{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:36:03Z","timestamp":1776886563932,"version":"3.51.2"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100013101","name":"National Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100013101","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010002","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447181","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"8686-8690","source":"Crossref","is-referenced-by-count":22,"title":["CST-Former: Transformer with Channel-Spectro-Temporal Attention for Sound Event Localization and Detection"],"prefix":"10.1109","author":[{"given":"Yusun","family":"Shul","sequence":"first","affiliation":[{"name":"Korea Advanced Institute of Science and Technology,School of Electrical Engineering,Daejeon,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jung-Woo","family":"Choi","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology,School of Electrical Engineering,Daejeon,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2885636"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3047233"},{"key":"ref3","article-title":"The ustc-iflytek system for sound event localization and detection of dcase2020 challenge","volume-title":"Tech. Rep., DCASE2020 Challenge","author":"Wang","year":"2020"},{"key":"ref4","article-title":"Sound event localization and detection with various loss functions","volume-title":"Tech. Rep., DCASE2020 Challenge","author":"Park","year":"2020"},{"key":"ref5","article-title":"Dcase 2020 task 3: Ensemble of sequence matching networks for dynamic sound event localization, detection, and tracking","volume-title":"Tech. Rep., DCASE2020 Challenge","author":"Nguyen","year":"2020"},{"key":"ref6","article-title":"Sound event localization and detection for real spatial sound scenes: Event-independent network and data augmentation chains","volume-title":"Tech. Rep., DCASE2022 Challenge","author":"Hu","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413609"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746384"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096460"},{"key":"ref10","first-page":"125","article-title":"STARSS22: A dataset of spatial recordings of real scenes with spatiotemporal annotations of sound events","volume-title":"Proc. of DCASE Workshop","author":"Politis"},{"key":"ref11","article-title":"STARSS23: Sony-TAu Realistic Spatial Soundscapes 2023","author":"Politis","year":"2023"},{"key":"ref12","article-title":"[DCASE2022 Task 3] Synthetic SELD mixtures for baseline training","author":"Politis","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref14","article-title":"TAU Spatial Room Impulse Response Database (TAU-SRIR DB)","author":"Politis","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3256088"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094681"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747373"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095037"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3244428"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref21","article-title":"Divided spectro-temporal attention for sound event localization and detection in real scenes for dcase2023 challenge","volume-title":"Tech. Rep., DCASE2023 Challenge","author":"Shul","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"ref23","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. of ICLR","author":"Dosovitskiy"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447181.pdf?arnumber=10447181","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:31:39Z","timestamp":1722576699000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447181\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447181","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}