{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,9]],"date-time":"2025-11-09T03:51:49Z","timestamp":1762660309546},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"36","license":[{"start":{"date-parts":[[2023,2,20]],"date-time":"2023-02-20T00:00:00Z","timestamp":1676851200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,2,20]],"date-time":"2023-02-20T00:00:00Z","timestamp":1676851200000},"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":["Neural Comput & Applic"],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1007\/s00521-023-08351-0","type":"journal-article","created":{"date-parts":[[2023,2,23]],"date-time":"2023-02-23T17:14:45Z","timestamp":1677172485000},"page":"25013-25026","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Intelligent recognition of audio scene based on hybrid attention and parallel deep feature processing under genetic evolutionary computing"],"prefix":"10.1007","volume":"35","author":[{"given":"Danyang","family":"Li","sequence":"first","affiliation":[]},{"given":"Chunlei","family":"Jia","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,2,20]]},"reference":[{"issue":"1","key":"8351_CR1","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1080\/00016489.2021.1888504","volume":"141","author":"A Dhanasingh","year":"2021","unstructured":"Dhanasingh A, Hochmair I (2021) Signal processing & audio processors. Acta Otolaryngol 141(1):106\u2013134","journal-title":"Acta Otolaryngol"},{"issue":"2","key":"8351_CR2","doi-asserted-by":"publisher","first-page":"693","DOI":"10.32604\/iasc.2022.019811","volume":"31","author":"R Kumar","year":"2022","unstructured":"Kumar R, Gupta M, Ahmed S et al (2022) Intelligent audio signal processing for detecting rainforest species using deep learning. Intell Autom Soft Comput 31(2):693\u2013706","journal-title":"Intell Autom Soft Comput"},{"issue":"1","key":"8351_CR3","doi-asserted-by":"publisher","first-page":"1251","DOI":"10.1109\/TITS.2022.3179024","volume":"24","author":"J Pei","year":"2022","unstructured":"Pei J, Zhong K, Li J et al (2022) PAC: Partial area clustering for re-adjusting the layout of traffic stations in city\u2019s public transport. IEEE Transactions on Intelligent Transportation Systems\u00a024(1):1251\u20131260","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"issue":"4","key":"8351_CR4","doi-asserted-by":"publisher","first-page":"913","DOI":"10.1007\/s10772-020-09681-3","volume":"24","author":"J Chaki","year":"2021","unstructured":"Chaki J (2021) Pattern analysis based acoustic signal processing: a survey of the state-of-art. Int J Speech Technol 24(4):913\u2013955","journal-title":"Int J Speech Technol"},{"key":"8351_CR5","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2022.856232","volume":"5","author":"S Amiriparian","year":"2022","unstructured":"Amiriparian S, H\u00fcbner T, Karas V et al (2022) DeepSpectrumLite: a power-efficient transfer learning framework for embedded speech and audio processing from decentralized data. Front Artif Intell 5:856232","journal-title":"Front Artif Intell"},{"key":"8351_CR6","doi-asserted-by":"publisher","first-page":"177863","DOI":"10.1109\/ACCESS.2020.3027474","volume":"8","author":"D Jiang","year":"2020","unstructured":"Jiang D, Huang D, Song Y et al (2020) An audio data representation for traffic acoustic scene recognition. IEEE Access 8:177863\u2013177873","journal-title":"IEEE Access"},{"issue":"3","key":"8351_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3322240","volume":"52","author":"S Chandrakala","year":"2019","unstructured":"Chandrakala S, Jayalakshmi SL (2019) Environmental audio scene and sound event recognition for autonomous surveillance: a survey and comparative studies. ACM Comput Surv 52(3):1\u201334","journal-title":"ACM Comput Surv"},{"issue":"5","key":"8351_CR8","doi-asserted-by":"publisher","first-page":"483","DOI":"10.3390\/electronics8050483","volume":"8","author":"S Aziz","year":"2019","unstructured":"Aziz S, Awais M, Akram T et al (2019) Automatic scene recognition through acoustic classification for behavioral robotics. Electronics 