{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T08:47:20Z","timestamp":1778575640653,"version":"3.51.4"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"21","license":[{"start":{"date-parts":[[2021,5,26]],"date-time":"2021-05-26T00:00:00Z","timestamp":1621987200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,5,26]],"date-time":"2021-05-26T00:00:00Z","timestamp":1621987200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100007297","name":"international islamic university malaysia","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100007297","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2021,11]]},"DOI":"10.1007\/s00521-021-06091-7","type":"journal-article","created":{"date-parts":[[2021,5,26]],"date-time":"2021-05-26T08:02:43Z","timestamp":1622016163000},"page":"14495-14506","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Rethinking environmental sound classification using convolutional neural networks: optimized parameter tuning of single feature extraction"],"prefix":"10.1007","volume":"33","author":[{"given":"Yousef Abd","family":"Al-Hattab","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7209-4355","authenticated-orcid":false,"given":"Hasan Firdaus","family":"Zaki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amir Akramin","family":"Shafie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,5,26]]},"reference":[{"issue":"6","key":"6091_CR1","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1007\/s00521-016-2501-7","volume":"29","author":"H Ali","year":"2018","unstructured":"Ali H, Tran SN, Benetos E, Garcez ASDA (2018) Speaker recognition with hybrid features from a deep belief network. Neural Comput Appl 29(6):13\u201319","journal-title":"Neural Comput Appl"},{"key":"6091_CR2","doi-asserted-by":"crossref","unstructured":"Ghosal, D, Kolekar MH (2018) Music genre recognition using deep neural networks and transfer learning. In: Interspeech, pp 2087\u20132091","DOI":"10.21437\/Interspeech.2018-2045"},{"key":"6091_CR3","doi-asserted-by":"crossref","unstructured":"Chachada S, Kuo CCJ (2014) Environmental sound recognition: a survey. APSIPA Trans Signal Inf Process 3","DOI":"10.1017\/ATSIP.2014.12"},{"key":"6091_CR4","doi-asserted-by":"crossref","unstructured":"Zhang Z, Xu S, Cao S, Zhang S (2018) Deep convolutional neural network with mixup for environmental sound classification. In: Chinese conference on pattern recognition and computer vision (prcv), Springer, Cham, pp 356\u2013367","DOI":"10.1007\/978-3-030-03335-4_31"},{"key":"6091_CR5","doi-asserted-by":"crossref","unstructured":"Shkurti F, Chang WD et al (2017) Underwater multi-robot convoying using visual tracking by detection. In: 2017 IEEE\/RSJ international conference on intelligent robots and systems (IROS), pp 4189\u20134196. IEEE","DOI":"10.1109\/IROS.2017.8206280"},{"issue":"6","key":"6091_CR6","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 CCJ (2009) Environmental sound recognition with time\u2013frequency audio features. IEEE Trans Audio Speech Lang Process 17(6):1142\u20131158","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"6091_CR7","doi-asserted-by":"crossref","unstructured":"Giannoulis D, Benetos E, Stowell D, Rossignol M, Lagrange M, Plumbley MD (2013) Detection and classification of acoustic scenes and events: an IEEE AASP challenge. In: 2013 IEEE workshop on applications of signal processing to audio and acoustics, pp 1\u20134. IEEE","DOI":"10.1109\/WASPAA.2013.6701819"},{"key":"6091_CR8","doi-asserted-by":"crossref","unstructured":"Zhang H, McLoughlin I, Song Y (2015) Robust sound event recognition using convolutional neural networks. In: 2015 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 559\u2013563. IEEE","DOI":"10.1109\/ICASSP.2015.7178031"},{"key":"6091_CR9","doi-asserted-by":"crossref","unstructured":"LeCun Y, Bengio Y, Hinton G (2015). Deep Learn Nat 521(7553):436\u2013444","DOI":"10.1038\/nature14539"},{"key":"6091_CR10","doi-asserted-by":"crossref","unstructured":"Palaz D, Collobert R (2015) Analysis of cnn-based speech recognition system using raw speech as input (No. REP_WORK). Idiap","DOI":"10.21437\/Interspeech.2015-3"},{"key":"6091_CR11","unstructured":"Adavanne, S., & Virtanen, T. (2017). Sound event detection using weakly labeled dataset with stacked convolutional and recurrent neural network. arXiv preprint axXiv:1701.02998"},{"key":"6091_CR12","doi-asserted-by":"crossref","unstructured":"Adavanne S, Pertil\u00e4 P, Virtanen T (2017) Sound event detection using spatial features and convolutional recurrent neural network. In: 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 771\u2013775. IEEE","DOI":"10.1109\/ICASSP.2017.7952260"},{"key":"6091_CR13","doi-asserted-by":"crossref","unstructured":"Zaki HF, Shafait F, Mian A (2016) Modeling 2D appearance evolution for 3D object categorization. In: 2016 international conference on digital image computing: techniques and applications (DICTA), pp 1\u20138. IEEE","DOI":"10.1109\/DICTA.2016.7797065"},{"key":"6091_CR14","doi-asserted-by":"crossref","unstructured":"Piczak KJ (2015) Environmental sound classification with convolutional neural networks. In: 2015 IEEE 25th international workshop on machine learning for signal processing (MLSP), pp 1\u20136. IEEE","DOI":"10.1109\/MLSP.2015.7324337"},{"key":"6091_CR15","unstructured":"Meyer, M., Cavigelli, L., & Thiele, L. (2017). Efficient convolutional neural network for audio event detection. arXiv preprint axXiv:1709.09888"},{"key":"6091_CR16","doi-asserted-by":"crossref","unstructured":"Pons J, Serra X (2019) Randomly weighted cnns for (music) audio classification. In: ICASSP 2019\u20132019 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 