{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:14:12Z","timestamp":1740132852605,"version":"3.37.3"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62171470"],"award-info":[{"award-number":["62171470"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Central Plains Science and Technology Innovation Leading Talents Project of Henan Province","award":["234200510019"],"award-info":[{"award-number":["234200510019"]}]},{"DOI":"10.13039\/501100006407","name":"Natural Science Foundation of Henan Province","doi-asserted-by":"publisher","award":["232300421240"],"award-info":[{"award-number":["232300421240"]}],"id":[{"id":"10.13039\/501100006407","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/lsp.2024.3393353","type":"journal-article","created":{"date-parts":[[2024,4,24]],"date-time":"2024-04-24T17:36:57Z","timestamp":1713980217000},"page":"1259-1263","source":"Crossref","is-referenced-by-count":0,"title":["Improving Speech Translation by Understanding the Speech From Latent Code"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8852-6311","authenticated-orcid":false,"given":"Hao","family":"Zhang","sequence":"first","affiliation":[{"name":"School of the Information Engineering University, Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4619-4325","authenticated-orcid":false,"given":"Nianwen","family":"Si","sequence":"additional","affiliation":[{"name":"School of the Information Engineering University, Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6842-9722","authenticated-orcid":false,"given":"Wenlin","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of the Information Engineering University, Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7989-7089","authenticated-orcid":false,"given":"Xukui","family":"Yang","sequence":"additional","affiliation":[{"name":"School of the Information Engineering University, Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9917-7794","authenticated-orcid":false,"given":"Dan","family":"Qu","sequence":"additional","affiliation":[{"name":"School of the Information Engineering University, Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-503"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461690"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00270"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.758176"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17509"},{"article-title":"Bridging the modality gap for speech-to-text translation","year":"2020","author":"Liu","key":"ref6"},{"key":"ref7","first-page":"7050","article-title":"STEMM: Self-learning with speech-text manifold mixup for speech translation","volume-title":"Proc. Annu. Meeting Assoc. Comput. Linguistics","author":"Fang","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.376"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3244521"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.57"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.230"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.216"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095090"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21303"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1065"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.436"},{"key":"ref18","first-page":"18667","article-title":"Pre-training for speech translation: CTC meets optimal transport","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Le","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746117"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1050"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w19-4315"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.694"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.89"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.899"},{"key":"ref25","first-page":"2012","article-title":"MuST-C: A multilingual speech translation corpus","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol., Volume 1 (Long Short Papers)","author":"Gangi","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.108"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/k16-1002"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref30","first-page":"388","article-title":"Statistical significance tests for machine translation evaluation","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Koehn","year":"2004"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.884"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2396"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/10380231\/10508042.pdf?arnumber=10508042","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T05:46:50Z","timestamp":1725688010000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10508042\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/lsp.2024.3393353","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"type":"print","value":"1070-9908"},{"type":"electronic","value":"1558-2361"}],"subject":[],"published":{"date-parts":[[2024]]}}}