{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,24]],"date-time":"2026-05-24T00:09:35Z","timestamp":1779581375050,"version":"3.53.1"},"reference-count":71,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"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":[[2026,6]]},"DOI":"10.1016\/j.asoc.2026.115021","type":"journal-article","created":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:26:37Z","timestamp":1773246397000},"page":"115021","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Learning with guidance: Auxiliary supervision and feature enhancement for sound event localization and detection"],"prefix":"10.1016","volume":"196","author":[{"given":"Yufei","family":"Lu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8964-9759","authenticated-orcid":false,"given":"Jianguo","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhuan","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7644-0518","authenticated-orcid":false,"given":"Ruiteng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongwen","family":"Ying","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6605-2052","authenticated-orcid":false,"given":"Masashi","family":"Unoki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.asoc.2026.115021_bib0005","doi-asserted-by":"crossref","first-page":"684","DOI":"10.1109\/TASLP.2020.3047233","article-title":"Overview and evaluation of sound event localization and detection in Dcase 2019","volume":"29","author":"Politis","year":"2021","journal-title":"IEEE\/ACM Trans. Audio, Speech, Language Process."},{"key":"10.1016\/j.asoc.2026.115021_bib0010","doi-asserted-by":"crossref","first-page":"984","DOI":"10.1109\/TASLP.2023.3346643","article-title":"Leveraging visual supervision for array-based active speaker detection and localization","volume":"32","author":"Berghi","year":"2024","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.asoc.2026.115021_bib0015","series-title":"Proc. IEEE Cloud Summit","first-page":"65","article-title":"A novel method for recognition, localization, and alarming to prevent swimmers from drowning","author":"Liu","year":"2019"},{"key":"10.1016\/j.asoc.2026.115021_bib0020","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1109\/TITS.2015.2470216","article-title":"Audio surveillance of roads: a system for detecting anomalous sounds","volume":"17","author":"Foggia","year":"2016","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.asoc.2026.115021_bib0025","doi-asserted-by":"crossref","first-page":"6794","DOI":"10.1002\/ece3.6216","article-title":"Acoustic localization of terrestrial wildlife: current practices and future opportunities","volume":"10","author":"Rhinehart","year":"2020","journal-title":"Ecol. Evol."},{"key":"10.1016\/j.asoc.2026.115021_bib0030","doi-asserted-by":"crossref","first-page":"1251","DOI":"10.1109\/TASLP.2023.3256088","article-title":"A four-stage data augmentation approach to resnet-conformer based acoustic modeling for sound event localization and detection","volume":"31","author":"Wang","year":"2023","journal-title":"IEEE\/ACM Trans. Audio, Speech, Language Process."},{"key":"10.1016\/j.asoc.2026.115021_bib0035","series-title":"Proc. IEEE 20th Eur. Signal Process. Conf","first-page":"1673","article-title":"Daily sound recognition using a combination of GMM and SVM for home Automation","author":"Sehili","year":"2012"},{"key":"10.1016\/j.asoc.2026.115021_bib0040","series-title":"Proc. IEEE 18th Eur. Signal Process. Conf","first-page":"1267","article-title":"Acoustic event detection in real life recordings","author":"Mesaros","year":"2010"},{"key":"10.1016\/j.asoc.2026.115021_bib0045","series-title":"Proc. IEEE 19th Eur. Signal Process. Conf","first-page":"1317","article-title":"Two-source acoustic event detection and localization: online implementation in a smart-room","author":"Butko","year":"2011"},{"key":"10.1016\/j.asoc.2026.115021_bib0050","series-title":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"559","article-title":"Robust sound event recognition using convolutional neural networks","author":"Zhang","year":"2015"},{"key":"10.1016\/j.asoc.2026.115021_bib0055","series-title":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"6440","article-title":"Recurrent neural networks for polyphonic sound event detection in real life recordings","author":"Parascandolo","year":"2016"},{"key":"10.1016\/j.asoc.2026.115021_bib0060","series-title":"Proc. Interspeech 2021","first-page":"571","article-title":"Ast: audio spectrogram transformer","author":"Gong","year":"2021"},{"key":"10.1016\/j.asoc.2026.115021_bib0065","series-title":"ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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.2026.115021_bib0070","series-title":"Interspeech","first-page":"1479","article-title":"Time delay estimation for speaker localization using Cnn-based parametrized gcc-phat features","author":"Salvati","year":"2021"},{"key":"10.1016\/j.asoc.2026.115021_bib0075","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1109\/TAP.1986.1143830","article-title":"Multiple emitter location and signal parameter estimation","volume":"34","author":"Schmidt","year":"1986","journal-title":"IEEE Trans. Antennas Propag."