{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T05:31:05Z","timestamp":1785648665730,"version":"3.56.0"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T00:00:00Z","timestamp":1758844800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T00:00:00Z","timestamp":1758844800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.42277217"],"award-info":[{"award-number":["No.42277217"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No. 41877374"],"award-info":[{"award-number":["No. 41877374"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100012543","name":"Shanghai Science and Technology Development Foundation","doi-asserted-by":"publisher","award":["No. 21SQBS01900"],"award-info":[{"award-number":["No. 21SQBS01900"]}],"id":[{"id":"10.13039\/100012543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Wireless Com Network"],"DOI":"10.1186\/s13638-025-02483-8","type":"journal-article","created":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T10:07:55Z","timestamp":1758881275000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["YAMNet-based transfer learning for compact noise classification in urban and wireless systems"],"prefix":"10.1186","volume":"2025","author":[{"given":"LiFeng","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"QiNan","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"ShaoHua","family":"Mao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"JianKang","family":"Mu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"XuXia","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"WeiHua","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ping","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,26]]},"reference":[{"key":"2483_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.heares.2016.10.004","author":"CGL Prell","year":"2017","unstructured":"C.G.L. Prell, O.H. Clavier, Effects of noise on speech recognition: challenges for communication by service members. Hear. Res. (2017). https:\/\/doi.org\/10.1016\/j.heares.2016.10.004","journal-title":"Hear. Res."},{"key":"2483_CR2","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2014.33","author":"M Braverman","year":"2014","unstructured":"M. Braverman, K. Efremenko, List and unique coding for interactive communication in the presence of adversarial noise\/\/Foundations of computer science. IEEE (2014). https:\/\/doi.org\/10.1109\/FOCS.2014.33","journal-title":"IEEE"},{"key":"2483_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.optlastec.2022.108695","author":"K Klnarslan","year":"2023","unstructured":"K. Klnarslan, S.E. Karlik, Combined impact of SRS, FWM and ASE noise in UDWDM\/DWDM long-haul communication systems using EDFAs. Opt. Laser Technol. (2023). https:\/\/doi.org\/10.1016\/j.optlastec.2022.108695","journal-title":"Opt. Laser Technol."},{"key":"2483_CR4","doi-asserted-by":"crossref","unstructured":"K. J. Piczak. ESC: Dataset for environmental sound classification[C]\/\/Proceedings of the 23rd ACM international conference on Multimedia. 2015: 1015\u20131018.","DOI":"10.1145\/2733373.2806390"},{"key":"2483_CR5","doi-asserted-by":"crossref","unstructured":"B. Anam, N. G. Kumar. Environmental Sound Classification: A descriptive review of the literature. Intell. Syst. Appl., 2022, 16.","DOI":"10.1016\/j.iswa.2022.200115"},{"key":"2483_CR6","doi-asserted-by":"crossref","unstructured":"J. Wang, C. Lin, B. Chen, et al. Gabor-Based Nonuniform Scale-Frequency Map for Environmental Sound Classification in Home Automation. IEEE Trans. Automat. Sci. Eng., 2014, 11(2).","DOI":"10.1109\/TASE.2013.2285131"},{"key":"2483_CR7","doi-asserted-by":"crossref","unstructured":"A. Raman, A R L. An efficient code for environmental sound classification. The Journal of the Acoustical Society of America, 2009, 126(1).","DOI":"10.1121\/1.3139982"},{"key":"2483_CR8","doi-asserted-by":"crossref","unstructured":"Yang C, Gan X, Peng A, et al. ResNet based on multi-feature attention mechanism for sound classification in noisy environments. Sustainability, 2023, 15(14).","DOI":"10.3390\/su151410762"},{"key":"2483_CR9","doi-asserted-by":"crossref","unstructured":"R. M. Ahmed, I. T. Robin, A. A. Shafin. Automatic environmental sound recognition (AESR) using convolutional neural network. Int. J. Modern Educat. Comput. Sci. (IJMECS), 2020, 12(5).","DOI":"10.5815\/ijmecs.2020.05.04"},{"key":"2483_CR10","doi-asserted-by":"crossref","unstructured":"D. Fatih, D. A. Abdulsalam, S. Abdulkadir. A