{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:34:13Z","timestamp":1776890053960,"version":"3.51.2"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890381","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Transcribing and Translating, Fast and Slow: Joint Speech Translation and Recognition"],"prefix":"10.1109","author":[{"given":"Niko","family":"Moritz","sequence":"first","affiliation":[{"name":"Meta AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruiming","family":"Xie","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yashesh","family":"Gaur","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ke","family":"Li","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simone Merello","family":"Zeeshan Ahmed","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Frank","family":"Seide","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christian","family":"Fuegen","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Seamless: Multilingual expressive and streaming speech translation","author":"Communication","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.202"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.485"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003774"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1759"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2582"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.68"},{"key":"ref8","first-page":"58312","article-title":"ComSl: A composite speech-language model for end-to-end speech-to-text translation","volume-title":"Proc. NeurIPS","volume":"36","author":"Le"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1693"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389715"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747375"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-7"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.4"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10953"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2004"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10551"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747706"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447278"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2076"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023141"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.181"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2024-2"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.507"},{"issue":"107","key":"ref26","first-page":"1","article-title":"Beyond english-centric multilingual machine translation","volume":"22","author":"Fan","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"ref27","article-title":"Opensubtitles2016: Extracting large parallel corpora from movie and tv subtitles","author":"Lison","year":"2016"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.protcy.2014.11.024"},{"key":"ref29","volume-title":"Chime 8 task 3: Multi-talker word error rate","author":"Mandel"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890381.pdf?arnumber=10890381","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:56Z","timestamp":1774416236000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890381\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890381","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}