},{"key":"10.1016\/j.asoc.2026.115021_bib0080","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/j.patrec.2022.11.022","article-title":"Learning based method for near field acoustic range estimation in spherical harmonics domain using intensity vectors","volume":"165","author":"Dwivedi","year":"2023","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.asoc.2026.115021_bib0085","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1109\/JSTSP.2019.2900164","article-title":"Crnn-based multiple doa estimation using acoustic intensity features for ambisonics recordings","volume":"13","author":"Perotin","year":"2019","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"10.1016\/j.asoc.2026.115021_bib0090","series-title":"2021 IEEE\/SICE International Symposium on System Integration (SII)","first-page":"382","article-title":"Multi-channel environmental sound segmentation utilizing sound source localization and separation u-net","author":"Sudo","year":"2021"},{"key":"10.1016\/j.asoc.2026.115021_bib0095","series-title":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"4680","article-title":"Sslide: sound source localization for indoors based on deep learning","author":"Wu","year":"2021"},{"key":"10.1016\/j.asoc.2026.115021_bib0100","doi-asserted-by":"crossref","first-page":"1620","DOI":"10.1109\/TASLP.2020.2990485","article-title":"The Locata Challenge: acoustic source localization and tracking","volume":"28","author":"Evers","year":"2020","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.asoc.2026.115021_bib0105","doi-asserted-by":"crossref","first-page":"2122","DOI":"10.1109\/TASLP.2018.2855960","article-title":"Robust binaural localization of a target sound source by combining spectral source models and deep neural networks","volume":"26","author":"Ma","year":"2018","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.asoc.2026.115021_bib0110","series-title":"Proc. IEEE Int. Conf. Acoust, Speech Signal Process","first-page":"1","article-title":"The nercslip-Ustc system for the l3das23 Challenge task2: 3d sound event localization and detection (seld)","author":"Yan","year":"2023"},{"key":"10.1016\/j.asoc.2026.115021_bib0115","series-title":"Proc. IEEE Int. Conf. Acoust, Speech Signal Process","first-page":"1","article-title":"Ad-Yolo: you look only once in training multiple sound event localization and detection","author":"Kim","year":"2023"},{"key":"10.1016\/j.asoc.2026.115021_bib0120","series-title":"Proc. Detect. Classification Acoust. Scenes Events Workshop","first-page":"30","article-title":"Polyphonic sound event detection and localization using a two-stage strategy","author":"Cao","year":"2019"},{"key":"10.1016\/j.asoc.2026.115021_bib0125","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1109\/JSTSP.2018.2885636","article-title":"Sound event localization and detection of overlapping sources using convolutional recurrent neural networks","volume":"13","author":"Adavanne","year":"2019","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"10.1016\/j.asoc.2026.115021_bib0130","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1109\/TASLP.2017.2778423","article-title":"Detection and classification of acoustic scenes and events: outcome of the Dcase 2016 challenge","volume":"26","author":"Mesaros","year":"2017","journal-title":"IEEE\/ACM Trans. Audio, Speech, Language Process."},{"key":"10.1016\/j.asoc.2026.115021_bib0135","author":"Nguyen"},{"key":"10.1016\/j.asoc.2026.115021_bib0140","series-title":"Proc. IEEE Int. Conf. Acoust, Speech Signal Process","first-page":"1","article-title":"An experimental study on sound event localization and detection under realistic testing conditions","author":"Niu","year":"2023"},{"key":"10.1016\/j.asoc.2026.115021_bib0145","series-title":"Proc. IEEE Int. Conf. Acoust, Speech Signal Process","first-page":"1","article-title":"Loss function design for Dnn-based sound event localization and detection on low-resource realistic data","author":"Wang","year":"2023"},{"key":"10.1016\/j.asoc.2026.115021_bib0150","series-title":"Proc. IEEE Int. Conf. Acoust, Speech Signal Process","first-page":"9196","article-title":"A track-wise ensemble event independent network for polyphonic sound event localization and detection","author":"Hu","year":"2022"},{"key":"10.1016\/j.asoc.2026.115021_bib0155","series-title":"Proc. IEEE Int. Conf. Acoust, Speech Signal Process","first-page":"915","article-title":"Accdoa: activity-coupled cartesian direction of arrival representation for sound event localization and detection","author":"Shimada","year":"2021"},{"key":"10.1016\/j.asoc.2026.115021_bib0160","series-title":"Proc. IEEE Int. Conf. Acoust, Speech Signal Process","first-page":"316","article-title":"Multi-accdoa: localizing and detecting overlapping sounds from the same class with auxiliary duplicating permutation invariant