{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:00:17Z","timestamp":1775199617441,"version":"3.50.1"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"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":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434612","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["LLM-Based Dictation Detection from Doctor-Patient Conversations"],"prefix":"10.1109","author":[{"given":"Siyuan","family":"Chen","sequence":"first","affiliation":[{"name":"Solventum Health Information Systems"}]},{"given":"Mojtaba Kadkhodaie","family":"Elyaderani","sequence":"additional","affiliation":[{"name":"Solventum Health Information Systems"}]},{"given":"Jing","family":"Su","sequence":"additional","affiliation":[{"name":"Solventum Health Information Systems"}]},{"given":"Susanne","family":"Burger","sequence":"additional","affiliation":[{"name":"Solventum Health Information Systems"}]},{"given":"Thomas","family":"Schaaf","sequence":"additional","affiliation":[{"name":"Solventum Health Information Systems"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMp1716845"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1097\/pq9.0000000000000345"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1370\/afm.2122"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.nlpmc-1.4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.384"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.313"},{"key":"ref7","first-page":"9","article-title":"In-domain pre-training improves clinical note generation from doctor-patient conversations","volume-title":"Proceedings of the First Workshop on Natural Language Generation in Healthcare","author":"Grambow"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocae022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10935"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.clinicalnlp-1.36"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.38124\/ijisrt\/IJISRT24MAY1483"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-8186-0_17"},{"key":"ref13","article-title":"Automatic summarization of doctor-patient encounter dialogues using large language model through prompt tuning","author":"Lyu","year":"2024","journal-title":"arXiv preprint arXiv:2403.13089"},{"key":"ref14","first-page":"610","article-title":"Towards an automated soap note: Classifying utterances from medical conversations","volume-title":"Proceedings of the 5th Machine Learning for Healthcare Conference, ser. Proceedings of Machine Learning Research","volume":"126","author":"Schloss"},{"key":"ref15","first-page":"185","article-title":"Joint dialogue topic segmentation and categorization: A case study on clinical spoken conversations","volume-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track","author":"Liu"},{"key":"ref16","first-page":"1347","article-title":"Overview of the mediqa-sum task at imageclef 2023: Summarization and classification of doctor-patient conversations","author":"Yim","year":"2023","journal-title":"CLEF (Working Notes)"},{"key":"ref17","first-page":"121","article-title":"From dictations to clinical reports using machine translation","volume-title":"Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"3","author":"Finley"},{"key":"ref18","first-page":"413","article-title":"Alignment annotation for clinic visit dialogue to clinical note sentence language generation","volume-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference","author":"Yim"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688118"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-02487-3"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-895"},{"key":"ref22","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proceedings of the 40th International Conference on Machine Learning, ser. ICML\u201923. JMLR.org","author":"Radford"},{"key":"ref23","first-page":"9340","article-title":"Optimizing instructions and demonstrations for multistage language model programs","volume-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","author":"Opsahl-Ong"},{"key":"ref24","article-title":"DSPy: Compiling declarative language model calls into self-improving pipelines","author":"Khattab","year":"2024"},{"key":"ref25","article-title":"Qwen2 technical report","author":"Yang","year":"2024"},{"key":"ref26","article-title":"Llamafactory: Unified efficient fine-tuning of 100+ language models","volume-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics","volume":"3","author":"Zheng"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref28","article-title":"Fullstop: Multilingual deep models for punctuation prediction","volume-title":"Proceedings of the Swiss Text Analytics Conference 2021","author":"Guhr"},{"key":"ref29","article-title":"The llama 3 herd of models","volume-title":"arXiv preprint arXiv:2407.21783","author":"Grattafiori"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434612.pdf?arnumber=11434612","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:57:03Z","timestamp":1775192223000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434612\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434612","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}