{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T17:41:20Z","timestamp":1776102080634,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":75,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T00:00:00Z","timestamp":1689724800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Hong Kong Research Grants Council","award":["CityU 21209419"],"award-info":[{"award-number":["CityU 21209419"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,19]]},"DOI":"10.1145\/3571884.3597134","type":"proceedings-article","created":{"date-parts":[[2023,7,17]],"date-time":"2023-07-17T18:04:11Z","timestamp":1689617051000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Gist and Verbatim: Understanding Speech to Inform New Interfaces for Verbal Text Composition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0606-8191","authenticated-orcid":false,"given":"Brinda","family":"Mehra","sequence":"first","affiliation":[{"name":"School of Creative Media, City University of Hong Kong, China and School of Information, University of Michigan, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6500-3138","authenticated-orcid":false,"given":"Kejia","family":"Shen","sequence":"additional","affiliation":[{"name":"Research and Development Department, ChengDu Planning Information Technology Center, China and School of Creative Media, City University of Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8212-4100","authenticated-orcid":false,"given":"Hen Chen","family":"Yen","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, China and University of Waterloo, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3267-3317","authenticated-orcid":false,"given":"Can","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Creative Media, City University of Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0022-5371(74)80039-3"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Matthew\u00a0P Aylett Per\u00a0Ola Kristensson Steve Whittaker and Yolanda Vazquez-Alvarez. 2014. None of a CHInd: relationship counselling for HCI and speech technology. In CHI\u201914 Extended Abstracts on Human Factors in Computing Systems. 749\u2013760.","DOI":"10.1145\/2559206.2578868"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0089914"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0285(85)90008-8"},{"key":"e_1_3_2_1_5_1","volume-title":"The science of false memory","author":"Brainerd J","unstructured":"Charles\u00a0J Brainerd and Valerie\u00a0F Reyna. 2005. The science of false memory. Oxford University Press."},{"key":"e_1_3_2_1_6_1","volume-title":"The abstraction of linguistic ideas. Cognitive psychology 2, 4","author":"Bransford D","year":"1971","unstructured":"John\u00a0D Bransford and Jeffery\u00a0J Franks. 1971. The abstraction of linguistic ideas. Cognitive psychology 2, 4 (1971), 331\u2013350."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-011-3740-9_1"},{"key":"e_1_3_2_1_8_1","volume-title":"Computer text-editing: An information-processing analysis of a routine cognitive skill. Cognitive psychology 12, 1","author":"Card K","year":"1980","unstructured":"Stuart\u00a0K Card, Thomas\u00a0P Moran, and Allen Newell. 1980. Computer text-editing: An information-processing analysis of a routine cognitive skill. Cognitive psychology 12, 1 (1980), 32\u201374."},{"key":"e_1_3_2_1_9_1","volume-title":"consciousness, and time: The flow and displacement of conscious experience in speaking and writing","author":"Chafe Wallace","unstructured":"Wallace Chafe. 1994. Discourse, consciousness, and time: The flow and displacement of conscious experience in speaking and writing. University of Chicago Press."},{"key":"e_1_3_2_1_10_1","volume-title":"The relation between written and spoken language. Annual review of anthropology 16","author":"Chafe Wallace","year":"1987","unstructured":"Wallace Chafe and Deborah Tannen. 1987. The relation between written and spoken language. Annual review of anthropology 16 (1987), 383\u2013407."},{"key":"e_1_3_2_1_11_1","volume-title":"How native-like is non-native language processing?Trends in cognitive sciences 10, 12","author":"Clahsen Harald","year":"2006","unstructured":"Harald Clahsen and Claudia Felser. 2006. How native-like is non-native language processing?Trends in cognitive sciences 10, 12 (2006), 564\u2013570."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1093\/iwc\/iwz016"},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the 3rd International Conference on Automotive User Interfaces and Interactive Vehicular Applications. 13\u201320","author":"Cu\u0159\u00edn Jan","year":"2011","unstructured":"Jan Cu\u0159\u00edn, Martin Labsk\u1ef3, Tom\u00e1\u0161 Macek, Jan Kleindienst, Hoi Young, Ann Thyme-Gobbel, Holger Quast, and Lars K\u00f6nig. 2011. Dictating and editing short texts while driving: Distraction and task completion. In Proceedings of the 3rd International Conference on Automotive User Interfaces and Interactive Vehicular Applications. 13\u201320."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.2307\/1511284"},{"key":"e_1_3_2_1_15_1","volume-title":"Revise, Repeat: A System Demonstration for Human-in-the-loop Iterative Text Revision. arXiv preprint arXiv:2204.03685","author":"Du Wanyu","year":"2022","unstructured":"Wanyu Du, Zae\u00a0Myung Kim, Vipul Raheja, Dhruv Kumar, and Dongyeop Kang. 2022. Read, Revise, Repeat: A System Demonstration for Human-in-the-loop Iterative Text Revision. arXiv preprint arXiv:2204.03685 (2022)."