{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T03:37:02Z","timestamp":1774064222776,"version":"3.50.1"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414897","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"7523-7527","source":"Crossref","is-referenced-by-count":7,"title":["Streaming Simultaneous Speech Translation with Augmented Memory Transformer"],"prefix":"10.1109","author":[{"given":"Xutai","family":"Ma","sequence":"first","affiliation":[]},{"given":"Yongqiang","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Mohammad Javad","family":"Dousti","sequence":"additional","affiliation":[]},{"given":"Philipp","family":"Koehn","sequence":"additional","affiliation":[]},{"given":"Juan","family":"Pino","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"3487","article-title":"Simple, lexicalized choice of translation timing for simultaneous speech translation","author":"fujita","year":"2013","journal-title":"InterSpeech"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-3017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2079"},{"key":"ref13","first-page":"2012","article-title":"MuST-C: a Multilingual Speech Translation Corpus","author":"di gangi","year":"2019","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies Volume 1 (Long and Short Papers)"},{"key":"ref14","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.34"},{"key":"ref16","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding"},{"key":"ref17","article-title":"Transformers with convolutional context for asr","author":"mohamed","year":"2019"},{"key":"ref18","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"ICLR (Poster)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1126"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1289"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.350"},{"key":"ref5","article-title":"Monotonic multihead attention","author":"ma","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-2090"},{"key":"ref7","article-title":"SimulMT to SimulST: Adapting Simultaneous Text Translation to End-to-End Simultaneous Speech Translation","author":"ma","year":"2020","journal-title":"Proceedings of 2020 Asia-Pacific Chapter of the Association for Computational Linguistics and the International Joint Conference on Natural Language Processing"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-1099"},{"key":"ref1","article-title":"Can neural ma-chine translation do simultaneous translation?","author":"cho","year":"2016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s10590-008-9047-0"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414897.pdf?arnumber=9414897","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:47Z","timestamp":1652197247000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414897\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414897","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}