{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T08:56:30Z","timestamp":1773392190350,"version":"3.50.1"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,8,26]],"date-time":"2024-08-26T00:00:00Z","timestamp":1724630400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,26]],"date-time":"2024-08-26T00:00:00Z","timestamp":1724630400000},"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":[[2024,8,26]]},"DOI":"10.1109\/ro-man60168.2024.10731379","type":"proceedings-article","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T17:45:45Z","timestamp":1730310345000},"page":"1733-1738","source":"Crossref","is-referenced-by-count":7,"title":["Predictive Turn-Taking: Leveraging Language Models to Anticipate Turn Transitions in Human-Robot Dialogue"],"prefix":"10.1109","author":[{"given":"Maria J.","family":"Pinto","sequence":"first","affiliation":[{"name":"Ghent University—Imec,AIRO–IDLab,Ghent,Belgium,9052"}]},{"given":"Tony","family":"Belpaeme","sequence":"additional","affiliation":[{"name":"Ghent University—Imec,AIRO–IDLab,Ghent,Belgium,9052"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2014.02.002"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2005.05.009"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101178"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.2002-565"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-4642"},{"key":"ref6","first-page":"220","article-title":"Towards a general, continuous model of turn-taking in spoken dialogue using LSTM recurrent neural networks","volume-title":"Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue","author":"Skantze"},{"key":"ref7","first-page":"224","article-title":"Neural dialogue context online end-of-turn detection","volume-title":"Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue","author":"Masumura"},{"key":"ref8","first-page":"2981","article-title":"TurnGPT: a transformer-based language model for predicting turn-taking in spoken dialog","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2020","author":"Ekstedt"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.17323\/1728-192x-2015-1-142-202"},{"key":"ref10","article-title":"Voice extensible markup language (voicexml) version 2.0","author":"McGlashan","year":"2004","journal-title":"World Wide Web Consortium (W3C) Recommendation"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-014-9265-1"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3115\/1622064.1622066"},{"key":"ref13","first-page":"2","article-title":"Real-time handling of fragmented utterances","volume-title":"Proc. NAACL workshop on adaptation in dialogue systems","author":"Bell"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.2002-293"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3340555.3353727"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.wocn.2010.08.002"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3115\/1609067.1609146"},{"key":"ref18","first-page":"986","article-title":"DailyDialog: A manually labelled multi-turn dialogue dataset","volume-title":"Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","author":"Li"},{"key":"ref19","article-title":"Dialogstudio: Towards richest and most diverse unified dataset collection for conversational ai","author":"Zhang","year":"2023"},{"key":"ref20","volume-title":"Switchboard-1 Release 2 LDC97S62, Linguistic Data Consortium, Philadelphia","author":"Godfrey","year":"1993"},{"key":"ref21","article-title":"Speaker diarization using x-vectors"}],"event":{"name":"2024 33rd IEEE International Conference on Robot and Human Interactive Communication (ROMAN)","location":"Pasadena, CA, USA","start":{"date-parts":[[2024,8,26]]},"end":{"date-parts":[[2024,8,30]]}},"container-title":["2024 33rd IEEE International Conference on Robot and Human Interactive Communication (ROMAN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10731142\/10731137\/10731379.pdf?arnumber=10731379","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T04:41:37Z","timestamp":1732682497000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10731379\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,26]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/ro-man60168.2024.10731379","relation":{},"subject":[],"published":{"date-parts":[[2024,8,26]]}}}