{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T08:38:53Z","timestamp":1777711133529,"version":"3.51.4"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683343","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"page":"7180-7184","source":"Crossref","is-referenced-by-count":54,"title":["Leveraging Weakly Supervised Data to Improve End-to-end Speech-to-text Translation"],"prefix":"10.1109","author":[{"given":"Ye","family":"Jia","sequence":"first","affiliation":[]},{"given":"Melvin","family":"Johnson","sequence":"additional","affiliation":[]},{"given":"Wolfgang","family":"Macherey","sequence":"additional","affiliation":[]},{"given":"Ron J.","family":"Weiss","sequence":"additional","affiliation":[]},{"given":"Yuan","family":"Cao","sequence":"additional","affiliation":[]},{"given":"Chung-Cheng","family":"Chiu","sequence":"additional","affiliation":[]},{"given":"Naveen","family":"Ari","sequence":"additional","affiliation":[]},{"given":"Stella","family":"Laurenzo","sequence":"additional","affiliation":[]},{"given":"Yonghui","family":"Wu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","article-title":"Hierarchical generative modeling for controllable speech synthesis","author":"hsu","year":"2019","journal-title":"Proc ICLR"},{"key":"ref32","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"2018","journal-title":"Proc ICML"},{"key":"ref31","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with Tacotron","author":"skerry-ryan","year":"2018","journal-title":"Proc ICML"},{"key":"ref30","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc Association for Computational Linguistics (ACL)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1008"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461690"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.758176"},{"key":"ref13","article-title":"On the integration of speech recognition and statistical machine translation","author":"matusov","year":"2005","journal-title":"European Conference on Speech Communication and Technology"},{"key":"ref14","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"},{"key":"ref15","article-title":"Pre-training on high-resource speech recognition improves low-resource speech-to-text translation","author":"bansal","year":"2018","journal-title":"arXiv preprint arXiv 1809 01431"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-944"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1558"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2456"},{"key":"ref19","article-title":"Back-translation-style data augmentation for end-to-end ASR","author":"hayashi","year":"2018","journal-title":"arXiv preprint arXiv 1807 10893"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref27","article-title":"Lib-riSpeech: an ASR corpus based on public domain audio books","author":"panayotov","year":"2015","journal-title":"Proc ICASSP"},{"key":"ref3","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Adv Neur In"},{"key":"ref6","article-title":"Google’s neural machine translation system: Bridging the gap between human and machine translation","author":"wu","year":"2016","journal-title":"arXiv preprint arXiv 1609 09861"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref5","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc ICLR"},{"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":"NeurIPS Workshop on End-to-end Learning for Speech and Audio Processing"},{"key":"ref7","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Adv Neur In"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref9","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"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref20","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"Proc Deep Learn Represent Learn Workshop"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289079"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1009"},{"key":"ref24","article-title":"Natural TTS synthesis by conditioning wavenet on mel spectrogram predictions","author":"shen","year":"2017","journal-title":"Proc ICASSP"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1008"},{"key":"ref26","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","author":"jia","year":"2018","journal-title":"Adv Neur In"},{"key":"ref25","article-title":"Deep voice 3: 2000-speaker neural text-to-speech","author":"ping","year":"2018","journal-title":"Proc ICLR"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, United Kingdom","start":{"date-parts":[[2019,5,12]]},"end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683343.pdf?arnumber=8683343","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:11:59Z","timestamp":1657854719000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683343\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683343","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}