new deep CNN model for environmental Sound Classification. IEEE Access, 2020, 8.","DOI":"10.1109\/ACCESS.2020.2984903"},{"key":"2483_CR11","doi-asserted-by":"publisher","first-page":"132306","DOI":"10.1016\/j.physd.2019.132306","volume":"404","author":"A Sherstinsky","year":"2020","unstructured":"A. Sherstinsky, Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network[J]. Physica D 404, 132306 (2020)","journal-title":"Physica D"},{"key":"2483_CR12","doi-asserted-by":"crossref","unstructured":"D. Widhyanti, D. Juniati. Classification of baby cry sound using higuchi\u2019s fractal dimension with K-nearest neighbor and support vector machine. J. Phys.: Conf. Series, 2021, 1747(1).","DOI":"10.1088\/1742-6596\/1747\/1\/012014"},{"issue":"7","key":"2483_CR13","doi-asserted-by":"publisher","first-page":"2038","DOI":"10.1016\/j.patcog.2006.12.019","volume":"40","author":"ML Zhang","year":"2007","unstructured":"M.L. Zhang, Z.H. Zhou, ML-KNN: A lazy learning approach to multi-label learning. Pattern Recogn.attern Recogn. 40(7), 2038\u20132048 (2007)","journal-title":"Pattern Recogn.attern Recogn."},{"key":"2483_CR14","unstructured":"K. Yamauchi, M. Yamashita, S. Matsunaga, et al. An Examination of Constructive Method of HMM Considering the Segmentation of Respiratory Sound and Variety of Adventitious Sounds in Classification between Normal and Abnormal Respiratory Sounds. D - Abstracts of IEICE TRANSACTIONS on Information and Systems (Japanese Edition), 2013, J96-D (9)."},{"key":"2483_CR15","unstructured":"Y. C. Joo, S. K. Woo. Class determination based on Kullback-Leibler distance in heart sound classification. J. Acoust. Soc. Korea, 2008, 27(2E)."},{"key":"2483_CR16","doi-asserted-by":"crossref","unstructured":"T. Prasath, V. Ramachandran, S. Geetha, et al. HMM Based Cough Sound Scrutiny for Classification of Asthma and Pneumonia in Paediatry. International Journal of Recent Technology and Engineering (IJRTE), 2019, 8(2s3).","DOI":"10.35940\/ijrte.B1152.0782S319"},{"issue":"06","key":"2483_CR17","doi-asserted-by":"publisher","first-page":"29","DOI":"10.13465\/j.cnki.jvs.2014.06.005.(inChinese)","volume":"33","author":"W-Y Zhang","year":"2014","unstructured":"W.-Y. Zhang, X.-M. Guo, Application of improved GMM in classification and recognition of heart sound. J. Vib. Shock 33(06), 29\u201334 (2014). https:\/\/doi.org\/10.13465\/j.cnki.jvs.2014.06.005.(inChinese)","journal-title":"J. Vib. Shock"},{"key":"2483_CR18","unstructured":"M. Jugurta, I. Dan, B. Jer\u00f4me, et al. Sound event detection in remote health care - small learning datasets and over constrained Gaussian Mixture Models. Conference proceedings: Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Eng. Med. Biol. Soc. Annual Conference, 2010, 2010."},{"key":"2483_CR19","doi-asserted-by":"crossref","unstructured":"J. Timothy. O\u2019Shea and Johnathan Corgan. Convolutional Radio Modulation Recognition Networks. CoRR, 2016, abs\/1602.04105.","DOI":"10.1007\/978-3-319-44188-7_16"},{"key":"2483_CR20","doi-asserted-by":"publisher","first-page":"124528","DOI":"10.1016\/j.eswa.2024.124528","volume":"255","author":"S Malathi","year":"2024","unstructured":"S. Malathi, S. Razool Begum, Enhancing trustworthiness among iot network nodes with ensemble deep learning-based cyber attack detection. Expert Syst. Appl. 255, 124528\u2013124528 (2024)","journal-title":"Expert Syst. Appl."},{"key":"2483_CR21","doi-asserted-by":"crossref","unstructured":"C N. Evaluation of convolutional neural networks for visual recognition.[J]. IEEE transactions on neural networks,1998,9(4).","DOI":"10.1109\/72.701181"},{"key":"2483_CR22","doi-asserted-by":"crossref","unstructured":"Gong Y, Chung Y A, Glass J. Ast: Audio spectrogram transformer[J]. arXiv preprint arXiv:2104.01778, 2021.","DOI":"10.21437\/Interspeech.2021-698"},{"key":"2483_CR23","unstructured":"S. Chen, Y. Wu, C. Wang, et al. Beats: Audio pre-training with acoustic tokenizers. arXiv preprint arXiv:2212.09058, 2022."},{"key":"2483_CR24","doi-asserted-by":"crossref","unstructured":"H. Sakai, S. Sato, Y. Ando. A new system of environmental noise identification and subjective evaluation. J. Acoustical Soc. Am., 1999, 106(4).","DOI":"10.1121\/1.427511"},{"key":"2483_CR25","doi-asserted-by":"crossref","unstructured":"D. Giannoulis, E. Benetos, D. Stowell, et al. Detection and classification of acoustic scenes and events: an IEEE AASP challenge[C]\/\/2013 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics. IEEE, 2013: 1\u20134.","DOI":"10.1109\/WASPAA.2013.6701819"},{"key":"2483_CR26","doi-asserted-by":"crossref","unstructured":"Z. Dongping, Z. Ziyin, X. Yuejian, et al. An Automatic Classification System for Environmental Sound in Smart Cities.