},{"key":"e_1_3_2_1_16_1","volume-title":"Deictic expressions and the connexity of text. Text and discourse connectedness","author":"Ehlich Konrad","year":"1989","unstructured":"Konrad Ehlich. 1989. Deictic expressions and the connexity of text. Text and discourse connectedness (1989), 33\u201352."},{"key":"e_1_3_2_1_17_1","unstructured":"John\u00a0F Ehrich. 2006. Vygotskyan inner speech and the reading process. (2006)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1093\/deafed\/6.4.285"},{"key":"e_1_3_2_1_19_1","volume-title":"Mobile voice usage trends","author":"Enge Eric","year":"2020","unstructured":"Eric Enge. 2020. Mobile voice usage trends in 2020. https:\/\/www.perficient.com\/insights\/research-hub\/voice-usage-trends"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3472749.3474795"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21753-1_24"},{"key":"e_1_3_2_1_22_1","unstructured":"Paul\u00a0L Garvin. 1989. Professor Vachek (revisited)-some contemporary issues in the study of speech and writing. (1989)."},{"key":"e_1_3_2_1_23_1","volume-title":"Surface information loss in comprehension. Cognitive psychology 17, 3","author":"Gernsbacher Morton\u00a0Ann","year":"1985","unstructured":"Morton\u00a0Ann Gernsbacher. 1985. Surface information loss in comprehension. Cognitive psychology 17, 3 (1985), 324\u2013363."},{"key":"e_1_3_2_1_24_1","volume-title":"Voice-based Interactions for Editing Text On The Go. In 2021 Joint Workshop of the German Research Training Groups in Computer Science. 143","author":"Ghosh Debjyoti","year":"2021","unstructured":"Debjyoti Ghosh. 2021. Voice-based Interactions for Editing Text On The Go. In 2021 Joint Workshop of the German Research Training Groups in Computer Science. 143."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173977"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376173"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3390889"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.3758\/s13423-019-01597-7"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1080\/17470218.2016.1183686"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3365610.3365627"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1111\/1467-8535.00300"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1038\/scientificamerican0960-88"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/S8755-4615(02)00174-3"},{"key":"e_1_3_2_1_34_1","first-page":"67","article-title":"Automatic speech recognition\u2013a brief history of the technology development. Georgia Institute of Technology","volume":"1","author":"Juang Biing-Hwang","year":"2005","unstructured":"Biing-Hwang Juang and Lawrence\u00a0R Rabiner. 2005. Automatic speech recognition\u2013a brief history of the technology development. Georgia Institute of Technology. Atlanta Rutgers University and the University of California. Santa Barbara 1 (2005), 67.","journal-title":"Atlanta Rutgers University and the University of California. Santa Barbara"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/302979.303160"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.actpsy.2018.01.012"},{"key":"e_1_3_2_1_37_1","volume-title":"Are written and spoken recall of text equivalent?The American Journal of Psychology 120, 3","author":"Kellogg T","year":"2007","unstructured":"Ronald\u00a0T Kellogg. 2007. Are written and spoken recall of text equivalent?The American Journal of Psychology 120, 3 (2007), 415\u2013428."},{"key":"e_1_3_2_1_38_1","volume-title":"research, theory, and applications","author":"Krashen D","unstructured":"Stephen\u00a0D Krashen. 1984. Writing, research, theory, and applications. Pergamon."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2207676.2208386"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11145-018-9929-3"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.7763\/IJSSH.2015.V5.546"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.1994-339"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.58680\/ce198213720"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3027063.3027117"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.3758\/BF03193375"},{"key":"e_1_3_2_1_46_1","volume-title":"Orality and literacy","author":"Ong J","unstructured":"Walter\u00a0J Ong. 2013. Orality and literacy. Routledge."},{"key":"e_1_3_2_1_47_1","volume-title":"Designing the user interface for multimodal speech and pen-based gesture applications: State-of-the-art systems and future research directions. Human-computer interaction 15, 4","author":"Oviatt Sharon","year":"2000","unstructured":"Sharon Oviatt, Phil Cohen, Lizhong Wu, Lisbeth Duncan, Bernhard Suhm, Josh Bers, Thomas Holzman, Terry Winograd, James Landay, Jim Larson, 2000. Designing the user interface for multimodal speech and pen-based gesture applications: State-of-the-art systems and future research directions. Human-computer interaction 15, 4 (2000), 263\u2013322."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jneuroling.2010.02.011"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-018-0947-0"},{"key":"e_1_3_2_1_50_1","volume-title":"Examining the central and peripheral processes of written word production through meta-analysis. Frontiers in psychology 2","author":"Purcell J","year":"2011","unstructured":"Jeremy\u00a0J Purcell, Peter\u00a0E Turkeltaub, Guinevere\u00a0F Eden, and Brenda Rapp. 2011. Examining the central and peripheral processes of written word production through meta-analysis. Frontiers in psychology 2 (2011), 239."