336\u2013340. IEEE","DOI":"10.1109\/ICASSP.2019.8682912"},{"key":"6091_CR17","doi-asserted-by":"crossref","unstructured":"Dai W, Dai C, Qu S, Li J, Das S (2017) Very deep convolutional neural networks for raw waveforms. In: 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 421\u2013425. IEEE","DOI":"10.1109\/ICASSP.2017.7952190"},{"issue":"3","key":"6091_CR18","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1109\/LSP.2017.2657381","volume":"24","author":"J Salamon","year":"2017","unstructured":"Salamon J, Bello JP (2017) Deep convolutional neural networks and data augmentation for environmental sound classification. IEEE Signal Process Lett 24(3):279\u2013283","journal-title":"IEEE Signal Process Lett"},{"key":"6091_CR19","doi-asserted-by":"publisher","first-page":"2048","DOI":"10.1016\/j.procs.2017.08.250","volume":"112","author":"V Boddapati","year":"2017","unstructured":"Boddapati V, Petef A, Rasmusson J, Lundberg L (2017) Classifying environmental sounds using image recognition networks. Proc Comput Sci 112:2048\u20132056","journal-title":"Proc Comput Sci"},{"key":"6091_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 AL (2019) End-to-end environmental sound classification using a 1D convolutional neural network. Expert Syst Appl 136:252\u2013263","journal-title":"Expert Syst Appl"},{"issue":"7","key":"6091_CR21","doi-asserted-by":"publisher","first-page":"1733","DOI":"10.3390\/s19071733","volume":"19","author":"Y Su","year":"2019","unstructured":"Su Y, Zhang K, Wang J, Madani K (2019) Environment sound classification using a two-stream CNN based on decision-level fusion. Sensors 19(7):1733","journal-title":"Sensors"},{"key":"6091_CR22","doi-asserted-by":"crossref","unstructured":"Sharma, J., Granmo, O. C., & Goodwin, M. (2019). Environment sound classification using multiple feature channels and attention based deep convolutional neural network. arXiv preprint axXiv:1908.11219","DOI":"10.21437\/Interspeech.2020-1303"},{"key":"6091_CR23","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-319-63450-0_1","volume-title":"Computational analysis of sound scenes and events","year":"2018","unstructured":"Virtanen T, Plumbley MD, Ellis D (eds) (2018) Computational analysis of sound scenes and events. Springer, Heidelberg, pp 3\u201312"},{"issue":"4","key":"6091_CR24","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1016\/j.specom.2011.11.004","volume":"54","author":"M Sahidullah","year":"2012","unstructured":"Sahidullah M, Saha G (2012) Design, analysis and experimental evaluation of block based transformation in MFCC computation for speaker recognition. Speech Commun 54(4):543\u2013565","journal-title":"Speech Commun"},{"issue":"12","key":"6091_CR25","doi-asserted-by":"publisher","first-page":"2346","DOI":"10.1121\/1.1919362","volume":"36","author":"RN Shepard","year":"1964","unstructured":"Shepard RN (1964) Circularity in judgments of relative pitch. J Acoust Soc Am 36(12):2346\u20132353","journal-title":"J Acoust Soc Am"},{"key":"6091_CR26","unstructured":"Paulus J, M\u00fcller M, Klapuri A (2010) State of the art report: audio-based music structure analysis. In: Ismir, pp 625\u2013636"},{"key":"6091_CR27","unstructured":"Glorot X, Bordes A, Bengio Y (2011) Deep sparse rectifier neural networks. In: Proceedings of the fourteenth international conference on artificial intelligence and statistics. JMLR workshop and conference proceedings, pp 315\u2013323"},{"key":"6091_CR28","unstructured":"Hinton, G. E., Srivastava, N., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. R. (2012). Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint axXiv:1207.0580"},{"issue":"4","key":"6091_CR29","first-page":"1387","volume":"9","author":"SH Jung","year":"2020","unstructured":"Jung SH, Chung YJ (2020) Performance analysis of the convolutional recurrent neural network on acoustic event detection. Bull Electr Eng and Info 9(4):1387\u20131393","journal-title":"Bull Electr Eng and Info"},{"key":"6091_CR30","doi-asserted-by":"crossref","unstructured":"Lezhenin I, Bogach N, Pyshkin E (2019) Urban sound classification using long short-term memory neural network. In: 2019 federated conference on computer science and information systems (FedCSIS), pp 57\u201360. IEEE","DOI":"10.15439\/2019F185"},{"key":"6091_CR31","doi-asserted-by":"crossref","unstructured":"Salamon J, Jacoby C, Bello JP (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"},{"key":"6091_CR32","doi-asserted-by":"crossref","unstructured":"Tokozume, Y, Harada T (2017) Learning environmental sounds with end-to-end convolutional neural network. In: 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 2721\u20132725). IEEE","DOI":"10.1109\/ICASSP.2017.7952651"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-06091-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-021-06091-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-06091-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,24]],"date-time":"2021-10-24T06:16:35Z","timestamp":1635056195000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-021-06091-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,26]]},"references-count":32,"journal-issue":{"issue":"21","published-print":{"date-parts":[[2021,11]]}},"alternative-id":["6091"],"URL":"https:\/\/doi.org\/10.1007\/s00521-021-06091-7","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,26]]},"assertion":[{"value":"25 July 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 April 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 May 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declaration"}},{"value":"We have no conflicts of interest to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}