# Localized time-frequency representation learning for bioacoustic classification in complex soundscapes

arXiv: https://arxiv.org/abs/2502.13440 · HTML: https://mlsanity.com/paper/2502.13440/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 46 references that are in the map.
- First posted on arXiv 19 Feb 2025.

## Builds on (most cited first, 6 of 6)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Computational bioacoustics with deep learning: a review and roadmap](https://mlsanity.com/paper/2112.06725/) (2021)
- [BirdSet: A Large-Scale Dataset for Audio Classification in Avian Bioacoustics](https://mlsanity.com/paper/2403.10380/) (2024)
- [Learning to detect an animal sound from five examples](https://mlsanity.com/paper/2305.13210/) (2023)
- [Self-Supervised Learning for Few-Shot Bird Sound Classification](https://mlsanity.com/paper/2312.15824/) (2023)
- [Multiscale CNN based Deep Metric Learning for Bioacoustic Classification: Overcoming Training Data Scarcity Using Dynamic Triplet Loss](https://mlsanity.com/paper/1903.10713/) (2019)

## Built on by (most cited first, 1 of 1)

- [Time-frequency localization of bird calls in dense soundscapes](https://mlsanity.com/paper/2606.10407/) (2026)

## Abstract (arXiv)

Prevailing bioacoustic classifiers assign species labels to fixed time-frequency windows rather than to individual vocalizations. When multiple vocalizations occur within the same window, predictions cannot be unambiguously linked to specific calls, which limits analyses at the level of individual vocalizations. This work introduces a framework for time-frequency localized bird classification. A Local-Context Classifier (LCC) identifies species from localized time-frequency events (TFEs), while a Dual-Context Classifier (DCC) combines local and global acoustic context through a fine-tuned bioacoustic foundation model. On an in-distribution dataset from Singapore comprising 306 vocalization classes from 103 bird species, the LCC achieves an F1-micro score of 79.3%, while combining local and global context through the DCC yields the highest overall performance (94.6%). To reduce labeled data requirements, the LCC is pre-trained via self-supervised contrastive learning, achieving an 18.8% relative gain on an out-of-distribution dataset. A focused evaluation on continuous soundscape recordings further demonstrates the potential of the framework for long-term monitoring applications. By preserving the time-frequency localization of individual vocalizations, the proposed framework supports both ecological monitoring and vocalization-level studies of animal acoustic behavior.