{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T07:55:24Z","timestamp":1776930924640,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":199,"publisher":"ACM","funder":[{"DOI":"10.13039\/100008398","name":"Villum Fonden","doi-asserted-by":"publisher","award":["00069162"],"award-info":[{"award-number":["00069162"]}],"id":[{"id":"10.13039\/100008398","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3772318.3791708","type":"proceedings-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T09:47:11Z","timestamp":1776073631000},"page":"1-21","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["(Computer) Vision in Action: Comparing Remote Sighted Assistance and a Multimodal Voice Agent in Inspection Sequences"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0357-8946","authenticated-orcid":false,"given":"Damien","family":"Rudaz","sequence":"first","affiliation":[{"name":"Department of Nordic Studies and Linguistics, University of Copenhagen, Copenhagen, Denmark"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2742-4714","authenticated-orcid":false,"given":"Barbara","family":"Nino Carreras","sequence":"additional","affiliation":[{"name":"Department of Nordic Studies and Linguistics, University of Copenhagen, Copenhagen, Denmark"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3335-0328","authenticated-orcid":false,"given":"Sara","family":"Merlino","sequence":"additional","affiliation":[{"name":"Department of Nordic Studies and Linguistics, University of Copenhagen, Copenhagen, Denmark"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3670-9102","authenticated-orcid":false,"given":"Brian L.","family":"Due","sequence":"additional","affiliation":[{"name":"Department of Nordic Studies and Linguistics, University of Copenhagen, Copenhagen, Denmark"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9710-6607","authenticated-orcid":false,"given":"Barry","family":"Brown","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Copenhagen, Copenhagen, Denmark"}]}],"member":"320","published-online":{"date-parts":[[2026,4,13]]},"reference":[{"key":"e_1_3_3_2_1_2","doi-asserted-by":"publisher","DOI":"10.1145\/3368426"},{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.3389\/frdem.2024.1343052"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2024.1356477"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3663548.3675631"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3571884.3597140"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1111\/tops.12339"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3663548.3675659"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3663548.3675659"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/5254.796083"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1177\/14614456211015745"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2021.730985"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1075\/slsi.36.09aue"},{"key":"e_1_3_3_2_13_2","volume-title":"How to do things with words","author":"Austin John Langshaw","unstructured":"John Langshaw Austin. 1975. How to do things with words. Harvard university press."},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581052"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364916688253"},{"key":"e_1_3_3_2_16_2","unstructured":"Be My Eyes. 2025. Be My Eyes App. Retrieved from https:\/\/www.bemyeyes.com\/bme-app\/"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.5898\/JHRI.3.2.Beer"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.actpsy.2021.103476"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445922"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.chbr.2024.100411"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1017\/9781108936583.007"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2401227121"},{"key":"e_1_3_3_2_23_2","volume-title":"Proceedings of the SIGDIAL 2011 Conference (SIGDIAL \u201911)","author":"Bohus Dan","year":"2011","unstructured":"Dan Bohus and Eric Horvitz. 2011. Multiparty turn taking in situated dialog: study, lessons, and directions. In Proceedings of the SIGDIAL 2011 Conference (SIGDIAL \u201911), 98\u2013109."