{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T10:35:25Z","timestamp":1789036525011,"version":"build-2803163510"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2025,6,14]],"date-time":"2025-06-14T00:00:00Z","timestamp":1749859200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,6,14]],"date-time":"2025-06-14T00:00:00Z","timestamp":1749859200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.62201163"],"award-info":[{"award-number":["No.62201163"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangxi Technology Base and Talent Special","award":["No.GuiKe AD20159018"],"award-info":[{"award-number":["No.GuiKe AD20159018"]}]},{"DOI":"10.13039\/100012547","name":"Natural Science Foundation of Guangxi Zhuang Autonomous Region","doi-asserted-by":"publisher","award":["No.2020GXNSFAA159004"],"award-info":[{"award-number":["No.2020GXNSFAA159004"]}],"id":[{"id":"10.13039\/100012547","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Innovation Project of GUET Graduate Education","award":["No.2024YCXS023"],"award-info":[{"award-number":["No.2024YCXS023"]}]},{"name":"Innovation Project of Guang xi Graduate Education","award":["YCSW2023296"],"award-info":[{"award-number":["YCSW2023296"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Circuits Syst Signal Process"],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1007\/s00034-025-03195-6","type":"journal-article","created":{"date-parts":[[2025,6,14]],"date-time":"2025-06-14T04:49:34Z","timestamp":1749876574000},"page":"8853-8875","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Optimized Network Combining Depthwise Separable Convolutional with Multi-scale Dilated Convolution Used for Polyphonic Sound Event Detection"],"prefix":"10.1007","volume":"44","author":[{"given":"Liyan","family":"Luo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3274-8599","authenticated-orcid":false,"given":"Fukun","family":"Mi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2892-8606","authenticated-orcid":false,"given":"Zhenghong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,6,14]]},"reference":[{"key":"3195_CR1","unstructured":"S. Adavanne, T. Virtanen, A report on sound event detection with different binaural features. arXiv preprint arXiv:1710.02997. (2017)"},{"key":"3195_CR2","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1186\/s40537-024-01011-7","volume":"11","author":"A Ameen","year":"2024","unstructured":"A. Ameen, I.E. Fattoh, T. Abd El-Hafeez, K. Ahmed, Advances in Ecg and pcg-based cardiovascular disease classification: a review of deep learning and machine learning methods. J. Big Data. 11, 159 (2024). https:\/\/doi.org\/10.1186\/s40537-024-01011-7","journal-title":"J. Big Data"},{"key":"3195_CR3","doi-asserted-by":"crossref","unstructured":"E. Cakir, T. Heittola, H. Huttunen, T. Virtanen, Polyphonic sound event detection using multi label deep neural networks. In: 2015 International Joint Conference on Neural Networks (IJCNN). IEEE, New York (2015)","DOI":"10.1109\/IJCNN.2015.7280624"},{"key":"3195_CR4","doi-asserted-by":"publisher","first-page":"1291","DOI":"10.1109\/TASLP.2017.2690575","volume":"25","author":"E Cakir","year":"2017","unstructured":"E. Cakir, G. Parascandolo, T. Heittola, H. Huttunen, T. Virtanen, Convolutional recurrent neural networks for polyphonic sound event detection. IEEE\/ACM Trans. Audio Speech Lang. Process. 25, 1291\u20131303 (2017). https:\/\/doi.org\/10.1109\/TASLP.2017.2690575","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"3195_CR5","doi-asserted-by":"publisher","unstructured":"C. Castorena, M. Cobos, J. Lopez-Ballester, F.J. Ferri, A safety-oriented framework for sound event detection in driving scenarios. Appl. Acoust. 215 (2024). https:\/\/doi.org\/10.1016\/j.apacoust.2023.109719","DOI":"10.1016\/j.apacoust.2023.109719"},{"key":"3195_CR6","doi-asserted-by":"publisher","first-page":"5767","DOI":"10.1007\/s00521-018-3407-3","volume":"31","author":"TK Chan","year":"2019","unstructured":"T.K. Chan, C.S. Chin, Health stages diagnostics of underwater thruster using sound features with imbalanced dataset. Neural Comput. Appl. 31, 5767\u20135782 (2019). https:\/\/doi.org\/10.1007\/s00521-018-3407-3","journal-title":"Neural Comput. Appl."