Vocal expression of emotions has been observed across species and could provide a non-invasive and reliable means to assess animal emotions. We investigated if pig vocal indicators of emotions revealed in previous studies are valid across call types and contexts, and could potentially be used to develop an automated emotion monitoring tool. We performed an analysis of an extensive and unique dataset of low (LF) and high frequency (HF) calls emitted by pigs across numerous commercial contexts from birth to slaughter (7414 calls from 411 pigs). Our results revealed that the valence attributed to the contexts of production (positive versus negative) affected all investigated parameters in both LF and HF. Similarly, the context category affected all parameters. We then tested two different automated methods for call classification; a neural network revealed much higher classification accuracy compared to a permuted discriminant function analysis (pDFA), both for the valence (neural network: 91.5%; pDFA analysis weighted average across LF and HF (cross-classified): 61.7% with a chance level at 50.5%) and context (neural network: 81.5%; pDFA analysis weighted average across LF and HF (cross-classified): 19.4% with a chance level at 14.3%). These results suggest that an automated recognition system can be developed to monitor pig welfare on-farm.

Animal Husbandry and Ethology Albrecht Daniel Thaer Institut Faculty of Life Sciences Humboldt Universität Zu Berlin Philippstrasse 13 10115 Berlin Germany

Behavioural Ecology Group Section for Ecology and Evolution Department of Biology University of Copenhagen 2100 Copenhagen Denmark

Bureau ETRE 63210 Bravant Olby France

Center for Artificial Intelligence Research University of Agder 4604 Kristiansand Norway

Center for Coastal Research University of Agder 4604 Kristiansand Norway

Department of Agricultural and Environmental Sciences Università Degli Studi Di Milano Milano Italy

Department of Ethology Institute of Animal Science 104 01 Prague Czechia

Department of Zoology Faculty of Science University of South Bohemia 370 05 Č Budějovice Czechia

Faculty of Agrobiology Food and Natural Resources Czech University of Life Sciences 165 21 Prague Czechia

Faculty of Veterinary Medicine Norwegian University of Life Sciences Universitetstunet 3 1433 Ås Norway

Institute of Agricultural Sciences ETH Zurich Universitätsstrasse 2 8092 Zürich Switzerland

Institute of Behavioural Physiology Research Institute for Farm Animal Biology 18196 Dummerstorf Germany

PEGASE INRAE Institut Agro 35590 Saint Gilles France

School of Engineering and Applied Sciences Harvard University Cambridge MA USA

University of Clermont Auvergne INRAE VetAgro Sup UMR Herbivores 63122 Saint Genès Champanelle France

Sci Rep. 2023 Nov 1;13(1):18824. doi: 10.1038/s41598-023-45242-9. PubMed

Zobrazit více v PubMed

Fraser D. Animal behaviour, animal welfare and the scientific study of affect. Appl. Anim. Behav. Sci. 2009;118:108–117. doi: 10.1016/j.applanim.2009.02.020. DOI

Boissy A, Lee C. How assessing relationships between emotions and cognition can improve farm animal welfare. Rev. Sci. Tech. 2014;33:103–110. doi: 10.20506/rst.33.1.2260. PubMed DOI

Scherer, K. R. Appraisal considered as a process of multilevel sequential checking in Appraisal processes in emotion: Theory, methods, research (eds. Scherer, K. R., Schorr, A., & Johnstone T.) 92–120 (Oxford University Press, Oxford, 2001).

Mendl M, Burman OHP, Paul ES. An integrative and functional framework for the study of animal emotion and mood. Proc. R. Soc. B. 2010;277:2895–2904. doi: 10.1098/rspb.2010.0303. PubMed DOI PMC

Špinka M. Social dimension of emotions and its implication for animal welfare. Appl. Anim. Behav. Sci. 2012;138:170–181. doi: 10.1016/j.applanim.2012.02.005. DOI

Briefer EF. Vocal contagion of emotions in non-human animals. Proc. R. Soc. B. 2018;258:20172783. doi: 10.1098/rspb.2017.2783. PubMed DOI PMC

Titze IR. A framework for the study of vocal registers. J. Voice. 1988;2:183–194. doi: 10.1016/S0892-1997(88)80075-4. DOI

Scherer KR. Vocal communication of emotion: a review of research paradigms. Speech Commun. 2003;40:227–256. doi: 10.1016/S0167-6393(02)00084-5. DOI

Manteuffel G, Puppe B, Schön P-C. Vocalization of farm animals as a measure of welfare. Appl. Anim. Behav. Sci. 2004;88:163–182. doi: 10.1016/j.applanim.2004.02.012. DOI

Briefer, E. F. Coding for ‘Dynamic’ Information: Vocal Expression of Emotional Arousal and Valence in Non-human Animals in Coding Strategies in Vertebrate Acoustic Communication (eds. Aubin, T. & Mathevon, N.) 137–162 (Springer, New York, 2020).