},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.3138\/jircd-2024-0015"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/2702123.2702511"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581045"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/2157689.2157693"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.3758\/s13421-025-01755-4"},{"key":"e_1_3_3_2_29_2","volume-title":"Proceedings of the 15th International Workshop on Spoken Dialogue Systems Technology, 254\u2013271","author":"Castillo-L\u00f3pez Galo","year":"2025","unstructured":"Galo Castillo-L\u00f3pez, Ga\u00ebl de Chalendar, and Nasredine Semmar. 2025. A Survey of Recent Advances on Turn-taking Modeling in Spoken Dialogue Systems. In Proceedings of the 15th International Workshop on Spoken Dialogue Systems Technology, 254\u2013271."},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676375"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3663547.3746319"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713457"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1177\/03063127221126148"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00779-015-0890-8"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.21125\/iceri.2024.1813"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3650117"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/738"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657843"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10746-011-9187-8"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1080\/0163853X.2020.1842630"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3027063.3027072"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7221.001.0001"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2023.0149"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.2307\/3823297"},{"key":"e_1_3_3_2_45_2","volume-title":"Dreyfus","author":"Dreyfus Hubert L.","year":"1999","unstructured":"Hubert L. Dreyfus and Stuart E. Dreyfus. 1999. The Challenge of Merleau-Ponty's Phenomenology of Embodiment for Cognitive Science. In Perspectives on Embodiment: The Intersections of Nature and Culture, Gail Weiss and Honi Fern Haber (eds.). Routledge, 103\u2013120."},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.4324\/9781003156819-1"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.lcsi.2023.100792"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1177\/1206331217734541"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.pragma.2019.07.015"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10746-023-09664-8"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1515\/9783839475010-006"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00146-023-01793-z"},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1111\/tops.12682"},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706599.3719881"},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3342775.3342788"},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"crossref","unstructured":"Stan Franklin and Art Graesser. 1997. Is It an agent or just a program?: A taxonomy for autonomous agents. In Intelligent Agents III Agent Theories Architectures and Languages 21\u201335.","DOI":"10.1007\/BFb0013570"},{"key":"e_1_3_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053313"},{"key":"e_1_3_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.4324\/9781003320609-8"},{"key":"e_1_3_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3502016"},{"key":"e_1_3_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.3389\/fcomp.2024.1521066"},{"key":"e_1_3_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.3389\/fcomp.2024.1521066"},{"key":"e_1_3_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642211"},{"key":"e_1_3_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642211"},{"key":"e_1_3_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706599.3719714"},{"key":"e_1_3_3_2_65_2","volume-title":"Everyday Language: Studies in Ethnomethodology","author":"Goodwin Charles","unstructured":"Charles Goodwin. 1979. The Interactive Construction of a Sentence in Natural Conversation. In Everyday Language: Studies in Ethnomethodology, George Psathas (ed.). Irvington Publishers, New York, 97\u2013121."},{"key":"e_1_3_3_2_66_2","volume-title":"Conversational Organization: Interaction between Speakers and Hearers","author":"Goodwin Charles","year":"1981","unstructured":"Charles Goodwin. 1981. Conversational Organization: Interaction between Speakers and Hearers. Irvington Publishers, New York."},{"key":"e_1_3_3_2_67_2","doi-asserted-by":"publisher","unstructured":"Charles Goodwin. 2017. Co-Operative Action. Cambridge University Press. 