{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T18:10:28Z","timestamp":1776276628867,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":75,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T00:00:00Z","timestamp":1715385600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,11]]},"DOI":"10.1145\/3613904.3642183","type":"proceedings-article","created":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T08:39:12Z","timestamp":1715416752000},"page":"1-13","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":35,"title":["Cooking With Agents: Designing Context-aware Voice Interaction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6649-1242","authenticated-orcid":false,"given":"Razan","family":"Jaber","sequence":"first","affiliation":[{"name":"Department of Computer and System Sciences, Stockholm University, Sweden and Department of Computer and System Sciences, Stockholm University, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4465-9565","authenticated-orcid":false,"given":"Sabrina","family":"Zhong","sequence":"additional","affiliation":[{"name":"UCL Interaction Centre, University College London, United Kingdom and UCL Interaction Centre, University College London, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7985-4057","authenticated-orcid":false,"given":"Sanna","family":"Kuoppam\u00e4ki","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering and Health Systems, KTH Royal Institute of Technology, Sweden and Department of Biomedical Engineering and Health Systems, KTH Royal Institute of Technology, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5003-5223","authenticated-orcid":false,"given":"Aida","family":"Hosseini","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology, Sweden and KTH Royal Institute of Technology, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5333-9794","authenticated-orcid":false,"given":"Iona","family":"Gessinger","sequence":"additional","affiliation":[{"name":"School of Information and Communication Studies, University College Dublin, Ireland and School of Information and Communication Studies, University College Dublin, Ireland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2846-2592","authenticated-orcid":false,"given":"Duncan P","family":"Brumby","sequence":"additional","affiliation":[{"name":"UCL Interaction Centre, University College London, United Kingdom and UCL Interaction Centre, University College London, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8595-8132","authenticated-orcid":false,"given":"Benjamin R.","family":"Cowan","sequence":"additional","affiliation":[{"name":"School of Information & Communication Studies, University College Dublin, Ireland and School of Information & Communication Studies, University College Dublin, Ireland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1392-5737","authenticated-orcid":false,"given":"Donald","family":"Mcmillan","sequence":"additional","affiliation":[{"name":"Department of Computer and Systems Sciences, Stockholm University, Sweden and Department of Computer and Systems Sciences, Stockholm University, Sweden"}]}],"member":"320","published-online":{"date-parts":[[2024,5,11]]},"reference":[{"key":"e_1_3_3_3_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3469595.3469608"},{"key":"e_1_3_3_3_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3311956"},{"key":"e_1_3_3_3_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3469595.3469625"},{"key":"e_1_3_3_3_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2559206.2578868"},{"key":"e_1_3_3_3_5_1","volume-title":"Proceedings of the 24th Workshop on the Semantics and Pragmatics of Dialogue-Full Papers, Virually at Brandeis","author":"Balaraman Vevake","year":"2020","unstructured":"Vevake Balaraman and Bernardo Magnini. 2020. Proactive systems and influenceable users: Simulating proactivity in task-oriented dialogues. In Proceedings of the 24th Workshop on the Semantics and Pragmatics of Dialogue-Full Papers, Virually at Brandeis, Waltham, New Jersey, July. SEMDIAL. http:\/\/semdial.org\/anthology\/Z20-Balaraman_semdial_0007.pdf"},{"key":"e_1_3_3_3_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04380-2_26"},{"key":"e_1_3_3_3_7_1","doi-asserted-by":"publisher","DOI":"10.1017\/S004740450001037X"},{"key":"e_1_3_3_3_8_1","doi-asserted-by":"publisher","DOI":"10.21437\/eurospeech.1999-266"},{"key":"e_1_3_3_3_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/506443.506598"},{"key":"e_1_3_3_3_10_1","volume-title":"Proc. AAAI Fall Symposium on Socially Intelligent Agents. https:\/\/api.semanticscholar.org\/CorpusID:13190315","author":"Bickmore Timothy","year":"2000","unstructured":"Timothy Bickmore and Justine Cassell. 