{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T16:45:30Z","timestamp":1765039530993},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053406","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"7924-7928","source":"Crossref","is-referenced-by-count":8,"title":["SkinAugment: Auto-Encoding Speaker Conversions for Automatic Speech Translation"],"prefix":"10.1109","author":[{"given":"Arya D.","family":"McCarthy","sequence":"first","affiliation":[]},{"given":"Liezl","family":"Puzon","sequence":"additional","affiliation":[]},{"given":"Juan","family":"Pino","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-28"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1789"},{"key":"ref12","article-title":"Augmenting Librispeech with French translations: A multimodal corpus for direct speech translation evaluation","author":"kocabiyikoglu","year":"2018","journal-title":"Proc LREC"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461690"},{"key":"ref14","article-title":"MuST-C: a multilingual speech translation corpus","author":"di gangi","year":"2019","journal-title":"Proc NAACL-HLT"},{"key":"ref15","first-page":"311","article-title":"BLEU: a method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc ACL"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3115\/1557769.1557821"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref18","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1006"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683343"},{"key":"ref5","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 2017"},{"key":"ref8","article-title":"TTS skins: Speaker conversion via ASR","author":"polyak","year":"2019","journal-title":"CoRR"},{"key":"ref7","article-title":"Harnessing indirect training data for end-to-end automatic speech translation: Tricks of the trade","author":"pino","year":"2019","journal-title":"Proc IWSLT"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854197"},{"article-title":"Voice conversion: state of the art and perspectives (special issue of speech communication)","year":"1995","author":"moulines","key":"ref9"},{"key":"ref1","article-title":"Improved speech-to-text translation with the Fisher and Callhome Spanish–English speech translation corpus","author":"post","year":"2013","journal-title":"Proc IWSLT"},{"article-title":"Measuring the effectiveness of voice conversion on speaker identification and automatic speech recognition systems","year":"2019","author":"keskin","key":"ref20"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053406.pdf?arnumber=9053406","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:21:04Z","timestamp":1656375664000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053406\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053406","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}