Briefer EF. Vocal expression of emotions in mammals: mechanisms of production and evidence. J. Zool. 2012;288:1–20. doi: 10.1111/j.1469-7998.2012.00920.x. DOI

Zimmermann, E., Leliveld, L. M. C. & Schehka, S. Towards the evolutionary roots of affective prosody in human acoustic communication: a comparative approach to mammalian voices in Evolution of emotional communication: from sound in nonhuman mammals to speech and music in man (eds. Altenmüller, E., Schmidt, S. & Zimmermann, E.) 116–132 (Oxford University Press, Oxford, 2013).

Jahns G. Call recognition to identify cow conditions: a call-recogniser translating calls to text. Comput. Electron. Agric. 2008;62:54–58. doi: 10.1016/j.compag.2007.09.005. DOI

Röttgen V, et al. Automatic recording of individual oestrus vocalisation in group-housed dairy cattle: development of a cattle call monitor. Animal. 2020;14:198–205. doi: 10.1017/S1751731119001733. PubMed DOI

Schön P-C, Puppe B, Manteuffel G. Automated recording of stress vocalization as a tool to document impaired welfare in pigs. Anim. Welf. 2004;13:105–110. doi: 10.1017/S096272860002683X. DOI

Mcloughlin MP, Stewart R, McElligott AG. Automated bioacoustics: methods in ecology and conservation and their potential for animal welfare monitoring. J. R. Soc. Interface. 2019;16:20190225. doi: 10.1098/rsif.2019.0225. PubMed DOI PMC

Tallet C, et al. Encoding of situations in the vocal repertoire of piglets (Sus scrofa): A comparison of discrete and graded classifications. PLoS ONE. 2013;8:e71841. doi: 10.1371/journal.pone.0071841. PubMed DOI PMC

Leliveld LMC, Düpjan S, Tuchscherer A, Puppe B. Behavioural and physiological measures indicate subtle variations in the emotional valence of young pigs. Physiol. Behav. 2016;157:116–124. doi: 10.1016/j.physbeh.2016.02.002. PubMed DOI

Linhart P, Ratcliffe VF, Reby D, Špinka M. Expression of emotional arousal in two different piglet call types. PLoS ONE. 2015;10:e0135414. doi: 10.1371/journal.pone.0135414. PubMed DOI PMC

Briefer EF, Vizier E, Gygax L, Hillmann E. Expression of emotional valence in pig closed-mouth grunts: Involvement of both source- and filter-related parameters. J. Acoust. Soc. Am. 2019;145:2895. doi: 10.1121/1.5100612. PubMed DOI

Friel M, Kunc HP, Griffin K, Asher L, Collins LM. Positive and negative contexts predict duration of pig vocalisations. Sci. Rep. 2019;9:2062. doi: 10.1038/s41598-019-38514-w. PubMed DOI PMC

Van der Maaten, L. & Hinton, G. Visualizing data using t-SNE. J. Mach. Learn. Res.9, (2008).

Buda M, Maki A, Mazurowski MA. A systematic study of the class imbalance problem in convolutional neural networks. Neural Netw. 2018;106:249–259. doi: 10.1016/j.neunet.2018.07.011. PubMed DOI

Herborn KA, et al. Spectral entropy of early-life distress calls as an iceberg indicator of chicken welfare. J. R. Soc. Interface. 2020;17:20200086. doi: 10.1098/rsif.2020.0086. PubMed DOI PMC

Gómez Y, et al. A systematic review on validated precision livestock farming technologies for pig production and its potential to assess animal welfare. Front. Vet. Sci. 2021;8:492. doi: 10.3389/fvets.2021.660565. PubMed DOI PMC

Cohen J. Statistical power analysis for the behavioral sciences. Academic Press; 2013.

