{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T17:32:53Z","timestamp":1768584773671,"version":"3.49.0"},"reference-count":28,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T00:00:00Z","timestamp":1768348800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Animals"],"abstract":"<jats:p>Respiratory diseases pose a significant threat to intensive pig farming, and cough recognition serves as a key indicator for early intervention. However, its practical application is constrained by the scarcity of labeled samples and the complex acoustic conditions of farm environments. To address these challenges, this study proposes a lightweight pig cough recognition method based on a pre-trained model. By freezing the backbone of a pre-trained audio neural network and fine-tuning only the classifier, our approach achieves effective knowledge transfer and domain adaptation with very limited data. We further enhance the model\u2019s ability to capture temporal\u2013spectral features of coughs through a time\u2013frequency dual-stream module. On a dataset consisting of 107 cough events and 590 environmental noise clips, the proposed method achieved an accuracy of 94.59% and an F1-score of 92.86%, significantly outperforming several traditional machine learning and deep learning baseline models. Ablation studies validated the effectiveness of each component, with the model attaining a mean accuracy of 96.99% in cross-validation and demonstrating good calibration. The results indicate that our framework can achieve high-accuracy and well-generalized pig cough recognition under small-sample conditions. The main contribution of this work lies in proposing a lightweight fine-tuning paradigm for small-sample audio recognition in agricultural settings, offering a reliable technical solution for early warning of respiratory diseases on farms. It also highlights the potential of transfer learning in resource-limited scenarios.<\/jats:p>","DOI":"10.3390\/ani16020253","type":"journal-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T15:12:04Z","timestamp":1768403524000},"page":"253","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Lightweight Fine-Tuning for Pig Cough Detection"],"prefix":"10.3390","volume":"16","author":[{"given":"Xu","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Agricultural Structure and Bioenvironmental Engineering, College of Water Resources and Civil Engineering, China Agricultural University, Beijing 100083, China"},{"name":"Beijing Engineering Research Center of Precision Measurement Technology and Instruments, Beijing University of Technology, Beijing 100124, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5368-4969","authenticated-orcid":false,"given":"Baoming","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Agricultural Structure and Bioenvironmental Engineering, College of Water Resources and Civil Engineering, China Agricultural University, Beijing 100083, China"},{"name":"Key Laboratory of Agricultural Engineering in Structure and Environment, Ministry of Agriculture and Rural Affairs, Beijing 100083, China"},{"name":"Beijing Engineering Research Center for Animal Health Environment, Beijing 100083, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoliu","family":"Xue","sequence":"additional","affiliation":[{"name":"Department of Agricultural Structure and Bioenvironmental Engineering, College of Water Resources and Civil Engineering, China Agricultural University, Beijing 100083, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"167","DOI":"10.13031\/2013.2532","article-title":"An intelligent alarm for early detection of swine epidemics based on neural networks","volume":"44","author":"Moshou","year":"2001","journal-title":"Trans. ASABE"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1136\/adc.58.4.319-a","article-title":"Pathological cry, stridor, and cough in infants","volume":"58","author":"Davis","year":"1983","journal-title":"Arch. Dis. Child."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1016\/j.compag.2008.07.003","article-title":"Cough sound analysis to identify respiratory infection in pigs","volume":"64","author":"Ferrari","year":"2008","journal-title":"Comput. Electron. Agric."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1364","DOI":"10.1016\/S0140-6736(08)60595-4","article-title":"Prevalence, pathogenesis, and causes of chronic cough","volume":"371","author":"Chung","year":"2008","journal-title":"Lancet"},{"key":"ref_5","first-page":"174","article-title":"Pig continuous cough recognition based on continuous speech recognition technology","volume":"35","author":"Li","year":"2019","journal-title":"Trans. Chin. Soc. Agric. Eng."},{"key":"ref_6","unstructured":"Zhang, S., Tian, J., Banerjee, A., and Li, J. (2019, January 12\u201317). Automatic recognition of porcine abnormalities based on a sound detection and recognition system. Proceedings of the 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK."},{"key":"ref_7","first-page":"195","article-title":"Pig sound classification based on deep neural network","volume":"36","author":"Cang","year":"2020","journal-title":"Trans. Chin. Soc. Agric. Eng."},{"key":"ref_8","unstructured":"Tu, D. (2020). Research on Pig Cough Sound Recognition Method Based on Audio Technology. [Ph.D. Thesis, Northeast Agricultural University]."