{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:09:52Z","timestamp":1776888592174,"version":"3.51.2"},"reference-count":49,"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\/asru57964.2023.10389715","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:40Z","timestamp":1705689520000},"page":"1-8","source":"Crossref","is-referenced-by-count":7,"title":["Token-Level Serialized Output Training for Joint Streaming ASR and ST Leveraging Textual Alignments"],"prefix":"10.1109","author":[{"given":"Sara","family":"Papi","sequence":"first","affiliation":[{"name":"Fondazione Bruno Kessler and University of Trento,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peidong","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junkun","family":"Chen","sequence":"additional","affiliation":[{"name":"Microsoft,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Xue","sequence":"additional","affiliation":[{"name":"Microsoft,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yashesh","family":"Gaur","sequence":"additional","affiliation":[{"name":"Microsoft,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2006-266"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10590-008-9047-0"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00340"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.iwslt-1.26"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5420"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17508"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.314"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.iwslt-1.7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.406"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.216"},{"key":"ref11","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. 31st NeurIPS","author":"Vaswani"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1055"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.iwslt-1.27"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2004"},{"key":"ref16","article-title":"Transformer-transducer: End-to-end speech recognition with self-attention","author":"Yeh","year":"2019"},{"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","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-7"},{"issue":"12","key":"ref20","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1145\/3381831","article-title":"Green ai","volume":"63","author":"Schwartz","year":"2020","journal-title":"Commun. ACM"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-0999"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10095367"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095896"},{"key":"ref24","article-title":"Defining maximum acceptable latency of ai-enhanced cai tools","author":"Fantinuoli","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2203"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095553"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054260"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413562"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1949"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413803"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414560"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054476"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2361"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10953"},{"key":"ref37","article-title":"A weakly-supervised streaming multilingual speech model with truly zeroshot capability","author":"Xue","year":"2022","journal-title":"arXiv preprint arXiv:2211.02499"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.4"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.695"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.181"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-2027"},{"key":"ref42","article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w18-6319"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.autosimtrans-1.2"},{"key":"ref46","first-page":"582","article-title":"SimulMT to SimulST: Adapting simultaneous text translation to end-to-end simultaneous speech translation","volume-title":"Proc. 1st AACL and 10th IJCNLP","author":"Ma"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1289"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.2307\/415392"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.iwslt-1.6"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Taipei, Taiwan","start":{"date-parts":[[2023,12,16]]},"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\/10389715.pdf?arnumber=10389715","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:36:15Z","timestamp":1706027775000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389715\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389715","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}