{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T20:53:27Z","timestamp":1774558407384,"version":"3.50.1"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"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-037"}],"funder":[{"DOI":"10.13039\/501100011878","name":"Vlaamse regering","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011878","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Onderzoeksprogramma Artificiele Intelligentie (AI) Vlaanderen"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3651023","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:01:52Z","timestamp":1768255312000},"page":"2186-2200","source":"Crossref","is-referenced-by-count":0,"title":["Soundscape Captioning Using Sound Affective Quality Network and Large Language Model"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8469-5740","authenticated-orcid":false,"given":"Yuanbo","family":"Hou","sequence":"first","affiliation":[{"name":"Department of Information Technology, WAVES Research Group, Ghent University, Gent, Belgium"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5561-1747","authenticated-orcid":false,"given":"Qiaoqiao","family":"Ren","sequence":"additional","affiliation":[{"name":"AIRO-IDLab, Ghent University-Imec, Gent, Belgium"}]},{"given":"Andrew","family":"Mitchell","sequence":"additional","affiliation":[{"name":"University College London, London, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8393-5703","authenticated-orcid":false,"given":"Wenwu","family":"Wang","sequence":"additional","affiliation":[{"name":"CVSSP, University of Surrey, Guildford, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8995-5636","authenticated-orcid":false,"given":"Jian","family":"Kang","sequence":"additional","affiliation":[{"name":"University College London, London, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5207-7745","authenticated-orcid":false,"given":"Tony","family":"Belpaeme","sequence":"additional","affiliation":[{"name":"AIRO-IDLab, Ghent University-Imec, Gent, Belgium"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7756-7238","authenticated-orcid":false,"given":"Dick","family":"Botteldooren","sequence":"additional","affiliation":[{"name":"Department of Information Technology, WAVES Research Group, Ghent University, Gent, Belgium"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jenvp.2021.101660"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph16193533"},{"key":"ref3","article-title":"ISO 12913-1:2014 - Acoustics - Soundscape - Part 1: Definition and Conceptual Framework","year":"2014"},{"key":"ref4","article-title":"ISO 12913-3:2019 - Acoustics - Soundscape - Part 3: Data analysis","year":"2019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1121\/1.3493436"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1037\/h0077714"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446633"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63450-0"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2907016"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683627"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.33682\/m5kp-fa97"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3319233"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3323135"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170058"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref18","article-title":"ChatGPT","year":"2023"},{"key":"ref19","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref20","article-title":"ISO 532-1:2017","year":"2017"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3149712"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3430813"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3189536"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.361"},{"key":"ref25","article-title":"Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models","author":"Chu","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2024.176083"},{"key":"ref27","first-page":"2017","article-title":"On urban soundscape mapping: A computer can predict the outcome of soundscape assessments","volume-title":"Proc. Inter-Noise Noise-Con Congr.","author":"Lundn","year":"2016"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/EHB64556.2024.10805681"},{"key":"ref29","volume-title":"The International Affective Digitized Sounds Affective Ratings of Sounds and Instruction Manual","author":"Bradley","year":"2007"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3390\/app10072397"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1121\/10.0022408"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3247914"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1201\/b19145-9"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3109\/14992027.2013.876108"},{"key":"ref35","article-title":"ISO 12913-2 Acoustics Soundscape - Part 2: Data collection and reporting requirements","year":"2018"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00163"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3083283"},{"key":"ref38","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan","year":"2015"},{"key":"ref39","article-title":"Residual gated graph convnets","author":"Bresson","year":"2017"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3346998"},{"key":"ref42","first-page":"794","article-title":"Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen","year":"2018"},{"key":"ref43","first-page":"7482","article-title":"Multi-task learning using uncertainty to weigh losses for scene geometry and semantics","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Kendall","year":"2018"},{"key":"ref44","first-page":"1","article-title":"It\u2019s never too late: Fusing acoustic information into large language models for automatic speech recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.444"},{"key":"ref46","article-title":"Beyond fine-tuning: Effective strategies for mitigating hallucinations in large language models for data analytics","author":"Rumiantsau","year":"2024"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2017.7952261"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref49","first-page":"5407","article-title":"Urban soundscapes of the world: Selection and reproduction of urban acoustic environments with soundscape in mind","volume-title":"Proc. Inter-Noise","volume":"255","author":"Coensel","year":"2017"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6287886"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0306261"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.landurbplan.2015.05.004"},{"issue":"3","key":"ref56","first-page":"3137","article-title":"Soundscape assessment: Towards a validated translation of perceptual attributes in different languages","volume":"261","author":"Aletta","year":"2020","journal-title":"Int. Congr. Expo Noise Control Eng."},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1037\/\/0033-2909.86.2.420"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1038\/s44387-025-00048-0"},{"issue":"1","key":"ref59","doi-asserted-by":"crossref","first-page":"35","DOI":"10.7748\/nr.2025.e1958","volume":"3","author":"Mursa","year":"2025","journal-title":"Nurse Researcher"},{"issue":"1","key":"ref60","first-page":"142","volume":"23","author":"Rakotomamonjy","year":"2015","journal-title":"IEEE\/ACM Trans. Audio, Speech, Lang. Process."},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1121\/1.3567073"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.254"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11329491.pdf?arnumber=11329491","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T19:50:57Z","timestamp":1774554657000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11329491\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3651023","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}