Villain AS, et al. Piglets vocally express the anticipation of pseudo-social contexts in their grunts. Sci. Rep. 2020;10:18496. doi: 10.1038/s41598-020-75378-x. PubMed DOI PMC

Maigrot A-L, Hillmann E, Briefer EF. Encoding of emotional valence in wild boars (Sus Scrofa) calls. Animals. 2018;8:85. doi: 10.3390/ani8060085. PubMed DOI PMC

Maigrot A, Hillmann E, Callista A, Briefer EF. Vocal expression of emotional valence in Przewalski’s horses. Sci. Rep. 2017;18:8779. doi: 10.1038/s41598-017-09437-1. PubMed DOI PMC

Chan, W. Y. The meaning of barks: vocal communication of fearful and playful affective states in pigs. PhD thesis, Washington State University (2011).

Rasmussen JH, Širović A. Using faster region-based convolutional neural network for automatic detection of baleen whale social calls. J. Acoust. Soc. Am. 2019;146:2985–2985. doi: 10.1121/1.5137333. PubMed DOI

Russell J. A circumplex model of affect. J. Pers. Soc. Psychol. 1980;39:1161–1178. doi: 10.1037/h0077714. DOI

Bradley M, Codispoti M, Cuthbert B, Lang P. Emotion and motivation I: defensive and appetitive reactions in picture processing. Emotion. 2001;1:276–298. doi: 10.1037/1528-3542.1.3.276. PubMed DOI

Boersma, P. & Weenink, D. Praat: doing phonetics by computer v.5.3.57 [Computer program].http://www.praat.org/ (2013).

Beckers, G. J. L. Wiener entropy [Script developed in Praat v. 4.2.06] https://gbeckers.nl/pages/phonetics.html (2004).

Charlton BD, Zhihe Z, Snyder RJ. Vocal cues to identity and relatedness in giant pandas (Ailuropoda melanoleuca) J. Acoust. Soc. Am. 2009;126:2721–2732. doi: 10.1121/1.3224720. PubMed DOI

Garcia M, et al. Structural classification of wild boar (Sus scrofa) vocalizations. Ethology. 2016;122:329–342. doi: 10.1111/eth.12472. PubMed DOI PMC

Schrader L, Todt D. Vocal quality is correlated with levels of stress hormones in domestic pigs. Ethology. 1998;104:859–876. doi: 10.1111/j.1439-0310.1998.tb00036.x. DOI

Leliveld LMC, Düpjan S, Tuchscherer A, Puppe B. Vocal correlates of emotional reactivity within and across contexts in domestic pigs (Sus scrofa) Physiol. Behav. 2017;181:117–126. doi: 10.1016/j.physbeh.2017.09.010. PubMed DOI

Villain AS, Lanthony M, Guérin C, Tallet C. Manipulable object and human contact: preference and modulation of emotional states in weaned pigs. Front. Vet. Sci. 2020;7:930. doi: 10.3389/fvets.2020.577433. PubMed DOI PMC

Puppe B, Schön P-C, Tuchscherer A, Manteuffel G. Castration-induced vocalisation in domestic piglets, Sus scrofa: complex and specific alterations of the vocal quality. Appl. Anim. Behav. Sci. 2005;95:67–78. doi: 10.1016/j.applanim.2005.05.001. DOI

R Development Core Team. R Foundation for Statistical Computing v.3.6.1. [Computer program]. https://cran.r-project.org/bin/windows/base/old/3.6.1/ (2019).

Bates, D., Maechler, M., Bolker, B., Walker, S., Christensen, R. H. B., Singmann, H., Dai, B., Scheipl, F. & Grothendieck, G. lme4: Linear mixed-effects models using S4 classes [R package]. http://CRAN.R-project.org/package=lme4 (2011).

Mundry R, Sommer C. Discriminant function analysis with nonindependent data: consequences and an alternative. Anim. Behav. 2007;74:965–976. doi: 10.1016/j.anbehav.2006.12.028. DOI

Venables R, Ripley BD. Modern applied statistics with S-PLUS. Springer; 2013.

Ruff ZJ, Lesmeister DB, Duchac LS, Padmaraju BK, Sullivan CM. Automated identification of avian vocalizations with deep convolutional neural networks. Remote Sens. Ecol. Conserv. 2020;6:79–92. doi: 10.1002/rse2.125. DOI

Thomas, M., Martin, B., Kowarski, K., Gaudet, B. & Matwin, S. Marine mammal species classification using convolutional neural networks and a novel acoustic representation. in Joint European Conference on Machine Learning and Knowledge Discovery in Databases 290–305 (Springer, New York, 2019).

Anders F, Hlawitschka M, Fuchs M. Automatic classification of infant vocalization sequences with convolutional neural networks. Speech Commun. 2020;119:36–45. doi: 10.1016/j.specom.2020.03.003. DOI

He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition 770–778 (2016).