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1016\/j.compag.2019.03.001","article-title":"Cough sound analysis to assess air quality in commercial weaner barns","volume":"160","author":"Wang","year":"2019","journal-title":"Comput. Electron. Agric."},{"key":"ref_10","first-page":"237","article-title":"Probabilistic analysis of coughs in pigs to diagnose respiratory infections","volume":"61","author":"Giesert","year":"2011","journal-title":"Comput. Electron. Agric."},{"key":"ref_11","first-page":"97","article-title":"Automatic recognition technology of pig status based on Hidden Markov Model","volume":"2016","author":"Zhang","year":"2016","journal-title":"Heilongjiang Anim. Sci. Vet. Med."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2880","DOI":"10.1109\/TASLP.2020.3030497","article-title":"PANNs: Large-scale pre-trained audio neural networks for audio pattern recognition","volume":"28","author":"Kong","year":"2020","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"ref_13","unstructured":"Liu, Z.Y., He, X.Y., Sang, J., Li, Y.T., Wu, Z.Q., and Lu, Z.M. (2015, January 7\u20139). Research on the recognition of pig coughs based on Hidden Markov Model. Proceedings of the Academic Symposium of Information Technology Branch of Chinese Society of Animal Science and Veterinary Medicine, Beijing, China."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"475","DOI":"10.1016\/S0378-4754(01)00316-0","article-title":"Neural recognition system for swine cough","volume":"56","author":"Moshou","year":"2001","journal-title":"Math. Comput. Simul."},{"key":"ref_15","first-page":"179","article-title":"Recognition of pig coughs based on deep belief network","volume":"49","author":"Li","year":"2018","journal-title":"Trans. Chin. Soc. Agric. Mach."},{"key":"ref_16","unstructured":"Zhao, J. (2019). Research on the Recognition of Pig Coughs Based on Deep Learning. [Master\u2019s Thesis, Huazhong Agricultural University]."},{"key":"ref_17","first-page":"148","article-title":"Recognition of pig coughs based on BP neural network","volume":"43","author":"Sun","year":"2022","journal-title":"Trans. Chin. Soc. Agric. Mach."},{"key":"ref_18","unstructured":"Ma, D.H. (2021). Research on the Recognition Method of Pig Coughs Based on Deep Learning. [Master\u2019s Thesis, China Agricultural University]."},{"key":"ref_19","first-page":"257","article-title":"Recognition method of pig coughs based on deep neural network","volume":"53","author":"Shen","year":"2022","journal-title":"Trans. Chin. Soc. Agric. Mach."},{"key":"ref_20","unstructured":"Song, H. (2023). Research on Pig Cough Sound Recognition Model Based on Mel-Frequency Cepstral Coefficients and Deep Learning. [Ph.D. Thesis, Heilongjiang Bayi Agricultural University]."},{"key":"ref_21","unstructured":"Wang, Q. (2018). Research on Multi-Objective Learning and Fusion Based Speech Enhancement Using Deep Neural Networks. [Ph.D. Thesis, University of Science and Technology of China]."},{"key":"ref_22","first-page":"669","article-title":"Single-channel speech enhancement method based on multi-dimensional attention mechanism","volume":"59","author":"Yao","year":"2023","journal-title":"J. Nanjing Univ. (Nat. Sci.)"},{"key":"ref_23","first-page":"223","article-title":"Research Progress on Audio Information Technology in the Field of Agriculture","volume":"56","author":"Yu","year":"2025","journal-title":"Trans. Chin. Soc. Agric. Mach."},{"key":"ref_24","unstructured":"Tian, L.D. (2023). Research and Application of Few-Shot Learning in Audio Event Classification. [Ph.D. Thesis, University of Electronic Science and Technology of China]."},{"key":"ref_25","first-page":"1893","article-title":"Improving voice recognition in Iraqi dialect using deep CNN-LSTM architecture: A comprehensive deep learning approach","volume":"12","author":"Ismael","year":"2025","journal-title":"Math. Model. Eng. Probl."},{"key":"ref_26","unstructured":"Schmidt, L., Santurkar, S., Tsipras, D., Talwar, K., and Madry, A. (2018). Adversarially robust generalization requires more data. Neural Inf. Process. Syst. (NIPS), 31."},{"key":"ref_27","first-page":"105","article-title":"Research on the recognition of meat breed chicken alarm sounds based on deep learning model PANNS-CNN","volume":"45","author":"Teng","year":"2023","journal-title":"Chin. Poult."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Lagua, E.B., Mun, H.-S., Ampode, K.M.B., Chem, V., Kim, Y.-H., and Yang, C.-J. (2023). Artificial intelligence for automatic monitoring of respiratory health conditions in smart swine farming. Animals, 13.","DOI":"10.3390\/ani13111860"}],"container-title":["Animals"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2076-2615\/16\/2\/253\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T05:28:54Z","timestamp":1768541334000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2076-2615\/16\/2\/253"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,14]]},"references-count":28,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["ani16020253"],"URL":"https:\/\/doi.org\/10.3390\/ani16020253","relation":{},"ISSN":["2076-2615"],"issn-type":[{"value":"2076-2615","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,14]]}}}