10.1017\/9781139016735","DOI":"10.1017\/9781139016735"},{"key":"e_1_3_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579531"},{"key":"e_1_3_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.pragma.2022.06.005"},{"key":"e_1_3_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713633"},{"key":"e_1_3_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.4135\/9781849208895"},{"key":"e_1_3_3_2_72_2","doi-asserted-by":"publisher","DOI":"10.4135\/9781526435385"},{"key":"e_1_3_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.1145\/142750.142769"},{"key":"e_1_3_3_2_74_2","doi-asserted-by":"publisher","DOI":"10.1145\/302979.303030"},{"key":"e_1_3_3_2_75_2","doi-asserted-by":"publisher","DOI":"10.1145\/3708359.3712089"},{"key":"e_1_3_3_2_76_2","doi-asserted-by":"publisher","DOI":"10.1109\/HRI.2016.7451737"},{"key":"e_1_3_3_2_77_2","volume-title":"Postphenomenology: Essays in the postmodern context","author":"Ihde Don","year":"1995","unstructured":"Don Ihde. 1995. Postphenomenology: Essays in the postmodern context. Northwestern University Press."},{"key":"e_1_3_3_2_78_2","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3659040"},{"key":"e_1_3_3_2_79_2","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3659040"},{"key":"e_1_3_3_2_80_2","doi-asserted-by":"publisher","unstructured":"Koji Inoue Bing'er Jiang Erik Ekstedt Tatsuya Kawahara and Gabriel Skantze. 2024. Real-time and Continuous Turn-taking Prediction Using Voice Activity Projection. 10.48550\/ARXIV.2401.04868","DOI":"10.48550\/ARXIV.2401.04868"},{"key":"e_1_3_3_2_81_2","doi-asserted-by":"publisher","DOI":"10.63317\/3s77rw77asqh"},{"key":"e_1_3_3_2_82_2","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3428704"},{"key":"e_1_3_3_2_83_2","doi-asserted-by":"publisher","DOI":"10.1075\/pbns.125.02jef"},{"key":"e_1_3_3_2_84_2","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2015.174"},{"key":"e_1_3_3_2_85_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580885"},{"key":"e_1_3_3_2_86_2","doi-asserted-by":"publisher","unstructured":"Waki Kamino and S. Sabanovic. 2023. Coffee Tea Robots?: The Performative Staging of Service Robots in \u201cRobot Cafes\u201d in Japan. 10.1145\/3568162.3576967","DOI":"10.1145\/3568162.3576967"},{"key":"e_1_3_3_2_87_2","doi-asserted-by":"publisher","DOI":"10.1515\/sem-2012-0061"},{"key":"e_1_3_3_2_88_2","doi-asserted-by":"publisher","DOI":"10.1080\/02687038.2022.2094335"},{"key":"e_1_3_3_2_89_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3714203"},{"key":"e_1_3_3_2_90_2","volume-title":"Kr\u00e4mer","author":"Kopp Stefan","year":"2021","unstructured":"Stefan Kopp and Nicole C. Kr\u00e4mer. 2021. Revisiting Human-Agent Communication: The Importance of Joint Co-construction and Understanding Mental States. Frontiers in Psychology 12."},{"key":"e_1_3_3_2_91_2","doi-asserted-by":"publisher","DOI":"10.1145\/3340631.3394840"},{"key":"e_1_3_3_2_92_2","doi-asserted-by":"publisher","DOI":"10.1075\/z.186.13kre"},{"key":"e_1_3_3_2_93_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-578"},{"key":"e_1_3_3_2_94_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501999"},{"key":"e_1_3_3_2_95_2","doi-asserted-by":"publisher","DOI":"10.1111\/tops.12317"},{"key":"e_1_3_3_2_96_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642230"},{"key":"e_1_3_3_2_97_2","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376591"},{"key":"e_1_3_3_2_98_2","doi-asserted-by":"publisher","DOI":"10.1145\/3490099.3511113"},{"key":"e_1_3_3_2_99_2","volume-title":"Proceedings of the 28th Workshop on the Semantics and Pragmatics of Dialogue - Full Papers.","author":"Leishman Sean","year":"2024","unstructured":"Sean Leishman, Peter Bell, and Sarenne Wallbridge. 2024. PairwiseTurnGPT: a multi-stream turn prediction model for spoken dialogue. In Proceedings of the 28th Workshop on the Semantics and Pragmatics of Dialogue - Full Papers. Retrieved from http:\/\/semdial.org\/anthology\/Z24-Leishman_semdial_0002.pdf"},{"key":"e_1_3_3_2_100_2","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2022.941593"},{"key":"e_1_3_3_2_101_2","doi-asserted-by":"publisher","unstructured":"Stephen C. Levinson. 2012. Action Formation and Ascription. In The Handbook of Conversation Analysis. 101\u2013130. 10.1002\/9781118325001.ch6","DOI":"10.1002\/9781118325001.ch6"},{"key":"e_1_3_3_2_102_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642625"},{"key":"e_1_3_3_2_103_2","doi-asserted-by":"publisher","DOI":"10.1145\/2901790.2901842"},{"key":"e_1_3_3_2_104_2","doi-asserted-by":"publisher","DOI":"10.1145\/1613858.1613903"},{"key":"e_1_3_3_2_105_2","unstructured":"Christian Licoppe and Sylvaine Tuncer. 