{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:11:57Z","timestamp":1766067117104},"reference-count":29,"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\/icassp40776.2020.9053176","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"source":"Crossref","is-referenced-by-count":87,"title":["Deep Contextualized Acoustic Representations for Semi-Supervised Speech Recognition"],"prefix":"10.1109","author":[{"given":"Shaoshi","family":"Ling","sequence":"first","affiliation":[]},{"given":"Yuzong","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Julian","family":"Salazar","sequence":"additional","affiliation":[]},{"given":"Katrin","family":"Kirchhoff","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2593800"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref12","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL-HLT"},{"key":"ref13","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","author":"yang","year":"2019","journal-title":"arXiv preprint arXiv 1906 03008"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3167"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3246"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref18","first-page":"153","article-title":"Greedy layer-wise training of deep networks","author":"bengio","year":"2007","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462037"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1780"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1746"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462331"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707741"},{"key":"ref29","article-title":"SpanBERT: Improving pretraining by representing and predicting spans","author":"joshi","year":"2019","journal-title":"arXiv preprint arXiv 1907 11634"},{"key":"ref5","first-page":"6670","article-title":"Lessons from building acoustic models with a million hours of speech","author":"parthasarathi","year":"2019","journal-title":"ICASSP"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"1353","DOI":"10.21437\/Interspeech.2010-19","article-title":"Semisupervised training of gaussian mixture models by conditional entropy minimization","author":"huang","year":"2010","journal-title":"InterSpeech"},{"key":"ref7","first-page":"529","article-title":"Semi-supervised learning by entropy minimization","author":"grandvalet","year":"2005","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1596"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2009.03.004"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638959"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2341"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2938863"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref24","article-title":"vqwav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"2019","journal-title":"arXiv preprint arXiv 1910 05453"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"}],"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\/09053176.pdf?arnumber=9053176","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,29]],"date-time":"2023-09-29T19:29:01Z","timestamp":1696015741000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053176\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053176","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}