{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T06:07:40Z","timestamp":1749017260827,"version":"3.28.0"},"reference-count":39,"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\/icassp48485.2024.10446102","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11971-11975","source":"Crossref","is-referenced-by-count":2,"title":["Enhancing End-to-End Conversational Speech Translation Through Target Language Context Utilization"],"prefix":"10.1109","author":[{"given":"Amir","family":"Hussein","sequence":"first","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brian","family":"Yan","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonios","family":"Anastasopoulos","sequence":"additional","affiliation":[{"name":"George Mason University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sanjeev","family":"Khudanpur","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"1","key":"ref1","first-page":"327","article-title":"The role of translator in intercultural communication","volume":"12","author":"K\u00f6ksal","year":"2020","journal-title":"International Journal of Curriculum and Instruction"},{"key":"ref2","first-page":"183","article-title":"Machine translation of speech","volume-title":"Speech and language processing","author":"Stentiford","year":"1990"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.iwslt-1.1"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1991.150456"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2005.1566492"},{"key":"ref6","first-page":"90","article-title":"Toward robust neural machine translation for noisy input sequences","volume-title":"Proceedings of the 14th International Conference on Spoken Language Translation","author":"Sperber"},{"article-title":"Harnessing indirect training data for end-to-end automatic speech translation: Tricks of the trade","volume-title":"Proceedings of the 16th International Conference on Spoken Language Translation","author":"Pino","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.iwslt-1.29"},{"article-title":"Listen and translate: A proof of concept for end-to-end speech-to-text translation","volume-title":"Proceedings of the NIPS Workshop on end-to-end learning for speech and audio processing","author":"Berard","key":"ref9"},{"key":"ref10","first-page":"6224","article-title":"End-to-end automatic speech translation of audio-books","volume-title":"Proc. ICASSP","author":"Berard"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.151"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.iwslt-1.8"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-demo.38"},{"article-title":"Incorporating pronoun function into statistical machine translation","year":"2016","author":"Guillou","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-4702"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1116"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1301"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1325"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1117"},{"key":"ref20","first-page":"225","article-title":"Document-level neural MT: A systematic comparison","volume-title":"Proceedings of the 22nd Annual Conference of the European Association for Machine Translation","author":"Lopes"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/551"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094687"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1643"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1283"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3173"},{"article-title":"Robust speech recognition via large-scale weak supervision","year":"2022","author":"Radford","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2036"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534444"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.200"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-0999"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-demo.38"},{"article-title":"Improved speech-to-text translation with the fisher and callhome Spanish-English speech translation corpus","volume-title":"Proceedings of the 10th International Workshop on Spoken Language Translation: Papers","author":"Post","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.iwslt-1.1"},{"key":"ref35","first-page":"1699","article-title":"Collecting natural SMS and chat conversations in multiple languages: The BOLT phase 2 corpus","volume-title":"Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC\u201914)","author":"Song"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","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\/10446102.pdf?arnumber=10446102","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:37:36Z","timestamp":1722573456000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446102\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446102","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}