},{"key":"3195_CR7","doi-asserted-by":"crossref","unstructured":"K. Drossos, S.I. Mimilakis, S. Gharib, Y. Li, T. Virtanen, Sound event detection with depthwise separable and dilated convolutions. http:\/\/arxiv.org\/abs\/2002.00476, (2020)","DOI":"10.1109\/IJCNN48605.2020.9207532"},{"key":"3195_CR8","doi-asserted-by":"publisher","first-page":"395","DOI":"10.3390\/arm92050037","volume":"92","author":"EHI Eliwa","year":"2024","unstructured":"E.H.I. Eliwa, M.E. Koshiry, A. Abd El-Hafeez, T. Omar, Secure and transparent lung and colon cancer classification using blockchain and Microsoft Azure. ARM. 92, 395\u2013420 (2024). https:\/\/doi.org\/10.3390\/arm92050037","journal-title":"ARM"},{"key":"3195_CR9","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1109\/TITS.2015.2470216","volume":"17","author":"P Foggia","year":"2016","unstructured":"P. Foggia, N. Petkov, A. Saggese, N. Strisciuglio, M. Vento, Audio surveillance of roads: a system for detecting anomalous sounds. IEEE Trans. Intell. Transp. Syst. 17, 279\u2013288 (2016). https:\/\/doi.org\/10.1109\/TITS.2015.2470216","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"3195_CR10","unstructured":"E. Fonseca, A. Ferraro, X. Serra, Improving sound event classification by increasing shift invariance in convolutional neural networks. http:\/\/arxiv.org\/abs\/2107.00623, (2021)"},{"key":"3195_CR11","doi-asserted-by":"publisher","first-page":"3396","DOI":"10.1109\/TGRS.2020.3008286","volume":"59","author":"H Gao","year":"2021","unstructured":"H. Gao, Y. Yang, C. Li, L. Gao, B. Zhang, Multiscale residual network with mixed depthwise Convolution for hyperspectral image classification. IEEE Trans. Geosci. Remote Sens. 59, 3396\u20133408 (2021). https:\/\/doi.org\/10.1109\/TGRS.2020.3008286","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"3195_CR12","doi-asserted-by":"crossref","unstructured":"T. Hayashi, S. Watanabe, T. Toda, T. Hori, Le J. Roux, K. Takeda, Blstm-Hmm hybrid system combined with sound activity detection network for polyphonic sound event detection. In: 2017 Ieee International Conference on Acoustics, Speech and Signal Processing (ICASSP). pp. 766\u2013770. IEEE, New York (2017)","DOI":"10.1109\/ICASSP.2017.7952259"},{"key":"3195_CR13","doi-asserted-by":"publisher","first-page":"103930","DOI":"10.1016\/j.jvcir.2023.103930","volume":"96","author":"S Hwang","year":"2023","unstructured":"S. Hwang, D. Han, M. Jeon, Making depthwise Convolution sr-friendly via kernel attention injection. J. Vis. Commun. Image Represent. 96, 103930 (2023). https:\/\/doi.org\/10.1016\/j.jvcir.2023.103930","journal-title":"J. Vis. Commun. Image Represent."},{"key":"3195_CR14","doi-asserted-by":"publisher","unstructured":"K. Imoto, S. Mishima, Y. Arai, R. Kondo, Impact of sound duration and inactive frames on sound event detection performance. In: 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2021). pp. 860\u2013864. IEEE, New York (2021). https:\/\/doi.org\/10.1109\/ICASSP39728.2021.9414949","DOI":"10.1109\/ICASSP39728.2021.9414949"},{"key":"3195_CR15","doi-asserted-by":"publisher","first-page":"5653","DOI":"10.1007\/s40747-024-01463-7","volume":"10","author":"Y Jiang","year":"2024","unstructured":"Y. Jiang, D. Guo, L. Wang, H. Zhang, H. Dong, Y. Qiu, H. Zou, Sound event detection in traffic scenes based on graph convolutional network to obtain multi-modal information. Complex. Intell. Syst. 10, 5653\u20135668 (2024). https:\/\/doi.org\/10.1007\/s40747-024-01463-7","journal-title":"Complex. Intell. Syst."},{"key":"3195_CR16","doi-asserted-by":"publisher","unstructured":"T. Khandelwal, R.K. Das, E.S. Chng, Sound event detection: a journey through Dcase challenge series. SIP. 13 (2024). https:\/\/doi.org\/10.1561\/116.00000051","DOI":"10.1561\/116.00000051"},{"key":"3195_CR17","doi-asserted-by":"publisher","unstructured":"J. Liao, H. Duan, K. Feng, W. Zhao, Y. Yang, L. Chen, A light weight model for active speaker detection. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 22932\u201322941. IEEE, Vancouver, BC, Canada (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.02196","DOI":"10.1109\/CVPR52729.2023.02196"},{"key":"3195_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3618104","volume":"56","author":"D Meedeniya","year":"2024","unstructured":"D. Meedeniya, I. Ariyarathne, M. Bandara, R. Jayasundara, C. Perera, A survey on deep learning based forest environment sound classification at the edge. ACM Comput. Surv. 56, 1\u201336 (2024). https:\/\/doi.org\/10.1145\/3618104","journal-title":"ACM Comput. Surv."