Improving Bird Classification with Primary Color Additives

TL;DR

This paper introduces a novel spectrogram colorization technique using primary colors to embed frequency information, significantly improving bird species classification accuracy in noisy and complex audio recordings.

Contribution

It proposes a new spectrogram colorization method that enhances deep learning models' ability to distinguish bird species by embedding frequency data with primary colors.

Findings

Achieved a 7.3% increase in F1 score over baseline models.

Surpassed the BirdCLEF 2024 winner in key metrics.

Demonstrated statistically significant improvements in classification accuracy.

Abstract

We address the problem of classifying bird species using their song recordings, a challenging task due to environmental noise, overlapping vocalizations, and missing labels. Existing models struggle with low-SNR or multi-species recordings. We hypothesize that birds can be classified by visualizing their pitch pattern, speed, and repetition, collectively called motifs. Deep learning models applied to spectrogram images help, but similar motifs across species cause confusion. To mitigate this, we embed frequency information into spectrograms using primary color additives. This enhances species distinction and improves classification accuracy. Our experiments show that the proposed approach achieves statistically significant gains over models without colorization and surpasses the BirdCLEF 2024 winner, improving F1 by 7.3%, ROC-AUC by 6.2%, and CMAP by 6.6%. These results demonstrate the effectiveness of incorporating frequency information via colorization.