{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:32:53Z","timestamp":1763202773805},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095090","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":7,"title":["M<sup>3<\/sup>ST: Mix at Three Levels for Speech Translation"],"prefix":"10.1109","author":[{"given":"Xuxin","family":"Cheng","sequence":"first","affiliation":[{"name":"Peking University,ADSPLAB, School of ECE,China"}]},{"given":"Qianqian","family":"Dong","sequence":"additional","affiliation":[{"name":"ByteDance"}]},{"given":"Fengpeng","family":"Yue","sequence":"additional","affiliation":[{"name":"ByteDance"}]},{"given":"Tom","family":"Ko","sequence":"additional","affiliation":[{"name":"ByteDance"}]},{"given":"Mingxuan","family":"Wang","sequence":"additional","affiliation":[{"name":"ByteDance"}]},{"given":"Yuexian","family":"Zou","sequence":"additional","affiliation":[{"name":"Peking University,ADSPLAB, School of ECE,China"}]}],"member":"263","reference":[{"key":"ref13","article-title":"OpenSubtitles2016: Extracting large parallel corpora from movie and TV subtitles","author":"lison","year":"2016","journal-title":"Proc LREC"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.486"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21303"},{"key":"ref14","article-title":"Fairseq S2T: Fast speech-to-text modeling with fairseq","author":"wang","year":"2020","journal-title":"Proc of AACL"},{"key":"ref11","article-title":"mixup: Beyond empirical risk minimization","author":"zhang","year":"2018","journal-title":"Proc of ICLR"},{"key":"ref10","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc of NeurIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.195"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1065"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.376"},{"article-title":"Revisiting end-to-end speech-to-text translation from scratch","year":"2022","author":"zhang","key":"ref16"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414703"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.204"},{"article-title":"Efficient estimation of word representations in vector space","year":"2013","author":"mikolov","key":"ref24"},{"key":"ref23","article-title":"A simple, fast, and effective reparameterization of IBM model 2","author":"dyer","year":"2013","journal-title":"Proc of NAACL"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"kingma","key":"ref25"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.148"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1386","article-title":"Montreal forced aligner: Trainable text-speech alignment using kaldi","author":"mcauliffe","year":"2017","journal-title":"Proc of Interspeech"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref7","article-title":"MuST-C: a Multilingual Speech Translation Corpus","author":"di gangi","year":"2019","journal-title":"Proc of NAACL"},{"article-title":"Gigast: A 10,000-hour pseudo speech translation corpus","year":"2022","author":"ye","key":"ref9"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053406"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3140693"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414483"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.27"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095090.pdf?arnumber=10095090","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T18:57:06Z","timestamp":1700506626000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095090\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095090","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}