{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T08:54:04Z","timestamp":1772528044648,"version":"3.50.1"},"reference-count":31,"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\/icassp40776.2020.9053541","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"6889-6893","source":"Crossref","is-referenced-by-count":43,"title":["Unsupervised Pre-Training of Bidirectional Speech Encoders via Masked Reconstruction"],"prefix":"10.1109","author":[{"given":"Weiran","family":"Wang","sequence":"first","affiliation":[]},{"given":"Qingming","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Karen","family":"Livescu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424251"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1002\/grl.50288"},{"key":"ref11","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL-HLT"},{"key":"ref12","article-title":"GLUE: A multi-task benchmark and analysis platform for natural language understanding","author":"wang","year":"2019","journal-title":"ICLRE"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2904"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2938863"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.04.008"},{"key":"ref17","article-title":"Unsupervised learning of spoken language with visual context","author":"harwath","year":"2016","journal-title":"NeurIPS"},{"key":"ref18","article-title":"Unsupervised learning of disentangled and interpretable representations from sequential data","author":"hsu","year":"2017","journal-title":"NeurIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2194"},{"key":"ref28","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"ICLRE"},{"key":"ref4","article-title":"Rectified linear units improve restricted Boltzmann machines","author":"nair","year":"2010","journal-title":"ICML"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref3","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"AIS-TATS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2605"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.21437\/Eurospeech.1995-411","article-title":"Speaker-adaptation for hybrid HMM-ANN continuous speech recognition system","author":"neto","year":"1995","journal-title":"Eurospeech"},{"key":"ref5","article-title":"Dropout: A simple way to prevent neural networks from overfitting","author":"srivastava","year":"2014","journal-title":"JMLR"},{"key":"ref8","author":"schneider","year":"2019","journal-title":"wav2vec Unsupervised pre-training for speech recognition"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref9","article-title":"Deep contex-tualized word representations","author":"peters","year":"2018","journal-title":"NAACL-HLT"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/089976602760128018"},{"key":"ref20","author":"oord","year":"2018","journal-title":"Representation learning with contrastive predictive coding"},{"key":"ref22","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","year":"2020","journal-title":"ICLRE"},{"key":"ref21","article-title":"Learning deep representations by mutual information estimation and maximization","author":"hjelm","year":"2018","journal-title":"ICLRE"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref26","author":"abadi","year":"2015","journal-title":"TensorFlow Large-Scale Machine Learning on Heterogeneous Systems"},{"key":"ref25","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"ASRU"}],"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\/09053541.pdf?arnumber=9053541","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,29]],"date-time":"2023-09-29T19:28:22Z","timestamp":1696015702000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053541\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053541","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}