Recognizing bird species in diverse soundscapes under weak supervision
This work addresses automated biodiversity monitoring for avian populations, enabling scalable global assessment that is infeasible with manual methods.
The paper tackled bird species recognition in complex soundscapes using weak supervision, achieving second place in the BirdCLEF2021 challenge by improving generalization from crowd-sourced to autonomous recording data.
We present a robust classification approach for avian vocalization in complex and diverse soundscapes, achieving second place in the BirdCLEF2021 challenge. We illustrate how to make full use of pre-trained convolutional neural networks, by using an efficient modeling and training routine supplemented by novel augmentation methods. Thereby, we improve the generalization of weakly labeled crowd-sourced data to productive data collected by autonomous recording units. As such, we illustrate how to progress towards an accurate automated assessment of avian population which would enable global biodiversity monitoring at scale, impossible by manual annotation.