{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:26:53Z","timestamp":1775230013258,"version":"3.50.1"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"China NSFC Projects","award":["62122050"],"award-info":[{"award-number":["62122050"]}]},{"name":"China NSFC Projects","award":["62071288"],"award-info":[{"award-number":["62071288"]}]},{"name":"Shanghai Municipal Science and Technology Commission Project","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3366756","type":"journal-article","created":{"date-parts":[[2024,2,16]],"date-time":"2024-02-16T19:06:47Z","timestamp":1708110407000},"page":"1636-1649","source":"Crossref","is-referenced-by-count":23,"title":["Attention-Based Encoder-Decoder End-to-End Neural Diarization With Embedding Enhancer"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1293-8146","authenticated-orcid":false,"given":"Zhengyang","family":"Chen","sequence":"first","affiliation":[{"name":"Auditory Cognition and Computational Acoustics Lab, Department of Computer Science and Engineering and the MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6319-6755","authenticated-orcid":false,"given":"Bing","family":"Han","sequence":"additional","affiliation":[{"name":"Auditory Cognition and Computational Acoustics Lab, Department of Computer Science and Engineering and the MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1523-9631","authenticated-orcid":false,"given":"Shuai","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0314-3790","authenticated-orcid":false,"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[{"name":"Auditory Cognition and Computational Acoustics Lab, Department of Computer Science and Engineering and the MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960644"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004009"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383556"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682572"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022924"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2264673"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078610"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2014.05.001"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-420"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1893"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462628"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1388"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178881"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-21"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2813"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2899"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003959"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref19","article-title":"Neural speaker diarization with speaker-wise chain rule","author":"Fujita","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383555"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1004"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3233237"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462661"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2987429"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2922820"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-574"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1602"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/chime.2020\u20139"},{"key":"ref30","article-title":"The DKU-SMIIP diarization system for the voxceleb speaker recognition challenge 2022","volume-title":"Proc. Voxsrc Workshop","author":"Wang","year":"2022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3279781"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095185"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094752"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3162080"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1228"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10451"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097049"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1909"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101316"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747772"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413436"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747301"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746225"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414841"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746602"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023388"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095589"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746749"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746964"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-19"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687875"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414371"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383523"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2215"},{"key":"ref57","article-title":"2000 NIST speaker recognition evaluation","year":"2000"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/11677482_3"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1268"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101254"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096436"},{"key":"ref64","article-title":"Silero vad: Pre-trained enterprise-grade voice activity detector (vad), number detector and language classifier","author":"Team","year":"2021"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052974"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-560"},{"key":"ref67","article-title":"But system description for dihard speech diarization challenge 2019","author":"Landini","year":"2019"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.21437\/odyssey.2020-59"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383602"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413752"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-991"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3265199"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10438838.pdf?arnumber=10438838","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,8]],"date-time":"2024-03-08T02:24:37Z","timestamp":1709864677000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10438838\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":72,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3366756","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}