{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T17:49:00Z","timestamp":1777052940687,"version":"3.51.4"},"reference-count":25,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T00:00:00Z","timestamp":1776988800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Vet. Sci."],"abstract":"<jats:p>Respiratory diseases are common on poultry farms during spring and autumn. Due to the high density of the farm environment, an epidemic can spread very quickly and cause large-scale biological infections. Therefore, developing software capable of monitoring or providing early warnings of respiratory disease in chickens is very important because it helps prevent the spread of diseases and enhances the health of the chickens. This study proposes an acoustic detection system for chicken coughing (ASCT-CC) designed for real-world poultry farming environments. This system is based on an improved audio spectrogram transformer (AST) architecture, using a hybrid convolutional-transformer backbone network that replaces the global attention mechanism with local multi-head attention. This architecture effectively improves the model\u2019s ability to capture crucial local acoustic information and increases its robustness against noise at a lower computation cost. Besides, the study constructs a two-branch co-learning structure, adopts focal loss as an auxiliary strategy to reduce sample bias, and combines these with the connectionist temporal classification (CTC) decoder to accurately identify and temporally localize the cough event. To meet practical application requirements, the system is deployed with low latency on edge computing devices using TensorRT acceleration and INT8 quantization technology. Experiments demonstrated that our model achieves an mAP of 92.86% during training and reaches an identification rate of 92.11% on the independent test set, with an inference time of only around 200\u202fms. This system provides 24\u202fh real-time monitoring and multi-level early warning capabilities, offering effective technical support for the early detection and intelligent control of respiratory diseases in poultry.<\/jats:p>","DOI":"10.3389\/fvets.2026.1810310","type":"journal-article","created":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T17:28:27Z","timestamp":1777051707000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Automatic chick cough detection system based on improved audio spectrogram convolutional transformer neural network"],"prefix":"10.3389","volume":"13","author":[{"given":"Bowen","family":"Cai","sequence":"first","affiliation":[{"name":"School of Environmental, Tsinghua University","place":["Beijing, China"]},{"name":"Key Laboratory of Digital and Intelligent Technology Integration for Healthy Poultry Farming, Ministry of Agriculture and Rural Affairs","place":["Nanjing, Jiangsu, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Zhou","sequence":"additional","affiliation":[{"name":"Key Laboratory of Digital and Intelligent Technology Integration for Healthy Poultry Farming, Ministry of Agriculture and Rural Affairs","place":["Nanjing, Jiangsu, China"]},{"name":"Shanghai Xiashu Intelligent Technology","place":["Shanghai, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangshuai","family":"Kong","sequence":"additional","affiliation":[{"name":"Shanghai Xiashu Intelligent Technology","place":["Shanghai, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengsi","family":"Zhai","sequence":"additional","affiliation":[{"name":"Key Laboratory of Digital and Intelligent Technology Integration for Healthy Poultry Farming, Ministry of Agriculture and Rural Affairs","place":["Nanjing, Jiangsu, China"]},{"name":"Shanghai Xiashu Intelligent Technology","place":["Shanghai, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,4,24]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"1585","DOI":"10.1071\/an18281","article-title":"A review of the financial impact of production diseases in poultry production systems","volume":"59","author":"Jones","year":"2019","journal-title":"Anim Prod Sci"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"45","DOI":"10.3390\/vetsci12111059","article-title":"The rising threat of antibiotic resistance in poultry: veterinary and one health perspectives","volume":"12","author":"Sana","year":"2025","journal-title":"Vet Sci"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"5601","DOI":"10.3390\/app12115601","article-title":"Research progress in the early warning of chicken diseases by monitoring clinical symptoms","volume":"12","author":"He","year":"2022","journal-title":"Appl Sci"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/j.compag.2013.11.012","article-title":"A novel method to automatically measure the feed intake of broiler chickens by sound technology","volume":"101","author":"Aydin","year":"2014","journal-title":"Comput Electron Agric"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"100367","DOI":"10.1016\/j.sbsr.2020.100367","article-title":"The role of sensors, big data and machine learning in modern animal farming","volume":"29","author":"Neethirajan","year":"2020","journal-title":"Sens Bio-Sens Res"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"e958","DOI":"10.7717\/peerj-cs.958","article-title":"A systematic