{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T17:52:14Z","timestamp":1782928334822,"version":"3.54.5"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,6,13]],"date-time":"2025-06-13T00:00:00Z","timestamp":1749772800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,6,13]],"date-time":"2025-06-13T00:00:00Z","timestamp":1749772800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Iran J Comput Sci"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s42044-025-00289-x","type":"journal-article","created":{"date-parts":[[2025,6,13]],"date-time":"2025-06-13T12:57:08Z","timestamp":1749819428000},"page":"1801-1834","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Artificial intelligence-powered environmental sound recognition with explainable AI techniques"],"prefix":"10.1007","volume":"8","author":[{"given":"Farida Siddiqi","family":"Prity","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Md. Mubarak","family":"Hossain","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Md. Maruf","family":"Hossain","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Md. Shihab","family":"Uddin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Md. Rabiul","family":"Islam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mirza","family":"Raquib","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Md. Rehan","family":"Ali","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6918-2648","authenticated-orcid":false,"given":"K. M. Aslam","family":"Uddin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,6,13]]},"reference":[{"issue":"15","key":"289_CR1","doi-asserted-by":"publisher","first-page":"6972","DOI":"10.3390\/s23156972","volume":"23","author":"HC Chu","year":"2023","unstructured":"Chu, H.C., Zhang, Y.L., Chiang, H.C.: A CNN sound classification mechanism using data augmentation. Sensors 23(15), 6972 (2023)","journal-title":"Sensors"},{"key":"289_CR2","doi-asserted-by":"crossref","unstructured":"Salamon, J., Jacoby, C. and Bello, J.P., 2014 A dataset and taxonomy for urban sound research. In Proceedings of the 22nd ACM international conference on Multimedia. pp. 1041\u20131044.","DOI":"10.1145\/2647868.2655045"},{"issue":"3","key":"289_CR3","doi-asserted-by":"publisher","first-page":"1476","DOI":"10.3390\/app13031476","volume":"13","author":"M Ashraf","year":"2023","unstructured":"Ashraf, M., Abid, F., Din, I.U., Rasheed, J., Yesiltepe, M., Yeo, S.F., Ersoy, M.T.: A hybrid cnn and rnn variant model for music classification. Appl. Sci. 13(3), 1476 (2023)","journal-title":"Appl. Sci."},{"issue":"1","key":"289_CR4","doi-asserted-by":"publisher","first-page":"1289","DOI":"10.1038\/s41598-023-27399-5","volume":"13","author":"JS Park","year":"2023","unstructured":"Park, J.S., Kim, K., Kim, J.H., Choi, Y.J., Kim, K., Suh, D.I.: A machine learning approach to the development and prospective evaluation of a pediatric lung sound classification model. Sci. Rep. 13(1), 1289 (2023)","journal-title":"Sci. Rep."},{"key":"289_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2020.107520","volume":"170","author":"F Demir","year":"2020","unstructured":"Demir, F., Turkoglu, M., Aslan, M., Sengur, A.: A new pyramidal concatenated CNN approach for environmental sound classification. Appl. Acoust. 170, 107520 (2020)","journal-title":"Appl. Acoust."},{"key":"289_CR6","doi-asserted-by":"publisher","first-page":"75702","DOI":"10.1109\/ACCESS.2020.2988986","volume":"8","author":"VT Tran","year":"2020","unstructured":"Tran, V.T., Tsai, W.H.: Acoustic-based emergency vehicle detection using convolutional neural networks. IEEE Access 8, 75702\u201375713 (2020)","journal-title":"IEEE Access"},{"issue":"13","key":"289_CR7","doi-asserted-by":"publisher","first-page":"5796","DOI":"10.3390\/app11135796","volume":"11","author":"L Nanni","year":"2021","unstructured":"Nanni, L., Maguolo, G., Brahnam, S., Paci, M.: An ensemble of convolutional neural networks for audio classification. Appl. Sci. 11(13), 5796 (2021)","journal-title":"Appl. Sci."},{"issue":"7","key":"289_CR8","doi-asserted-by":"publisher","first-page":"1152","DOI":"10.3390\/app8071152","volume":"8","author":"S Li","year":"2018","unstructured":"Li, S., Yao, Y., Hu, J., Liu, G., Yao, X., Hu, J.: An ensemble stacked convolutional neural network model for environmental event sound recognition. Appl. Sci. 8(7), 1152 (2018)","journal-title":"Appl. Sci."