Motif Mining and Unsupervised Representation Learning for BirdCLEF 2022
Sound
2024-07-10 v1 Machine Learning
Audio and Speech Processing
Abstract
We build a classification model for the BirdCLEF 2022 challenge using unsupervised methods. We implement an unsupervised representation of the training dataset using a triplet loss on spectrogram representation of audio motifs. Our best model performs with a score of 0.48 on the public leaderboard.
Cite
@article{arxiv.2206.04805,
title = {Motif Mining and Unsupervised Representation Learning for BirdCLEF 2022},
author = {Anthony Miyaguchi and Jiangyue Yu and Bryan Cheungvivatpant and Dakota Dudley and Aniketh Swain},
journal= {arXiv preprint arXiv:2206.04805},
year = {2024}
}
Comments
Submitted to CEUR-WS under LifeCLEF for the BirdCLEF 2022 challenge as a working note