{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T11:20:57Z","timestamp":1762341657112,"version":"3.28.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414558","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"7478-7482","source":"Crossref","is-referenced-by-count":18,"title":["St-Bert: Cross-Modal Language Model Pre-Training for End-to-End Spoken Language Understanding"],"prefix":"10.1109","author":[{"given":"Minjeong","family":"Kim","sequence":"first","affiliation":[{"name":"NAVER CLOVA"}]},{"given":"Gyuwan","family":"Kim","sequence":"additional","affiliation":[{"name":"NAVER CLOVA"}]},{"given":"Sang-Woo","family":"Lee","sequence":"additional","affiliation":[{"name":"NAVER CLOVA"}]},{"given":"Jung-Woo","family":"Ha","sequence":"additional","affiliation":[{"name":"NAVER CLOVA"}]}],"member":"263","reference":[{"key":"ref31","first-page":"7979","article-title":"End-to-end spoken language understanding without matched language speech model pretraining data","author":"price","year":"2020","journal-title":"ICASSP"},{"article-title":"Nsml: Meet the mlaas platform with a real-world case study","year":"2018","author":"kim","key":"ref30"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461718"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2366"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639585"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref14","first-page":"13","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"lu","year":"2019","journal-title":"NeurIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"ref17","first-page":"7354","article-title":"Unsupervised cross-modal alignment of speech and text embedding spaces","author":"chung","year":"2018","journal-title":"NeurIPS"},{"article-title":"Distilling the knowledge in a neural network","year":"2015","author":"hinton","key":"ref18"},{"article-title":"Speechbert: Cross-modal pre-trained language model for endto-end spoken question answering","year":"2019","author":"chuang","key":"ref19"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054689"},{"key":"ref4","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL-HLT"},{"article-title":"Snips voice platform: an embedded spoken language understanding system for private-by-design voice interfaces","year":"2018","author":"coucke","key":"ref27"},{"key":"ref3","first-page":"7999","article-title":"Large-scale unsupervised pre-training for end-to-end spoken language understanding","author":"wang","year":"2020","journal-title":"ICASSP"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2456"},{"article-title":"Spoken language understanding on the edge","year":"2018","author":"saade","key":"ref29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1246"},{"article-title":"Cross-lingual language model pretraining","year":"2019","author":"lample","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2396"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-31372-2_4"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461785"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1252"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"498","DOI":"10.21437\/Interspeech.2017-1386","article-title":"Montreal forced aligner: Trainable text-speech alignment using kaldi","volume":"2017","author":"mcauliffe","year":"2017","journal-title":"InterSpeech"},{"key":"ref21","first-page":"8342","article-title":"Don’t stop pretraining: Adapt language models to domains and tasks","author":"gururangan","year":"2020","journal-title":"ACL"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.344"},{"article-title":"Google’s neural machine translation system: Bridging the gap between human and machine translation","year":"2016","author":"wu","key":"ref23"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"kingma","key":"ref26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414558.pdf?arnumber=9414558","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:18:37Z","timestamp":1659485917000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414558\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414558","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}