{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T15:41:08Z","timestamp":1783698068708,"version":"3.55.0"},"reference-count":43,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2024,2,16]],"date-time":"2024-02-16T00:00:00Z","timestamp":1708041600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Major Scientific and Technological Projects in Anhui Province, China","award":["2023n06020051"],"award-info":[{"award-number":["2023n06020051"]}]},{"name":"Major Scientific and Technological Projects in Anhui Province, China","award":["202103b06020013"],"award-info":[{"award-number":["202103b06020013"]}]},{"name":"Major Scientific and Technological Projects in Anhui Province, China","award":["2022lhpysfjd023"],"award-info":[{"award-number":["2022lhpysfjd023"]}]},{"name":"Major Scientific and Technological Projects in Anhui Province, China","award":["2022cxcyjs010"],"award-info":[{"award-number":["2022cxcyjs010"]}]},{"name":"Anhui Province Department of Education","award":["2023n06020051"],"award-info":[{"award-number":["2023n06020051"]}]},{"name":"Anhui Province Department of Education","award":["202103b06020013"],"award-info":[{"award-number":["202103b06020013"]}]},{"name":"Anhui Province Department of Education","award":["2022lhpysfjd023"],"award-info":[{"award-number":["2022lhpysfjd023"]}]},{"name":"Anhui Province Department of Education","award":["2022cxcyjs010"],"award-info":[{"award-number":["2022cxcyjs010"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>In order to solve the problem of low recognition accuracy of traditional pig sound recognition methods, deep neural network (DNN) and Hidden Markov Model (HMM) theory were used as the basis of pig sound signal recognition in this study. In this study, the sounds made by 10 landrace pigs during eating, estrus, howling, humming and panting were collected and preprocessed by Kalman filtering and an improved endpoint detection algorithm based on empirical mode decomposition-Teiger energy operator (EMD-TEO) cepstral distance. The extracted 39-dimensional mel-frequency cepstral coefficients (MFCCs) were then used as a dataset for network learning and recognition to build a DNN- and HMM-based sound recognition model for pig states. The results show that in the pig sound dataset, the recognition accuracy of DNN-HMM reaches 83%, which is 22% and 17% higher than that of the baseline models HMM and GMM-HMM, and possesses a better recognition effect. In a sub-dataset of the publicly available dataset AudioSet, DNN-HMM achieves a recognition accuracy of 79%, which is 8% and 4% higher than the classical models SVM and ResNet18, respectively, with better robustness.<\/jats:p>","DOI":"10.3390\/s24041269","type":"journal-article","created":{"date-parts":[[2024,2,19]],"date-time":"2024-02-19T03:18:38Z","timestamp":1708312718000},"page":"1269","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Research on Pig Sound Recognition Based on Deep Neural Network and Hidden Markov Models"],"prefix":"10.3390","volume":"24","author":[{"given":"Weihao","family":"Pan","sequence":"first","affiliation":[{"name":"School of Information and Artificial Intelligence, Anhui Agricultural University, Hefei 230036, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hualong","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei 230031, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaobo","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Information and Artificial Intelligence, Anhui Agricultural University, Hefei 230036, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Jiao","sequence":"additional","affiliation":[{"name":"School of Information and Artificial Intelligence, Anhui Agricultural University, Hefei 230036, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Information and Artificial Intelligence, Anhui Agricultural University, Hefei 230036, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Biosystems Engineering, University of Manitoba, Winnipeg, MB R3T 5V6, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,2,16]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Zha, W., Li, H., Wu, G., Zhang, L., Pan, W., Gu, L., Jiao, J., and Zhang, Q. (2023). Research on the recognition and tracking of group-housed pigs\u2019 posture based on edge computing. Sensors, 23.","DOI":"10.3390\/s23218952"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"107645","DOI":"10.1016\/j.compag.2023.107645","article-title":"An investigation of fusion strategies for boosting pig cough sound recognition","volume":"205","author":"Yin","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"ref_3","first-page":"104","article-title":"Endpoint detection of live pig audio signal based on improved emd-teo cepstrum distance","volume":"26","author":"Wu","year":"2021","journal-title":"J. China Agric. Univ."