[J]. Sensors (Basel, Switzerland), 2023, 23(15).","DOI":"10.3390\/s23156823"},{"key":"2483_CR27","doi-asserted-by":"crossref","unstructured":"Y. Wei, X. Yancai, S. Haikuo, et al. An effective data enhancement method of deep learning for small weld data defect identification [J]. Measurement, 2023, 206.","DOI":"10.1016\/j.measurement.2022.112245"},{"key":"2483_CR28","doi-asserted-by":"crossref","unstructured":"H. Gupta, D. Gupta. LPC and LPCC method of feature extraction in Speech Recognition System[C]\/\/2016 6th international conference-cloud system and big data engineering (confluence). IEEE, 2016: 498\u2013502.","DOI":"10.1109\/CONFLUENCE.2016.7508171"},{"key":"2483_CR29","doi-asserted-by":"crossref","unstructured":"K. K. Mohammed, E. I. Abd El-Latif, N. E. El-Sayad, et al. Radio frequency fingerprint-based drone identification and classification using Mel spectrograms and pre-trained YAMNet neural[J]. Internet of Things, 2023, 23.","DOI":"10.1016\/j.iot.2023.100879"},{"key":"2483_CR30","doi-asserted-by":"crossref","unstructured":"P. Sanjana, W. Kiran. Gear fault detection using noise analysis and machine learning algorithm with YAMNet pretrained network[J]. Materials Today: Proceedings, 2023, 72(P3).","DOI":"10.1016\/j.matpr.2022.09.307"},{"key":"2483_CR31","doi-asserted-by":"crossref","unstructured":"M. Arnab, P. Akanksha, S. Goutam. Transfer learning based heart valve disease classification from Phonocardiogram signal[J]. Biomedical Signal Processing and Control, 2023, 85.","DOI":"10.1016\/j.bspc.2023.104805"},{"key":"2483_CR32","doi-asserted-by":"crossref","unstructured":"K. Adem, S. Kili\u00e7arslan, O. C\u00f6mert. Classification and diagnosis of cervical cancer with softmax classification with stacked autoencoder. Expert. Syst. Appl. 2019, 115.","DOI":"10.1016\/j.eswa.2018.08.050"},{"issue":"9","key":"2483_CR33","doi-asserted-by":"publisher","first-page":"454","DOI":"10.3390\/e19090454","volume":"19","author":"JH Lee","year":"2017","unstructured":"J.H. Lee et al., Robust automatic modulation classification technique for fading channels via deep neural network. Entropy 19(9), 454\u2013454 (2017)","journal-title":"Entropy"},{"key":"2483_CR34","doi-asserted-by":"crossref","unstructured":"S. Chenhao, H. Xichuan. Improved Image Style Transfer Based on VGG-16 Convolutional Neural Network Model. J. Phys.: Conf. Series, 2023, 2424(1).","DOI":"10.1088\/1742-6596\/2424\/1\/012021"},{"key":"2483_CR35","doi-asserted-by":"crossref","unstructured":"C. Babu, M. Moorthi. EEG-dependent automatic speech recognition using deep residual encoder based VGG net CNN. Computer Speech & Language, 2023, 79.","DOI":"10.1016\/j.csl.2022.101477"},{"key":"2483_CR36","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, et al. Deep residual learning for image recognition[C]\/\/Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"2483_CR37","unstructured":"W. D. 0013, F. T. Zheng. Transfer Learning for Speech and Language Processing. CoRR,2015, abs\/1511.06066."},{"issue":"11","key":"2483_CR38","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"Y. LeCun, L. Bottou, Y. Bengio et al., Gradient-based learning applied to document recognition[J]. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"2483_CR39","doi-asserted-by":"crossref","unstructured":"T. Zoughi, M. M. Homayounpour. DBMiP: A Pre-training method for information propagation over deep networks [J]. Comput. Speech Language, 2018, 55.","DOI":"10.1016\/j.csl.2018.10.001"},{"key":"2483_CR40","doi-asserted-by":"crossref","unstructured":"D. M. Agrawal, H. B Sailor, M. H. Soni, et al. Novel TEO-based Gammatone features for environmental sound classification[C]\/\/2017 25th European Signal Processing Conference (EUSIPCO). IEEE, 2017: 1809\u20131813.","DOI":"10.23919\/EUSIPCO.2017.8081521"},{"key":"2483_CR41","doi-asserted-by":"crossref","unstructured":"E. Cakir, T. Heittola, H. Huttunen, et al. Polyphonic sound event detection using multi label deep neural networks[C]\/\/2015 international joint conference on neural networks (IJCNN). IEEE, 2015: 1\u20137.","DOI":"10.1109\/IJCNN.2015.7280624"},{"issue":"10","key":"2483_CR42","doi-asserted-by":"publisher","first-page":"1533","DOI":"10.1109\/TASLP.2014.2339736","volume":"22","author":"O Abdel-Hamid","year":"2014","unstructured":"O. Abdel-Hamid, A. Mohamed, H. Jiang et al., Convolutional neural networks for speech recognition[J]. IEEE\/ACM Trans. Audio, Speech, Language Process. 