{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T16:14:25Z","timestamp":1792080865610,"version":"4.4.0"},"reference-count":33,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9413609","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"915-919","source":"Crossref","is-referenced-by-count":88,"title":["Accdoa: Activity-Coupled Cartesian Direction of Arrival Representation for Sound Event Localization And Detection"],"prefix":"10.1109","author":[{"given":"Kazuki","family":"Shimada","sequence":"first","affiliation":[{"name":"Sony Corporation,Tokyo,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuichiro","family":"Koyama","sequence":"additional","affiliation":[{"name":"Sony Corporation,Tokyo,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naoya","family":"Takahashi","sequence":"additional","affiliation":[{"name":"Sony Corporation,Tokyo,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shusuke","family":"Takahashi","sequence":"additional","affiliation":[{"name":"Sony Corporation,Tokyo,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuki","family":"Mitsufuji","sequence":"additional","affiliation":[{"name":"Sony Corporation,Tokyo,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2441"},{"key":"ref32","article-title":"Network deconvolution","author":"ye","year":"2020","journal-title":"Proc of ICLR"},{"key":"ref31","article-title":"D3Net: Densely connected multidilated densenet for music source separation","author":"takahashi","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref10","article-title":"DCASE 2020 Task 3: Ensemble of sequence matching networks for dynamic sound event localization, detection, and tracking","author":"nguyen","year":"2020","journal-title":"DCASE Challenge Tech Rep"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054462"},{"key":"ref12","article-title":"Multi-beam and multi-task learning for joint sound event detection and localization","author":"xue","year":"2019","journal-title":"DCASE Challenge Tech Rep"},{"key":"ref13","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":"ref14","article-title":"A dataset of reverberant spatial sound scenes with moving sources for sound event localization and detection","author":"politis","year":"2020"},{"key":"ref15","article-title":"The USTC-iFLYTEK system for sound event localization and detection of DCASE2020 challenge","author":"wang","year":"2020","journal-title":"DCASE Challenge Tech Rep"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682711"},{"key":"ref17","article-title":"On multitask loss function for audio event detection and localization","author":"phan","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.33682\/4jhy-bj81"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.33682\/9f2t-ab23"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2017438"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2751969"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-805"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2007.4425280"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.20965\/jrm.2017.p0037"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471706"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.33682\/3qgs-e216"},{"key":"ref8","article-title":"Overview and evaluation of sound event localization and detection in DCASE 2019","author":"politis","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.33682\/1xwd-5v76"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IECON.2017.8217063"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2871183"},{"key":"ref9","first-page":"71","article-title":"A sequence matching network for polyphonic sound event localization and detection","author":"nguyen","year":"2020","journal-title":"Proc of IEEE ICASSP"},{"key":"ref20","article-title":"Data augmentation and prior knowledge-based regularization for sound event localization and detection","author":"zhang","year":"2019","journal-title":"Tech Rep DCASE2016 Challenge"},{"key":"ref22","article-title":"You Only Train Once: Loss-conditional training of deep networks","author":"dosovitskiy","year":"2020","journal-title":"Proc of ICLR"},{"key":"ref21","article-title":"Event-independent network for polyphonic sound event localization and detection","author":"cao","year":"2020"},{"key":"ref24","article-title":"The NIGENS general sound events database","author":"trowitzsch","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1111"},{"key":"ref26","article-title":"Sound event localization and detection using activity-coupled Cartesian DOA vector and RD3Net","author":"shimada","year":"2020","journal-title":"DCASE Challenge Tech Rep"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937220"}],"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\/09413609.pdf?arnumber=9413609","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:19:18Z","timestamp":1659485958000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413609\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413609","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}