{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T10:53:51Z","timestamp":1779101631183,"version":"3.51.4"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018556","name":"Science and Technology Program of Suzhou","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018556","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10094752","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":31,"title":["Target-Speaker Voice Activity Detection Via Sequence-to-Sequence Prediction"],"prefix":"10.1109","author":[{"given":"Ming","family":"Cheng","sequence":"first","affiliation":[{"name":"Wuhan University,School of Computer Science,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiqing","family":"Wang","sequence":"additional","affiliation":[{"name":"Duke Kunshan University,Data Science Research Center,Kunshan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yucong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Duke Kunshan University,Data Science Research Center,Kunshan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyi","family":"Qin","sequence":"additional","affiliation":[{"name":"Wuhan University,School of Computer Science,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Li","sequence":"additional","affiliation":[{"name":"Wuhan University,School of Computer Science,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.878256"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101317"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461921"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4409052"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1388"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1602"},{"key":"ref8","article-title":"The dku-dukeece-lenovo system for the diarization task of the 2021 voxceleb speaker recognition challenge","author":"Wang","year":"2021"},{"key":"ref9","article-title":"The dku-dukeece diarization system for the voxceleb speaker recognition challenge 2022","author":"Wang","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-516"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-516"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3196178"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10095185"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2337"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1208"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref18","article-title":"Dab-detr: Dynamic anchor boxes are better queries for detr","volume-title":"Proc. ICLR","author":"Liu"},{"key":"ref19","first-page":"10524","article-title":"On layer normalization in the transformer architecture","volume-title":"Proc. ICML","author":"Xiong"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref21","article-title":"The dku-dukeece systems for voxceleb speaker recognition challenge 2020","author":"Wang","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref26","article-title":"Musan: A music, speech, and noise corpus","author":"Snyder","year":"2015"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref28","article-title":"The bytedance speaker diarization system for the voxceleb speaker recognition challenge 2021","author":"Wang","year":"2021"},{"key":"ref29","article-title":"The hitachi-jhu dihard iii system: Competitive end-to-end neural diarization and x-vector clustering systems combined by dover-lap","author":"Horiguchi","year":"2021"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10094752.pdf?arnumber=10094752","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T22:33:12Z","timestamp":1709245992000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094752\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094752","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}