2019. The initiation of showing sequences in video-mediated communication. Gespr\u00e4chsforschung: Online-Zeitschrift zur verbalen Interaktion 20: 545\u2013571."},{"key":"e_1_3_3_2_106_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10746-012-9213-5"},{"key":"e_1_3_3_2_107_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.langcom.2024.11.003"},{"key":"e_1_3_3_2_108_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713760"},{"key":"e_1_3_3_2_109_2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511628122"},{"key":"e_1_3_3_2_110_2","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376311"},{"key":"e_1_3_3_2_111_2","doi-asserted-by":"publisher","DOI":"10.1145\/3359297"},{"key":"e_1_3_3_2_112_2","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025814"},{"key":"e_1_3_3_2_113_2","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2022.733954"},{"key":"e_1_3_3_2_114_2","doi-asserted-by":"publisher","DOI":"10.7146\/si.v4i3.128153"},{"key":"e_1_3_3_2_115_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00146-024-01919-x"},{"key":"e_1_3_3_2_116_2","doi-asserted-by":"publisher","DOI":"10.1177\/1461445613515325"},{"key":"e_1_3_3_2_117_2","doi-asserted-by":"publisher","DOI":"10.1111\/josl.1_12177"},{"key":"e_1_3_3_2_118_2","doi-asserted-by":"publisher","DOI":"10.1080\/08351813.2018.1413878"},{"key":"e_1_3_3_2_119_2","doi-asserted-by":"publisher","DOI":"10.7146\/si.v2i1.113150"},{"key":"e_1_3_3_2_120_2","doi-asserted-by":"publisher","DOI":"10.1017\/9781108650090"},{"key":"e_1_3_3_2_121_2","unstructured":"Lorenza Mondada. 2022. Adjusting step-by-step trajectories in public space: the micro-sequentiality of approaching and refusing to be approached. Gespr\u00e4chsforschung - Online-Zeitschrift zur verbalen Interaktion 23: 36\u201365."},{"key":"e_1_3_3_2_122_2","doi-asserted-by":"publisher","DOI":"10.17605\/OSF.IO\/G7N6S"},{"key":"e_1_3_3_2_123_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.langcom.2025.02.004"},{"key":"e_1_3_3_2_124_2","doi-asserted-by":"publisher","DOI":"10.1145\/3678884.3689134"},{"key":"e_1_3_3_2_125_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.pragma.2013.11.009"},{"key":"e_1_3_3_2_126_2","unstructured":"Kristian Mortensen and Johannes Wagner. 2019. Inspection sequences\u2013multisensorial inspections of unfamiliar objects. Gespr\u00e4chsforschung: Online-Zeitschrift zur verbalen Interaktion 20 399: 343."},{"key":"e_1_3_3_2_127_2","volume-title":"Proceedings of the 14th International Workshop on Spoken Dialogue Systems Technology.","author":"Mousavi Seyed Mahed","year":"2024","unstructured":"Seyed Mahed Mousavi, Gabriel Roccabruna, Simone Alghisi, Massimo Rizzoli, Mirco Ravanelli, and Giuseppe Riccardi. 2024. Are LLMs Robust for Spoken Dialogues? In Proceedings of the 14th International Workshop on Spoken Dialogue Systems Technology."},{"key":"e_1_3_3_2_128_2","doi-asserted-by":"publisher","DOI":"10.1080\/01426397.2021.1961701"},{"key":"e_1_3_3_2_129_2","doi-asserted-by":"publisher","DOI":"10.1177\/14703572241227517"},{"key":"e_1_3_3_2_130_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.pragma.2009.07.015"},{"key":"e_1_3_3_2_131_2","doi-asserted-by":"publisher","DOI":"10.1177\/0306312710386842"},{"key":"e_1_3_3_2_132_2","volume-title":"Proceedings of the 2nd European and the 5th Nordic Symposium on Multimodal Communication, 73\u201380","author":"Nothdurft Florian","year":"2014","unstructured":"Florian Nothdurft, Stefan Ultes, and Wolfgang Minker. 2014. Finding appropriate interaction strategies for proactive dialogue systems\u2014an open quest. In Proceedings of the 2nd European and the 5th Nordic Symposium on Multimodal Communication, 73\u201380."},{"key":"e_1_3_3_2_133_2","unstructured":"David Novick and Stephen Sutton. 1997. What is Mixed-Initiative Interaction?"},{"key":"e_1_3_3_2_134_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642193"},{"key":"e_1_3_3_2_135_2","doi-asserted-by":"publisher","DOI":"10.1145\/3623809.3623837"},{"key":"e_1_3_3_2_136_2","unstructured":"OpenAI. 