22(10), 1533\u20131545 (2014)","journal-title":"IEEE\/ACM Trans. Audio, Speech, Language Process."},{"key":"2483_CR43","doi-asserted-by":"crossref","unstructured":"Z. Zhang, S. Xu, S. Cao, et al. Deep convolutional neural network with mixup for environmental sound classification[C]\/\/Chinese conference on pattern recognition and computer vision (prcv). Springer, Cham, 2018: 356\u2013367.","DOI":"10.1007\/978-3-030-03335-4_31"},{"key":"2483_CR44","doi-asserted-by":"crossref","unstructured":"K. J. Piczak. Environmental sound classification with convolutional neural networks[C]\/\/2015 IEEE 25th international workshop on machine learning for signal processing (MLSP). IEEE, 2015: 1\u20136.","DOI":"10.1109\/MLSP.2015.7324337"},{"issue":"11","key":"2483_CR45","doi-asserted-by":"publisher","first-page":"2096","DOI":"10.1109\/TASLP.2016.2592698","volume":"24","author":"S Sigtia","year":"2016","unstructured":"S. Sigtia, A.M. Stark, S. Krstulovi\u0107 et al., Automatic environmental sound recognition: Performance versus computational cost[J]. IEEE\/ACM Trans. Audio, Speech, Language Process. 24(11), 2096\u20132107 (2016)","journal-title":"IEEE\/ACM Trans. Audio, Speech, Language Process."},{"key":"2483_CR46","doi-asserted-by":"crossref","unstructured":"J. F. Gemmeke, D. P. W. Ellis, D. Freedman, et al. Audio set: an ontology and human-labeled dataset for audio events[C]\/\/2017 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, 2017: 776\u2013780.","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"2483_CR47","doi-asserted-by":"crossref","unstructured":"J. Li, W. Dai, F. Metze, et al. A comparison of deep learning methods for environmental sound detection[C]\/\/2017 IEEE International conference on acoustics, speech and signal processing (ICASSP). IEEE, 2017: 126\u2013130.","DOI":"10.1109\/ICASSP.2017.7952131"},{"key":"2483_CR48","doi-asserted-by":"crossref","unstructured":"X. Zhang, Y. Zou, W. Shi. Dilated convolution neural network with Leaky ReLU for environmental sound classification[C]\/\/2017 22nd international conference on digital signal processing (DSP). IEEE, 2017: 1\u20135.","DOI":"10.1109\/ICDSP.2017.8096153"},{"issue":"2","key":"2483_CR49","first-page":"159","volume":"32","author":"C-N Zhang","year":"2015","unstructured":"C.-N. Zhang, Restricted Boltzmann machines. Chin. J. Eng. Math. 32(2), 159\u2013173 (2015). (in Chinese)","journal-title":"Chin. J. Eng. Math."},{"key":"2483_CR50","unstructured":"Z. L. Chang, L. Zhang. Research on Optimization Algorithm of Convolution Neural Network in Speech Recognition. J. Harbin Univ. Sci. Technol. 2016, 21(3).(in Chinese)"},{"key":"2483_CR51","unstructured":"UrbanSound8K. (2014). Public datasets for urban environmental sound classification research. Retrieved from https:\/\/zenodo.org\/record\/1203745\/files\/UrbanSound8K.tar.gz"},{"key":"2483_CR52","doi-asserted-by":"publisher","unstructured":"K. J. Piczak ESC: Dataset for Environmental Sound Classification. ieee transactions on wireless communications, 2015. https:\/\/doi.org\/10.1145\/2733373.2806390.","DOI":"10.1145\/2733373.2806390"}],"container-title":["EURASIP Journal on Wireless Communications and Networking"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13638-025-02483-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13638-025-02483-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13638-025-02483-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T22:03:23Z","timestamp":1758924203000},"score":1,"resource":{"primary":{"URL":"https:\/\/jwcn-eurasipjournals.springeropen.com\/articles\/10.1186\/s13638-025-02483-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,26]]},"references-count":52,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["2483"],"URL":"https:\/\/doi.org\/10.1186\/s13638-025-02483-8","relation":{},"ISSN":["1687-1499"],"issn-type":[{"value":"1687-1499","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,26]]},"assertion":[{"value":"15 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 June 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 September 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"74"}}