},{"key":"289_CR9","unstructured":"Koul, S., 2021. Application of deep learning in urban sounds classification. Turkish Online J. Qualitative Inquiry, 12(7)."},{"key":"289_CR10","doi-asserted-by":"crossref","unstructured":"Guo, J., Xu, N., Li, L.J. and Alwan, A., 2017 Attention based CLDNNs for short-duration acoustic scene classification. In Interspeech. pp. 469\u2013473.","DOI":"10.21437\/Interspeech.2017-440"},{"key":"289_CR11","doi-asserted-by":"publisher","first-page":"896","DOI":"10.1016\/j.neucom.2020.08.069","volume":"453","author":"Z Zhang","year":"2021","unstructured":"Zhang, Z., Xu, S., Zhang, S., Qiao, T., Cao, S.: Attention based convolutional recurrent neural network for environmental sound classification. Neurocomputing 453, 896\u2013903 (2021)","journal-title":"Neurocomputing"},{"issue":"6","key":"289_CR12","volume":"6","author":"R Jahangir","year":"2024","unstructured":"Jahangir, R.: CNN-SCNet: A CNN net-based deep learning framework for infant cry detection in household setting. Eng Rep 6(6), e12786 (2024)","journal-title":"Eng Rep"},{"issue":"1","key":"289_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s43926-023-00049-y","volume":"4","author":"MK Gourisaria","year":"2024","unstructured":"Gourisaria, M.K., Agrawal, R., Sahni, M., Singh, P.K.: Comparative analysis of audio classification with MFCC and STFT features using machine learning techniques. Discover Internet of Things 4(1), 1 (2024)","journal-title":"Discover Internet of Things"},{"issue":"6","key":"289_CR14","first-page":"2748","volume":"12","author":"M Lim","year":"2018","unstructured":"Lim, M., Lee, D., Park, H., Kang, Y., Oh, J., Park, J.S., Jang, G.J., Kim, J.H.: Convolutional neural network based audio event classification. KSII Trans Internet Inform Syst (TIIS) 12(6), 2748\u20132760 (2018)","journal-title":"KSII Trans Internet Inform Syst (TIIS)"},{"issue":"22","key":"289_CR15","doi-asserted-by":"publisher","first-page":"3795","DOI":"10.3390\/electronics11223795","volume":"11","author":"OO Abayomi-Alli","year":"2022","unstructured":"Abayomi-Alli, O.O., Dama\u0161evi\u010dius, R., Qazi, A., Adedoyin-Olowe, M., Misra, S.: Data augmentation and deep learning methods in sound classification: a systematic review. Electronics 11(22), 3795 (2022)","journal-title":"Electronics"},{"key":"289_CR16","first-page":"356","volume-title":"Chinese Conference on Pattern Recognition and Computer Vision (prcv)","author":"Z Zhang","year":"2018","unstructured":"Zhang, Z., Xu, S., Cao, S., Zhang, S.: Deep convolutional neural network with mixup for environmental sound classification. In: Chinese Conference on Pattern Recognition and Computer Vision (prcv), pp. 356\u2013367. Springer International Publishing, Cham (2018)"},{"issue":"3","key":"289_CR17","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1109\/LSP.2017.2657381","volume":"24","author":"J Salamon","year":"2017","unstructured":"Salamon, J., Bello, J.P.: Deep convolutional neural networks and data augmentation for environmental sound classification. IEEE Signal Process. Lett. 24(3), 279\u2013283 (2017)","journal-title":"IEEE Signal Process. Lett."},{"issue":"1","key":"289_CR18","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1007\/s13721-023-00423-4","volume":"12","author":"FS Prity","year":"2023","unstructured":"Prity, F.S., Nath, N., Nath, A., Uddin, K.A.: Neural network-based strategies for automatically diagnosing of COVID-19 from X-ray images utilizing different feature extraction algorithms. Network Modeling Anal. Health Inform. Bioinform. 12(1), 28 (2023)","journal-title":"Network Modeling Anal. Health Inform. Bioinform."},{"issue":"2","key":"289_CR19","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1109\/JSTSP.2019.2908700","volume":"13","author":"H Purwins","year":"2019","unstructured":"Purwins, H., Li, B., Virtanen, T., Schl\u00fcter, J., Chang, S.Y., Sainath, T.: Deep learning for audio signal processing. IEEE J. Selected Topics Signal Processing 13(2), 206\u2013219 (2019)","journal-title":"IEEE J. Selected Topics Signal Processing"},{"key":"289_CR20","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1016\/j.eswa.2019.06.040","volume":"136","author":"S Abdoli","year":"2019","unstructured":"Abdoli, S., Cardinal, P., Koerich, A.L.: End-to-end environmental sound classification using a 1D convolutional neural network. Expert Syst. Appl. 136, 252\u2013263 (2019)","journal-title":"Expert Syst. Appl."