{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T17:58:17Z","timestamp":1772301497884,"version":"3.50.1"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832281","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"78-85","source":"Crossref","is-referenced-by-count":2,"title":["Contextualized Automatic Speech Recognition With Dynamic Vocabulary"],"prefix":"10.1109","author":[{"given":"Yui","family":"Sudo","sequence":"first","affiliation":[{"name":"Honda Research Institute Japan Co., Ltd.,,Japan"}]},{"given":"Yosuke","family":"Fukumoto","sequence":"additional","affiliation":[{"name":"Honda Research Institute Japan Co., Ltd.,,Japan"}]},{"given":"Muhammad","family":"Shakeel","sequence":"additional","affiliation":[{"name":"Honda Research Institute Japan Co., Ltd.,,Japan"}]},{"given":"Yifan","family":"Peng","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3328283"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref4","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","volume-title":"Proc. ICML","author":"Graves"},{"key":"ref5","article-title":"Sequence transduction with recurrent neural networks","volume-title":"Proc. ICML","author":"Graves"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref7","article-title":"Attention-based models for speech recognition","volume":"28","author":"Chorowski","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref9","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053606"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1303"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1787"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2416"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462682"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1392"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1296"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639034"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2986"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-767"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747101"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687898"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.147"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447782"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1257"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1566"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389716"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682441"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1434"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447652"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1320"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3205753"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095434"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.549"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096065"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389676"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1194"},{"key":"ref38","article-title":"4d asr: Joint beam search integrating ctc, attention, transducer, and mask predict decoders","author":"Sudo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1333"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1517"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003749"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"},{"key":"ref44","article-title":"Corpus of spontaneous Japanese: Its design and evaluation","volume-title":"ISCA & IEEE Workshop on Spontaneous Speech Processing and Recognition","author":"Maekawa"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(90)90011-W"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","location":"Macao","start":{"date-parts":[[2024,12,2]]},"end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832281.pdf?arnumber=10832281","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:09:38Z","timestamp":1737101378000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832281\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832281","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}