{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T22:35:13Z","timestamp":1768343713371,"version":"3.49.0"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Open Research Projects of Zhejiang Lab","award":["2019KD0AD01\/004"],"award-info":[{"award-number":["2019KD0AD01\/004"]}]},{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","award":["LQ21F020004"],"award-info":[{"award-number":["LQ21F020004"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/taslp.2022.3153268","type":"journal-article","created":{"date-parts":[[2022,2,24]],"date-time":"2022-02-24T20:31:28Z","timestamp":1645734688000},"page":"1207-1218","source":"Crossref","is-referenced-by-count":15,"title":["ARoBERT: An ASR Robust Pre-Trained Language Model for Spoken Language Understanding"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1010-9678","authenticated-orcid":false,"given":"Chengyu","family":"Wang","sequence":"first","affiliation":[{"name":"Zhejiang Lab, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suyang","family":"Dai","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yipeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Yang","sequence":"additional","affiliation":[{"name":"Zhejiang Lab, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5184-9886","authenticated-orcid":false,"given":"Minghui","family":"Qiu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kehan","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Zhou","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Huang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1226"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3208"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054248"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3233\/KES-180374"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.07.053"},{"key":"ref6","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in English and Mandarin","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"48","author":"Amodei","year":"2016"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref8","first-page":"12 449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"33","author":"Baevski","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1178"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461831"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2211"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2018.12.007"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2020.03.002"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1118"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683573"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1958"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11431-020-1647-3"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref19","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lan","year":"2020"},{"key":"ref20","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-47"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2844"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054689"},{"issue":"30","key":"ref24","first-page":"5998","article-title":"Attention is all you need","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref26","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"ref27","article-title":"StructBERT: Incorporating language structures into pre-training for deep language understanding","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref29","first-page":"140:1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3340555.3356096"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3340555.3356099"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461785"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2158"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054314"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414313"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.81"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401050"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.195"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3340555.3356098"},{"key":"ref40","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3481911"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3340555.3356100"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1244"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2034"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1181"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852406"},{"key":"ref47","first-page":"1243","article-title":"Convolutional sequence to sequence learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gehring","year":"2017"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-7"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.160"},{"key":"ref50","article-title":"Phonetic word embeddings","author":"Sharma","year":"2021"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9657755\/09721159.pdf?arnumber=9721159","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T23:47:51Z","timestamp":1705535271000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9721159\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/taslp.2022.3153268","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}