{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T20:57:17Z","timestamp":1775509037904,"version":"3.50.1"},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100012389","name":"Korean Government through the grants from Institute of Information and Communications Technology Planning and Evaluation","doi-asserted-by":"publisher","award":["RS-2021-II211343"],"award-info":[{"award-number":["RS-2021-II211343"]}],"id":[{"id":"10.13039\/501100012389","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012389","name":"Korean Government through the grants from Institute of Information and Communications Technology Planning and Evaluation","doi-asserted-by":"publisher","award":["RS-2022-II220320"],"award-info":[{"award-number":["RS-2022-II220320"]}],"id":[{"id":"10.13039\/501100012389","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012389","name":"Korean Government through the grants from Institute of Information and Communications Technology Planning and Evaluation","doi-asserted-by":"publisher","award":["RS-2025-25442338"],"award-info":[{"award-number":["RS-2025-25442338"]}],"id":[{"id":"10.13039\/501100012389","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3678895","type":"journal-article","created":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T20:07:41Z","timestamp":1774901261000},"page":"48901-48917","source":"Crossref","is-referenced-by-count":0,"title":["Software\u2013Hardware Co-Design for Real-Time Speech Translation on Resource-Constrained NPUs"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6502-8207","authenticated-orcid":false,"given":"Geunjae","family":"Choi","sequence":"first","affiliation":[{"name":"Graduate School of Convergence Science and Technology, Seoul National University, Gwanak-gu, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongkyu","family":"Shin","sequence":"additional","affiliation":[{"name":"LG Electronics, Seocho-gu, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changjong","family":"Shin","sequence":"additional","affiliation":[{"name":"LG Electronics, Seocho-gu, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3845-1088","authenticated-orcid":false,"given":"Ellen Jieun","family":"Oh","sequence":"additional","affiliation":[{"name":"LG Electronics, Seocho-gu, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1792-0327","authenticated-orcid":false,"given":"Nojun","family":"Kwak","sequence":"additional","affiliation":[{"name":"Graduate School of Convergence Science and Technology, Seoul National University, Gwanak-gu, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-023-09704-w"},{"key":"ref3","first-page":"479","article-title":"OPUS-MT\u2014Building open translation services for the World","volume-title":"Proc. 22nd Annu. Conf. Eur. Assoc. Mach. Transl. (EAMT)","author":"Tiedemann"},{"key":"ref4","article-title":"Overcoming latency bottlenecks in on-device speech translation: A cascaded approach with alignment-based streaming MT","author":"Ahmed","year":"2025","journal-title":"arXiv:2508.13358"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.ijcnlp-demo.3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1814"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3711875.3729151"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-511"},{"key":"ref9","article-title":"WhisperKit: On-device real-time ASR with billion-scale transformers","author":"Orhon","year":"2025","journal-title":"arXiv:2507.10860"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-demo.20"},{"key":"ref11","article-title":"Google\u2019s neural machine translation system: Bridging the gap between human and machine translation","author":"Wu","year":"2016","journal-title":"arXiv:1609.08144"},{"key":"ref12","volume-title":"Offline Translation in Google Translate","year":"2019"},{"key":"ref13","volume-title":"Rtranslator: A real-time, on-device, speech-to-speech translator","author":"Martino","year":"2024"},{"key":"ref14","article-title":"No language left behind: Scaling human-centered machine translation","author":"Team","year":"2022","journal-title":"arXiv:2207.04672"},{"key":"ref15","article-title":"STACL: Simultaneous translation with implicit anticipation and controllable latency using prefix-to-prefix framework","author":"Ma","year":"2018","journal-title":"arXiv:1810.08398"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1126"},{"key":"ref17","article-title":"Monotonic simultaneous translation with chunk-wise reordering and refinement","author":"Han","year":"2021","journal-title":"arXiv:2110.09646"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.iwslt-1.41"},{"key":"ref19","volume-title":"Silero Vad: Pre-Trained Enterprise-Grade Voice Activity Detector (vad), Number Detector and Language Classifier","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref21","first-page":"114","article-title":"Keyformer: KV cache reduction through key tokens selection for efficient generative inference","volume-title":"Proc. Mach. Learn. Syst.","author":"Adnan"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1040"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.wmt-1.139"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.213"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.wmt-1.52"},{"key":"ref27","first-page":"979","article-title":"XCOMET: Transparent machine translation evaluation through fine-grained error detection","author":"Guerreiro","year":"2023","journal-title":"Trans. Assoc. Comput. Linguistics (TACL)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99579-3_21"},{"key":"ref29","first-page":"38087","article-title":"SmoothQuant: Accurate and efficient post-training quantization for large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xiao"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11457872.pdf?arnumber=11457872","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T19:58:07Z","timestamp":1775505487000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11457872\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3678895","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}