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Wu, X., Zhou, S.L., Chen, M.W., Zhao, Y.H., Wang, Y.F., Zhao, X.M., Li, D.Y., and Pu, H.B. (2022). Combined spectral and speech features for pig speech recognition. PLoS ONE, 17.","DOI":"10.1371\/journal.pone.0276778"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1016\/j.biosystemseng.2022.05.010","article-title":"Investigation of acoustic and visual features for pig cough classification","volume":"219","author":"Ji","year":"2022","journal-title":"Biosyst. Eng."},{"key":"ref_6","first-page":"148","article-title":"Recognition of pig coughing sound based on bp neural network","volume":"43","author":"Sun","year":"2022","journal-title":"J. Chin. Agric. Mech."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"12929","DOI":"10.3390\/s131012929","article-title":"Automatic detection and recognition of pig wasting diseases using sound data in audio surveillance systems","volume":"13","author":"Chung","year":"2013","journal-title":"Sensors"},{"key":"ref_8","unstructured":"Liu, Z., He, X., Sang, J., Li, Y., Wu, Z., and Lu, Z. (2015, January 7). Research on pig coughing sound recognition based on hidden markov model. Proceedings of the 10th Symposium of Information Technology Branch of Chinese Society of Animal Husbandry and Veterinary Medicine, Beijing, China."},{"key":"ref_9","first-page":"91","article-title":"Noise-robust porcine respiratory diseases classification using texture analysis and cnn","volume":"7","author":"Cho","year":"2018","journal-title":"KIPS Trans. Softw. Data Eng."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1016\/j.compag.2022.106994","article-title":"Fusion of acoustic and deep features for pig cough sound recognition","volume":"197","author":"Shen","year":"2022","journal-title":"Comput. Electron. Agric."},{"key":"ref_11","first-page":"4907","article-title":"Domestic pig sound classification based on transformercnn","volume":"53","author":"Liao","year":"2023","journal-title":"Appl. Intell."},{"key":"ref_12","first-page":"369","article-title":"Recognition of sick pig cough sounds based on convolutional neural network in field situations","volume":"8","author":"Yin","year":"2021","journal-title":"Inf. Process. Agric."},{"key":"ref_13","first-page":"573","article-title":"A new fusion feature based on convolutional neural network for pig cough recognition in field situations","volume":"8","author":"Shen","year":"2021","journal-title":"Inf. Process. Agric."},{"key":"ref_14","first-page":"119","article-title":"Recognition of pig cough sound based on vector quantization","volume":"36","author":"Gong","year":"2017","journal-title":"J. Huazhong Agric. Univ."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"101863","DOI":"10.1016\/j.ecoinf.2022.101863","article-title":"A lightweight cnn-based model for early warning in sow oestrus sound monitoring","volume":"72","author":"Wang","year":"2022","journal-title":"Ecol. Inform."},{"key":"ref_16","first-page":"805","article-title":"A study on classification of pig sounds based on supervised learning","volume":"70","author":"Min","year":"2021","journal-title":"J. Inst. Electr. Eng."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1016\/j.livsci.2019.103847","article-title":"Status quo analysis of noise levels in pig fattening units in germany","volume":"230","author":"Wegner","year":"2019","journal-title":"Livest. Sci."},{"key":"ref_18","first-page":"30","article-title":"Overview of speech enhancement algorithms","volume":"37","author":"Cao","year":"2020","journal-title":"J. Hebei Acad. Sci."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1016\/j.compeleceng.2007.10.007","article-title":"Noise reduction in biomedical speech signal processing based on time and frequency kalman filtering combined with spectral subtraction","volume":"34","author":"Joaquim","year":"2008","journal-title":"Comput. Electr. Eng."},{"key":"ref_20","unstructured":"Fu, W., Zhou, Y., Zhang, X., and Liu, N. (2023). Single-channel blind source separation algorithm based on parameter estimation and kalman filter. Syst. Eng. Electron., 1\u20139. Available online: https:\/\/kns.cnki.net\/kcms\/detail\/11.2422.TN.20231206.1112.002.html."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.apacoust.2019.107133","article-title":"An overview of speech endpoint detection algorithms","volume":"160","author":"Zhang","year":"2020","journal-title":"Appl. Acoust."},{"key":"ref_22","first-page":"85","article-title":"Multilevel emotion recognition of audio features based on multitask learning and attention mechanism","volume":"14","author":"Li","year":"2024","journal-title":"Intell. Comput. Appl."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1504\/IJBIC.2012.049884","article-title":"Enhancing robustness for speech recognition through bio-inspired auditory filter-bank","volume":"4","author":"Maganti","year":"2012","journal-title":"Int. J. Bio-Inspired Comput."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"11669","DOI":"10.1007\/s10586-017-1447-6","article-title":"Speech recognition system using enhanced mel frequency cepstral coefficient with windowing and framing method","volume":"22","author":"Lokesh","year":"2019","journal-title":"Cluster Comput."