{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:54:27Z","timestamp":1753602867926},"reference-count":33,"publisher":"IEEE","license":[{"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\/icassp39728.2021.9414411","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"7538-7542","source":"Crossref","is-referenced-by-count":6,"title":["Machine Translation Verbosity Control for Automatic Dubbing"],"prefix":"10.1109","author":[{"given":"Surafel M.","family":"Lakew","sequence":"first","affiliation":[{"name":"Amazon AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcello","family":"Federico","sequence":"additional","affiliation":[{"name":"Amazon AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yue","family":"Wang","sequence":"additional","affiliation":[{"name":"Amazon AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cuong","family":"Hoang","sequence":"additional","affiliation":[{"name":"Amazon AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yogesh","family":"Virkar","sequence":"additional","affiliation":[{"name":"Amazon AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roberto","family":"Barra-Chicote","sequence":"additional","affiliation":[{"name":"Amazon AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert","family":"Enyedi","sequence":"additional","affiliation":[{"name":"Amazon AI"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"kingma","key":"ref33"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3115\/1557769.1557821"},{"key":"ref10","article-title":"Controllable Abstractive Summarization","author":"fan","year":"2017","journal-title":"Proc of the 2nd Workshop on Neural Machine Translation and Generation"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1401"},{"key":"ref12","article-title":"Machine Translation with Unsupervised Length-Constraints","author":"niehues","year":"2020","journal-title":"Proc of AMTA"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1166"},{"key":"ref14","first-page":"193","article-title":"Controlling the Reading Level of Machine Translation Output","author":"marchisio","year":"2019","journal-title":"Proc of Machine Translation Summit XVII Volume 1 Research Track"},{"key":"ref15","first-page":"6","article-title":"Improved Neural Machine Translation using Side Information","author":"hoang","year":"2018","journal-title":"Proc of the Australasian Language Technology Association Workshop 2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2050"},{"key":"ref17","first-page":"2012","article-title":"MuST-C: a Multilingual Speech Translation Cor-pus","author":"di gangi","year":"2019","journal-title":"Proc NAACL"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"2625","DOI":"10.21437\/Interspeech.2017-503","article-title":"Sequence-to-Sequence Models Can Directly Translate For-eign Speech","author":"weiss","year":"2017","journal-title":"Proc Interspeech 2017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/IberSPEECH.2018-13"},{"key":"ref28","article-title":"Room impulse response generator","author":"habets","year":"2006","journal-title":"Tech Rep 4"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2019-1621","article-title":"Prosodic Phrase Alignment for Machine Dubbing","author":"\u00f6ktem","year":"2019","journal-title":"Proc INTERSPEECH"},{"key":"ref27","first-page":"1","article-title":"An improved algorithm for blind reverberation time estimation","author":"l\u00f6llmann","year":"2010","journal-title":"Proc IWAENC"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1075\/btl.56.07cha"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2983"},{"article-title":"Google’s neural machine translation system: Bridging the gap between human and machine translation","year":"2016","author":"wu","key":"ref29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.iwslt-1.31"},{"key":"ref8","article-title":"Controlling the output length of neural machine translation","author":"lakew","year":"2019","journal-title":"Proc IWSLT"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-5210"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.661"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1140"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2008.917989"},{"key":"ref20","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-2026"},{"key":"ref21","article-title":"Ro-bust neural machine translation for clean and noisy speech translation","author":"di gangi","year":"2019","journal-title":"Proc IWSLT"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1424"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682168"},{"key":"ref26","article-title":"Singing voice separation with deep u-net convolutional networks","author":"jansson","year":"2017","journal-title":"Proc ISMIR"},{"key":"ref25","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"Proc ICMAI"}],"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\/09414411.pdf?arnumber=9414411","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:19:47Z","timestamp":1659485987000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414411\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414411","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}