{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T12:36:55Z","timestamp":1775738215962,"version":"3.50.1"},"reference-count":23,"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\/icassp40776.2020.9054314","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"7974-7978","source":"Crossref","is-referenced-by-count":13,"title":["End-to-End Architectures for ASR-Free Spoken Language Understanding"],"prefix":"10.1109","author":[{"given":"Elisavet","family":"Palogiannidi","sequence":"first","affiliation":[]},{"given":"Ioannis","family":"Gkinis","sequence":"additional","affiliation":[]},{"given":"George","family":"Mastrapas","sequence":"additional","affiliation":[]},{"given":"Petr","family":"Mizera","sequence":"additional","affiliation":[]},{"given":"Themos","family":"Stafylakis","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2158"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2396"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-04212-7_57"},{"key":"ref13","article-title":"Joint slot filling and intent detection via capsule neural networks","author":"zhang","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2118"},{"key":"ref15","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"bengio","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref16","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc of ASRU"},{"key":"ref17","article-title":"Musan: A music, speech, and noise corpus","author":"snyder","year":"2015"},{"key":"ref18","article-title":"Natural language understanding for dialogue systems using n-best lists","author":"mansalis","year":"2019","journal-title":"M S thesis"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-595"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2226"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2005.07.005"},{"key":"ref6","first-page":"569","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":"Proc of ASRU"},{"key":"ref5","first-page":"553","article-title":"Speech utterance classification model training without manual transcriptions","author":"wang","year":"2006","journal-title":"Proc of ICASSP"},{"key":"ref8","first-page":"720","article-title":"From audio to semantics: Approaches to end-to- end spoken language understanding","author":"haghani","year":"2018","journal-title":"Proc of SLT"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461718"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-5514"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/9781119992691"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461785"},{"key":"ref20","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref22","article-title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","author":"sanh","year":"2019"},{"key":"ref21","article-title":"Roberta: A robustly optimized BERT pretraining approach","author":"liu","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"}],"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\/09054314.pdf?arnumber=9054314","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:25:12Z","timestamp":1656375912000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054314\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054314","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}