{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T00:00:58Z","timestamp":1775692858845,"version":"3.50.1"},"reference-count":36,"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\/icassp40776.2020.9053847","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"7909-7913","source":"Crossref","is-referenced-by-count":20,"title":["Analyzing ASR Pretraining for Low-Resource Speech-to-Text Translation"],"prefix":"10.1109","author":[{"given":"Mihaela C.","family":"Stoian","sequence":"first","affiliation":[]},{"given":"Sameer","family":"Bansal","sequence":"additional","affiliation":[]},{"given":"Sharon","family":"Goldwater","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","article-title":"Multilingual and unsupervised subword modeling for zero-resource languages","author":"hermann","year":"4791"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461802"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639655"},{"key":"ref30","article-title":"Multilingual end-to-end speech recognition with a single transformer on low-resource languages","author":"zhou","year":"2018"},{"key":"ref36","article-title":"Visualisation and ‘diagnostic classifiers’ reveal how recurrent and recursive neural networks process hierarchical structure","author":"hupkes","year":"2017","journal-title":"CoRR"},{"key":"ref35","article-title":"Analyzing hidden representations in end-to-end automatic speech recognition systems","author":"belinkov","year":"2017","journal-title":"NIPS"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2334"},{"key":"ref10","article-title":"How does pre-training improve low-resource speech-to-text translationƒ — a case study on a Swahili-English dataset","author":"tian","year":"2019","journal-title":"Master’s thesis"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1009"},{"key":"ref12","article-title":"Audio augmentation for speech recognition","author":"ko","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref13","article-title":"The Kaldi Speech Recognition Toolkit","author":"povey","year":"2011","journal-title":"Proc ASRU"},{"key":"ref14","article-title":"BLEU: a method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc ACL"},{"key":"ref15","article-title":"Fisher and CALLHOME Spanish-English Speech Translation","author":"post","year":"0"},{"key":"ref16","article-title":"Globalphone: a multilingual speech and text database developed at Karlsruhe University","author":"schultz","year":"2002","journal-title":"ICSLP"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref18","article-title":"Switchboard-1 Release 2 (LDC97S62)","author":"godfrey","year":"1993"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref28","article-title":"Google’s neural machine translation system: Bridging the gap between human and machine translation","author":"wu","year":"2016","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461690"},{"key":"ref27","article-title":"A theoretically grounded application of dropout in recurrent neural networks","author":"gal","year":"2016","journal-title":"Proc NIPS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1326"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00270"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461972"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1006"},{"key":"ref8","article-title":"A very low resource language speech corpus for computational language documentation experiments","author":"godard","year":"2018","journal-title":"Proc LREC"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1285"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-503"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1008"},{"key":"ref1","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":"ref20","article-title":"Rectified linear units improve restricted Boltzmann machines","author":"nair","year":"2010","journal-title":"Proc ICML"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref21","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc ICML"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"key":"ref26","article-title":"Dropout: A simple way to prevent neural networks from overfitting","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref25","article-title":"Adam: A method for stochastic opti-mization","author":"kingma","year":"2015","journal-title":"Proc ICLR"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"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\/09053847.pdf?arnumber=9053847","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:28:06Z","timestamp":1656376086000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053847\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053847","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}