{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T06:07:04Z","timestamp":1749017224066,"version":"3.28.0"},"reference-count":31,"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\/icassp39728.2021.9413719","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"7508-7512","source":"Crossref","is-referenced-by-count":4,"title":["Cascaded Models with Cyclic Feedback for Direct Speech Translation"],"prefix":"10.1109","author":[{"given":"Tsz Kin","family":"Lam","sequence":"first","affiliation":[]},{"given":"Shigehiko","family":"Schamoni","sequence":"additional","affiliation":[]},{"given":"Stefan","family":"Riezler","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003774"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref10","first-page":"4197","article-title":"Covost: A di-verse multilingual speech-to-text translation corpus","author":"wang","year":"2020","journal-title":"Language Re-sources and Evaluation Conference (LREC)"},{"key":"ref11","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Annual Meeting of the Association for Computational Linguistics (ACL)"},{"key":"ref12","first-page":"276","article-title":"Spoken language translation using automatically transcribed text in training","author":"peitz","year":"2012","journal-title":"International Workshop on Spoken Language Translation"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/E14-1065"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053126"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683602"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3115\/1075096.1075117"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3115\/1220355.1220523"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947637"},{"key":"ref19","first-page":"2469","article-title":"Deep reinforcement learning for sequence-to-sequence models","volume":"31","author":"keneshloo","year":"2020","journal-title":"IEEE Trans Neural Networks Learn Syst"},{"key":"ref28","first-page":"1019","article-title":"A theoretically grounded application of dropout in recurrent neural networks","author":"gal","year":"2016","journal-title":"Proc NIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1008"},{"key":"ref27","article-title":"Regularizing and optimizing LSTM language models","author":"merity","year":"2018","journal-title":"Proc ICLR"},{"key":"ref3","first-page":"6224","article-title":"End-to-end automatic speech translation of audio-books","author":"b\u00e9rard","year":"2018","journal-title":"Proc ICASSP"},{"key":"ref6","article-title":"Harnessing indirect training data for end-to-end automatic speech translation: Tricks of the trade","author":"pino","year":"2019","journal-title":"International Work-shop on Spoken Language Translation (IWSLT)"},{"key":"ref29","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683343"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1109"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.661"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00270"},{"key":"ref9","first-page":"3590","article-title":"LibriVoxDeEn: A corpus for german-to-english speech translation and german speech recognition","author":"beilharz","year":"2020","journal-title":"Proc Int Conference on Language Resources and Evaluation (LREC)"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"2625","DOI":"10.21437\/Interspeech.2017-503","article-title":"Sequence-to-sequence models can directly translate foreign speech","author":"weiss","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"1128","DOI":"10.21437\/Interspeech.2019-2582","article-title":"End-to-end speech translation with knowledge distillation","author":"liu","year":"2019","journal-title":"Proc INTERSPEECH"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-3049"},{"key":"ref21","first-page":"7904","article-title":"End-end speech-to-text translation with modality agnostic meta-learning","author":"indurthi","year":"0"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-017-9410-y"},{"key":"ref23","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","author":"ardila","year":"2020","journal-title":"Proc Int Conference on Language Resources and Evaluation (LREC)"},{"key":"ref26","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc NIPS"},{"key":"ref25","article-title":"Fast and accurate deep network learning by exponential linear units (elus)","author":"clevert","year":"2016","journal-title":"Proc ICLR"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","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\/09413719.pdf?arnumber=9413719","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:41:06Z","timestamp":1652197266000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413719\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413719","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}