{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T17:43:40Z","timestamp":1778694220140,"version":"3.51.4"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10448050","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"8816-8820","source":"Crossref","is-referenced-by-count":15,"title":["Fusion of Audio and Visual Embeddings for Sound Event Localization and Detection"],"prefix":"10.1109","author":[{"given":"Davide","family":"Berghi","sequence":"first","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,U.K"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peipei","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,U.K"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinzheng","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,U.K"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenwu","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,U.K"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philip J. B.","family":"Jackson","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,U.K"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2885636"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.33682\/1xwd-5v76"},{"key":"ref3","article-title":"STARSS23: An audio-visual dataset of spatial recordings of real scenes with spatiotemporal annotations of sound events","author":"Shimada","year":"2023"},{"key":"ref4","article-title":"Audio-visual speaker tracking: Progress, challenges, and future directions","author":"Zhao","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746872"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.33682\/4jhy-bj81"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3173054"},{"key":"ref8","article-title":"The USTC-iFlytek system for sound event localization and detection of DCASE2020 challenge technical report","author":"Wang","year":"2020","journal-title":"Tech. Rep. of DCASE Challenge"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413473"},{"key":"ref10","article-title":"PLDISET: Probabilistic localization and detection of independent sound events with transformers","volume-title":"DCASE Workshop","author":"Wu"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3256088"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP39728.2021.9413473","article-title":"Event-independent network for polyphonic sound event localization and detection","volume-title":"DCASE Workshop","author":"Cao"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746132"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746384"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3226330"},{"key":"ref19","article-title":"Audio-visual sound event localization and detection based on CRNN using depth-wise separable convolution","author":"Wang","year":"2023","journal-title":"Tech. Report of DCASE Challenge"},{"key":"ref20","article-title":"The NERC-SLIP system for sound event localization and detection of DCASE2023 challenge","author":"Wang","year":"2023","journal-title":"Tech. Report of DCASE Challenge"},{"key":"ref21","article-title":"The distillation system for sound event localization and detection of DCASE2023 challenge","author":"Kang","year":"2023","journal-title":"Tech. Report of DCASE Challenge"},{"key":"ref22","article-title":"Data augmentation, neural networks, and ensemble methods for sound event localization and detection","author":"Kim","year":"2023","journal-title":"Tech. Report of DCASE Challenge"},{"key":"ref23","article-title":"Attention is all you need","volume-title":"Int. Conf. on Neural Information Processing Systems","author":"Vaswani"},{"key":"ref24","article-title":"STARSS22: A dataset of spatial recordings of real scenes with spatiotemporal annotations of sound events","volume-title":"DCASE Workshop","author":"Politis"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10448050.pdf?arnumber=10448050","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T06:40:44Z","timestamp":1722580844000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448050\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448050","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}