{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T16:15:36Z","timestamp":1784391336814,"version":"3.55.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746384","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"316-320","source":"Crossref","is-referenced-by-count":70,"title":["Multi-ACCDOA: Localizing And Detecting Overlapping Sounds From The Same Class With Auxiliary Duplicating Permutation Invariant Training"],"prefix":"10.1109","author":[{"given":"Kazuki","family":"Shimada","sequence":"first","affiliation":[{"name":"Sony Group Corporation,Tokyo,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuichiro","family":"Koyama","sequence":"additional","affiliation":[{"name":"Sony Group Corporation,Tokyo,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shusuke","family":"Takahashi","sequence":"additional","affiliation":[{"name":"Sony Group Corporation,Tokyo,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naoya","family":"Takahashi","sequence":"additional","affiliation":[{"name":"Sony Group Corporation,Tokyo,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emiru","family":"Tsunoo","sequence":"additional","affiliation":[{"name":"Sony Group Corporation,Tokyo,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuki","family":"Mitsufuji","sequence":"additional","affiliation":[{"name":"Sony Group Corporation,Tokyo,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.33682\/4jhy-bj81"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413609"},{"key":"ref12","article-title":"A dataset of dynamic reverberant sound scenes with directional interferers for sound event localization and detection","author":"politis","year":"2021"},{"key":"ref13","article-title":"Multi-scale network for sound event localization and detection","author":"emmanuel","year":"2021","journal-title":"Tech Rep DCASE2016 Challenge"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413473"},{"key":"ref15","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":"ref16","article-title":"SoundDet: polyphonic moving sound event detection and localization from raw waveform","author":"he","year":"2021","journal-title":"Proc of ICML"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref18","article-title":"Separating varying numbers of sources with auxiliary autoencoding loss","author":"luo","year":"2020","journal-title":"Proc of Interspeech"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937220"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461639"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.20965\/jrm.2017.p0037"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2017438"},{"key":"ref6","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 Trans on ASLP"},{"key":"ref29","article-title":"DCASE 2021 task 3: Spectrotemporally-aligned features for polyphonic sound event localization and detection","author":"nguyen","year":"2021","journal-title":"DCASE Challenge Tech Rep"},{"key":"ref5","article-title":"Emergency vehicles audio detection and localization in autonomous driving","author":"sun","year":"2021"},{"key":"ref8","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 DCAS Workshop"},{"key":"ref7","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":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2007.4425280"},{"key":"ref9","article-title":"A four-stage data augmentation approach to resnet-conformer based acoustic modeling for sound event localization and detection","author":"wang","year":"2021"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2871183"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2441"},{"key":"ref22","article-title":"Averaging weights leads to wider optima and better generalization","author":"izmailov","year":"2018","journal-title":"Proc Of UAI"},{"key":"ref21","article-title":"Accurate, large mini-batch SGD: Training ImageNet in 1 hour","author":"goyal","year":"2017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2751969"},{"key":"ref23","article-title":"Ensemble of ACCDOA- and EINV2-based systems with D3Nets and impulse response simulation for sound event localization and detection","author":"shimada","year":"2021","journal-title":"DCASE Challenge Tech Rep"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.33682\/3qgs-e216"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"2982","DOI":"10.21437\/Interspeech.2016-805","article-title":"Deep convolutional neural networks and data augmentation for acoustic event detection","author":"takahashi","year":"2016","journal-title":"Proc of Interspeech"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746384.pdf?arnumber=9746384","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T03:24:04Z","timestamp":1727061844000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746384\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746384","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}