{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T08:53:59Z","timestamp":1772528039117,"version":"3.50.1"},"reference-count":25,"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\/icassp40776.2020.9054458","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"6419-6423","source":"Crossref","is-referenced-by-count":199,"title":["Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders"],"prefix":"10.1109","author":[{"given":"Andy T.","family":"Liu","sequence":"first","affiliation":[]},{"given":"Shu-wen","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Po-Han","family":"Chi","sequence":"additional","affiliation":[]},{"given":"Po-chun","family":"Hsu","sequence":"additional","affiliation":[]},{"given":"Hung-yi","family":"Lee","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2048"},{"key":"ref11","article-title":"Recurrent neural` network based language model","author":"mikolov","year":"2010","journal-title":"Eleventh Annual Conference of the International Speech Communication Association"},{"key":"ref12","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref13","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1910"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2702"},{"key":"ref16","article-title":"Convolutional sequence to sequence learning","author":"gehring","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1177\/107769905303000401"},{"key":"ref18","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"liu","year":"2019"},{"key":"ref19","article-title":"Albert: A lite bert for self-supervised learning of language representations","author":"lan","year":"2019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-82"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2341"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref5","article-title":"Representation learning with contrastive predictive coding","author":"den oord","year":"2018"},{"key":"ref8","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"authors","year":"2020","journal-title":"ICLR 2020 Conference Blind Submission"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2938863"},{"key":"ref9","article-title":"Unsupervised learning of efficient and robust speech representations","author":"authors","year":"2020","journal-title":"ICLR 2020 Conference Blind Submission"},{"key":"ref1","article-title":"Attention is all you need","author":"vaswani","year":"2017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref22","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref23","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"}],"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\/09054458.pdf?arnumber=9054458","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:21:36Z","timestamp":1656375696000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054458\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054458","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}