{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T06:18:38Z","timestamp":1762237118540,"version":"build-2065373602"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T00:00:00Z","timestamp":1756080000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T00:00:00Z","timestamp":1756080000000},"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":[[2025,8,25]]},"DOI":"10.1109\/ro-man63969.2025.11217726","type":"proceedings-article","created":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T18:42:29Z","timestamp":1762195349000},"page":"692-699","source":"Crossref","is-referenced-by-count":0,"title":["Dynamic Prompting Improves Turn-taking in Embodied Spoken Dialogue Systems"],"prefix":"10.1109","author":[{"given":"Yifan","family":"Shen","sequence":"first","affiliation":[{"name":"Hong Kong University of Science and Technology,Department of Industrial Engineering and Decision Analytics (FT), and the Center for Aging Science (BES),Department of Electronic and Computer Engineering (YS, BES), Department of Computer Science (DL, XJM), Division of Emerging Interdisciplinary Areas(XYM)"}]},{"given":"Dingdong","family":"Liu","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology,Department of Industrial Engineering and Decision Analytics (FT), and the Center for Aging Science (BES),Department of Electronic and Computer Engineering (YS, BES), Department of Computer Science (DL, XJM), Division of Emerging Interdisciplinary Areas(XYM)"}]},{"given":"Xiaoyu","family":"Mo","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology,Department of Industrial Engineering and Decision Analytics (FT), and the Center for Aging Science (BES),Department of Electronic and Computer Engineering (YS, BES), Department of Computer Science (DL, XJM), Division of Emerging Interdisciplinary Areas(XYM)"}]},{"given":"Fugee","family":"Tsung","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology,Department of Industrial Engineering and Decision Analytics (FT), and the Center for Aging Science (BES),Department of Electronic and Computer Engineering (YS, BES), Department of Computer Science (DL, XJM), Division of Emerging Interdisciplinary Areas(XYM)"}]},{"given":"Xiaojuan","family":"Ma","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology,Department of Industrial Engineering and Decision Analytics (FT), and the Center for Aging Science (BES),Department of Electronic and Computer Engineering (YS, BES), Department of Computer Science (DL, XJM), Division of Emerging Interdisciplinary Areas(XYM)"}]},{"given":"Bertram E.","family":"Shi","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology,Department of Industrial Engineering and Decision Analytics (FT), and the Center for Aging Science (BES),Department of Electronic and Computer Engineering (YS, BES), Department of Computer Science (DL, XJM), Division of Emerging Interdisciplinary Areas(XYM)"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3624716"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3319502.3374839"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-011-0122-y"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN60168.2024.10731285"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2017.2753879"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICHI.2013.13"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.sigdial-1.27"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN46459.2019.8956300"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101178"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511620539"},{"volume-title":"Spoken Dialogue Systems, ser. Synthesis Lectures on Human Language Technologies","year":"2010","author":"Jokinen","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10955"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.268"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-9348-5_1"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.709"},{"article-title":"OpenOmni: Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-Time Self-Aware Emotional Speech Synthesis","year":"2025","author":"Luo","key":"ref16"},{"article-title":"Moshi: a speech-text foundation model for real-time dialogue","year":"2024","author":"D\u00e9fossez","key":"ref17"},{"article-title":"Real-Time Textless Dialogue Generation","year":"2025","author":"Mai","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3115\/1620754.1620846"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1037\/h0033031"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/0022-1031(74)90070-5"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2820749"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539209"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2168748.2168749"},{"key":"ref25","first-page":"4866","article-title":"Duplex Conversation in Outbound Agent System","author":"Jin","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/HRI61500.2025.10973958"},{"article-title":"A Full-duplex Speech Dialogue Scheme Based On Large Language Model","year":"2024","author":"Wang","key":"ref27"},{"article-title":"VoiceBench: Benchmarking LLM-Based Voice Assistants","year":"2024","author":"Chen","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN60168.2024.10731379"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.29327\/9786527216247.1057106"},{"article-title":"Silero VAD: pre-trained enterprise-grade Voice Activity Detector (VAD), Number Detector and Language Classifier","year":"2024","author":"Team","key":"ref31"},{"year":"2025","key":"ref32","article-title":"openai\/openai-realtime-console"},{"key":"ref33","article-title":"Humanoid Robot | Robotics Institute - The Hong Kong University of Science and Technology"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1002\/9781119171386"}],"event":{"name":"2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","start":{"date-parts":[[2025,8,25]]},"location":"Eindhoven, Netherlands","end":{"date-parts":[[2025,8,29]]}},"container-title":["2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11217544\/11217526\/11217726.pdf?arnumber=11217726","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T06:14:33Z","timestamp":1762236873000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11217726\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,25]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/ro-man63969.2025.11217726","relation":{},"subject":[],"published":{"date-parts":[[2025,8,25]]}}}