{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T15:25:00Z","timestamp":1767626700954,"version":"3.28.0"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"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":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10022399","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:54:03Z","timestamp":1674845643000},"page":"406-413","source":"Crossref","is-referenced-by-count":9,"title":["A Study on the Integration of Pre-Trained SSL, ASR, LM and SLU Models for Spoken Language Understanding"],"prefix":"10.1109","author":[{"given":"Yifan","family":"Peng","sequence":"first","affiliation":[{"name":"Carnegie Mellon University,Pittsburgh,PA,USA"}]},{"given":"Siddhant","family":"Arora","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Pittsburgh,PA,USA"}]},{"given":"Yosuke","family":"Higuchi","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Pittsburgh,PA,USA"}]},{"given":"Yushi","family":"Ueda","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Pittsburgh,PA,USA"}]},{"given":"Sujay","family":"Kumar","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Pittsburgh,PA,USA"}]},{"given":"Karthik","family":"Ganesan","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Pittsburgh,PA,USA"}]},{"given":"Siddharth","family":"Dalmia","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Pittsburgh,PA,USA"}]},{"given":"Xuankai","family":"Chang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Pittsburgh,PA,USA"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Pittsburgh,PA,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-3014"},{"key":"ref2","article-title":"Snips voice platform: an embedded spoken language under-standing system for private-by-design voice interfaces","author":"Coucke","year":"2018","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2396"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.588"},{"key":"ref5","article-title":"Spoken language understanding on the edge","author":"Saade","year":"2018","journal-title":"ar Xiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1915"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461371"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/089120100561737"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639043"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461785"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2396"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9746137"},{"article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL HLT","author":"Devlin","key":"ref15"},{"article-title":"DeBERTa: decoding-enhanced BERT with disentangled attention","volume-title":"Proc. ICLR","author":"He","key":"ref16"},{"article-title":"wav2vec 2. 0: A framework for self-supervised learning of speech representations","volume-title":"Proc. NeurIPS","author":"Baevski","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414922"},{"key":"ref19","article-title":"On the use of external data for spoken named entity recognition","author":"Pasad","year":"2021","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1570"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9747759"},{"key":"ref22","article-title":"SPLAT: Speech-language joint pre-training for spoken language under-standing","author":"Chung","year":"2020","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1228"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/jstsp.2022.3188113"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1860"},{"article-title":"A large scale speech sentiment corpus","volume-title":"Proc. LREC","author":"Chen","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747674"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10890"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/asru51503.2021.9688137"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053606"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1341"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"article-title":"A post-processing system to yield re-duced word error rates: Recognizer output voting error reduction (rover)","volume-title":"Proc. ASRU","author":"Fiscus","key":"ref39"},{"article-title":"PyTorch: An im-perative style, high-performance deep learning library","volume-title":"Proc. NeurIPS","author":"Paszke","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"issue":"1","key":"ref45","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"The journal of machine learning research"},{"article-title":"When does label smoothing help?","volume-title":"Proc. NeurIPS","author":"M\u00fcller","key":"ref46"},{"key":"ref47","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1048"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2929"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1537"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2014.80"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/2792745.2792775"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2023,1,9]]},"location":"Doha, Qatar","end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10022399.pdf?arnumber=10022399","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T02:53:31Z","timestamp":1710384811000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10022399\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10022399","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}