{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T20:10:42Z","timestamp":1790712642772,"version":"4.1.0"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"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":[[2019,12]]},"DOI":"10.1109\/asru46091.2019.9004003","type":"proceedings-article","created":{"date-parts":[[2020,2,21]],"date-time":"2020-02-21T02:01:33Z","timestamp":1582250493000},"page":"585-592","source":"Crossref","is-referenced-by-count":19,"title":["One-to-Many Multilingual End-to-End Speech Translation"],"prefix":"10.1109","author":[{"given":"Mattia A.","family":"Di Gangi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matteo","family":"Negri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Turchi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3045"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.4000\/books.aaccademia.2419"},{"key":"ref32","author":"zhou","year":"2018","journal-title":"Multilingual End-to-End Speech Recognition with a Single Transformer on Low-Resource Languages"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461972"},{"key":"ref30","author":"lakew","year":"2018","journal-title":"A Comparison of Transformer and Recurrent Neural Networks on Multilingual Neural Machine Translation"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref36","article-title":"Deep Neural Machine Translation with Weakly-Recurrent Units","author":"di gangi","year":"2018","journal-title":"Proc of EAMT"},{"key":"ref35","article-title":"Convolutional Sequence to Sequence Learning","author":"gehring","year":"2017","journal-title":"Proc of ICML"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-3204"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472617"},{"key":"ref11","article-title":"State-of-the-art Speech Recognition With Sequence-to-Sequence Models","author":"chung-cheng","year":"2018","journal-title":"Proc of ICASSP"},{"key":"ref12","author":"hassan","year":"2018","journal-title":"Achieving human parity on automatic chinese to english news translation"},{"key":"ref13","first-page":"2012","article-title":"MuST-C: a Multilingual Speech Translation Corpus","author":"di gangi","year":"2019","journal-title":"Proc of NAACL"},{"key":"ref14","doi-asserted-by":"crossref","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":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1006"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461690"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1008"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-944"},{"key":"ref19","author":"jia","year":"2018","journal-title":"Leveraging Weakly Supervised Data to Improve End-to-End Speech-to-Text Translation"},{"key":"ref28","article-title":"Toward Multilingual Neural Machine Translation with Universal Encoder and Decoder","author":"ha","year":"2016","journal-title":"Proceedings of International Workshop on Spoken Language Translation (IWSLT)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6309"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref6","article-title":"Attention is All You Need","author":"ashish","year":"2017","journal-title":"Proc of NIPS 2017"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00065"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1616"},{"key":"ref8","article-title":"Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation","author":"b\u00e9rard","year":"2016","journal-title":"Proc of NIPS Workshop on end-to-end learning for speech and audio processing"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6401"},{"key":"ref2","article-title":"Deep Speech 2: End-to-end Speech Recognition in English and Mandarin","author":"amodei","year":"2016","journal-title":"Proc of ICML"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2076"},{"key":"ref1","article-title":"Se-quence to Sequence Learning with Neural Networks","author":"sutskever","year":"2014","journal-title":"Proc of NIPS"},{"key":"ref46","article-title":"Au-tomatic differentiation in PyTorch","author":"paszke","year":"0","journal-title":"NIPS 2017 Workshop on Autodiff"},{"key":"ref20","author":"liu","year":"2019","journal-title":"End-to-End Speech Translation with Knowledge Distillation"},{"key":"ref45","article-title":"Adam: A Method for Stochastic Optimization","author":"kingma","year":"2015","journal-title":"Proc of ICLR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1004"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00270"},{"key":"ref42","first-page":"448","article-title":"Batch normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","author":"loffe","year":"2015","journal-title":"Proc of ICML"},{"key":"ref24","article-title":"Multi-task Sequence to Sequence Learning","author":"luong","year":"2016","journal-title":"Proc of ICLR"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1166"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1101"},{"key":"ref43","author":"ba","year":"2016","journal-title":"Layer normalization"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1026"}],"event":{"name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"SG, Singapore","start":{"date-parts":[[2019,12,14]]},"end":{"date-parts":[[2019,12,18]]}},"container-title":["2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8985378\/9003727\/09004003.pdf?arnumber=9004003","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T10:44:17Z","timestamp":1658141057000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9004003\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/asru46091.2019.9004003","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}