2025. Voice Mode FAQ. Retrieved from https:\/\/help.openai.com\/en\/articles\/8400625-voice-mode-faq"},{"key":"e_1_3_3_2_137_2","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-013-0181-3"},{"key":"e_1_3_3_2_138_2","doi-asserted-by":"publisher","DOI":"10.7146\/si.v5i3.129915"},{"key":"e_1_3_3_2_139_2","volume-title":"Validity in Research on Naturally Occurring Social Interaction","author":"Per\u00e4kyl\u00e4 Anssi","unstructured":"Anssi Per\u00e4kyl\u00e4. 2011. Validity in Research on Naturally Occurring Social Interaction. In Qualitative Research. Third Edition., David Silverman (ed.). Sage, London."},{"key":"e_1_3_3_2_140_2","doi-asserted-by":"publisher","DOI":"10.3758\/s13423-017-1393-6"},{"key":"e_1_3_3_2_141_2","doi-asserted-by":"publisher","DOI":"10.3167\/sa.2017.610209"},{"key":"e_1_3_3_2_142_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3174214"},{"key":"e_1_3_3_2_143_2","doi-asserted-by":"publisher","DOI":"10.1145\/2998181.2998298"},{"key":"e_1_3_3_2_144_2","doi-asserted-by":"publisher","DOI":"10.1080\/14649365.2024.2399198"},{"key":"e_1_3_3_2_145_2","volume-title":"Text in Context: Contributions to Ethnomethodology","author":"Psathas George","unstructured":"George Psathas. 1992. The study of extended sequences: the case of the garden lesson. In Text in Context: Contributions to Ethnomethodology. Sage."},{"key":"e_1_3_3_2_146_2","doi-asserted-by":"publisher","unstructured":"Andrew Reece Gus Cooney Peter Bull Christine Chung Bryn Dawson Casey Fitzpatrick Tamara Glazer Dean Knox Alex Liebscher and Sebastian Marin. 2023. The CANDOR corpus: Insights from a large multimodal dataset of naturalistic conversation. Science Advances 9 13: eadf3197. 10.1126\/sciadv.adf3197","DOI":"10.1126\/sciadv.adf3197"},{"key":"e_1_3_3_2_147_2","doi-asserted-by":"publisher","DOI":"10.1145\/3469595.3469629"},{"key":"e_1_3_3_2_148_2","doi-asserted-by":"publisher","unstructured":"Elena T Remillard Lyndsie M Koon Tracy L Mitzner and Wendy A Rogers. 2024. Everyday Challenges for Individuals Aging With Vision Impairment: Technology Implications. The Gerontologist 64 6: gnad169. 10.1093\/geront\/gnad169","DOI":"10.1093\/geront\/gnad169"},{"key":"e_1_3_3_2_149_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411763.3443425"},{"key":"e_1_3_3_2_150_2","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376767"},{"key":"e_1_3_3_2_151_2","doi-asserted-by":"publisher","DOI":"10.1145\/3514236"},{"key":"e_1_3_3_2_152_2","doi-asserted-by":"publisher","DOI":"10.1145\/3546155.3546697"},{"key":"e_1_3_3_2_153_2","doi-asserted-by":"publisher","DOI":"10.3390\/app13031925"},{"key":"e_1_3_3_2_154_2","doi-asserted-by":"publisher","DOI":"10.1177\/17504813241271481"},{"key":"e_1_3_3_2_155_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642163"},{"key":"e_1_3_3_2_156_2","doi-asserted-by":"publisher","DOI":"10.1145\/3701571.3701606"},{"key":"e_1_3_3_2_157_2","first-page":"1","article-title":"Sociological description","volume":"8","author":"Sacks Harvey","year":"1963","unstructured":"Harvey Sacks. 1963. Sociological description. Berkeley Journal of Sociology 8: 1\u201316.","journal-title":"Berkeley Journal of Sociology"},{"key":"e_1_3_3_2_158_2","doi-asserted-by":"publisher","DOI":"10.1002\/9781444328301"},{"key":"e_1_3_3_2_159_2","doi-asserted-by":"publisher","DOI":"10.2307\/412243"},{"key":"e_1_3_3_2_160_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544549.3582735"},{"key":"e_1_3_3_2_161_2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511791208"},{"key":"e_1_3_3_2_162_2","doi-asserted-by":"publisher","DOI":"10.1515\/semi.1973.8.4.289"},{"key":"e_1_3_3_2_163_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11948-022-00407-z"},{"key":"e_1_3_3_2_164_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.im.2019.103174"},{"key":"e_1_3_3_2_165_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713490"},{"key":"e_1_3_3_2_166_2","doi-asserted-by":"publisher","DOI":"10.17705\/1thci.00131"},{"key":"e_1_3_3_2_167_2","doi-asserted-by":"publisher","DOI":"10.1177\/1461445607076204"},{"key":"e_1_3_3_2_168_2","volume-title":"Conversation analysis: An introduction","author":"Sidnell Jack","unstructured":"Jack Sidnell. 2010. Conversation analysis: An introduction. John Wiley & Sons."},{"key":"e_1_3_3_2_169_2","doi-asserted-by":"publisher","DOI":"10.4135\/9781036233358"},{"key":"e_1_3_3_2_170_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.pragma.2019.09.008"},{"key":"e_1_3_3_2_171_2","doi-asserted-by":"publisher","DOI":"10.1080\/08351813.2021.1974742"},{"key":"e_1_3_3_2_172_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101178"},{"key":"e_1_3_3_2_173_2","doi-asserted-by":"publisher","DOI":"10.1109\/HRI61500.2025.10973958"},{"key":"e_1_3_3_2_174_2","doi-asserted-by":"crossref","unstructured":"Katta Spiel Kathrin Gerling Cynthia L Bennett Emeline Brul\u00e9 Rua M Williams Jennifer Rode and Jennifer Mankoff. 