},{"key":"289_CR21","doi-asserted-by":"crossref","unstructured":"Sharma, J., Granmo, O.C. and Goodwin, M.: 2020 Environment sound classification using multiple feature channels and attention based deep convolutional neural network.","DOI":"10.21437\/Interspeech.2020-1303"},{"key":"289_CR22","doi-asserted-by":"crossref","unstructured":"Prity, F.S., Hasan, A.J., Anik, M.M.H., Hossain, R., Hossain, M.M., Bhuiyan, S.H., Islam, M.A. and Lavlu, M.T.H.: 2024 RvXmBlendNet: a multi-architecture hybrid model for improved skin cancer detection. Human-Centric Intelligent Systems, pp.1\u201326.","DOI":"10.1007\/s44230-024-00083-1"},{"key":"289_CR23","doi-asserted-by":"publisher","first-page":"125714","DOI":"10.1109\/ACCESS.2020.3007906","volume":"8","author":"X Dong","year":"2020","unstructured":"Dong, X., Yin, B., Cong, Y., Du, Z., Huang, X.: Environment sound event classification with a two-stream convolutional neural network. IEEE Access 8, 125714\u2013125721 (2020)","journal-title":"IEEE Access"},{"key":"289_CR24","doi-asserted-by":"crossref","unstructured":"Piczak, K.J.: 2015 Environmental sound classification with convolutional neural networks. In 2015 IEEE 25th International Workshop on Machine Learning for Signal Processing (MLSP). IEEE, pp. 1\u20136","DOI":"10.1109\/MLSP.2015.7324337"},{"issue":"6","key":"289_CR25","doi-asserted-by":"publisher","first-page":"1142","DOI":"10.1109\/TASL.2009.2017438","volume":"17","author":"S Chu","year":"2009","unstructured":"Chu, S., Narayanan, S., Kuo, C.C.J.: Environmental sound recognition with time\u2013frequency audio features. IEEE Trans. Audio Speech Lang. Process. 17(6), 1142\u20131158 (2009)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"12","key":"289_CR26","doi-asserted-by":"publisher","first-page":"3749","DOI":"10.3390\/s24123749","volume":"24","author":"D Ranmal","year":"2024","unstructured":"Ranmal, D., Ranasinghe, P., Paranayapa, T., Meedeniya, D., Perera, C.: Esc-nas: environment sound classification using hardware-aware neural architecture search for the edge. Sensors 24(12), 3749 (2024)","journal-title":"Sensors"},{"key":"289_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2025.110593","volume":"232","author":"F Chen","year":"2025","unstructured":"Chen, F., Zhu, Z., Sun, C., Xia, L.: Evaluating metric and contrastive learning in pretrained models for environmental sound classification. Appl. Acoust. 232, 110593 (2025)","journal-title":"Appl. Acoust."},{"issue":"4","key":"289_CR28","doi-asserted-by":"publisher","first-page":"1521","DOI":"10.3390\/s22041521","volume":"22","author":"Z Tariq","year":"2022","unstructured":"Tariq, Z., Shah, S.K., Lee, Y.: Feature-based fusion using CNN for lung and heart sound classification. Sensors 22(4), 1521 (2022)","journal-title":"Sensors"},{"issue":"4","key":"289_CR29","doi-asserted-by":"publisher","first-page":"2032","DOI":"10.3390\/s23042032","volume":"23","author":"M Bandara","year":"2023","unstructured":"Bandara, M., Jayasundara, R., Ariyarathne, I., Meedeniya, D., Perera, C.: Forest sound classification dataset: Fsc22. Sensors 23(4), 2032 (2023)","journal-title":"Sensors"},{"issue":"11","key":"289_CR30","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"289_CR31","unstructured":"UrbanSound8K. https:\/\/www.kaggle.com\/datasets\/chrisfilo\/urbansound8k\/data\\. Accessed 26 Apr 2024"},{"key":"289_CR32","doi-asserted-by":"crossref","unstructured":"Prity, F.S., Islam, M.S., Fahim, E.H., Hossain, M.M., Bhuiyan, S.H., Islam, M.A. and Raquib, M.: 2024 Machine learning-based cyber threat detection: an approach to malware detection and security with explainable AI insights. Human-Intelligent Systems Integration, pp.1\u201330.","DOI":"10.1007\/s42454-024-00055-7"},{"key":"289_CR33","doi-asserted-by":"crossref","unstructured":"Dai, W., Dai, C., Qu, S., Li, J. and Das, S.: 2017 Very deep convolutional neural networks for raw waveforms. In 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp. 421\u2013425","DOI":"10.1109\/ICASSP.2017.7952190"},{"issue":"1","key":"289_CR34","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1016\/j.aej.2020.06.019","volume":"60","author":"D Pysal","year":"2021","unstructured":"Pysal, D., Abdulkadir, S.J., Shukri, S.R.M., Alhussian, H.: Classification of children\u2019s drawing strategies on touch-screen of seriation objects using a novel deep learning hybrid model. Alex. Eng. J. 60(1), 115\u2013129 (2021)","journal-title":"Alex. Eng. J."