{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T18:42:54Z","timestamp":1747680174673,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"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":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389709","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T13:38:40Z","timestamp":1705671520000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["Improving Stability in Simultaneous Speech Translation: A Revision-Controllable Decoding Approach"],"prefix":"10.1109","author":[{"given":"Junkun","family":"Chen","sequence":"first","affiliation":[{"name":"Microsoft"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Xue","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peidong","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Pan","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.350"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.406"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10953"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.695"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3115\/1620754.1620810"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3758\/s13414-020-02237-2"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3115\/1626431.1626471"},{"key":"ref8","first-page":"28","article-title":"Long-distance reordering during search for hierarchical phrase-based smt","volume-title":"Proceedings of the Annual Conference of the European Association for Machine Translation (EAMT)","author":"Braune"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.349"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511815829"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1289"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1144"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00270"},{"key":"ref14","article-title":"Sequence transduction with recurrent neural networks","author":"Graves","year":"2012","journal-title":"arXiv preprint arXiv:1211.3711"},{"key":"ref15","article-title":"Token-level serialized output training for joint streaming asr and st leveraging textual alignments","author":"Papi","year":"2023","journal-title":"arXiv preprint arXiv:2307.03354"},{"key":"ref16","article-title":"Transformer-transducer: End-to-end speech recognition with self-attention","author":"Yeh","year":"2019","journal-title":"arXiv preprint arXiv:1910.12977"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413535"},{"key":"ref19","volume-title":"Automatic speech recognition","volume":"1","author":"Yu","year":"2016"},{"key":"ref20","article-title":"A weakly-supervised streaming multilingual speech model with truly zero-shot capability","author":"Xue","year":"2022","journal-title":"arXiv preprint arXiv:2211.02499"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-2027"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w18-6319"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054585"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9983"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.473"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023016"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2023,12,16]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389709.pdf?arnumber=10389709","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T11:49:42Z","timestamp":1706010582000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389709\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389709","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}