{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:10:20Z","timestamp":1775200220067,"version":"3.50.1"},"reference-count":36,"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\/asru65441.2025.11434755","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":["Enhancing Dialogue Annotation with Speaker Characteristics Leveraging a Frozen LLM"],"prefix":"10.1109","author":[{"given":"Thomas","family":"Thebaud","sequence":"first","affiliation":[{"name":"Johns Hopkins University,Electrical and Computer Engineering Department,Baltimore,MD,USA"}]},{"given":"Yen-Ju","family":"Lu","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Electrical and Computer Engineering Department,Baltimore,MD,USA"}]},{"given":"Matthew","family":"Wiesner","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Human Language Technology Center of Excellence,Baltimore,MD,USA"}]},{"given":"Peter","family":"Viechnicki","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Human Language Technology Center of Excellence,Baltimore,MD,USA"}]},{"given":"Najim","family":"Dehak","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Electrical and Computer Engineering Department,Baltimore,MD,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3068045"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688085"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/AUTOID.2005.10"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref5","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref8","volume-title":"Gpt-4 technical report","author":"OpenAI","year":"2024"},{"key":"ref9","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv:2307.09288"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-968"},{"key":"ref11","article-title":"Large language models are efficient learners of noise-robust speech recognition","author":"Hu","year":"2024","journal-title":"arXiv preprint arXiv:2401.10446"},{"key":"ref12","article-title":"The sound of healthcare: Improving medical transcription asr accuracy with large language models","author":"Adedeji","year":"2024","journal-title":"arXiv preprint arXiv:2402.07658"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389742"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-4399-5_13"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/iccvw69036.2025.00447"},{"key":"ref16","article-title":"Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models","author":"Chu","year":"2023","journal-title":"arXiv preprint arXiv:2311.07919"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.263"},{"key":"ref18","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint arXiv:2106.09685"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0441"},{"issue":"3","key":"ref20","first-page":"6","volume-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality","volume":"2","author":"Chiang","year":"2023"},{"key":"ref21","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref22","article-title":"Listen, think, and understand","author":"Gong","year":"2023","journal-title":"arXiv preprint arXiv:2305.10790"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/odyssey.2024-41"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CISS64860.2025.10944678"},{"key":"ref25","article-title":"Vox-profile: A speech foundation model benchmark for characterizing diverse speaker and speech traits","author":"Feng","year":"2025","journal-title":"arXiv preprint arXiv:2505.14648"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref31","article-title":"SpeechBrain: A generalpurpose speech toolkit","author":"Ravanelli","year":"2021","journal-title":"arXiv:2106.04624."},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/odyssey.2024-35"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660173"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref35","article-title":"X-former: Unifying contrastive and reconstruction learning for mllms","author":"Swetha","year":"2024","journal-title":"arXiv preprint arXiv:2407.13851"},{"key":"ref36","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"}],"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\/11434755.pdf?arnumber=11434755","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:59:24Z","timestamp":1775192364000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434755\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434755","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}