{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:25:44Z","timestamp":1775229944660,"version":"3.50.1"},"reference-count":28,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096361","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["Speaker Change Detection For Transformer Transducer ASR"],"prefix":"10.1109","author":[{"given":"Jian","family":"Wu","sequence":"first","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,WA,USA"}]},{"given":"Zhuo","family":"Chen","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,WA,USA"}]},{"given":"Min","family":"Hu","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,WA,USA"}]},{"given":"Xiong","family":"Xiao","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,WA,USA"}]},{"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,WA,USA"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2846"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054715"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref11","article-title":"Linguistically aided speaker diarization using speaker role information","author":"flemotomos","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-407"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101317"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2125954"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1943"},{"key":"ref16","article-title":"Turn-taking pre-diction for natural conversational speech","author":"chang","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-7"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3039"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688101"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053426"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413535"},{"key":"ref22","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref21","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413803"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616142"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-914"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746531"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1364"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953097"},{"key":"ref3","article-title":"Speaker change detection in broadcast tv using bidirectional long short-term memory net-works","author":"bredin","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref6","first-page":"6286","article-title":"Pre-training of speaker embeddings for low-latency speaker change detection in broadcast news","author":"sar?","year":"2019","journal-title":"Proc ICASSP"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IntelliSys.2017.8324268"}],"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\/10096361.pdf?arnumber=10096361","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T13:59:22Z","timestamp":1699883962000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096361\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096361","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}