{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T15:33:38Z","timestamp":1778168018892,"version":"3.51.4"},"reference-count":59,"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\/asru46091.2019.9003832","type":"proceedings-article","created":{"date-parts":[[2020,2,21]],"date-time":"2020-02-21T07:01:33Z","timestamp":1582268493000},"page":"570-577","source":"Crossref","is-referenced-by-count":38,"title":["Multilingual End-to-End Speech Translation"],"prefix":"10.1109","author":[{"given":"Hirofumi","family":"Inaguma","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin","family":"Duh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tatsuya","family":"Kawahara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"921","article-title":"To-wards fluent translations from disfluent speech","author":"salesky","year":"2018","journal-title":"Proceedings of SLT"},{"key":"ref38","first-page":"147","article-title":"Fine-tuning on clean data for end-to-end speech translation: FBK@IWSLT 2018","author":"di gangi","year":"2018","journal-title":"Proceedings of IWSLT"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1101"},{"key":"ref32","first-page":"3586","article-title":"Audio augmentation for speech recognition","author":"ko","year":"2015","journal-title":"Proceedings of Inter r-speech"},{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-343","article-title":"Recurrent neural network based language model","author":"mikolov","year":"2010","journal-title":"Proceedings of Interspeech"},{"key":"ref30","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proceedings of NIPS"},{"key":"ref37","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proceedings of ASRU"},{"key":"ref36","first-page":"5206","article-title":"Librispeech: an ASR corpus based on public domain audio books","author":"panayotov","year":"2015","journal-title":"Proceedings of ICASSP"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854197"},{"key":"ref34","first-page":"2012","article-title":"MuST-C: a multilingual speech translation corpus","author":"di gangi","year":"2019","journal-title":"Proc HLT-NAACL"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"1240","DOI":"10.1109\/JSTSP.2017.2763455","article-title":"Hybrid CTC\/attention architecture for end-to-end speech recognition","volume":"11","author":"shinji","year":"2017","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1048"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1320"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.758176"},{"key":"ref20","article-title":"Aug-menting Librispeech with French translations: A multimodal corpus for direct speech translation evaluation","author":"kocabiyikoglu","year":"2018","journal-title":"Proceedings of LREC"},{"key":"ref22","author":"godard","year":"2017","journal-title":"A very low resource language speech corpus for computational language documentation experiments"},{"key":"ref21","first-page":"2","article-title":"The iwslt 2018 evaluation campaign","author":"jan","year":"2018","journal-title":"Proceedings of IWSLT"},{"key":"ref24","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proceedings of ICL"},{"key":"ref23","article-title":"Attention is all you need","author":"ashish","year":"2017","journal-title":"Proc NIPS"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1008"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268972"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00067"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6309"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1166"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462083"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855086"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424246"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1009"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1308"},{"key":"ref10","first-page":"89","article-title":"Kit lecture translator: Multilingual speech translation with one-shot learning","author":"dessloch","year":"2018","journal-title":"Proceedings of the 27th International Conference on Computational Linguistics System Demonstrations"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268945"},{"key":"ref40","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proceedings of ACL"},{"key":"ref12","first-page":"4904","article-title":"Multilingual speech recognition with a single end-to-end model","author":"shubham","year":"2018","journal-title":"Proceedings of ICASSP"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461802"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639655"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682918"},{"key":"ref16","article-title":"Google's multilingual neural machine translation system: enabling zero-shot translation","author":"melvin","year":"2016","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref17","article-title":"Toward multilingual neural machine translation with universal encoder and decoder","author":"ha","year":"2016","journal-title":"Proceedings of IWSLT"},{"key":"ref18","first-page":"105","article-title":"Effective strategies in zero-shot neural machine translation","author":"ha","year":"2017","journal-title":"Proceedings of IWSLT"},{"key":"ref19","article-title":"Improved speech-to-text translation with the Fisher and Callhome Spanish-English speech translation corpus","author":"post","year":"2013","journal-title":"Proceedings of IWSLT"},{"key":"ref4","first-page":"2625","article-title":"Sequence-to-sequence models can directly translate foreign speech","author":"ron","year":"2017","journal-title":"Proceedings of Interspeech"},{"key":"ref3","author":"berard","year":"2016","journal-title":"Listen and translate A proof of concept for end-to-end speech-to-text translation"},{"key":"ref6","first-page":"450","article-title":"Exploring the use of acoustic embeddings in neural machine translation","author":"salil","year":"2017","journal-title":"Proceedings of ASRU"},{"key":"ref5","first-page":"6224","article-title":"End-to-end automatic speech translation of audio-books","author":"b\u00e9rard","year":"2018","journal-title":"Proceedings of ICASSP"},{"key":"ref8","article-title":"Leveraging weakly supervised data to improve end-to-end speech-to-text translation","author":"ye","year":"2019","journal-title":"Proceedings of ICASSP"},{"key":"ref7","author":"liu","year":"2019","journal-title":"End-to-End Speech Translation with Knowledge Distillation"},{"key":"ref49","first-page":"4272","article-title":"Parallel corpora in Mboshi (Bantu C25, Congo-Brazzaville)","author":"rialland","year":"2018","journal-title":"Proceedings of LREC"},{"key":"ref9","first-page":"261","article-title":"Wit3: Web inventory of transcribed and translated talks","author":"cettolo","year":"2012","journal-title":"10th Conference of the European Association for Machine Translation"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref45","author":"zaremba","year":"2014","journal-title":"Recurrent Neural Network Regularization"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1006"},{"key":"ref47","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"bengio","year":"2015","journal-title":"Proceedings of NIPS"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref41","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proceedings of ICL"},{"key":"ref44","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"},{"key":"ref43","author":"matthew","year":"2012","journal-title":"ADADELTA An Adaptive Learning Rate Method"}],"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\/09003832.pdf?arnumber=9003832","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,27]],"date-time":"2023-09-27T08:50:04Z","timestamp":1695804604000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9003832\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/asru46091.2019.9003832","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}