaron
diferentes
problemas
durante
realización
ruido
fondo,
ubicación
micrófonos,
reconocimiento
algorítmico,
otros,
dificultan
algorítmico
aves
encontradas
paisajes
sonoros,
resultando
obras
artísticas
interdisciplinarias
emplean
creaciones
tanto
científicas.