Unlabeled Echoes: Pseudo-Labels and Genus-Aware Smoothing for Bat Call Recognition
Abstract
Passive acoustic monitoring produces far more bat recordings than experts can label. We show that simple model-generated pseudo-labels turn this surplus into effective supervision. We compare pseudo-labeling with other semi-supervised learning methods on an 18-species European corpus using only 10% of its training labels, then transfer the strongest approaches to South African field audio containing nine bat taxa and a nuisance class. Pseudo-labeling outperforms the other semi-supervised learning methods on every European measure, recovering up to 61.5% of the gap to full supervision. It transfers to field audio with gains of 10.69 points in species accuracy and 4.96 points in species macro-F1. We also introduce genus-aware smoothing, which directs uncertain target mass toward congeneric species. Combined with uniform smoothing, it reaches 79.16 species macro-F1, 4.73 points above hard targets. Simple pseudo-labels are therefore highly effective at this ecological data scale, while genus-aware targets inject useful biological structure at no annotation cost. https://code4conservation.github.io/UnlabeledEchoes/
Related
- Cultural echoes in social bonding: Universal and culture-specific effects of movement synchrony and music on connectedness, likeability, and well-being
- Echoes of Evolution in Holocentridae : Harmony Between Phylogeny, Morphology and Acoustics
- ProDTI: prior-guided positive-unlabeled learning for robust drug-target interaction prediction.
- Moral echoes: do morality and humanness affect emotional and aesthetic responses to music?
- Echoes of Thought: Task Complexity, Inner Speech Analogs, and Prompt Design Shape LLMs’ Response Behavior in the Two-Step Task
BibTeX
@misc{fundel2026unlabeled,
title = {{Unlabeled Echoes: Pseudo-Labels and Genus-Aware Smoothing for Bat Call Recognition}},
author = {Frank Fundel and Alexandra Howard},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.11986},
eprint = {2609.11986},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.11986},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Unlabeled Echoes: Pseudo-Labels and Genus-Aware Smoothing for Bat Call Recognition
AU - Frank Fundel
AU - Alexandra Howard
PY - 2026
DA - 2026/09/08
PB - arXiv
DO - 10.48550/arxiv.2609.11986
UR - https://arxiv.org/abs/2609.11986
AB - Passive acoustic monitoring produces far more bat recordings than experts can label. We show that simple model-generated pseudo-labels turn this surplus into effective supervision. We compare pseudo-labeling with other semi-supervised learning methods on an 18-species European corpus using only 10% of its training labels, then transfer the strongest approaches to South African field audio containing nine bat taxa and a nuisance class. Pseudo-labeling outperforms the other semi-supervised learning methods on every European measure, recovering up to 61.5% of the gap to full supervision. It transfers to field audio with gains of 10.69 points in species accuracy and 4.96 points in species macro-F1. We also introduce genus-aware smoothing, which directs uncertain target mass toward congeneric species. Combined with uniform smoothing, it reaches 79.16 species macro-F1, 4.73 points above hard targets. Simple pseudo-labels are therefore highly effective at this ecological data scale, while genus-aware targets inject useful biological structure at no annotation cost. https://code4conservation.github.io/UnlabeledEchoes/
ER -