2020. Nothing about us without us: Investigating the role of critical disability studies in HCI. 1\u20138.","DOI":"10.1145\/3334480.3375150"},{"key":"e_1_3_3_2_175_2","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X05000087"},{"key":"e_1_3_3_2_176_2","doi-asserted-by":"publisher","DOI":"10.1515\/semi.2005.2005.156.1"},{"key":"e_1_3_3_2_177_2","volume-title":"Plans and situated actions:  The problem of human-machine communication","author":"Suchman Lucy","unstructured":"Lucy Suchman. 1987. Plans and situated actions: The problem of human-machine communication. Cambridge University Press, New York, NY, US."},{"key":"e_1_3_3_2_178_2","volume-title":"ICLR 2023-11th International Conference on Learning Representation.","author":"Taillandier Valentin","year":"2023","unstructured":"Valentin Taillandier, Dieuwke Hupkes, Beno\u00eet Sagot, Emmanuel Dupoux, and Paul Michel. 2023. Neural Agents Struggle to Take Turns in Bidirectional Emergent Communication. In ICLR 2023-11th International Conference on Learning Representation."},{"key":"e_1_3_3_2_179_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713433"},{"key":"e_1_3_3_2_180_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.sigdial-1.20"},{"key":"e_1_3_3_2_181_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-91755-w"},{"key":"e_1_3_3_2_182_2","volume-title":"Lena Warnke, and Jan P. de Ruiter.","author":"Umair Muhammad","year":"2024","unstructured":"Muhammad Umair, Julia Beret Mertens, Lena Warnke, and Jan P. de Ruiter. 2024. Can language models trained on written monologue learn to predict spoken dialogue? Cognitive Science."},{"key":"e_1_3_3_2_183_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.909"},{"key":"e_1_3_3_2_184_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1192"},{"key":"e_1_3_3_2_185_2","doi-asserted-by":"publisher","DOI":"10.1177\/0162243905285847"},{"key":"e_1_3_3_2_186_2","doi-asserted-by":"publisher","DOI":"10.1145\/3449143"},{"key":"e_1_3_3_2_187_2","volume-title":"Joint Proceedings of the ACM IUI 2025 Workshops.","author":"Viswanath Anargh","year":"2025","unstructured":"Anargh Viswanath and Hendrik Buschmeier. 2025. Insights for Proactive Agents: Design Considerations, Challenges, and Recommendations. In Joint Proceedings of the ACM IUI 2025 Workshops."},{"key":"e_1_3_3_2_188_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2023.102391"},{"key":"e_1_3_3_2_189_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544549.3585640"},{"key":"e_1_3_3_2_190_2","doi-asserted-by":"publisher","DOI":"10.1558\/slte.20738"},{"key":"e_1_3_3_2_191_2","volume-title":"Computer power and human reason: from judgment to calculation","author":"Weizenbaum Joseph","unstructured":"Joseph Weizenbaum. 1976. Computer power and human reason: from judgment to calculation. Freeman, San Francisco."},{"key":"e_1_3_3_2_192_2","doi-asserted-by":"publisher","DOI":"10.1145\/3563657.3596019"},{"key":"e_1_3_3_2_193_2","doi-asserted-by":"publisher","DOI":"10.1145\/3532106.3533560"},{"key":"e_1_3_3_2_194_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3714210"},{"key":"e_1_3_3_2_195_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642030"},{"key":"e_1_3_3_2_196_2","doi-asserted-by":"publisher","DOI":"10.1142\/S0218213012500042"},{"key":"e_1_3_3_2_197_2","doi-asserted-by":"publisher","DOI":"10.3390\/fi16070254"},{"key":"e_1_3_3_2_198_2","doi-asserted-by":"publisher","DOI":"10.1145\/3543829.3543834"},{"key":"e_1_3_3_2_199_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713110"}],"event":{"name":"CHI 2026: CHI Conference on Human Factors in Computing Systems","location":"Barcelona Spain","acronym":"CHI '26","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3772318.3791708","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T10:29:39Z","timestamp":1776248979000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3772318.3791708"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,13]]},"references-count":199,"alternative-id":["10.1145\/3772318.3791708","10.1145\/3772318"],"URL":"https:\/\/doi.org\/10.1145\/3772318.3791708","relation":{},"subject":[],"published":{"date-parts":[[2026,4,13]]},"assertion":[{"value":"2026-04-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}