{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T15:53:08Z","timestamp":1776181988588,"version":"3.50.1"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"\u201cCentro Nacional de Processamento de Alto Desempenho em S\u00e3o Paulo (CENAPAD-SP)\u201d"},{"DOI":"10.13039\/501100002322","name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior-Brasil","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100002322","id-type":"DOI","asserted-by":"crossref"}]},{"name":"S\u00e3o Paulo Research Foundation (FAPESP), Brasil","award":["2017\/08120-6"],"award-info":[{"award-number":["2017\/08120-6"]}]},{"name":"The Brazilian National Council for Scientific and Technological Development","award":["313047\/2022-7"],"award-info":[{"award-number":["313047\/2022-7"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3510453","type":"journal-article","created":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T18:41:02Z","timestamp":1733164862000},"page":"181553-181569","source":"Crossref","is-referenced-by-count":7,"title":["w2v-SELD: A Sound Event Localization and Detection Framework for Self-Supervised Spatial Audio Pre-Training"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3942-6418","authenticated-orcid":false,"given":"Orlem Lima Dos","family":"Santos","sequence":"first","affiliation":[{"name":"Department of Computer Engineering and Industrial Automation, University of Campinas, Campinas, Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8118-4213","authenticated-orcid":false,"given":"Karen","family":"Rosero","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, The University of Texas at Dallas, Richardson, TX, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2246-4450","authenticated-orcid":false,"given":"Bruno","family":"Masiero","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering and Industrial Automation, University of Campinas, Campinas, Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5652-0852","authenticated-orcid":false,"given":"Roberto","family":"de Alencar Lotufo","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering and Industrial Automation, University of Campinas, Campinas, Brazil"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.23919\/Eusipco47968.2020.9287716"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/PerComWorkshops59983.2024.10503381"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11050766"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/jzbg2020011"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3653018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2022.110067"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2885636"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.33682\/9f2t-ab23"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-024-05438-6"},{"key":"ref11","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Baevski"},{"key":"ref12","first-page":"5","article-title":"Sound event localization and detection with pre-trained audio spectrogram transformer and multichannel separation network","volume":"13","author":"Scheibler","year":"2022","journal-title":"OMNI (1ch)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095687"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3256088"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747283"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094681"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3284525"},{"key":"ref18","first-page":"1","article-title":"The USTC-IFLYTEK system for sound event localization and detection of DCASE 2020 challenge","author":"Wang","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413609"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.23919\/Eusipco47968.2020.9287224"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-124"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447181"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747814"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095036"},{"key":"ref29","first-page":"3","article-title":"The challenge of realistic music generation: Modelling raw audio at scale","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dieleman"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-17207-7"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1673"},{"key":"ref35","first-page":"3","article-title":"SSELDNet: A fully end-to-end sample-level framework for sound event localization and detection","volume-title":"Proc. DCASE","author":"Huang"},{"key":"ref36","article-title":"DVC: Data version control-git for data & models (2.3. 0)","author":"Kuprieiev","year":"2021"},{"key":"ref37","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref38","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP52302.2021.9596248"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746872"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.33682\/1xwd-5v76"},{"key":"ref44","article-title":"A dataset of reverberant spatial sound scenes with moving sources for sound event localization and detection","author":"Politis","year":"2020","journal-title":"arXiv:2006.01919"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3390\/app6060162"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1121\/1.4981118"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10772471.pdf?arnumber=10772471","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,12]],"date-time":"2024-12-12T06:37:33Z","timestamp":1733985453000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10772471\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3510453","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}