{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T20:56:56Z","timestamp":1774645016176,"version":"3.50.1"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["NRF-2020R1A2B5B03001980"],"award-info":[{"award-number":["NRF-2020R1A2B5B03001980"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2023-00262527"],"award-info":[{"award-number":["RS-2023-00262527"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Biomed. Health Inform."],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1109\/jbhi.2023.3345897","type":"journal-article","created":{"date-parts":[[2023,12,22]],"date-time":"2023-12-22T19:48:03Z","timestamp":1703274483000},"page":"1692-1703","source":"Crossref","is-referenced-by-count":10,"title":["Improving Medical Speech-to-Text Accuracy using Vision-Language Pre-training Models"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2126-0763","authenticated-orcid":false,"given":"Jaeyoung","family":"Huh","sequence":"first","affiliation":[{"name":"Department of Bio and Brain Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9223-3172","authenticated-orcid":false,"given":"Sangjoon","family":"Park","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, Yonsei College of Medicine, Seodaemun-gu, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9566-7489","authenticated-orcid":false,"given":"Jeong Eun","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Radiology, Chungnam National University Hospital, Chungnam National University College of Medicine, Daejeon, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9763-9609","authenticated-orcid":false,"given":"Jong Chul","family":"Ye","sequence":"additional","affiliation":[{"name":"Department of Kim Jaechul Graduate School of AI, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.2307\/1268779"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-73003-5_196"},{"key":"ref4","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"Hannun","year":"2014"},{"key":"ref5","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Amodei","year":"2016"},{"key":"ref6","article-title":"Wav2letter: An end-to-end convnet-based speech recognition system","author":"Collobert","year":"2016"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683535"},{"key":"ref8","article-title":"The Kaldi speech recognition toolkit","volume-title":"Proc. IEEE Workshop Autom. Speech Recognit. Understanding","author":"Povey","year":"2011"},{"key":"ref9","first-page":"1691","article-title":"JuliusAn open source real-time large vocabulary recognition engine","volume-title":"Proc. EUROSPEECH 2001 Scandinavia, 7th Eur. Conf. Speech Commun. Technol., 2nd INTERSPEECH Event","author":"Lee","year":"2001"},{"key":"ref10","article-title":"Vl-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Su","year":"2019"},{"key":"ref11","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu","year":"2019"},{"key":"ref12","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Li","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref14","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref16","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3207502"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20204"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2023.103021","article-title":"Self-supervised co-learning of uncurated images and reports enables oversight ai in radiology","volume":"91","author":"Park","year":"2024","journal-title":"Med. Image Anal."},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1561\/9781601981219"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4613-1367-0_10"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639693"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-169"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707749"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2339736"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1819"},{"key":"ref30","article-title":"Fully convolutional speech recognition","author":"Zeghidour","year":"2018"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2059"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1363"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref36","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Baevski","year":"2020"},{"key":"ref37","first-page":"1186","article-title":"Automatically detecting likely edits in clinical notes created using automatic speech recognition","volume-title":"Proc. AMIA Annu. Symp. Amer. Med. Inform. Assoc.","author":"Lybarger","year":"2017"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.nlpmc-1.2"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-09850-5_5"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-6309-3_27"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"ref43","article-title":"NegBio: A high-performance tool for negation and uncertainty detection in radiology reports","volume":"2018","author":"Peng","year":"2018","journal-title":"AMIA Summits Transl. Sci. Proc."},{"key":"ref44","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2017"},{"key":"ref45","first-page":"311","article-title":"Bleu: A method for automatic evaluation of machine translation","volume-title":"Proc. 40th Annu. Meeting Assoc. Comput. Linguistics","author":"Papineni","year":"2002"},{"key":"ref46","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee","year":"2005"},{"key":"ref47","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref49","article-title":"Radgraph: Extracting clinical entities and relations from radiology reports","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Jain","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2023.100802"},{"key":"ref51","article-title":"BERTScore: Evaluating text generation with BERT","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2020"},{"key":"ref52","article-title":"ChexBERT: Combining automatic labelers and expert annotations for accurate radiology report labeling using BERT","author":"Smit","year":"2020","journal-title":"Prco. Conf. Emp. Methods Natural Lang. Process."}],"container-title":["IEEE Journal of Biomedical and Health Informatics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221020\/10461324\/10372102.pdf?arnumber=10372102","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T20:03:10Z","timestamp":1736971390000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10372102\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3]]},"references-count":52,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/jbhi.2023.3345897","relation":{},"ISSN":["2168-2194","2168-2208"],"issn-type":[{"value":"2168-2194","type":"print"},{"value":"2168-2208","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3]]}}}