2000. How about this weather?\u201d social dialogue with embodied conversational agents. In Proc. AAAI Fall Symposium on Socially Intelligent Agents. https:\/\/api.semanticscholar.org\/CorpusID:13190315"},{"key":"e_1_3_3_3_11_1","doi-asserted-by":"publisher","DOI":"10.1017\/S0047404500021035"},{"key":"e_1_3_3_3_12_1","doi-asserted-by":"publisher","unstructured":"Dan Bohus and Alexander\u00a0I Rudnicky. 2003. RavenClaw: Dialog Management Using Hierarchical Task Decomposition and an Expectation Agenda. (2003) 4. https:\/\/doi.org\/10.21437\/eurospeech.2003-255","DOI":"10.21437\/eurospeech.2003-255"},{"key":"e_1_3_3_3_13_1","doi-asserted-by":"publisher","DOI":"10.1038\/scientificamerican0692-116"},{"key":"e_1_3_3_3_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2011.05.011"},{"key":"e_1_3_3_3_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411810"},{"key":"e_1_3_3_3_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445131"},{"key":"e_1_3_3_3_17_1","unstructured":"Alexander Chen. 2023. How it\u2019s Made: Interacting with Gemini through multimodal prompting. https:\/\/developers.googleblog.com\/2023\/12\/how-its-made-gemini-multimodal-prompting.html"},{"key":"e_1_3_3_3_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/B0-08-044854-2"},{"key":"e_1_3_3_3_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/0364-0213(89)90008-6"},{"key":"e_1_3_3_3_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300705"},{"key":"e_1_3_3_3_21_1","doi-asserted-by":"publisher","unstructured":"Benjamin\u00a0R. Cowan and Holly\u00a0P. Branigan. 2015. Does voice anthropomorphism affect lexical alignment in speech-based human-computer dialogue?155\u2013159. https:\/\/doi.org\/10.21437\/Interspeech.2015-75","DOI":"10.21437\/Interspeech.2015-75"},{"key":"e_1_3_3_3_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3342775.3342786"},{"key":"e_1_3_3_3_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3098279.3098539"},{"key":"e_1_3_3_3_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-476-05871-3_44"},{"key":"e_1_3_3_3_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445206"},{"key":"e_1_3_3_3_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3078072.3084330"},{"key":"e_1_3_3_3_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3469595.3469618"},{"key":"e_1_3_3_3_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3342775.3342785"},{"key":"e_1_3_3_3_29_1","doi-asserted-by":"publisher","DOI":"10.1177\/1090198109339453"},{"key":"e_1_3_3_3_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3342775.3342788"},{"key":"e_1_3_3_3_31_1","volume-title":"Gemini: A Family of Highly Capable Multimodal Models. https:\/\/paperswithcode.com\/paper\/gemini-a-family-of-highly-capable-multimodal","author":"Google GeminiTeam","year":"2023","unstructured":"GeminiTeam Google, Google. 2023. Gemini: A Family of Highly Capable Multimodal Models. https:\/\/paperswithcode.com\/paper\/gemini-a-family-of-highly-capable-multimodal"},{"key":"e_1_3_3_3_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2556325.2566247"},{"key":"e_1_3_3_3_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3593013.3594067"},{"key":"e_1_3_3_3_34_1","doi-asserted-by":"publisher","DOI":"10.1111\/cogs.12926"},{"key":"e_1_3_3_3_35_1","doi-asserted-by":"crossref","unstructured":"Alyssa Hwang Natasha Oza Chris Callison-Burch and Andrew Head. 2023. Rewriting the Script: Adapting Text Instructions for Voice Interaction. http:\/\/arxiv.org\/abs\/2306.09992","DOI":"10.1145\/3563657.3596059"},{"key":"e_1_3_3_3_36_1","doi-asserted-by":"publisher","unstructured":"Jiepu Jiang Wei Jeng and Daqing He. 2013. How do users respond to voice input errors?: lexical and phonetic query reformulation in voice search. (2013) 