8(5):483","journal-title":"Electronics"},{"key":"8351_CR9","doi-asserted-by":"publisher","first-page":"2880","DOI":"10.1109\/TASLP.2020.3030497","volume":"28","author":"Q Kong","year":"2020","unstructured":"Kong Q, Cao Y, Iqbal T et al (2020) Panns: Large-scale pretrained audio neural networks for audio pattern recognition. IEEE\/ACM Trans Audio Speech Lang Process 28:2880\u20132894","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"issue":"14","key":"8351_CR10","doi-asserted-by":"publisher","first-page":"2707","DOI":"10.1016\/j.cub.2020.05.018","volume":"30","author":"O Woolnough","year":"2020","unstructured":"Woolnough O, Rollo PS, Forseth KJ et al (2020) Category selectivity for face and scene recognition in human medial parietal cortex. Curr Biol 30(14):2707\u20132715","journal-title":"Curr Biol"},{"key":"8351_CR11","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1016\/j.neucom.2019.05.024","volume":"357","author":"N Khan","year":"2019","unstructured":"Khan N, Chaudhuri U, Banerjee B et al (2019) Graph convolutional network for multi-label VHR remote sensing scene recognition. Neurocomputing 357:36\u201346","journal-title":"Neurocomputing"},{"issue":"1","key":"8351_CR12","doi-asserted-by":"publisher","first-page":"20","DOI":"10.3390\/technologies7010020","volume":"7","author":"E Spyrou","year":"2019","unstructured":"Spyrou E, Nikopoulou R, Vernikos I et al (2019) Emotion recognition from speech using the bag-of-visual words on audio segment spectrograms. Technologies 7(1):20","journal-title":"Technologies"},{"key":"8351_CR13","first-page":"2388697","volume":"2021","author":"S Sun","year":"2021","unstructured":"Sun S (2021) Digital audio scene recognition method based on machine learning technology. Sci Program 2021:2388697","journal-title":"Sci Program"},{"key":"8351_CR14","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/1178100","volume":"2022","author":"X Zhao","year":"2022","unstructured":"Zhao X (2022) Evaluation of multimedia popular music teaching effect based on audio frame feature recognition technology. Adv Multimed 2022:1178100","journal-title":"Adv Multimed"},{"key":"8351_CR15","doi-asserted-by":"publisher","first-page":"2392","DOI":"10.1109\/TMM.2021.3080076","volume":"24","author":"S Liu","year":"2021","unstructured":"Liu S, Tian G, Zhang Y et al (2021) Scene recognition mechanism for service robot adapting various families: a CNN-based approach using multi-type cameras. IEEE Trans Multimedia 24:2392\u20132406","journal-title":"IEEE Trans Multimedia"},{"key":"8351_CR16","unstructured":"Peltonen VTK, Eronen AJ, Parviainen MP et al (2001) Recognition of everyday auditory scenes: potentials, latencies and cues. Preprints-Audio Engineering Society, 1"},{"issue":"1","key":"8351_CR17","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1109\/TNN.2002.806626","volume":"14","author":"G Guo","year":"2003","unstructured":"Guo G, Li SZ (2003) Content-based audio classification and retrieval by support vector machines. IEEE Trans Neural Networks 14(1):209\u2013215","journal-title":"IEEE Trans Neural Networks"},{"issue":"12","key":"8351_CR18","doi-asserted-by":"publisher","first-page":"1224","DOI":"10.1016\/j.apacoust.2007.10.001","volume":"69","author":"J Tardieu","year":"2008","unstructured":"Tardieu J, Susini P, Poisson F et al (2008) Perceptual study of soundscapes in train stations. Appl Acoust 69(12):1224\u20131239","journal-title":"Appl Acoust"},{"key":"8351_CR19","doi-asserted-by":"crossref","unstructured":"Chu S, Narayanan S, Kuo CCJ (2008) Environmental sound recognition using MP-based features. In: IEEE international conference on acoustics, speech and signal processing. IEEE, pp 1\u20134","DOI":"10.1109\/ICASSP.2008.4517531"},{"issue":"2","key":"8351_CR20","doi-asserted-by":"publisher","first-page":"700","DOI":"10.1109\/TCE.2012.6227479","volume":"58","author":"K Hwang","year":"2012","unstructured":"Hwang K, Lee SY (2012) Environmental audio scene and activity recognition through mobile-based crowdsourcing. IEEE Trans Consum Electron 58(2):700\u2013705","journal-title":"IEEE Trans Consum Electron"},{"key":"8351_CR21","unstructured":"Li D, Tam