training","author":"Shimada","year":"2022"},{"key":"10.1016\/j.asoc.2026.115021_bib0165","doi-asserted-by":"crossref","first-page":"4313","DOI":"10.1109\/TASLP.2024.3451974","article-title":"Selective-memory meta-learning with environment representations for sound event localization and detection","volume":"32","author":"Hu","year":"2024","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.asoc.2026.115021_bib0170","doi-asserted-by":"crossref","first-page":"2845","DOI":"10.1109\/TASLPRO.2025.3587446","article-title":"PSELDNets: pre-trained neural networks on a large-scale synthetic dataset for sound event localization and detection","volume":"33","author":"Hu","year":"2025","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.asoc.2026.115021_bib0175","series-title":"Proc. IEEE Int. Conf. Acoust, Speech Signal Process","first-page":"8686","article-title":"Cst-former: transformer with channel-spectro-temporal attention for sound event localization and detection","author":"Shul","year":"2024"},{"key":"10.1016\/j.asoc.2026.115021_bib0180","author":"Shul"},{"key":"10.1016\/j.asoc.2026.115021_bib0185","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10489-024-06062-0","article-title":"Fa3-net: feature aggregation and augmentation with attention network for sound event localization and detection","volume":"55","author":"Wang","year":"2025","journal-title":"Appl. Intell."},{"key":"10.1016\/j.asoc.2026.115021_bib0190","article-title":"Starss23: an audio-visual dataset of spatial recordings of real scenes with spatiotemporal annotations of sound events","volume":"36","author":"Shimada","year":"2024","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"10.1016\/j.asoc.2026.115021_bib0195","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1121\/10.0011809","article-title":"A survey of sound source localization with deep learning methods","volume":"152","author":"Grumiaux","year":"2022","journal-title":"J. Acoust. Soc. Am."},{"key":"10.1016\/j.asoc.2026.115021_bib0200","series-title":"2020 28th European Signal Processing Conference (EUSIPCO)","first-page":"16","article-title":"Seld-tcn: sound event localization & detection via temporal convolutional networks","author":"Guirguis","year":"2021"},{"key":"10.1016\/j.asoc.2026.115021_bib0205","doi-asserted-by":"crossref","first-page":"109157","DOI":"10.1109\/ACCESS.2024.3438947","article-title":"Feature aggregation in joint sound classification and localization neural networks","volume":"12","author":"Healy","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.asoc.2026.115021_bib0210","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"9197","article-title":"Panet: few-shot image semantic segmentation with prototype alignment","author":"Wang","year":"2019"},{"key":"10.1016\/j.asoc.2026.115021_bib0215","series-title":"Proc. IEEE Int. Conf. Acoust, Speech Signal Process","first-page":"9191","article-title":"Icassp 2022 l3das22 challenge: ensemble of resnet-conformers with ambisonics data augmentation for sound event localization and detection","author":"Mao","year":"2022"},{"key":"10.1016\/j.asoc.2026.115021_bib0220","series-title":"Conformer-Based Sound Event Detection with Semi-Supervised Learning and Data Augmentation","author":"Miyazaki","year":"2022"},{"key":"10.1016\/j.asoc.2026.115021_bib0225","series-title":"Proc. Interspeech","first-page":"5036","article-title":"Conformer: convolution-augmented transformer for speech recognition","author":"Gulati","year":"2020"},{"key":"10.1016\/j.asoc.2026.115021_bib0230","doi-asserted-by":"crossref","first-page":"A256","DOI":"10.1121\/10.0023458","article-title":"Divided spectro-temporal transformer for sound event localization and detection in real scenes","volume":"154","author":"Shul","year":"2023","journal-title":"J. Acoust. Soc. Am."},{"key":"10.1016\/j.asoc.2026.115021_bib0235","first-page":"1","article-title":"A sound event localization and detection research based on inception depth-wise convolution and adaptive efficient channel attention block","author":"Qiu","year":"2025","journal-title":"Circ. Syst. Signal Process."},{"key":"10.1016\/j.asoc.2026.115021_bib0240","series-title":"Proc. Interspeech","first-page":"92","article-title":"Mff-einv2: multi-scale feature fusion across spectral-spatial-temporal domains for sound event localization and detection","author":"Mu","year":"2024"},{"key":"10.1016\/j.asoc.2026.115021_bib0245","doi-asserted-by":"crossref","first-page":"6479","DOI":"10.3390\/s25206479","article-title":"Msfdnet: a multi-scale feature dual-layer fusion model for sound event localization and detection","volume":"25","author":"Chen","year":"2025","journal-title":"Sensors"},{"key":"10.1016\/j.asoc.2026.115021_bib0250","article-title":"Self-supervised generalisation with meta auxiliary learning","volume":"32","author":"Liu","year":"2019","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"10.1016\/j.asoc.2026.115021_bib0255","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"94","article-title":"Facial landmark detection