{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T04:39:32Z","timestamp":1779251972591,"version":"3.51.4"},"reference-count":33,"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":["62176211"],"award-info":[{"award-number":["62176211"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Project of the Science, Technology, and Innovation Commission of Shenzhen Municipality, China","award":["JCYJ20210324143006016"],"award-info":[{"award-number":["JCYJ20210324143006016"]}]},{"name":"Project of the Science, Technology, and Innovation Commission of Shenzhen Municipality, China","award":["JSGG20210802152546026"],"award-info":[{"award-number":["JSGG20210802152546026"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/lsp.2024.3353039","type":"journal-article","created":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T18:32:05Z","timestamp":1704997925000},"page":"371-375","source":"Crossref","is-referenced-by-count":14,"title":["Transformer-Based End-to-End Speech Translation With Rotary Position Embedding"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9835-1682","authenticated-orcid":false,"given":"Xueqing","family":"Li","sequence":"first","affiliation":[{"name":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengqiang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7694-193X","authenticated-orcid":false,"given":"Xiao-Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0831-6934","authenticated-orcid":false,"given":"Susanto","family":"Rahardja","sequence":"additional","affiliation":[{"name":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016351"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.486"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21303"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.661"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10590-020-09250-0"},{"key":"ref6","article-title":"Listen and translate: A proof of concept for end-to-end speech-to-text translation","volume-title":"Proc. NIPS Workshop End-to-End Learn. Speech Audio Process.","author":"Brard","year":"2016"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-503"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461690"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683343"},{"key":"ref10","article-title":"On using specaugment for end-to-end speech translation","volume-title":"Proc. 16th Int. Conf. Spoken Lang. Transl.","author":"Bahar","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3045"},{"key":"ref12","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000045"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-872"},{"key":"ref15","first-page":"3588","article-title":"FitHuBERT: Going thinner and deeper for knowledge distillation of speech self-supervised learning","volume-title":"Proc. 23rd Annu. Conf. Int. Speech Commun. Assoc.","author":"Lee","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2526"},{"key":"ref17","article-title":"ELECTRA: Pre-training text encoders as discriminators rather than generators","author":"Clark","year":"2020"},{"key":"ref18","article-title":"Rethinking positional encoding in language pre-training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ke","year":"2020"},{"key":"ref19","article-title":"How much position information do convolutional neural networks encode","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Islam","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.325"},{"issue":"1","key":"ref22","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00445"},{"key":"ref24","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.","author":"Gangi","year":"2019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"},{"key":"ref26","first-page":"33","article-title":"FAIRSEQ S2T: Fast speech-to-text modeling with FAIRSEQ","volume-title":"Proc. 1st Conf. Asia-Pacific Chapter Assoc. Comput. Linguistics 10th Int. Joint Conf. Natural Lang. Process. Syst. Demonstrations","author":"Wang","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.34"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.230"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.127"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.602"},{"key":"ref31","article-title":"Room impulse response (RIR) generator","author":"Habets","year":"2016"},{"key":"ref32","first-page":"15","article-title":"Synthetic structure of industrial plastics","volume-title":"Plastics","volume":"3","author":"Young","year":"1964"},{"key":"ref33","first-page":"123","volume-title":"Linear Networks and Systems","author":"Chen","year":"1993"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/10380231\/10388427.pdf?arnumber=10388427","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T18:54:20Z","timestamp":1725648860000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10388427\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/lsp.2024.3353039","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}