Identifying acoustic features to distinguish between highly and moderately altered soundscapes in Colombia

• Fernando Martínez-Tabares ^[1] ; Mauricio Orozco-Alzate ^[1]
  1. [1] Universidad Nacional de Colombia

     Universidad Nacional de Colombia

     Colombia

     
• Localización: Inteligencia artificial: Revista Iberoamericana de Inteligencia Artificial, ISSN-e 1988-3064, ISSN 1137-3601, Vol. 26, Nº. 71, 2023, págs. 34-45
• Idioma: inglés
• Enlaces
  • Texto completo
• Resumen

  • Numerous acoustic features have been proposed as useful measures to characterize natural soundscapes,which can be employed to examine the impact of land transformation on the audible properties of a location.The extensive collection of available features demands an examination to identify the most informative anddiscriminative ones for a given problem. In this study, we conduct an empirical investigation into the selectionof acoustic features for discriminating between highly and moderately transformed versions of four Colombiansoundscapes: moorlands, coffee plantations, dry tropical forests, and pastures. We employ classical supervisedfeature selection techniques along with exploratory tools such as correlation matrices and scatter plots. Our resultsindicate that a few acoustic features are sufficient to differentiate between the classes. Specifically, those featuresthat estimate acoustic complexity via intrinsic variability of sound intensities or biodiversity through speciesrichness or abundance in specific frequency bands are the most discriminative ones. These findings suggest thatthe selection of acoustic features can assist in analyzing and distinguishing between different soundscapes.