{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:04:14Z","timestamp":1776888254745,"version":"3.51.2"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746531","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"8077-8081","source":"Crossref","is-referenced-by-count":44,"title":["Turn-to-Diarize: Online Speaker Diarization Constrained by Transformer Transducer Speaker Turn Detection"],"prefix":"10.1109","author":[{"given":"Wei","family":"Xia","sequence":"first","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Lu","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quan","family":"Wang","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anshuman","family":"Tripathi","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiling","family":"Huang","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ignacio Lopez","family":"Moreno","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hasim","family":"Sak","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-411"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0602-z"},{"key":"ref10","article-title":"Speaker diarization using an end-to-end model","author":"wang","year":"2019","journal-title":"Google Patents"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953094"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"3827","DOI":"10.21437\/Interspeech.2017-65","article-title":"Speaker change detection in broadcast tv using bidirectional long short-term memory networks","author":"yin","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1750"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1364"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414841"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref17","article-title":"Transformer transducer: One model unifying streaming and non-streaming speech recognition","author":"tripathi","year":"2020"},{"key":"ref18","article-title":"Transformer-transducer: End-to-end speech recognition with self-attention","author":"yeh","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2961071"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-007-9033-z"},{"key":"ref3","first-page":"4879","article-title":"Generalized end-to-end loss for speaker verification","author":"wan","year":"2018","journal-title":"ICASSP"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462628"},{"key":"ref29","author":"basu","year":"2008","journal-title":"Constrained Clustering Advances in Algorithms Theory and Applications"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2264673"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383617"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683892"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2899"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101317"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1943"},{"key":"ref22","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012"},{"key":"ref21","article-title":"Links: A high-dimensional online clustering method","author":"mansfield","year":"2018"},{"key":"ref24","article-title":"CALLHOME American English speech LDC97S42","author":"canavan","year":"1997","journal-title":"LDC Catalog"},{"key":"ref23","first-page":"69","article-title":"The Fisher corpus: A resource for the next generations of speech-to-text","volume":"4","author":"cieri","year":"2004","journal-title":"LREC"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-204"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2021-641","article-title":"DrVectors: Decision residual networks and an improved loss for speaker recognition","author":"pelecanos","year":"2021","journal-title":"Proc INTERSPEECH"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746531.pdf?arnumber=9746531","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T03:20:39Z","timestamp":1727061639000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746531\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746531","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}