# BeeVe: Unsupervised Acoustic State Discovery in Honey Bee Buzzing

arXiv: https://arxiv.org/abs/2605.07903 · HTML: https://mlsanity.com/paper/2605.07903/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 18 references that are in the map.
- First posted on arXiv 8 May 2026.

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

- [Efficient Training of Audio Transformers with Patchout](https://mlsanity.com/paper/2110.05069/) (2021)
- [AVES: Animal Vocalization Encoder based on Self-Supervision](https://mlsanity.com/paper/2210.14493/) (2022)
- [NatureLM-audio: an Audio-Language Foundation Model for Bioacoustics](https://mlsanity.com/paper/2411.07186/) (2024)
- [Comparing Self-Supervised Learning Models Pre-Trained on Human Speech and Animal Vocalizations for Bioacoustics Processing](https://mlsanity.com/paper/2501.05987/) (2025)
- [UrBAN: Urban Beehive Acoustics and PheNotyping Dataset](https://mlsanity.com/paper/2406.03657/) (2024)
- [Towards Leveraging Sequential Structure in Animal Vocalizations](https://mlsanity.com/paper/2511.10190/) (2025)

## Abstract (arXiv)

Discovering structure in biological signals without supervision is a fundamental problem in computational intelligence, yet existing bioacoustic methods assume vocal production models or predefined semantic units, leaving non-vocal species poorly served. This work introduces BeeVe, an unsupervised framework for acoustic state discovery in collective honey bee buzzing. BeeVe uses the self-supervised Patchout Spectrogram Transformer (PaSST) as a frozen feature extractor, then trains a Vector-Quantized Variational Autoencoder (VQ-VAE) without labels on those embeddings, learning a finite discrete codebook of acoustic tokens directly from unlabelled hive audio. No labels, pretext tasks, or contrastive objectives are used at any stage. Post-hoc evaluation against known queen status reveals that the learned tokens separate queenright and queenless conditions with Jensen-Shannon Divergence values between 0.609 and 0.688, and that the queenless condition further decomposes into three internally coherent sub-states stable across experiments with different codebook sizes and random seeds. Token transition analysis confirms non-random sequential structure (p << 0.001) across all experiments. Generalisation to unseen recordings preserves both token overlap (Jaccard = 0.947) and global manifold topology. These results demonstrate that unsupervised discrete codebook learning can recover repeatable acoustic structure from a non-vocal biological signal without annotation, opening a path toward non-invasive acoustic hive health monitoring.