{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T16:44:58Z","timestamp":1759941898522,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T00:00:00Z","timestamp":1698710400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T00:00:00Z","timestamp":1698710400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100005683","name":"Kyoto University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005683","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,31]]},"DOI":"10.1109\/apsipaasc58517.2023.10317433","type":"proceedings-article","created":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T14:07:46Z","timestamp":1700489266000},"page":"2061-2067","source":"Crossref","is-referenced-by-count":5,"title":["DOA-Aware Audio-Visual Self-Supervised Learning for Sound Event Localization and Detection"],"prefix":"10.1109","author":[{"given":"Yoto","family":"Fujita","sequence":"first","affiliation":[{"name":"Kyoto University,Graduate School of Informatics,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshiaki","family":"Bando","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keisuke","family":"Imoto","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masaki","family":"Onishi","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuyoshi","family":"Yoshii","sequence":"additional","affiliation":[{"name":"Kyoto University,Graduate School of Informatics,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21315"},{"journal-title":"TAU Spatial Room Impulse Response Database (TAU- SRIR DB)","year":"2022","author":"politis","key":"ref24"},{"key":"ref12","article-title":"A four-stage data augmentation approach to resnet-conformer based acoustic modeling for sound event localization and detection","volume":"abs 2101 2919","author":"wang","year":"2021","journal-title":"CoRR"},{"key":"ref23","first-page":"829","article-title":"FSD50K: An open dataset of human-labeled sound events","volume":"30","author":"fonseca","year":"2021","journal-title":"IEEE\/ACM TASLP"},{"key":"ref15","first-page":"1","article-title":"Sound event localization and detection with pre-trained audio spectrogram transformer and multichannel separation network","author":"scheibler","year":"2022","journal-title":"DCAS Workshop"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746384"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.33682\/3qgs-e216"},{"article-title":"Decoupled weight decay regularization","year":"2017","author":"loshchilov","key":"ref22"},{"key":"ref10","first-page":"2982","article-title":"Deep convolutional neural networks and data augmentation for acoustic event detection","author":"takahashi","year":"2016","journal-title":"InterSpeech"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2018.8521403"},{"key":"ref2","first-page":"71","article-title":"A sequence matching network for polyphonic sound event localization and detection","author":"nguyen","year":"2020","journal-title":"IEEE ICASSP"},{"key":"ref1","first-page":"684","article-title":"Overview and evaluation of sound event localization and detection in DCASE 2019","volume":"29","author":"politis","year":"2020","journal-title":"IEEE\/ACM TASLP"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11004-009-9257-x"},{"key":"ref16","first-page":"7774","article-title":"Cooperative learning of audio and video models from self-supervised synchronization","volume":"31","author":"korbar","year":"2018","journal-title":"NeurIPS"},{"key":"ref19","first-page":"1","article-title":"Representation learning with contrastive predictive coding","author":"oord","year":"2018"},{"article-title":"Gnomonic projection","year":"2001","author":"weisstein","key":"ref18"},{"key":"ref8","first-page":"609","article-title":"Look, listen and learn","author":"arandjelovic","year":"2017","journal-title":"IEEE ICCV"},{"key":"ref7","first-page":"4733","article-title":"Learning representations from audio-visual spatial alignment","volume":"33","author":"morgado","year":"2020","journal-title":"NeurIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413609"},{"key":"ref3","first-page":"34","article-title":"Sound event localization and detection of overlapping sources using convolutional recurrent neural networks","volume":"13","author":"adavanne","year":"2018","journal-title":"IEEE JSTSP"},{"key":"ref6","article-title":"The nerc-slip system for sound event localization and detection of dcase2022 challenge","author":"wang","year":"2022","journal-title":"Tech Rep DCASE2016 Challenge"},{"key":"ref5","first-page":"1","article-title":"STARSS22: A dataset of spatial recordings of real scenes with spatiotemporal annotations of sound events","author":"politis","year":"2022"}],"event":{"name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2023,10,31]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2023,11,3]]}},"container-title":["2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10317071\/10317095\/10317433.pdf?arnumber=10317433","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T18:13:41Z","timestamp":1701281621000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10317433\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,31]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc58517.2023.10317433","relation":{},"subject":[],"published":{"date-parts":[[2023,10,31]]}}}