{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T15:55:21Z","timestamp":1774367721214,"version":"3.50.1"},"reference-count":27,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100023443","name":"Commercializations Promotion Agency for R and D Outcomes","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100023443","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Korea Government","award":["RS2023-00235082"],"award-info":[{"award-number":["RS2023-00235082"]}]},{"name":"Institute of Information & Communications Technology Planning & Evaluation"},{"name":"Korea Government","award":["2021-0-01341"],"award-info":[{"award-number":["2021-0-01341"]}]},{"name":"Artificial Intelligence Graduate School Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/lsp.2024.3491019","type":"journal-article","created":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T18:42:45Z","timestamp":1730745765000},"page":"26-30","source":"Crossref","is-referenced-by-count":1,"title":["Towards Maximum Likelihood Training for Transducer-Based Streaming Speech Recognition"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6997-205X","authenticated-orcid":false,"given":"Hyeonseung","family":"Lee","sequence":"first","affiliation":[{"name":"XL8 Inc., Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8631-4489","authenticated-orcid":false,"given":"Ji Won","family":"Yoon","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Chung-Ang University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5062-7209","authenticated-orcid":false,"given":"Sungsoo","family":"Kim","sequence":"additional","affiliation":[{"name":"Institute of New Media and Communications, Department of Electrical and Computer Engineering, Seoul National University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0568-4902","authenticated-orcid":false,"given":"Nam Soo","family":"Kim","sequence":"additional","affiliation":[{"name":"Institute of New Media and Communications, Department of Electrical and Computer Engineering, Seoul National University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054235"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003775"},{"key":"ref3","article-title":"Google USM: Scaling automatic speech recognition beyond 100 languages","author":"Zhang","year":"2023"},{"key":"ref4","first-page":"1","article-title":"Scaling speech technology to 1,000 languages","volume":"25","author":"Pratap","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413899"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414607"},{"key":"ref7","first-page":"2021","article-title":"Dual-mode ASR: Unify and improve streaming ASR with full-context modeling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054250"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682256"},{"key":"ref15","first-page":"1403","article-title":"Imputer: Sequence modelling via imputation and dynamic programming","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chan","year":"2020"},{"key":"ref16","first-page":"4257","article-title":"Global normalization for streaming speech recognition in a modular framework","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Variani","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref18","first-page":"1530","article-title":"Variational inference with normalizing flows","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rezende","year":"2015"},{"key":"ref19","article-title":"Icefall [Source Code]","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99579-3_21"},{"issue":"2","key":"ref22","first-page":"23","article-title":"A new algorithm for data compression","volume":"12","author":"Gage","year":"1994","journal-title":"C Users J."},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref24","article-title":"Zipformer: A faster and better encoder for automatic speech recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yao","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054419"},{"key":"ref26","first-page":"881","article-title":"Made: Masked autoencoder for distribution estimation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Germain","year":"2015"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/97\/10802935\/10742492.pdf?arnumber=10742492","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,17]],"date-time":"2024-12-17T19:39:29Z","timestamp":1734464369000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10742492\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/lsp.2024.3491019","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}