{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T08:47:01Z","timestamp":1778575621905,"version":"3.51.4"},"reference-count":37,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Applied Soft Computing"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1016\/j.asoc.2025.114192","type":"journal-article","created":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T15:57:21Z","timestamp":1762617441000},"page":"114192","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"PD","title":["Enhancing environmental sound classification with weighted attention-based spectrogram fusion and overlapping pre-patching"],"prefix":"10.1016","volume":"186","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8252-7513","authenticated-orcid":false,"given":"Krishna","family":"Presannakumar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anuj","family":"Mohamed","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.asoc.2025.114192_bib0005","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1016\/j.apacoust.2018.12.019","article-title":"Environmental sound classification with dilated convolutions","volume":"148","author":"Chen","year":"2019","journal-title":"Appl. Acoust."},{"key":"10.1016\/j.asoc.2025.114192_bib0010","first-page":"1","article-title":"Chapter 1 - background introduction","author":"Wang","year":"2020"},{"key":"10.1016\/j.asoc.2025.114192_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.apacoust.2020.107413","article-title":"An automated environmental sound classification methods based on statistical and textural feature","volume":"167","author":"Akbal","year":"2020","journal-title":"Appl. Acoust."},{"issue":"22","key":"10.1016\/j.asoc.2025.114192_bib0020","doi-asserted-by":"crossref","first-page":"27044","DOI":"10.1007\/s10489-023-04973-y","article-title":"Source identification of weak audio signals using attention based convolutional neural network","volume":"53","author":"Presannakumar","year":"2023","journal-title":"Applied Intell."},{"key":"10.1016\/j.asoc.2025.114192_bib0025","doi-asserted-by":"crossref","first-page":"79750","DOI":"10.1109\/ACCESS.2023.3298955","article-title":"Innovative feature selection method based on hybrid sine cosine and dipper throated optimization algorithms","volume":"11","author":"Abdelhamid","year":"2023","journal-title":"IEEE Access"},{"key":"10.1016\/j.asoc.2025.114192_bib0030","series-title":"Ast: Audio Spectrogram Transformer","author":"Gong","year":"2021"},{"key":"10.1016\/j.asoc.2025.114192_bib0035","series-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"579","article-title":"Incorporating convolution designs into visual transformers","author":"Yuan","year":"2021"},{"key":"10.1016\/j.asoc.2025.114192_bib0040","article-title":"Tiny transformers for environmental sound classification at the edge","author":"Elliott","year":"2021","journal-title":"IEEE J. Internet Things"},{"key":"10.1016\/j.asoc.2025.114192_bib0045","series-title":"Interspeech 2022","article-title":"SepTr: separable transformer for audio spectrogram processing","author":"Ristea","year":"2022"},{"key":"10.1016\/j.asoc.2025.114192_bib0050","article-title":"Multi-modal medical image fusion framework using co-occurrence filter and local extrema in NSST domain","volume":"68","author":"Zhang","year":"2021","journal-title":"Biomed. Signal Process. Control"},{"issue":"1","key":"10.1016\/j.asoc.2025.114192_bib0055","doi-asserted-by":"crossref","first-page":"502","DOI":"10.1109\/TPAMI.2020.3012548","article-title":"U2Fusion: a unified unsupervised image fusion network (an end-to-end content-aware generative adversarial network based method for multimodal medical image fusion)","volume":"44","author":"Xu","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.asoc.2025.114192_bib0060","first-page":"113","article-title":"Tsjnet: a multi-modality target and semantic awareness joint-driven image fusion network","volume":"86\u201387","author":"Tang","year":"2022","journal-title":"Inf. Fusion"},{"issue":"12","key":"10.1016\/j.asoc.2025.114192_bib0065","doi-asserted-by":"crossref","first-page":"9645","DOI":"10.1109\/TIM.2020.3005230","article-title":"Nestfuse: an infrared and visible image fusion architecture based on nest connection and spatial\/channel attention models (clustering based multi-modality medical image fusion)","volume":"69","author":"Li","year":"2020","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"10.1016\/j.asoc.2025.114192_bib0070","doi-asserted-by":"crossref","first-page":"2048","DOI":"10.1016\/j.procs.2017.08.250","article-title":"Classifying environmental sounds using image recognition networks","volume":"112","author":"Boddapati","year":"2017","journal-title":"Procedia Comput. Sci."},{"key":"10.1016\/j.asoc.2025.114192_bib0075","doi-asserted-by":"crossref","first-page":"125714","DOI":"10.1109\/ACCESS.2020.3007906","article-title":"Environment sound event classification with a two-stream convolutional neural network","volume":"8","author":"Dong","year":"2020","journal-title":"IEEE Access"},{"key":"10.1016\/j.asoc.2025.114192_bib0080","series-title":"IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"559","article-title":"Robust sound event recognition using convolutional neural networks","author":"Zhang","year":"2015"},{"key":"10.1016\/j.asoc.2025.114192_bib0085","series-title":"Chinese Conference on Pattern Recognition and Computer Vision (PRCV)","first-page":"356","article-title":"Deep convolutional neural network with mixup for environmental sound classification","author":"Zhang","year":"2018"},{"key":"10.1016\/j.asoc.2025.114192_bib0090","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"10699","article-title":"Ssast: self-supervised audio spectrogram transformer","author":"Gong","year":"2022"},{"key":"10.1016\/j.asoc.2025.114192_bib0095","first-page":"4907","article-title":"Domestic pig sound classification based on transformercnn","volume":"53","author":"Liao","year":"2023","journal-title":"Applied Intelligence"},{"key":"10.1016\/j.asoc.2025.114192_bib0100","series-title":"ICASSP 2022","first-page":"646","article-title":"Hts-at: a hierarchical token-semantic audio transformer for sound classification and detection","author":"Chen","year":"2022"},{"key":"10.1016\/j.asoc.2025.114192_bib0105","doi-asserted-by":"crossref","DOI":"10.1016\/j.ecoinf.2023.102001","article-title":"Transound: hyper-head attention transformer for birds sound recognition","volume":"75","author":"Tang","year":"2023","journal-title":"Ecol. Inform."