{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T18:59:35Z","timestamp":1767898775693,"version":"3.49.0"},"reference-count":26,"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.2019.8683550","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"page":"7170-7174","source":"Crossref","is-referenced-by-count":25,"title":["Towards Unsupervised Speech-to-text Translation"],"prefix":"10.1109","author":[{"given":"Yu-An","family":"Chung","sequence":"first","affiliation":[]},{"given":"Wei-Hung","family":"Weng","sequence":"additional","affiliation":[]},{"given":"Schrasing","family":"Tong","sequence":"additional","affiliation":[]},{"given":"James","family":"Glass","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Unsupervised cross-modal alignment of speech and text embedding spaces","author":"chung","year":"2018","journal-title":"NIPS"},{"key":"ref11","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"NIPS"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269008"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2341"},{"key":"ref15","article-title":"Learning word embeddings from speech","author":"chung","year":"2017","journal-title":"NIPS Machine Learning for Audio Signal Processing Workshop"},{"key":"ref16","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"NIPS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-1614"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1101"},{"key":"ref19","article-title":"Augmenting librispeech with french translations: A multimodal corpus for direct speech translation evaluation","author":"kocabiyikoglu","year":"2018","journal-title":"LREC"},{"key":"ref4","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 NIPS workshop on End-to-end Learning for Speech and Audio Processing"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461690"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1399"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1549"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1073"},{"key":"ref7","article-title":"Word translation without parallel data","author":"conneau","year":"2018","journal-title":"ICLRE"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1326"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1009"},{"key":"ref1","article-title":"Sequence-to-sequence models can directly translate foreign speech","author":"weiss","year":"2017","journal-title":"INTER-SPEECH"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"ref21","article-title":"Bleu: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"ACL"},{"key":"ref24","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref23","article-title":"Kenlm: Faster and smaller language model queries","author":"heafield","year":"2011","journal-title":"WMT"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-82"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1072"}],"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\/08683550.pdf?arnumber=8683550","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:11:49Z","timestamp":1657854709000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683550\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683550","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}