{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:23:31Z","timestamp":1775229811998,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747714","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"6642-6646","source":"Crossref","is-referenced-by-count":10,"title":["Spell My Name: Keyword Boosted Speech Recognition"],"prefix":"10.1109","author":[{"given":"Namkyu","family":"Jung","sequence":"first","affiliation":[{"name":"Naver Corporation,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Geonmin","family":"Kim","sequence":"additional","affiliation":[{"name":"Naver Corporation,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joon Son","family":"Chung","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Deep context: End-to-end contextual speech recognition","author":"golan","year":"2018","journal-title":"IEEE Spoken Language Technology Workshop"},{"key":"ref11","article-title":"Contextual speech recognition with difficult negative training examples","author":"uri","year":"2018","journal-title":"arXiv preprint arXiv 1810 12894"},{"key":"ref12","article-title":"Contextual rnn-t for open domain asr","author":"mahaveer","year":"2020","journal-title":"arXiv preprint arXiv 2006 04989"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846302"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-177"},{"key":"ref15","article-title":"Deep shallow fusion for rnn-t personalization","author":"duc","year":"2020","journal-title":"arXiv preprint arXiv 2006 04989"},{"key":"ref16","article-title":"Fast and robust unsupervised contextual biasing for speech recognition","author":"kang","year":"2020","journal-title":"arXiv preprint arXiv 2005 06138"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1209"},{"key":"ref18","article-title":"Contextualized streaming end-to-end speech recognition with trie-based deep biasing and shallow fusion","author":"duc","year":"2021","journal-title":"Proc INTERSPEECH"},{"key":"ref19","article-title":"Sequence transduction with recurrent neural networks","author":"alex","year":"2012","journal-title":"ICML Workshop on Representation Learning"},{"key":"ref4","article-title":"Speechstew: Simply mix all available speech recognition data to train one large neural network","author":"chan","year":"2021","journal-title":"arXiv preprint arXiv 2104 02133"},{"key":"ref3","article-title":"Pushing the limits of semi-supervised learning for automatic speech recognition","author":"zhang","year":"2020","journal-title":"arXiv preprint arXiv 2010 10504"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref5","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"arXiv preprint arXiv 2006 11116"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682490"},{"key":"ref7","article-title":"On using monolingual corpora in neural machine translation","author":"gulcehre","year":"2015","journal-title":"arXiv preprint arXiv 1503"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2059"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6321"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref20","article-title":"Regularizing and Optimizing LSTM Language Models","author":"merity","year":"2017","journal-title":"arXiv preprint arXiv 1708 02562"},{"key":"ref22","year":"0"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref24","year":"0"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref26","article-title":"Why inverse document frequency","author":"kishore","year":"2001","journal-title":"Proceedings of the North American Association for Computational Linguistic"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639693"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747714.pdf?arnumber=9747714","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:10:12Z","timestamp":1661199012000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747714\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747714","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}