Pig vocalizations contain shared acoustic structure for humans and machines, but limited correspondence with presumed affective valence
- 1ETH Zurich
Abstract
Pig vocalizations are increasingly used as indicators of affective state and welfare. This view is supported by above-chance human valence judgments and striking machine learning classification performance in prior studies. Yet, in both approaches the affective distinction is already built into the test. Algorithms are trained and evaluated using presumed valence labels assigned to recording contexts, while human listeners are asked directly to rate valence. We therefore asked what structure emerges when listeners are given no predefined categories, and how that structure relates to explicit human judgments and neural network representations. In a free-classification task, 224 participants labeled and sorted 2,192 pig vocalizations. A second group of 159 participants then classified vocalizations using predefined context categories and rated their valence. Humans and neural networks recovered corresponding organization, confirming that pig vocalizations contain reproducible acoustic information. Yet, affect was not the dominant spontaneous interpretation, with only 26.3% of participant-generated labels referring to feelings or emotions. Explicit valence judgments were systematic and agreed moderately with presumed valence, with 60.1% directional agreement. However, this correspondence disappeared when highly aversive situations were excluded, although neural networks still classified presumed valence with 92.0% accuracy after removing these contexts. In a matched permutation analysis, however, neural networks with arbitrary valence reassignments on the context level averaged 79% accuracy, with 5 of 100 exceeding the original grouping. Pig vocalizations therefore contain rich acoustic information that both humans and algorithms can recover, but successful recovery does not by itself establish what that information means for the animal. Progress in vocal indicators of pig affect and welfare will require moving beyond classification performance toward independent validation of the biological meaning assigned to acoustic differences.
Related
- "Mine" or "yours"? Acoustic structure of food calls predicts sharing decisions in marmosets
- The acoustic structure and possible mechanical origin of the male Corncrake call
- Kinship, acoustic signaling, and socio-spatial structure shape shared decisions and social influence in white-nosed coatis
- Millisecond-scale detection of mouse ultrasonic vocalizations enables closed-loop experiments
- Frequency-dependent cerebellar circuits independently gate social vocalizations and movement
BibTeX
@misc{gorssen2026vocalizations,
title = {{Pig vocalizations contain shared acoustic structure for humans and machines, but limited correspondence with presumed affective valence}},
author = {W. Gorssen and B. Sleurs and C. Winters},
howpublished = {bioRxiv},
year = {2026},
month = jul,
doi = {10.64898/2026.07.06.736900},
url = {https://www.biorxiv.org/content/10.64898/2026.07.06.736900v2},
note = {CC BY},
}
RIS
TY - UNPB
TI - Pig vocalizations contain shared acoustic structure for humans and machines, but limited correspondence with presumed affective valence
AU - W. Gorssen
AU - B. Sleurs
AU - C. Winters
PY - 2026
DA - 2026/07/06
PB - bioRxiv
DO - 10.64898/2026.07.06.736900
UR - https://www.biorxiv.org/content/10.64898/2026.07.06.736900v2
AB - Pig vocalizations are increasingly used as indicators of affective state and welfare. This view is supported by above-chance human valence judgments and striking machine learning classification performance in prior studies. Yet, in both approaches the affective distinction is already built into the test. Algorithms are trained and evaluated using presumed valence labels assigned to recording contexts, while human listeners are asked directly to rate valence. We therefore asked what structure emerges when listeners are given no predefined categories, and how that structure relates to explicit human judgments and neural network representations. In a free-classification task, 224 participants labeled and sorted 2,192 pig vocalizations. A second group of 159 participants then classified vocalizations using predefined context categories and rated their valence. Humans and neural networks recovered corresponding organization, confirming that pig vocalizations contain reproducible acoustic information. Yet, affect was not the dominant spontaneous interpretation, with only 26.3% of participant-generated labels referring to feelings or emotions. Explicit valence judgments were systematic and agreed moderately with presumed valence, with 60.1% directional agreement. However, this correspondence disappeared when highly aversive situations were excluded, although neural networks still classified presumed valence with 92.0% accuracy after removing these contexts. In a matched permutation analysis, however, neural networks with arbitrary valence reassignments on the context level averaged 79% accuracy, with 5 of 100 exceeding the original grouping. Pig vocalizations therefore contain rich acoustic information that both humans and algorithms can recover, but successful recovery does not by itself establish what that information means for the animal. Progress in vocal indicators of pig affect and welfare will require moving beyond classification performance toward independent validation of the biological meaning assigned to acoustic differences.
ER -