# Decoding Insect Song: A Multitask Semisupervised Orthoptera Bioacoustic Classifier

arXiv: https://arxiv.org/abs/2606.13236 · HTML: https://mlsanity.com/paper/2606.13236/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 23 references that are in the map.
- First posted on arXiv 11 Jun 2026.

## Builds on (most cited first, 9 of 9)

- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016)
- [FSD50K: An Open Dataset of Human-Labeled Sound Events](https://mlsanity.com/paper/2010.00475/) (2020)
- [On the importance of single directions for generalization](https://mlsanity.com/paper/1803.06959/) (2018)
- [Perch 2.0: The Bittern Lesson for Bioacoustics](https://mlsanity.com/paper/2508.04665/) (2025)
- [BIRB: A Generalization Benchmark for Information Retrieval in Bioacoustics](https://mlsanity.com/paper/2312.07439/) (2023)
- [Improved Algorithm for Deep Active Learning under Imbalance via Optimal Separation](https://mlsanity.com/paper/2312.09196/) (2023)
- [Adaptive Representations of Sound for Automatic Insect Recognition](https://mlsanity.com/paper/2304.12739/) (2023)

## Abstract (arXiv)

Passive acoustic monitoring holds great promise for ecological inference, yet existing automated tools are typically narrowly trained and non-transferable. We address these limitations with PULSE, a semi-supervised, multi-task framework for Orthoptera bioacoustics, combining weakly-supervised species classification, self-supervised learning on unlabelled field audio, and knowledge distillation from a general-purpose bioacoustic model. Our domain-adapted specialist model outperforms a state-of-the-art general model across all metrics (macro F1: 0.21 vs. 0.07; AUC: 0.74 vs. 0.45; AP: 0.32 vs. 0.19), with active learning further raising F1 to 0.34 and AUC to 0.84. Beyond classification, the learned embeddings encode ecologically meaningful structure, exposed through an interactive visualisation tool for ecological discovery.