{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T01:09:26Z","timestamp":1773277766879,"version":"3.50.1"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Anhui Province Major Science and Technology Research and Development Project","award":["S2023Z20004"],"award-info":[{"award-number":["S2023Z20004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/lsp.2025.3600168","type":"journal-article","created":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T18:18:44Z","timestamp":1755627524000},"page":"3350-3354","source":"Crossref","is-referenced-by-count":2,"title":["DOA or Speaker Embedding: Which is Better for Multi-Microphone Target Speaker Extraction"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-5493-2290","authenticated-orcid":false,"given":"Shuang","family":"Zhang","sequence":"first","affiliation":[{"name":"National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP), University of Science and Technology of China (USTC), Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1124-0854","authenticated-orcid":false,"given":"Jie","family":"Zhang","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP), University of Science and Technology of China (USTC), Hefei, China"}]},{"given":"Yichi","family":"Wang","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP), University of Science and Technology of China (USTC), Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8525-1557","authenticated-orcid":false,"given":"Haoyin","family":"Yan","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP), University of Science and Technology of China (USTC), Hefei, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907229"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746649"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095970"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094918"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-176"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2023.3240008"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3393713"},{"key":"ref8","volume-title":"Array Signal Processing: Concepts and Techniques","author":"Johnson","year":"1993"},{"key":"ref9","article-title":"Dual-path transformer based neural beamformer for target speech extraction","author":"Guo","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3076374"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446870"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2168"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2922820"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2987429"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1397"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746962"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889409"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2025.3572756"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3440638"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1101"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096648"},{"key":"ref23","article-title":"Multi-channel target speaker extraction with refinement: The WavLab submission to the second clarity enhancement challenge","volume-title":"Proc. Clarity Enhancement Challenge Workshop","author":"Cornell","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747395"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688198"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639593"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3229261"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2260"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413359"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095609"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096664"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413411"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054177"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref36","article-title":"100 nonspeech environmental sounds","author":"Hu","year":"2004"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09905-3"},{"key":"ref38","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/97\/10802935\/11129612.pdf?arnumber=11129612","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T04:30:16Z","timestamp":1756355416000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11129612\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/lsp.2025.3600168","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}