{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T00:46:30Z","timestamp":1793148390288,"version":"4.5.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9413473","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"885-889","source":"Crossref","is-referenced-by-count":72,"title":["An Improved Event-Independent Network for Polyphonic Sound Event Localization and Detection"],"prefix":"10.1109","author":[{"given":"Yin","family":"Cao","sequence":"first","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Turab","family":"Iqbal","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiuqiang","family":"Kong","sequence":"additional","affiliation":[{"name":"ByteDance,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fengyan","family":"An","sequence":"additional","affiliation":[{"name":"Qingdao University of Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenwu","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark D.","family":"Plumbley","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1206"},{"key":"ref10","first-page":"11","article-title":"Event-independent network for polyphonic sound event localization and detection","author":"cao","year":"2020","journal-title":"Proc DCASE 2020 Workshop"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref13","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref14","article-title":"Efficient Transformers: A Survey","author":"tay","year":"2020","journal-title":"arXiv preprint arXiv 2009 02026"},{"key":"ref15","article-title":"An Overview of Multi-Task Learning In Deep Neural Networks","author":"ruder","year":"2017","journal-title":"arXiv preprint arXiv 1706 05098"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.433"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/app6060162"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3047233"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937220"},{"key":"ref28","first-page":"527","article-title":"Multi-task learning as multi-objective optimization","volume":"31","author":"sener","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.33682\/53ed-z889"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00391"},{"key":"ref3","first-page":"2","author":"bishop","year":"2006","journal-title":"Pattern Recognition and Machine Learning"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.33682\/1xwd-5v76"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.126"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2272524"},{"key":"ref8","first-page":"165","article-title":"A dataset of reverberant spatial sound scenes with moving sources for sound event localization and detection","author":"politis","year":"2020","journal-title":"Proc DCASE 2020 Workshop"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2885636"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63450-0_1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.33682\/4jhy-bj81"},{"key":"ref1","first-page":"157","author":"brandstein","year":"2013","journal-title":"Microphone Arrays Signal Processing Techniques and Applications"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.33682\/4v2a-7q02"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.33682\/3qgs-e216"},{"key":"ref21","first-page":"71","article-title":"A sequence matching network for polyphonic sound event localization and detection","author":"nguyen","year":"2020","journal-title":"Proc IEEE ICASSP 2020"},{"key":"ref24","article-title":"A survey on multi-task learning","author":"zhang","year":"2017","journal-title":"arXiv preprint arXiv 1707 08114"},{"key":"ref23","article-title":"Sound event localization and detection using activity-coupled cartesian DOA vector and RD3net","author":"shimada","year":"2020","journal-title":"arXiv preprint arXiv 2006 12661"},{"key":"ref26","article-title":"Learning general purpose distributed sentence representations via large scale multi-task learning","author":"subramanian","year":"2018","journal-title":"Proc ICLR 2018"},{"key":"ref25","first-page":"5771","article-title":"Learning to Multitask","author":"zhang","year":"2018","journal-title":"Advances in neural information processing systems"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09413473.pdf?arnumber=9413473","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:19:13Z","timestamp":1659485953000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413473\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413473","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}