{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T18:24:31Z","timestamp":1747765471088},"reference-count":22,"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\/icassp40776.2020.9053063","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"8499-8503","source":"Crossref","is-referenced-by-count":16,"title":["Using Speech Synthesis to Train End-To-End Spoken Language Understanding Models"],"prefix":"10.1109","author":[{"given":"Loren","family":"Lugosch","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brett H.","family":"Meyer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Derek","family":"Nowrouzezahrai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mirco","family":"Ravanelli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"ICML"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1345"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref13","article-title":"Investigating backtranslation in neural machine translation","author":"poncelas","year":"2018","journal-title":"European Association for Machine Translation (EAMT)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-59496-5_337"},{"key":"ref15","article-title":"VoiceLoop: Voice fitting and synthesis via a phonological loop","author":"taigman","year":"2018","journal-title":"ICLRE"},{"key":"ref16","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":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2396"},{"key":"ref18","article-title":"Spoken language understanding on the edge","author":"saade","year":"2019","journal-title":"NeurIPS Workshop on Energy Efficient Machine Learning and Cognitive Computing"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1832"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2366"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461785"},{"key":"ref5","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":"ASRU"},{"article-title":"Training neural speech recognition systems with synthetic speech augmentation","year":"2018","author":"li","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461718"},{"key":"ref2","article-title":"From Audio to Semantics: Approaches to end-to-end spoken language understanding","author":"haghani","year":"0","journal-title":"Proc IEEE\/ACL Workshop Spoken Lang Technol (SLT)"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1007\/978-3-030-31372-2_4","article-title":"Recent advances in end-to-end spoken language understanding","author":"tomashenko","year":"2019","journal-title":"International Conference on Statistical Language and Speech Processing"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003990"},{"key":"ref20","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"ICLRE"},{"key":"ref22","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref21","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"Deep Learning Workshop"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","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\/09053063.pdf?arnumber=9053063","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:24:28Z","timestamp":1656375868000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053063\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053063","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}