Recognizing Birds from Sound - The 2018 BirdCLEF Baseline System

Stefan Kahl, Thomas Wilhelm-Stein, Holger Klinck, Danny Kowerko, Maximilian Eibl
4/19/2018
cs.CV

Official code: kahst/BirdCLEF-Baseline (52 stars, MIT, last commit 2021-12-30).

Abstract

Reliable identification of bird species in recorded audio files would be a transformative tool for researchers, conservation biologists, and birders. In recent years, artificial neural networks have greatly improved the detection quality of machine learning systems for bird species recognition. We present a baseline system using convolutional neural networks. We publish our code base as reference for participants in the 2018 LifeCLEF bird identification task and discuss our experiments and potential improvements.

View on arXivView PDF

Code Implementations(1)

kahst/BirdCLEF-BaselineOfficial100%
MIT

The 2018 LifeCLEF bird identification task baseline system.

5213Shell, PythonApr 6, 20184 years agoMIT
bioaccousticsbirdsbirdsongconvolutional-neural-networkslasagne+3 more

Similar Papers

Western Mediterranean wetlands bird species classification: evaluating small-footprint deep learning approaches on a new annotated dataset

88% match2022

A Bird Song Detector for improving bird identification through Deep Learning: a case study from Doñana

88% match2 repos142025

Automated Bioacoustic Monitoring for South African Bird Species on Unlabeled Data

86% match2024

Semi-supervised classification of bird vocalizations

86% match2025

Improving Bird Classification with Primary Color Additives

86% match2025

NBM: an Open Dataset for the Acoustic Monitoring of Nocturnal Migratory Birds in Europe

86% match2024

Cite this paper

@article{kahl2018recognizing,
  title  = {Recognizing Birds from Sound - The 2018 BirdCLEF Baseline System},
  author = {Stefan Kahl and Thomas Wilhelm-Stein and Holger Klinck and Danny Kowerko and Maximilian Eibl},
  year   = {2018},
  eprint = {1804.07177},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1804.07177}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1804.07177.svg)](https://codeofpaper.com/paper/1804.07177)

Discussion