by deep multi-task learning","author":"Zhang","year":"2014"},{"key":"10.1016\/j.asoc.2026.115021_bib0260","doi-asserted-by":"crossref","first-page":"2424","DOI":"10.1109\/TITS.2023.3319556","article-title":"Monocular 3d object detection utilizing auxiliary learning with deformable convolution","volume":"25","author":"Chen","year":"2023","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.asoc.2026.115021_bib0265","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"1810","article-title":"Learning auxiliary monocular contexts helps monocular 3d object detection","volume":"vol. 36","author":"Liu","year":"2022"},{"key":"10.1016\/j.asoc.2026.115021_bib0270","article-title":"Distributed representations of words and phrases and their compositionality","volume":"26","author":"Mikolov","year":"2013","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"10.1016\/j.asoc.2026.115021_bib0275","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1109\/TETCI.2020.3040444","article-title":"Auxiliary learning for relation extraction","volume":"6","author":"Lyu","year":"2020","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"10.1016\/j.asoc.2026.115021_bib0280","author":"Burda"},{"key":"10.1016\/j.asoc.2026.115021_bib0285","author":"Liebel"},{"key":"10.1016\/j.asoc.2026.115021_bib0290","series-title":"An Introduction to Higher Order Ambisonic","author":"Hollerweger","year":"2008"},{"key":"10.1016\/j.asoc.2026.115021_bib0295","series-title":"The Thirteenth International Conference on Learning Representations","article-title":"Differential transformer","author":"Ye","year":"2025"},{"key":"10.1016\/j.asoc.2026.115021_bib0300","series-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.asoc.2026.115021_bib0305","article-title":"Root mean square layer normalization","volume":"32","author":"Zhang","year":"2019","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"10.1016\/j.asoc.2026.115021_bib0310","series-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS\u201917","first-page":"6000","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.asoc.2026.115021_bib0315","series-title":"Proc. IEEE Int. Conf. Acoust, Speech Signal Process","first-page":"241","article-title":"Permutation invariant training of deep models for speaker-independent multi-talker speech separation","author":"Yu","year":"2017"},{"key":"10.1016\/j.asoc.2026.115021_bib0320","series-title":"Proc. IEEE Int. Conf. Acoust, Speech Signal Process","first-page":"6369","article-title":"Interrupted and cascaded permutation invariant training for speech separation","author":"Yang","year":"2020"},{"key":"10.1016\/j.asoc.2026.115021_bib0325","author":"Politis"},{"key":"10.1016\/j.asoc.2026.115021_bib0330","series-title":"Proc. Int. Conf. Learn. Represent","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2015"},{"key":"10.1016\/j.asoc.2026.115021_bib0335","series-title":"Proc. IEEE Workshop Appl. Signal Process Audio Acoust","first-page":"333","article-title":"Joint measurement of localization and detection of sound events","author":"Mesaros","year":"2019"},{"key":"10.1016\/j.asoc.2026.115021_bib0340","series-title":"Proceedings of the 6th Detection and Classification of Acoustic Scenes and Events 2021 Workshop (DCASE2021)","first-page":"125","article-title":"A dataset of dynamic reverberant sound scenes with directional interferers for sound event localization and detection","author":"Politis","year":"2021"},{"key":"10.1016\/j.asoc.2026.115021_bib0345","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"3","article-title":"CBAM: convolutional block attention module","author":"Woo","year":"2018"},{"key":"10.1016\/j.asoc.2026.115021_bib0350","series-title":"2021 IEEE Winter Conference on Applications of Computer Vision (WACV)","first-page":"3138","article-title":"Rotate to attend: convolutional triplet attention module","author":"Misra","year":"2021"},{"key":"10.1016\/j.asoc.2026.115021_bib0355","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"13713","article-title":"Coordinate attention for efficient mobile network design","author":"Hou","year":"2021"}],"container-title":["Applied Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626004692?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626004692?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,23]],"date-time":"2026-05-23T23:36:12Z","timestamp":1779579372000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1568494626004692"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":71,"alternative-id":["S1568494626004692"],"URL":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115021","relation":{},"ISSN":["1568-4946"],"issn-type":[{"value":"1568-4946","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Learning with guidance: Auxiliary supervision and feature enhancement for sound event localization and detection","name":"articletitle","label":"Article Title"},{"value":"Applied Soft Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115021","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"115021"}}