},{"key":"3195_CR19","doi-asserted-by":"publisher","first-page":"162","DOI":"10.3390\/app6060162","volume":"6","author":"A Mesaros","year":"2016","unstructured":"A. Mesaros, T. Heittola, T. Virtanen, Metrics for polyphonic sound event detection. Appl. Sci. -Basel. 6, 162 (2016). https:\/\/doi.org\/10.3390\/app6060162","journal-title":"Appl. Sci. -Basel"},{"key":"3195_CR20","doi-asserted-by":"publisher","first-page":"992","DOI":"10.1109\/TASLP.2019.2907016","volume":"27","author":"A Mesaros","year":"2019","unstructured":"A. Mesaros, A. Diment, B. Elizalde, T. Heittola, E. Vincent, B. Raj, T. Virtanen, Sound event detection in the DCASE 2017 challenge. IEEE-ACM trans. Audio Speech Lang. 27, 992\u20131006 (2019). https:\/\/doi.org\/10.1109\/TASLP.2019.2907016","journal-title":"Audio Speech Lang."},{"key":"3195_CR21","doi-asserted-by":"publisher","first-page":"5537","DOI":"10.1007\/s11042-021-11817-9","volume":"81","author":"Z Mnasri","year":"2022","unstructured":"Z. Mnasri, S. Rovetta, F. Masulli, Anomalous sound event detection: A survey of machine learning based methods and applications. Multimed Tools Appl. 81, 5537\u20135586 (2022). https:\/\/doi.org\/10.1007\/s11042-021-11817-9","journal-title":"Multimed Tools Appl."},{"key":"3195_CR22","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1186\/s40537-024-00944-3","volume":"11","author":"G Mostafa","year":"2024","unstructured":"G. Mostafa, H. Mahmoud, T. Abd El-Hafeez, M.E. ElAraby, Feature reduction for hepatocellular carcinoma prediction using machine learning algorithms. J. Big Data. 11, 88 (2024). https:\/\/doi.org\/10.1186\/s40537-024-00944-3","journal-title":"J. Big Data"},{"key":"3195_CR23","doi-asserted-by":"publisher","first-page":"2835","DOI":"10.1007\/s00521-023-09204-6","volume":"36","author":"A Omar","year":"2024","unstructured":"A. Omar, T. Abd El-Hafeez, Optimizing epileptic seizure recognition performance with feature scaling and dropout layers. Neural Comput. Applic. 36, 2835\u20132852 (2024). https:\/\/doi.org\/10.1007\/s00521-023-09204-6","journal-title":"Neural Comput. Applic"},{"key":"3195_CR24","doi-asserted-by":"crossref","unstructured":"G. Parascandolo, H. Huttunen, T. Virtanen, Recurrent neural networks for polyphonic sound event detection in real life recordings. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing Proceedings. pp. 6440\u20136444. IEEE, New York (2016)","DOI":"10.1109\/ICASSP.2016.7472917"},{"key":"3195_CR25","doi-asserted-by":"publisher","unstructured":"F. Ronchini, R. Serizel, Performance and energy balance: a comprehensive study of state-of-the-art sound event detection systems. In: ICASSP 2024\u20132024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). pp. 1096\u20131100. IEEE, Seoul, Korea, Republic of (2024). https:\/\/doi.org\/10.1109\/ICASSP48485.2024.10445834","DOI":"10.1109\/ICASSP48485.2024.10445834"},{"key":"3195_CR26","doi-asserted-by":"publisher","unstructured":"A. Semmad, M. Bahoura, Long short term memory based recurrent neural network for wheezing detection in pulmonary sounds. In: 2021 IEEE International Midwest Symposium on Circuits and Systems (MWSCAS). pp. 412\u2013415. IEEE, New York (2021). https:\/\/doi.org\/10.1109\/MWSCAS47672.2021.9531784","DOI":"10.1109\/MWSCAS47672.2021.9531784"},{"key":"3195_CR27","doi-asserted-by":"publisher","DOI":"10.1080\/03772063.2023.2253768","author":"V Spoorthy","year":"2023","unstructured":"V. Spoorthy, S.G. Koolagudi, Polyphonic sound event detection using mel-pseudo constant Q-transform and deep neural network. IETE J. Res. (2023). https:\/\/doi.org\/10.1080\/03772063.2023.2253768","journal-title":"IETE J. Res."},{"key":"3195_CR28","doi-asserted-by":"publisher","unstructured":"A. Tyagi, K. Singh, S. Jaswanth Kumar, P.V. Garg, P.R.Y. Abdullah, M.E.: Performance comparison of overlapping sound event detection methods. In: 2024 14th International Conference on Cloud Computing, Data Science & Engineering (Confluence). pp. 817\u2013822. IEEE, Noida, India (2024). https:\/\/doi.org\/10.1109\/Confluence60223.2024.10463375","DOI":"10.1109\/Confluence60223.2024.10463375"},{"key":"3195_CR29","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1016\/j.neucom.2020.09.038","volume":"421","author":"Y Wang","year":"2021","unstructured":"Y. Wang, G. Zhao, K. Xiong, G. Shi, Y. Zhang, Multi-scale and single-scale fully convolutional networks for sound event detection. Neurocomputing. 