{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T04:39:27Z","timestamp":1779251967547,"version":"3.51.4"},"reference-count":47,"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\/icassp49357.2023.10095896","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":4,"title":["Align, Write, Re-Order: Explainable End-to-End Speech Translation via Operation Sequence Generation"],"prefix":"10.1109","author":[{"given":"Motoi","family":"Omachi","sequence":"first","affiliation":[{"name":"Yahoo Japan Corporation,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brian","family":"Yan","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,PA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siddharth","family":"Dalmia","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,PA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuya","family":"Fujita","sequence":"additional","affiliation":[{"name":"Yahoo Japan Corporation,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,PA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-60087-6_33"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.iwslt-1.10"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413719"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.iwslt-1.15"},{"key":"ref5","article-title":"Listen and translate: A proof of concept for end-to-end speech-to-text translation","author":"B\u00e9rard","year":"2016"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003774"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415093"},{"key":"ref8","article-title":"Revisiting end-to-end speech-to-text translation from scratch","author":"Zhang","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00270"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383462"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.151"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.iwslt-1.27"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5420"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17508"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.216"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6360"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.314"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.119"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3115\/112405.112427"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3115\/1557769.1557821"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00292"},{"key":"ref22","article-title":"Sequence modeling with unconstrained generation order","volume":"32","author":"Emelianenko","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref23","article-title":"Learning non-monotonic automatic post-editing of translations from human orderings","author":"G\u00f3is","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17618"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00368"},{"key":"ref26","article-title":"The IWSLT 2019 KIT speech translation system","volume-title":"Proc. SIGSLT","author":"Pham"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1289"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054585"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00340"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.406"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.iwslt-1.1"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.50"},{"key":"ref33","article-title":"Phrase-based alignment combining corpus cooccurrences and linguistic knowledge","volume-title":"Proc. IWSLT","author":"Gispert"},{"key":"ref34","first-page":"127","article-title":"Satistical Phrase-Based Translation","volume-title":"Proc. NACCL","author":"Koehn"},{"key":"ref35","first-page":"2012","article-title":"MuST-C: a Multilingual Speech Translation Corpus","volume-title":"Proc. NAACL","author":"Di Gangi"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-503"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1006"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3115\/1622110.1622119"},{"key":"ref40","article-title":"Simulmt to simulst: Adapting simultaneous text translation to end-to-end simultaneous speech translation","author":"Ma","year":"2020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.34"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p16-1162"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414858"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383517"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"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\/10095896.pdf?arnumber=10095896","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T02:00:37Z","timestamp":1705024837000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095896\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095896","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}