},{"issue":"10","key":"289_CR35","doi-asserted-by":"publisher","first-page":"4660","DOI":"10.3390\/app11104660","volume":"11","author":"MG Ragab","year":"2021","unstructured":"Ragab, M.G., Abdulkadir, S.J., Aziz, N., Alhussian, H., Bala, A., Alqushaibi, A.: An ensemble one dimensional convolutional neural network with Bayesian optimization for environmental sound classification. Appl. Sci. 11(10), 4660 (2021)","journal-title":"Appl. Sci."},{"issue":"15","key":"289_CR36","doi-asserted-by":"publisher","first-page":"2279","DOI":"10.3390\/electronics11152279","volume":"11","author":"A Ashurov","year":"2022","unstructured":"Ashurov, A., Zhou, Y., Shi, L., Zhao, Y., Liu, H.: Environmental sound classification based on transfer-learning techniques with multiple optimizers. Electronics 11(15), 2279 (2022)","journal-title":"Electronics"},{"issue":"2","key":"289_CR37","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1007\/s42979-023-02591-6","volume":"5","author":"W Ansar","year":"2024","unstructured":"Ansar, W., Chatterjee, A., Goswami, S., Chakrabarti, A.: An EfficientNet-based ensemble for bird-call recognition with enhanced noise reduction. SN Comput. Sci. 5(2), 265 (2024)","journal-title":"SN Comput. Sci."},{"key":"289_CR38","first-page":"11113","volume":"46","author":"M Imran","year":"2021","unstructured":"Imran, M., Khader, P.S.A., Rafiq, M., Rawat, K.S.: Forecasting water level of Glacial fed perennial river using a genetically optimized hybrid Machine learning model. Mater. Today: Proc. 46, 11113\u201311119 (2021)","journal-title":"Mater. Today: Proc."},{"issue":"8","key":"289_CR39","doi-asserted-by":"publisher","first-page":"8913","DOI":"10.1007\/s13762-022-04467-3","volume":"20","author":"I Mirza","year":"2023","unstructured":"Mirza, I., Khader, S.A.P.: Investigating the effect of different support vector classifier variants to predict the flood risk of Himalayan river. Int. J. Environ. Sci. Technol. 20(8), 8913 (2023)","journal-title":"Int. J. Environ. Sci. Technol."},{"key":"289_CR40","doi-asserted-by":"crossref","unstructured":"Prity, F.S., Hasan, M.M., Saif, S.H., Hossain, M.M., Bhuiyan, S.H., Islam, M.A. and Lavlu, M.T.H.: 2024 Enhancing agricultural productivity: a machine learning approach to crop recommendations. Human-Centric Intelligent Systems, pp.1\u201314.","DOI":"10.1007\/s44230-024-00081-3"}],"container-title":["Iran Journal of Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42044-025-00289-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42044-025-00289-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42044-025-00289-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T17:20:36Z","timestamp":1782926436000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42044-025-00289-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,13]]},"references-count":40,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["289"],"URL":"https:\/\/doi.org\/10.1007\/s42044-025-00289-x","relation":{},"ISSN":["2520-8438","2520-8446"],"issn-type":[{"value":"2520-8438","type":"print"},{"value":"2520-8446","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,13]]},"assertion":[{"value":"12 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 May 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 June 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 July 2026","order":5,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Update","order":6,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"In this article the affiliation details for Farida Siddiqi Prity were incorrectly given as \"Department of Computer and Communication Engineering, International Islamic University, Chittagong, 4318, Bangladesh\" but should have been \"Department of Computer and Communication Engineering, International Islamic University Chittagong, Chittagong 4318, Bangladesh\". The original article has been corrected.","order":7,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no conflict of interest to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict interests"}},{"value":"This article does not contain any studies with human participants and animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}]}}