{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T04:39:31Z","timestamp":1779251971439,"version":"3.51.4"},"reference-count":26,"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\/icassp48485.2024.10447450","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"12727-12731","source":"Crossref","is-referenced-by-count":3,"title":["Memory-Augmented speech-to-text Translation with Multi-Scale Context Translation Strategy"],"prefix":"10.1109","author":[{"given":"Yuxuan","family":"Yuan","sequence":"first","affiliation":[{"name":"Xiamen University,School of Informatics,Department of Artificial Intelligence,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yue","family":"Zhou","sequence":"additional","affiliation":[{"name":"Xiamen University,School of Informatics,Department of Artificial Intelligence,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaodong","family":"Shi","sequence":"additional","affiliation":[{"name":"Xiamen University,School of Informatics,Department of Artificial Intelligence,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Listen and translate: A proof of concept for end-to-end speech-to-text translation","volume-title":"CoRR","author":"Berard"},{"key":"ref2","article-title":"Revisiting end-to-end speech-to-text translation from scratch","volume-title":"Proc. of ICML","author":"Zhang"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096899"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1116"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.81"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.262"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.267"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.200"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.105"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.57"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746117"},{"key":"ref12","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. of AACL","author":"Devlin"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref14","author":"Burtsev","year":"2021","journal-title":"Memory transformer"},{"key":"ref15","article-title":"Recurrent memory transformer","volume-title":"Proc. of NeurIPS","author":"Bulatov"},{"key":"ref16","article-title":"Block-recurrent transformers","volume-title":"Proc. of NeurIPS","author":"Hutchins"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref18","article-title":"MuST-C: a Multilingual Speech Translation Corpus","volume-title":"Proc. of AACL","author":"Di Gangi"},{"key":"ref19","author":"Liu","year":"2020","journal-title":"Bridging the modality gap for speech-to-text translation"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17508"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.704"},{"key":"ref26","article-title":"Learning pronunciation from a foreign language in speech synthesis networks","author":"Lee","year":"2018"}],"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\/10447450.pdf?arnumber=10447450","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:38:57Z","timestamp":1722577137000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447450\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447450","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}