{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T04:39:29Z","timestamp":1779251969641,"version":"3.51.4"},"reference-count":24,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10445849","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"12176-12180","source":"Crossref","is-referenced-by-count":2,"title":["Bridging the Gaps of Both Modality and Language: Synchronous Bilingual CTC for Speech Translation and Speech Recognition"],"prefix":"10.1109","author":[{"given":"Chen","family":"Xu","sequence":"first","affiliation":[{"name":"Harbin Engineering University,College of Computer Science and Technology,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoqian","family":"Liu","sequence":"additional","affiliation":[{"name":"Northeastern University,School of Computer Science and Engineering,Shenyang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Erfeng","family":"He","sequence":"additional","affiliation":[{"name":"Northeastern University,School of Computer Science and Engineering,Shenyang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Northeastern University,School of Computer Science and Engineering,Shenyang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qianqian","family":"Dong","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"Xiao","sequence":"additional","affiliation":[{"name":"Northeastern University,School of Computer Science and Engineering,Shenyang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingbo","family":"Zhu","sequence":"additional","affiliation":[{"name":"Northeastern University,School of Computer Science and Engineering,Shenyang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dapeng","family":"Man","sequence":"additional","affiliation":[{"name":"Harbin Engineering University,College of Computer Science and Technology,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wu","family":"Yang","sequence":"additional","affiliation":[{"name":"Harbin Engineering University,College of Computer Science and Technology,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/761"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003774"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-1006"},{"key":"ref7","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":"ref8","article-title":"Stacked acousticand-textual encoding: Integrating the pre-trained models into speech translation encoders","volume-title":"Proc. of ACL","author":"Xu"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.744"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414594"},{"key":"ref11","article-title":"Listen and translate: A proof of concept for end-to-end speech-to-text translation","author":"B\u00e9rard","year":"2016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-911"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref15","article-title":"MuST-C: a Multilingual Speech Translation Corpus","volume-title":"Proc. of NAACL","author":"Di Gangi"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.436"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.884"},{"key":"ref19","article-title":"Pre-training for speech translation: CTC meets optimal transport","volume-title":"Proc. of ICML","author":"Le"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1065"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.486"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.376"},{"key":"ref23","article-title":"M 3 st: Mix at three levels for speech translation","volume-title":"Proc. of ICASSP","author":"Cheng"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1139"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"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\/10445849.pdf?arnumber=10445849","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:56:48Z","timestamp":1722574608000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10445849\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10445849","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}