Weakly-Supervised Classification and Detection of Bird Sounds in the Wild. A BirdCLEF 2021 Solution
Published in
Conference and Labs of the Evaluation Forum(2021)External Links:
TL
TL;DR
This work proposes a sound detection and classification pipeline for analyzing complex soundscape recordings and identify birdcalls in the background and is robust against background sounds (e.g., airplanes, rain, etc).
Abstract
It is easier to hear birds than see them, however, they still play an essential role in nature and they are excellent indicators of deteriorating environmental quality and pollution. Recent advances in Machine Learning and Convolutional Neural Networks allow us to detect and classify bird sounds, by doing this, we can assist researchers in monitoring the status and trends of bird populations and biodiversity in ecosystems. We propose a sound detection and classification pipeline for analyzing complex soundscape recordings and identify birdcalls in the background. Our pipeline learns from weak labels, classifies fine-grained bird vocalizations in the wild, and is robust against background sounds (e.g., airplanes, rain, etc). Our solution achieved 10th place of 816 teams at the BirdCLEF 2021 Challenge hosted on Kaggle.
References23 items
1
Overview of LifeCLEF 2020: A System-Oriented Evaluation of Automated Species Identification and Species Distribution Prediction
2
Sound Event Detection with Depthwise Separable and Dilated Convolutions
3
PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition
4
Overview of BirdCLEF 2019: Large-Scale Bird Recognition in Soundscapes
5