421, 51\u201365 (2021). https:\/\/doi.org\/10.1016\/j.neucom.2020.09.038","journal-title":"Neurocomputing"},{"key":"3195_CR30","doi-asserted-by":"publisher","first-page":"103319","DOI":"10.1016\/j.dsp.2021.103319","volume":"122","author":"Y Wang","year":"2022","unstructured":"Y. Wang, G. Zhao, K. Xiong, G. Shi, MSFF-net: multi-scale feature fusing networks with dilated mixed Convolution and cascaded parallel framework for sound event detection. Digit. Signal Proc. 122, 103319 (2022). https:\/\/doi.org\/10.1016\/j.dsp.2021.103319","journal-title":"Digit. Signal Proc."},{"key":"3195_CR31","doi-asserted-by":"publisher","first-page":"3194","DOI":"10.3390\/electronics13163194","volume":"13","author":"Y Wang","year":"2024","unstructured":"Y. Wang, W. Wang, Y. Chen, X. Su, J. Chen, W. Yang, Q. Li, C. Duan, Effective sample selection and enhancement of long short-term dependencies in signal detection: hdc-inception and hybrid Ce loss. Electronics. 13, 3194 (2024). https:\/\/doi.org\/10.3390\/electronics13163194","journal-title":"Electronics"},{"key":"3195_CR32","doi-asserted-by":"publisher","unstructured":"J. Xu, J. Yu, X. Liu, H. Meng, Mixed precision dnn quantization for overlapped speech separation and recognition. In: ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). pp. 7297\u20137301. IEEE, Singapore, Singapore (2022). https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9746885","DOI":"10.1109\/ICASSP43922.2022.9746885"},{"key":"3195_CR33","doi-asserted-by":"publisher","unstructured":"H. Yang, L. Luo, M. Wang, X. Song, F. Mi, Sound event detection using multi-scale dense convolutional recurrent neural network with lightweight attention. In: 2023 3rd International Conference on Electronic Information Engineering and Computer (EIECT). pp. 35\u201340 (2023). https:\/\/doi.org\/10.1109\/EIECT60552.2023.10442997","DOI":"10.1109\/EIECT60552.2023.10442997"},{"key":"3195_CR34","doi-asserted-by":"publisher","first-page":"861286","DOI":"10.3389\/fbioe.2022.861286","volume":"10","author":"J Yun","year":"2022","unstructured":"J. Yun, D. Jiang, Y. Liu, Y. Sun, B. Tao, J. Kong, J. Tian, X. Tong, M. Xu, Z. Fang, Real-time target detection method based on lightweight convolutional neural network. Front. Bioeng. Biotechnol. 10, 861286 (2022). https:\/\/doi.org\/10.3389\/fbioe.2022.861286","journal-title":"Front. Bioeng. Biotechnol."},{"key":"3195_CR35","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.ecoinf.2017.04.003","volume":"39","author":"Z Zhao","year":"2017","unstructured":"Z. Zhao, S.-H. Zhang, Z. Xu, K. Bellisario, N. Dai, H. Omrani, B.C. Pijanowski, Automated bird acoustic event detection and robust species classification. Ecol. Inf. 39, 99\u2013108 (2017). https:\/\/doi.org\/10.1016\/j.ecoinf.2017.04.003","journal-title":"Ecol. Inf."}],"container-title":["Circuits, Systems, and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-025-03195-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00034-025-03195-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-025-03195-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T06:13:48Z","timestamp":1761977628000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00034-025-03195-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,14]]},"references-count":35,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["3195"],"URL":"https:\/\/doi.org\/10.1007\/s00034-025-03195-6","relation":{},"ISSN":["0278-081X","1531-5878"],"issn-type":[{"value":"0278-081X","type":"print"},{"value":"1531-5878","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,14]]},"assertion":[{"value":"13 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 May 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 May 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 June 2025","order":4,"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 conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}