Over het archief
Het OWA, het open archief van het Waterbouwkundig Laboratorium heeft tot doel alle vrij toegankelijke onderzoeksresultaten van dit instituut in digitale vorm aan te bieden. Op die manier wil het de zichtbaarheid, verspreiding en gebruik van deze onderzoeksresultaten, alsook de wetenschappelijke communicatie maximaal bevorderen.
Dit archief wordt uitgebouwd en beheerd volgens de principes van de Open Access Movement, en het daaruit ontstane Open Archives Initiative.
Basisinformatie over ‘Open Access to scholarly information'.
SoundLib: An underwater sound library of the North Sea
Cuyx, B.; Parcerisas, C.; Aubach, J.; Jälmby, M.; Mendes, J.; Regel, F.; Debusschere, E. (2026). SoundLib: An underwater sound library of the North Sea, in: Popper, A.N. et al. The effects of noise on aquatic life IV. pp. 1-12. https://dx.doi.org/10.1007/978-3-031-94229-7_43-1
|  |
| Author keywords |
Passive acoustic monitoring · Machine learning · Sound event detection · Bioacoustics · Soundscapes · Dataset |
| Abstract |
Passive acoustic monitoring (PAM) and soundscape analysis provide powerful tools to unlock biodiversity information embedded in underwater sound. These noninvasive techniques are gaining traction among marine bioacousticians for their effectiveness in species monitoring. The authors present the SoundLib project, an initiative to build a comprehensive library of acoustic events and long-term underwater sound trends from the North Sea.Sound plays an important role in aquatic communication and as such can be used to assess the health of marine ecosystems by analyzing the soundscape in terms of biophony, geophony, and anthrophony. To contribute to this understanding, the authors employ PAM in the Belgian part of the North Sea (BPNS) and contribute a dataset of annotated long-term recordings.To facilitate broader access and collaboration, the authors have developed an application programming interface (API) and a Python-based software development kit (SDK) for SoundLib. The SoundLib application allows researchers to query the recordings and its metadata, which includes annotations for detected events. Users can also contribute audio recordings, both long-term and isolated sound events, which can be processed using the provided standardized methods. By leveraging this SDK, researchers can efficiently analyze marine soundscapes and contribute to a growing repository of acoustic data. |
IMIS is ontwikkeld en wordt gehost door het VLIZ.