J, Toub D (2013) Auditory scene classification using machine learning techniques. In: IEEE AASP challenge on detection and classification of acoustic scenes and events, 22"},{"key":"8351_CR22","unstructured":"Roma G, Nogueira W, Herrera P et al (2013) Recurrence quantification analysis features for auditory scene classification. In: IEEE AASP challenge on detection and classification of acoustic scenes and events, 2"},{"key":"8351_CR23","unstructured":"Bisot V, Serizel R, Essid S et al (2016) Supervised nonnegative matrix factorization for acoustic scene classification. In: IEEE international evaluation campaign on detection and classification of acoustic scenes and events (DCASE 2016)"},{"key":"8351_CR24","first-page":"5024","volume":"6","author":"H Eghbal-Zadeh","year":"2016","unstructured":"Eghbal-Zadeh H, Lehner B, Dorfer M et al (2016) CP-JKU submissions for DCASE-2016: a hybrid approach using binaural i-vectors and deep convolutional neural networks. IEEE AASP Chall Detect Classif Acoust Scenes Events 6:5024\u20135028","journal-title":"IEEE AASP Chall Detect Classif Acoust Scenes Events"},{"key":"8351_CR25","unstructured":"Lostanlen V, And\u00e9n J (2016) Binaural scene classification with wavelet scattering. In: Detection and classification of acoustic scenes and events 2016 (DCASE 2016) challenge, Technical Report, 1"},{"key":"8351_CR26","unstructured":"Han Y, Park J, Lee K (2017) Convolutional neural networks with binaural representations and background subtraction for acoustic scene classification. In: DCASE, pp 46\u201350"},{"key":"8351_CR27","unstructured":"Mun S, Park S, Han DK et al (2017) Generative adversarial network based acoustic scene training set augmentation and selection using SVM hyper-plane. In: DCASE, pp 93\u2013102"},{"key":"8351_CR28","unstructured":"Dorfer M, Lehner B, Eghbal-zadeh H et al (2018) Acoustic scene classification with fully convolutional neural networks and I-vectors. In: Proceedings of the detection and classification of acoustic scenes and events, 2018, 1"},{"key":"8351_CR29","unstructured":"Sakashita Y, Aono M (2018) Acoustic scene classification by ensemble of spectrograms based on adaptive temporal divisions. In: Detection and classification of acoustic scenes and events (DCASE) challenge, 1"},{"key":"8351_CR30","unstructured":"Koutini K, Eghbal-zadeh H, Widmer G et al (2019) CP-JKU submissions to DCASE\u201919: Acoustic scene classification and audio tagging with receptive-field-regularized CNNs. In: Proceedings of the detection and classification of acoustic scenes and events 2019 workshop (DCASE2019), pp 25\u201326"},{"key":"8351_CR31","unstructured":"Chen H, Liu Z, Liu Z et al (2019) Integrating the data augmentation scheme with various classifiers for acoustic scene modeling. arXiv preprint arXiv:1907.06639"},{"key":"8351_CR32","unstructured":"Hu H, Yang C H H, Xia X et al (2020) Device-robust acoustic scene classification based on two-stage categorization and data augmentation. arXiv preprint arXiv:2007.08389"},{"key":"8351_CR33","unstructured":"Suh S, Park S, Jeong Y et al (2020) Designing acoustic scene classification models with CNN variants. Technical Report, DCASE2020 Challenge, 1"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-08351-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-023-08351-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-08351-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T15:05:16Z","timestamp":1701270316000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-023-08351-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,20]]},"references-count":33,"journal-issue":{"issue":"36","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["8351"],"URL":"https:\/\/doi.org\/10.1007\/s00521-023-08351-0","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,20]]},"assertion":[{"value":"15 November 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 January 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 February 2023","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 conflict of interest exists.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}