{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:06:14Z","timestamp":1775199974208,"version":"3.50.1"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"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":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434706","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Non-Autoregressive Multi-Speaker ASR with Decoupled Speaker Change Detection"],"prefix":"10.1109","author":[{"given":"Yingke","family":"Zhu","sequence":"first","affiliation":[{"name":"Fano,Hong Kong,SAR,China"}]},{"given":"Lahiru","family":"Samarakoon","sequence":"additional","affiliation":[{"name":"Fano,Hong Kong,SAR,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054029"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/asru46091.2019.9003986"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023037"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1244"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.09.003"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682822"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054328"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413471"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-999"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-7"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446059"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1521"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2155"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389762"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-9996"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10096361"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3070817"},{"key":"ref19","article-title":"Towards word-level end-to-end neural speaker diarization with auxiliary network","author":"Huang","year":"2023","journal-title":"arXiv preprint arXiv:2309.08489"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1085"},{"key":"ref21","first-page":"1","article-title":"The ami meeting corpus","volume-title":"Proc. International Conference on Methods and Techniques in Behavioral Research","author":"Kraaij"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1211.3711"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-101"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-102"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3318398"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097139"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref34","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint arXiv:1412.6980"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2020-1"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2006-91"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2284"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434706.pdf?arnumber=11434706","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:58:35Z","timestamp":1775192315000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434706\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434706","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}