Biodiversity monitoring using audio recordings is achievable at a truly global scale via large-scale deployment of inexpensive, unattended recording stations or by large-scale crowdsourcing using recording and species recognition on mobile devices. The ability, however, to reliably identify vocalising animal species is limited by the fact that acoustic signatures of interest in such recordings are typically embedded in a diverse and complex acoustic background.
Detecting bird sound in unknown acoustic background using crowdsourced training data
25 May 2015
Other Recent Journal Article / Working Papers
Wage effect of participation and position in GVC: An industry level-level analysis
The Arrival of Fiber and the Digital Dividend Gap: Evidence from the Asymmetric Homebuyers’ Responses
Structural change, productivity growth and labour market turbulence in Africa
The Impact of Firm Downsizing on Workers: Evidence from Ethiopia’s Ready-Made Garment Industry

A comparison in species distribution model performance of succulents using key species and subsets of environmental predictors
Why is productivity slowing down?