{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:33:55Z","timestamp":1753601635521},"reference-count":23,"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\/icassp43922.2022.9747604","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"711-715","source":"Crossref","is-referenced-by-count":5,"title":["Locate This, Not that: Class-Conditioned Sound Event DOA Estimation"],"prefix":"10.1109","author":[{"given":"Olga","family":"Slizovskaia","sequence":"first","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}]},{"given":"Gordon","family":"Wichern","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}]},{"given":"Zhong-Qiu","family":"Wang","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}]},{"given":"Jonathan","family":"Le Roux","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3082331"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462661"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1101"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2210"},{"key":"ref14","article-title":"Audio query-based music source separation","author":"lee","year":"2019","journal-title":"Proc ISMIR"},{"key":"ref15","first-page":"81","article-title":"Fewshot sound event detection","author":"wang","year":"2020","journal-title":"Proc ICASSP"},{"article-title":"TAUNIGENS Spatial Sound Events 2020","year":"2020","author":"politis","key":"ref16"},{"article-title":"TAU-NIGENS Spatial Sound Events 2021","year":"2021","author":"politis","key":"ref17"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.23915\/distill.00011","article-title":"Feature-wise transformations","author":"dumoulin","year":"2018","journal-title":"Distillation"},{"article-title":"A dataset of dynamic reverberant sound scenes with directional interferers for sound event localization and detection","year":"2021","author":"politis","key":"ref19"},{"article-title":"A survey of sound source localization with deep learning methods","year":"2021","author":"grumiaux","key":"ref4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2990485"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.conb.2007.07.011"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413609"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683007"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.52984"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3047233"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2885636"},{"key":"ref9","article-title":"Conditioned-U-Net: Introducing a control mechanism in the U-Net for multiple source separations","author":"meseguer-brocal","year":"2019","journal-title":"Proc ISMIR"},{"article-title":"A four-stage data augmentation approach to ResNet-Conformer based acoustic modeling for sound event localization and detection","year":"2021","author":"wang","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937220"},{"year":"0","key":"ref21","article-title":"Ensemble of ACCDOA- and EINV2-based systems with D3Nets and impulse response simulation for sound event localization and detection"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054462"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","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\/09747604.pdf?arnumber=9747604","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,29]],"date-time":"2022-08-29T21:53:53Z","timestamp":1661810033000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747604\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747604","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}