{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:29:50Z","timestamp":1775230190879,"version":"3.50.1"},"reference-count":23,"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\/icassp40776.2020.9054295","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"7084-7088","source":"Crossref","is-referenced-by-count":114,"title":["Self-Training for End-to-End Speech Recognition"],"prefix":"10.1109","author":[{"given":"Jacob","family":"Kahn","sequence":"first","affiliation":[]},{"given":"Ann","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Awni","family":"Hannun","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3167"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2008-122","article-title":"Unsupervised versus supervised training of acoustic models","author":"ma","year":"2008","journal-title":"InterSpeech"},{"key":"ref12","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"International Conference on Learning Representations"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-343","article-title":"Towards better decoding and language model integration in sequence to sequence models","author":"chorowski","year":"2017","journal-title":"InterSpeech"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3115\/1118108.1118117"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref17","article-title":"Wav2letter++: A fast opensource speech recognition system","author":"pratap","year":"2019","journal-title":"International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref18","article-title":"Fully convolutional speech recognition","author":"zeghidour","year":"2018"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.21437\/Eurospeech.1999-599","article-title":"Unsupervised training of a speech recognizer: Recent experiments","author":"kemp","year":"1999","journal-title":"Eurospeech"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.940841"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2460"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707741"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2004.838537"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1385"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1965.1053799"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1780"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683307"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846323"},{"key":"ref22","article-title":"Back-translation-style data augmentation for end-to-end ASR","author":"hayashi","year":"2018","journal-title":"Spoken Language Technology Workshop (SLT)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683690"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1746"}],"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\/09054295.pdf?arnumber=9054295","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,20]],"date-time":"2022-10-20T23:49:52Z","timestamp":1666309792000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054295\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054295","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}