review on cough sound analysis for COVID-19 diagnosis and screening: is my cough sound COVID-19?","volume":"8","author":"Santosh","year":"2022","journal-title":"PeerJ Comput"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"20190225","DOI":"10.1098\/rsif.2019.0225","article-title":"Automated bioacoustics: methods in ecology and conservation and their potential for animal welfare monitoring","volume":"16","author":"Mcloughlin","year":"2019","journal-title":"J R Soc Interface"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"1791","DOI":"10.21437\/interspeech.2021-698","article-title":"AST: audio spectrogram transformer","author":"Gong","year":"2021","journal-title":"arXiv"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1006\/JAER.2001.0719","article-title":"Recognition system for pig cough based on probabilistic neural networks","volume":"80","author":"Chedad","year":"2001","journal-title":"J Agric Eng Res"},{"key":"ref10","first-page":"1132","author":"Carroll","year":"2014"},{"key":"ref11","first-page":"1136","author":"Whitaker","year":"2014"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"105688","DOI":"10.1016\/j.compag.2020.105688","article-title":"Detection of avian influenza-infected chickens based on a chicken sound convolutional neural network","volume":"178","author":"Cuan","year":"2020","journal-title":"Comput Electron Agric"},{"key":"ref13","article-title":"SmartEars: an intelligent method for monitoring poultry respiratory illnesses based on audio signals (version 1) [data set]","author":"Huang","year":"2024","journal-title":"Mendeley Data"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"109468","DOI":"10.1016\/j.compag.2025.111241","article-title":"SmartEars: a practical framework for poultry respiratory monitoring via spectrogram-based audio classification and AI-assisted labeling","volume":"226","author":"Huang","year":"2025","journal-title":"Comput Electron Agric"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"975","DOI":"10.7685\/jnau.202208040","article-title":"Detection method for whole-life cycle cough of white-feathered broiler based on vocalization characteristics and deep learning","volume":"46","author":"Yuan","year":"2023","journal-title":"J Nanjing Agric Univ"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"110541","DOI":"10.1016\/j.compag.2025.110541","article-title":"Cough sound recognition in poultry using portable microphones for precision medication guidance","volume":"237","author":"Zhou","year":"2025","journal-title":"Comput Electron Agric"},{"key":"ref17","first-page":"172","author":"Bhandekar","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"e0316920","DOI":"10.1371\/journal.pone.0316920","article-title":"Edge intelligence for poultry welfare: utilizing tiny machine learning neural network processors for vocalization analysis","volume":"20","author":"Srinivasagan","year":"2025","journal-title":"PLoS One"},{"key":"ref19","first-page":"7132","author":"Hu","year":"2018"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1007\/978-3-642-24797-2_7","volume-title":"Supervised Sequence Labelling with Recurrent Neural Networks","author":"Graves","year":"2012"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"101056","DOI":"10.1016\/j.atech.2024.101056","article-title":"Decoding vocal indicators of stress in laying hens: a CNN-MFCC deep learning framework","volume":"11","author":"Neethirajan","year":"2025","journal-title":"Smart Agric Technol"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"105234","DOI":"10.1016\/j.dsp.2025.105234","article-title":"A hybrid CNN-LSTM model for environmental sound classification: leveraging feature engineering and transfer learning","volume":"163","author":"Akter","year":"2025","journal-title":"Digit Signal Process"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1016\/j.aiia.2025.11.002","article-title":"End-to-end detection of cough and snore based on ResNet18-TF for breeder laying hens: a field study","volume":"16","author":"Ma","year":"2025","journal-title":"Artif Intell Agric"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2412.16182","article-title":"Decoding poultry vocalizations--natural language processing and transformer models for semantic and emotional analysis","author":"Manikandan","year":"2024","journal-title":"arXiv"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"111241","DOI":"10.1016\/j.compag.2025.111241","article-title":"SmartEars: a practical framework for poultry respiratory monitoring via spectrogram-based audio classification and AI-assisted labeling","volume":"241","author":"Qiao","year":"2026","journal-title":"Comput Electron Agric"}],"container-title":["Frontiers in Veterinary Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fvets.2026.1810310\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T17:28:30Z","timestamp":1777051710000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fvets.2026.1810310\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,24]]},"references-count":25,"alternative-id":["10.3389\/fvets.2026.1810310"],"URL":"https:\/\/doi.org\/10.3389\/fvets.2026.1810310","relation":{},"ISSN":["2297-1769"],"issn-type":[{"value":"2297-1769","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,24]]},"article-number":"1810310"}}