# Domain-Invariant Representation Learning of Bird Sounds

arXiv: https://arxiv.org/abs/2409.08589 · HTML: https://mlsanity.com/paper/2409.08589/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Sep 2024.

## Built on by (most cited first, 9 of 9)

- [Can Masked Autoencoders Also Listen to Birds?](https://mlsanity.com/paper/2504.12880/) (2025)
- [Perch 2.0: The Bittern Lesson for Bioacoustics](https://mlsanity.com/paper/2508.04665/) (2025)
- [Foundation Models for Bioacoustics -- a Comparative Review](https://mlsanity.com/paper/2508.01277/) (2025)
- [Clustering and novel class recognition: evaluating bioacoustic deep learning feature extractors](https://mlsanity.com/paper/2504.06710/) (2025)
- [bacpipe: a Python package to make bioacoustic deep learning models accessible](https://mlsanity.com/paper/2604.11560/) (2026)
- [MetaPerch: Learning from metadata for bioacoustics foundation models](https://mlsanity.com/paper/2607.14072/) (2026)
- [Better audio representations are more brain-like: linking model-brain alignment with performance in downstream auditory tasks](https://mlsanity.com/paper/2511.16849/) (2025)
- [Torus embeddings](https://mlsanity.com/paper/2603.03135/) (2026)
- [Adaptive Loss Balancing for Multi-Task Bioacoustic Classification of Bird Species and Call Types](https://mlsanity.com/paper/2607.03304/) (2026)

## Abstract (arXiv)

Passive acoustic monitoring (PAM) is crucial for bioacoustic research, enabling non-invasive species tracking and biodiversity monitoring. Citizen science platforms provide large annotated datasets from focal recordings, where the target species is intentionally recorded. However, PAM requires monitoring in passive soundscapes, creating a domain shift between focal and passive recordings, challenging deep learning models trained on focal recordings. To address domain generalization, we leverage supervised contrastive learning by enforcing domain invariance across same-class examples from different domains. Additionally, we propose ProtoCLR, an alternative to SupCon loss which reduces the computational complexity by comparing examples to class prototypes instead of pairwise comparisons. We conduct few-shot classification based on BIRB, a large-scale bird sound benchmark to assess pre-trained bioacoustic models. Our findings suggest that ProtoCLR is a better alternative to SupCon.