},{"key":"10.1016\/j.asoc.2025.114192_bib0110","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","article-title":"ASiT: local-global audio spectrogram vision transformer for event classification","author":"Atito","year":"2022"},{"issue":"4","key":"10.1016\/j.asoc.2025.114192_bib0115","first-page":"347","article-title":"Sensor based EEG signal based dementia disease detection using artificial intelligence","volume":"27","author":"Babu","year":"2024","journal-title":"J. New Mater. Electrochem. Syst."},{"key":"10.1016\/j.asoc.2025.114192_bib0120","series-title":"2025 International Conference on Visual Analytics and Data Visualization (ICVADV)","first-page":"480","article-title":"Optimizing air pollution prediction in urban environments using a hybrid rnn-pbo model with IOT data","author":"Mohandas","year":"2025"},{"issue":"7","key":"10.1016\/j.asoc.2025.114192_bib0125","doi-asserted-by":"crossref","first-page":"1733","DOI":"10.3390\/s19071733","article-title":"Environment sound classification using a two-stream CNN based on decision-level fusion","volume":"19","author":"Su","year":"2019","journal-title":"Sensors"},{"key":"10.1016\/j.asoc.2025.114192_bib0130","series-title":"\u201cIOT with Smart Systems\u201d","first-page":"191","article-title":"\u201cpipeline for pre-processing of audio data\u201d","author":"Katti","year":"2023"},{"key":"10.1016\/j.asoc.2025.114192_bib0135","doi-asserted-by":"crossref","DOI":"10.1016\/j.apacoust.2020.107389","article-title":"Environmental sound classification using a regularized deep convolutional neural network with data augmentation","volume":"167","author":"Mushtaq","year":"2020","journal-title":"Appl. Acoust."},{"issue":"1","key":"10.1016\/j.asoc.2025.114192_bib0140","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10772-010-9066-0","article-title":"Blind separation of audio signals using trigonometric transforms and wavelet denoising","volume":"13","author":"Hammam","year":"2010","journal-title":"Int. J. Speech Technol."},{"key":"10.1016\/j.asoc.2025.114192_bib0145","series-title":"4th International Conference on Electronics and Signal Processing","first-page":"59","article-title":"An enhanced approach for environmental sound classification using multi-window augmentation","author":"Presannakumar","year":"2024"},{"key":"10.1016\/j.asoc.2025.114192_bib0150","doi-asserted-by":"crossref","first-page":"203655","DOI":"10.1109\/ACCESS.2020.3036769","article-title":"Drill fault diagnosis based on the scalogram and mel spectrogram of sound signals using artificial intelligence","volume":"8","author":"Tran","year":"2020","journal-title":"IEEE Access"},{"key":"10.1016\/j.asoc.2025.114192_bib0155","doi-asserted-by":"crossref","DOI":"10.1016\/j.apacoust.2019.107050","article-title":"Performance analysis of multiple aggregated acoustic features for environment sound classification","volume":"158","author":"Su","year":"2020","journal-title":"Appl. Acoust."},{"key":"10.1016\/j.asoc.2025.114192_bib0160","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2022.104555","article-title":"Cochleogram-based adventitious sounds classification using convolutional neural networks","volume":"82","author":"Mang","year":"2023","journal-title":"Biomed. Signal Process. Control"},{"key":"10.1016\/j.asoc.2025.114192_bib0165","doi-asserted-by":"crossref","first-page":"1901","DOI":"10.1016\/j.procs.2020.03.209","article-title":"Time-frequency representations: spectrogram, cochleogram and correlogram","volume":"167","author":"Chaurasiya","year":"2020","journal-title":"Procedia Comput. Sci."},{"issue":"12","key":"10.1016\/j.asoc.2025.114192_bib0170","doi-asserted-by":"crossref","first-page":"874","DOI":"10.1016\/j.specom.2007.05.003","article-title":"Exploiting correlogram structure for robust speech recognition with multiple speech sources","volume":"49","author":"Ma","year":"2007","journal-title":"Speech Communication"},{"key":"10.1016\/j.asoc.2025.114192_bib0175","series-title":"22nd ACM International Conference on Multimedia (ACM-MM\u201914)","first-page":"1041","article-title":"A dataset and taxonomy for urban sound research","author":"Salamon","year":"2014"},{"key":"10.1016\/j.asoc.2025.114192_bib0180","series-title":"2015 IEEE 25th International Workshop on Machine Learning for Signal Processing (MLSP)","first-page":"1","article-title":"Environmental sound classification with convolutional neural networks","author":"Piczak","year":"2015"},{"key":"10.1016\/j.asoc.2025.114192_bib0185","series-title":"Interspeech 2022","article-title":"MAE-AST: masked autoencoding audio spectrogram transformer","author":"Baade","year":"2022"}],"container-title":["Applied Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494625015054?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494625015054?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T20:47:29Z","timestamp":1765054049000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1568494625015054"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":37,"alternative-id":["S1568494625015054"],"URL":"https:\/\/doi.org\/10.1016\/j.asoc.2025.114192","relation":{},"ISSN":["1568-4946"],"issn-type":[{"value":"1568-4946","type":"print"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Enhancing environmental sound classification with weighted attention-based spectrogram fusion and overlapping pre-patching","name":"articletitle","label":"Article Title"},{"value":"Applied Soft Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.asoc.2025.114192","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114192"}}