{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:09:56Z","timestamp":1776888596055,"version":"3.51.2"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446050","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10866-10870","source":"Crossref","is-referenced-by-count":6,"title":["Diarist: Streaming Speech Translation with Speaker Diarization"],"prefix":"10.1109","author":[{"given":"Mu","family":"Yang","sequence":"first","affiliation":[{"name":"University of Texas at Dallas,Center for Robust Speech Systems (CRSS),Richardson,TX,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naoyuki","family":"Kanda","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,WA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaofei","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,WA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junkun","family":"Chen","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,WA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peidong","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,WA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Xue","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,WA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,WA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takuya","family":"Yoshioka","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,WA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.758176"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-726"},{"key":"ref3","article-title":"Improved speech-to-text translation with the Fisher and Callhome Spanish-English speech translation corpus","volume-title":"Proc. IWSLT","author":"Post"},{"key":"ref4","article-title":"Listen and translate: A proof of concept for end-to-end speech-to-text translation","volume-title":"Proc. NIPS Workshop on end-to-end learning for speech and audio processing","author":"B\u00e9rard"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/IberSPEECH.2018-13"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.661"},{"key":"ref7","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022"},{"key":"ref8","article-title":"SeamlessM4T-massively multilingual & multimodal machine translation","author":"Barrault","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10953"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/asru57964.2023.10389799"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2004"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101317"},{"key":"ref13","first-page":"373","article-title":"The rich transcription 2007 meeting recognition evaluation","author":"Fiscus","year":"2007","journal-title":"Multimodal Technologies for Perception of Humans"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2020-1"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-68585-2_46"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2012.6343426"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-78"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2001-352"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746465"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746270"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-7"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-253"},{"key":"ref23","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref24","first-page":"311","article-title":"BLEU: a method for automatic evaluation of machine translation","volume-title":"Proc. ACL","author":"Papineni"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383531"},{"key":"ref27","article-title":"The Microsoft system for VoxCeleb speaker recognition challenge 2022","author":"Liu","year":"2022"},{"key":"ref28","article-title":"SpeechBrain: A general-purpose speech toolkit","author":"Ravanelli","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2961071"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413535"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-102"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094928"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1276"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389715"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1947"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9746531"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746225"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446050.pdf?arnumber=10446050","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:01:46Z","timestamp":1722574906000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446050\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446050","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}