Machine-learning based detection of marine mammal vocalizations in snapping-shrimp dominated ambient noise.
Mar Environ Res
; 199: 106571, 2024 Jul.
Article
de En
| MEDLINE
| ID: mdl-38833807
ABSTRACT
Passive acoustics is an effective method for monitoring marine mammals, facilitating both detection and population estimation. In warm tropical waters, this technique encounters challenges due to the high persistent level of ambient impulsive noise originating from the snapping shrimp present throughout this region. This study presents the development and application of a neural-network based detector for marine-mammal vocalizations in long term acoustic data recorded by us at ten locations in Singapore waters. The detector's performance is observed to be impeded by the high shrimp noise activity. To counteract this, we investigate several techniques to improve detection capabilities in shrimp noise including the use of simple nonlinear denoisers and a machine-learning based denoiser. These are shown to enhance the detection performance significantly. Finally, we discuss some of the vocalizations detected over three years of our acoustic recorder deployments using the robust detectors developed.
Mots clés
Texte intégral:
1
Collection:
01-internacional
Base de données:
MEDLINE
Sujet principal:
Vocalisation animale
/
Acoustique
/
Surveillance de l'environnement
/
Apprentissage machine
/
Bruit
Limites:
Animals
Pays/Région comme sujet:
Asia
Langue:
En
Journal:
Mar Environ Res
/
Mar. environ. res
/
Marine environmental research
Sujet du journal:
BIOLOGIA
/
SAUDE AMBIENTAL
/
TOXICOLOGIA
Année:
2024
Type de document:
Article
Pays de publication:
Royaume-Uni