Producción CyT
Artículo
Autoría
Pérez-Granados, Cristian
;
Morant, Jon
;
Darras, Kevin F. A.
;
et al
;
ZURANO, JUAN PABLO
;
Sebastián-González, Esther
Fecha
2026
Editorial y Lugar de Edición
ECOLOGICAL SOC AMER
Revista
ECOLOGY,
vol. 107
ECOLOGICAL SOC AMER
Resumen
Información suministrada por el agente en
SIGEVA
Under the current global biodiversity crisis, there is a need for automated andnoninvasive monitoring techniques that can gather large amounts of datacost-effectively at various ecological scales, from local to large spatial scales.These data can then be analyzed to inform stakeholders and decision-makers.One such technique is passive acoustic monitoring, which is commonlycoupled with automatic identification of animal species based on their sound.Automated sound analyses usually require the tr...
Under the current global biodiversity crisis, there is a need for automated andnoninvasive monitoring techniques that can gather large amounts of datacost-effectively at various ecological scales, from local to large spatial scales.These data can then be analyzed to inform stakeholders and decision-makers.One such technique is passive acoustic monitoring, which is commonlycoupled with automatic identification of animal species based on their sound.Automated sound analyses usually require the training of sound detection andidentification algorithms. These algorithms are based on annotated acousticdatasets which mark the occurrence of sounds of species inside sound recordings.However, compiling large annotated acoustic datasets is time-consumingand requires experts, and therefore, they normally cover reduced spatial, temporal,and taxonomic scales. This data paper presents WABAD, the WorldAnnotated Bird Acoustic Dataset for passive acoustic monitoring. WABAD isdesigned to provide the public, the research community, and conservationmanagers with a novel and globally representative annotated acoustic dataset.This database includes 5047 min of audio files annotated to species-level bylocal experts with the start and end time and the upper and lower frequenciesof each identified bird vocalization in the recordings. The database has a widetaxonomic and spatial coverage, including information on 91,931 vocalizationsfrom 1192 bird species recorded at 72 recording sites in 29 recording locations(mainly countries) and distributed across 13 biomes. WABAD can be used, forexample, for developing and/or validating automatic species detection algorithms,answering ecological questions, such as assessing geographical variationson bird vocalizations, or comparing acoustic diversity indices withspecies-based diversity indices. The dataset is published under a CreativeCommons Attribution 4.0 International license that permits redistribution andreuse on the condition that the original work is properly credited.
Ver más
Ver menos
Palabras Clave
autonomous recording unitsautomated sound recordersongpassive acoustic monitoringbirdssoundscapeanimal vocalizationshuman expert annotation