{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:34:03Z","timestamp":1776890043047,"version":"3.51.2"},"reference-count":28,"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\/icassp40776.2020.9053281","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"7984-7988","source":"Crossref","is-referenced-by-count":32,"title":["Leveraging Unpaired Text Data for Training End-To-End Speech-to-Intent Systems"],"prefix":"10.1109","author":[{"given":"Yinghui","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong-Kwang","family":"Kuo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Samuel","family":"Thomas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zvi","family":"Kons","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kartik","family":"Audhkhasi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brian","family":"Kingsbury","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ron","family":"Hoory","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Picheny","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2018.8706581"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2158"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2366"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref14","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL-HLT"},{"key":"ref15","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref16","first-page":"689","article-title":"Multimodal deep learning","author":"ngiam","year":"2011","journal-title":"Proceedings of the 28th International Conference on Machine Learning (ICML-11)"},{"key":"ref17","first-page":"1247","article-title":"Deep canonical correlation analysis","author":"andrew","year":"2013","journal-title":"International Conference on Machine Learning"},{"key":"ref18","first-page":"1083","article-title":"On deep multi-view representation learning","author":"wang","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref19","first-page":"649","article-title":"Jointly discovering visual objects and spoken words from raw sensory input","author":"harwath","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"692","DOI":"10.1109\/SLT.2018.8639513","article-title":"End-to-end named entity and semantic concept extraction from speech","author":"ghannay","year":"2018","journal-title":"Proceedings of 2018 IEEE Spoken Language Technology Workshop (SLT)"},{"key":"ref27","article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit","author":"veaux","year":"2017","journal-title":"Centre for Speech Technology Research University of Edinburgh"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461718"},{"key":"ref6","first-page":"720","article-title":"From audio to semantics: Approaches to end-to-end spoken language understanding","author":"haghani","year":"2018","journal-title":"Proc 2018 IEEE SLT"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2396"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415176"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1832"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"569","DOI":"10.1109\/ASRU.2017.8268987","article-title":"Exploring ASR-free end-to-end modeling to improve spoken language understanding in a cloud-based dialog system","author":"qian","year":"2017","journal-title":"Automatic Speech Recognition and Understanding (ASRU) 2017 IEEE Workshop on"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2001106"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461785"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2841"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683706"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1952"},{"key":"ref24","article-title":"Transformers: State-of-the-art natural language processing","author":"wolf","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1705"}],"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\/09053281.pdf?arnumber=9053281","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:21:05Z","timestamp":1656375665000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053281\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053281","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}