10. https:\/\/doi.org\/10.1145\/2484028.2484092","DOI":"10.1145\/2484028.2484092"},{"key":"e_1_3_3_3_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0277(88)90003-0"},{"key":"e_1_3_3_3_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639044"},{"key":"e_1_3_3_3_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3405755.3406119"},{"key":"e_1_3_3_3_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376372"},{"key":"e_1_3_3_3_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-11694-0_8"},{"key":"e_1_3_3_3_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3463516"},{"key":"e_1_3_3_3_43_1","doi-asserted-by":"publisher","DOI":"10.3758\/BRM.41.3.841"},{"key":"e_1_3_3_3_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2438543"},{"key":"e_1_3_3_3_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/1040830.1040880"},{"key":"e_1_3_3_3_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2008.4543743"},{"key":"e_1_3_3_3_47_1","doi-asserted-by":"publisher","DOI":"10.1177\/0961000618759414"},{"key":"e_1_3_3_3_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858288"},{"key":"e_1_3_3_3_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.pragma.2010.06.009"},{"key":"e_1_3_3_3_50_1","doi-asserted-by":"publisher","DOI":"10.1080\/07370024.2022.2081571"},{"key":"e_1_3_3_3_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-95579-7_1"},{"key":"e_1_3_3_3_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268964"},{"key":"e_1_3_3_3_53_1","doi-asserted-by":"publisher","DOI":"10.1177\/002383099804100409"},{"key":"e_1_3_3_3_54_1","doi-asserted-by":"publisher","DOI":"10.1177\/0149206308321554"},{"key":"e_1_3_3_3_55_1","doi-asserted-by":"publisher","DOI":"10.5555\/3237383.3237883"},{"key":"e_1_3_3_3_56_1","unstructured":"Emma Persky. 2022. Now we\u2019re cooking \u2013 the assistant on {Google Home} is your secret ingredient. https:\/\/www.blog.google\/products\/assistant\/cooking-with-the-assistant-google-home-your-secret-ingredient\/"},{"key":"e_1_3_3_3_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3469595.3469619"},{"key":"e_1_3_3_3_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3174214"},{"key":"e_1_3_3_3_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/2998181.2998298"},{"key":"e_1_3_3_3_60_1","doi-asserted-by":"publisher","DOI":"10.4135\/9781529783193.n32"},{"key":"e_1_3_3_3_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3469595.3469629"},{"key":"e_1_3_3_3_62_1","doi-asserted-by":"publisher","DOI":"10.5898\/JHRI.1.1.Riek"},{"key":"e_1_3_3_3_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3410876"},{"key":"e_1_3_3_3_64_1","doi-asserted-by":"publisher","DOI":"10.2307\/412243"},{"key":"e_1_3_3_3_65_1","doi-asserted-by":"publisher","DOI":"10.1525\/aa.1968.70.6.02a00030"},{"key":"e_1_3_3_3_66_1","unstructured":"Derick Schweppe. 2022. Mycroft \u2013 The Open Source Privacy-Focused Voice Assistant. https:\/\/mycroft.ai\/"},{"key":"e_1_3_3_3_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/348941.348990"},{"key":"e_1_3_3_3_68_1","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso"},{"key":"e_1_3_3_3_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/544862.544922"},{"key":"e_1_3_3_3_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445536"},{"key":"e_1_3_3_3_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/3563657.3595975"},{"key":"e_1_3_3_3_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543829.3543839"},{"key":"e_1_3_3_3_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/2678025.2701408"},{"key":"e_1_3_3_3_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543829.3543834"},{"key":"e_1_3_3_3_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3502036"}],"event":{"name":"CHI '24: CHI Conference on Human Factors in Computing Systems","location":"Honolulu HI USA","acronym":"CHI '24","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGACCESS ACM Special Interest Group on Accessible Computing"]},"container-title":["Proceedings of the CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613904.3642183","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3613904.3642183","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:56:42Z","timestamp":1750291002000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613904.3642183"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,11]]},"references-count":75,"alternative-id":["10.1145\/3613904.3642183","10.1145\/3613904"],"URL":"https:\/\/doi.org\/10.1145\/3613904.3642183","relation":{},"subject":[],"published":{"date-parts":[[2024,5,11]]},"assertion":[{"value":"2024-05-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}