{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:36:01Z","timestamp":1740101761205,"version":"3.37.3"},"reference-count":23,"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"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095811","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Joint Training and Decoding for Multilingual End-to-End Simultaneous Speech Translation"],"prefix":"10.1109","author":[{"given":"Wuwei","family":"Huang","sequence":"first","affiliation":[{"name":"Xiaomi AI Lab,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Renren","family":"Jin","sequence":"additional","affiliation":[{"name":"Tianjin University,College of Intelligence and Computing,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xiaomi AI Lab,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Luan","sequence":"additional","affiliation":[{"name":"Xiaomi AI Lab,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Wang","sequence":"additional","affiliation":[{"name":"Xiaomi AI Lab,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deyi","family":"Xiong","sequence":"additional","affiliation":[{"name":"Tianjin University,College of Intelligence and Computing,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683343"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461690"},{"key":"ref23","article-title":"Can neural machine translation do simultaneous translation?","author":"cho","year":"2016","journal-title":"CoRR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.230"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1179"},{"key":"ref20","article-title":"MuST-C: a Multilingual Speech Translation Corpus","author":"di gangi","year":"2019","journal-title":"Proc of NAACL"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-503","article-title":"Sequence-to-sequence models can directly translate foreign speech","author":"weiss","year":"2017","journal-title":"Proc of Interspeech"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1289"},{"key":"ref10","article-title":"Listen, understand and translate”: Triple supervision decouples end-to-end speech-to-text translation","author":"dong","year":"2020","journal-title":"CoRR"},{"key":"ref21","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc of ACL"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.224"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.661"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.344"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2582"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.314"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10953"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414897"},{"key":"ref7","article-title":"Simulmt to simulst: Adapting simultaneous text translation to end-to-end simultaneous speech translation","author":"ma","year":"2020","journal-title":"Proc of AACL"},{"key":"ref9","article-title":"Listen and translate: A proof of concept for end-to-end speech-to-text translation","author":"berard","year":"2016","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855086"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1101"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004003"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003832"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","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\/10095811.pdf?arnumber=10095811","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:00:58Z","timestamp":1699902058000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095811\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095811","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}