{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T15:38:59Z","timestamp":1777736339404,"version":"3.51.4"},"reference-count":42,"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"}],"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.2022.3205753","type":"journal-article","created":{"date-parts":[[2022,9,12]],"date-time":"2022-09-12T19:55:03Z","timestamp":1663012503000},"page":"3089-3097","source":"Crossref","is-referenced-by-count":20,"title":["Towards Contextual Spelling Correction for Customization of End-to-End Speech Recognition Systems"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9036-2248","authenticated-orcid":false,"given":"Xiaoqiang","family":"Wang","sequence":"first","affiliation":[{"name":"Microsoft, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanqing","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1089-9748","authenticated-orcid":false,"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Veljko","family":"Miljanic","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sheng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Microsoft, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hosam","family":"Khalil","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054188"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3016"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1179"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003906"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053040"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1855"},{"key":"ref11","article-title":"Transformer-transducer: End-to-end speech recognition with self-attention","author":"Yeh","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413535"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2416"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639034"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1209"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383560"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2986"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682441"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-379"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1566"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687898"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687915"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683745"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1290"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053051"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053606"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747144"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746390"},{"key":"ref31","first-page":"21708","article-title":"Fastcorrect: Fast error correction with edit alignment for automatic speech recognition","volume-title":"Proc. Neural Inf. Process. Syst.","volume":"34","author":"Leng","year":"2021"},{"key":"ref32","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. Neural Inf. Process. Syst.","volume":"27","author":"Sutskever","year":"2014"},{"key":"ref33","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref34","article-title":"Layer normalization","volume-title":"Proc. Neural Inf. Process. Syst. Deep Learn. Symp.","author":"Ba","year":"2016"},{"issue":"8","key":"ref35","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref36","doi-asserted-by":"crossref","DOI":"10.21437\/Blizzard.2021-14","article-title":"Delightfultts: The microsoft speech synthesis system for blizzard challenge 2021","author":"Liu","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-432"},{"key":"ref38","article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. Neural Inf. Process. Syst. Deep Learn. Representation Learn. Workshop","author":"Hinton","year":"2015"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1075\/li.30.1.03nad"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2981314"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9498"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-49461-2_34"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9657755\/09887861.pdf?arnumber=9887861","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T18:26:44Z","timestamp":1727980004000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9887861\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/taslp.2022.3205753","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}