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1429","DOI":"10.1007\/s11831-020-09422-4","article-title":"A systematic review of hidden markov models and their applications","volume":"28","author":"Mor","year":"2021","journal-title":"Arch. Comput. Method Eng."},{"key":"ref_26","first-page":"22","article-title":"Survey of few shot learning of deep neural network","volume":"57","author":"Zhu","year":"2021","journal-title":"Comput. Eng. Appl."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Rascon, C. (2023). Characterization of deep learning-based speech-enhancement techniques in online audio processing applications. Sensors, 23.","DOI":"10.20944\/preprints202303.0158.v1"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"101158","DOI":"10.1016\/j.csl.2020.101158","article-title":"Advances in subword-based hmm-dnn speech recognition across languages","volume":"66","author":"Smit","year":"2021","journal-title":"Comput. Speech Lang."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Vetr\u00e1b, M., and Gosztolya, G. (2023). Using hybrid HMM\/DNN embedding extractor models in computational paralinguistic tasks. Sensors, 23.","DOI":"10.3390\/s23115208"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Zhang, M.C., Chen, X.M., and Li, W. (2021). A hybrid hidden markov model for pipeline leakage detection. Appl. Sci., 11.","DOI":"10.3390\/app11073138"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"15486","DOI":"10.3934\/math.2023790","article-title":"Note on fuzzifying probability density function and its properties","volume":"8","author":"Kim","year":"2023","journal-title":"AIMS Math."},{"key":"ref_32","first-page":"52","article-title":"Blind demodulation algorithm for short burst signals based on maximun likelihood rules","volume":"42","author":"Yan","year":"2016","journal-title":"Radio Commun. Technol."},{"key":"ref_33","unstructured":"Gilbert, D.F. (2012). A Comparative Analysis of Machine Learning Algorithms for Hidden Markov Models. [Master\u2019s Thesis, California State University]."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"9361","DOI":"10.1007\/s11071-023-08302-3","article-title":"Decomposition optimization method for switching models using em algorithm","volume":"111","author":"Chen","year":"2023","journal-title":"Nonlinear Dyn."},{"key":"ref_35","first-page":"18","article-title":"A recognition method for multi-reconnaissance data based on error back propagation algorithm","volume":"34","author":"Zhang","year":"2019","journal-title":"Electron. Inf. Warf. Technol."},{"key":"ref_36","first-page":"47","article-title":"Discussion on the basic models and application of deep learning","volume":"39","author":"Xu","year":"2020","journal-title":"J. Chang. Norm. Univ."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"15117","DOI":"10.1007\/s11042-018-6661-6","article-title":"Fruit category classification via an eight-layer convolutional neural network with parametric rectified linear unit and dropout technique","volume":"79","author":"Wang","year":"2020","journal-title":"Multimed. Tools Appl."},{"key":"ref_38","unstructured":"Zhao, J. (2020). Pig Cough Sounds Recognition Based on Deep Learning. [Master\u2019s Thesis, Huazhong Agricultural University]."},{"key":"ref_39","first-page":"186","article-title":"Dnn-hmm based acoustic model for continuous pig cough sound recognition","volume":"13","author":"Zhao","year":"2020","journal-title":"Int. J. Agric. Biol. Eng."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Jamin, A., and Humeau-Heurtier, A. (2020). (Multiscale) cross-entropy methods: A review. Entropy, 22.","DOI":"10.3390\/e22060644"},{"key":"ref_41","first-page":"69","article-title":"Support vector machine for acoustic scene classification algorith research based on multi-features fusion","volume":"40","author":"Zhao","year":"2020","journal-title":"Trans. Beijing Inst. Technol."},{"key":"ref_42","first-page":"21","article-title":"Fish behavior recognition based on mfcc and resnet","volume":"37","author":"Xu","year":"2022","journal-title":"J. Mar. Inf. Technol. Appl."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1791","DOI":"10.1109\/TASLP.2019.2930913","article-title":"Weakly labelled audioset tagging with attention neural networks","volume":"27","author":"Kong","year":"2019","journal-title":"IEEE-ACM Trans. Audio Speech Lang."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/4\/1269\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:00:58Z","timestamp":1760104858000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/4\/1269"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,16]]},"references-count":43,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2024,2]]}},"alternative-id":["s24041269"],"URL":"https:\/\/doi.org\/10.3390\/s24041269","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,16]]}}}