},{"key":"e_1_3_2_1_51_1","volume-title":"A new intuitionism: Meaning, memory, and development in Fuzzy-Trace Theory.Judgment and Decision making","author":"Reyna F","year":"2012","unstructured":"Valerie\u00a0F Reyna. 2012. A new intuitionism: Meaning, memory, and development in Fuzzy-Trace Theory.Judgment and Decision making (2012)."},{"key":"e_1_3_2_1_52_1","volume-title":"Fuzzy-trace theory: An interim synthesis. Learning and individual Differences 7, 1","author":"Reyna F","year":"1995","unstructured":"Valerie\u00a0F Reyna and Charles\u00a0J Brainerd. 1995. Fuzzy-trace theory: An interim synthesis. Learning and individual Differences 7, 1 (1995), 1\u201375."},{"key":"e_1_3_2_1_53_1","volume-title":"Gaze\u2019N\u2019Touch: Enhancing Text Selection on Mobile Devices Using Gaze. In Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems. 1\u20138.","author":"Rivu Radiah","year":"2020","unstructured":"Radiah Rivu, Yasmeen Abdrabou, Ken Pfeuffer, Mariam Hassib, and Florian Alt. 2020. Gaze\u2019N\u2019Touch: Enhancing Text Selection on Mobile Devices Using Gaze. In Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems. 1\u20138."},{"key":"e_1_3_2_1_54_1","unstructured":"David\u00a0A Rosenbaum. 2010. Human motor control. (2010)."},{"key":"e_1_3_2_1_55_1","volume-title":"Speech is 3x faster than typing for english and mandarin text entry on mobile devices. arXiv preprint arXiv:1608.07323","author":"Ruan Sherry","year":"2016","unstructured":"Sherry Ruan, Jacob\u00a0O Wobbrock, Kenny Liou, Andrew Ng, and James Landay. 2016. Speech is 3x faster than typing for english and mandarin text entry on mobile devices. arXiv preprint arXiv:1608.07323 (2016)."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.3758\/BF03208784"},{"key":"e_1_3_2_1_57_1","volume-title":"cognitive, and motoric aspects of transcription typing.Psychological bulletin 99, 3","author":"Salthouse A","year":"1986","unstructured":"Timothy\u00a0A Salthouse. 1986. Perceptual, cognitive, and motoric aspects of transcription typing.Psychological bulletin 99, 3 (1986), 303."},{"key":"e_1_3_2_1_58_1","volume-title":"International Encyclopedia of the Social & Behavioral Sciences","author":"Schriefers Herbert","unstructured":"Herbert Schriefers and Gabriella Vigliocco. 2015. Speech production, psychology of [repr.]. In International Encyclopedia of the Social & Behavioral Sciences (2nd ed) Vol. 23. Elsevier, 255\u2013258.","edition":"2"},{"key":"e_1_3_2_1_59_1","volume-title":"Does verbatim sentence recall underestimate the language competence of near-native speakers?Frontiers in psychology 6","author":"Schweppe Judith","year":"2015","unstructured":"Judith Schweppe, Sandra Barth, Almut Ketzer-N\u00f6ltge, and Ralf Rummer. 2015. Does verbatim sentence recall underestimate the language competence of near-native speakers?Frontiers in psychology 6 (2015), 63."},{"key":"e_1_3_2_1_60_1","volume-title":"speech-based navigation during dictation: difficulties, consequences, and solutions. Human-computer interaction 18, 3","author":"Sears Andrew","year":"2003","unstructured":"Andrew Sears, Jinhuan Feng, Kwesi Oseitutu, and Claire-Marie Karat. 2003. Hands-free, speech-based navigation during dictation: difficulties, consequences, and solutions. Human-computer interaction 18, 3 (2003), 229\u2013257."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376579"},{"key":"e_1_3_2_1_62_1","first-page":"65","article-title":"Review of speech-to-text recognition technology for enhancing learning","volume":"17","author":"Shadiev Rustam","year":"2014","unstructured":"Rustam Shadiev, Wu-Yuin Hwang, Nian-Shing Chen, and Yueh-Min Huang. 2014. Review of speech-to-text recognition technology for enhancing learning. Journal of Educational Technology & Society 17, 4 (2014), 65\u201384.","journal-title":"Journal of Educational Technology & Society"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/348941.348990"},{"key":"e_1_3_2_1_64_1","volume-title":"Haptic voice recognition: Augmenting speech modality with touch events for efficient speech recognition. In 2010 IEEE spoken language technology workshop","author":"Sim Khe\u00a0Chai","unstructured":"Khe\u00a0Chai Sim. 2010. Haptic voice recognition: Augmenting speech modality with touch events for efficient speech recognition. In 2010 IEEE spoken language technology workshop. IEEE, 73\u201378."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/2388676.2388793"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300433"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1177\/0022466907313453"},{"key":"e_1_3_2_1_68_1","volume-title":"Multimodal error correction for speech user interfaces. ACM transactions on computer-human interaction (TOCHI) 8, 1","author":"Suhm Bernhard","year":"2001","unstructured":"Bernhard Suhm, Brad Myers, and Alex Waibel. 2001. Multimodal error correction for speech user interfaces. ACM transactions on computer-human interaction (TOCHI) 8, 1 (2001), 60\u201398."},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1080\/08839514.2020.1842108"},{"key":"e_1_3_2_1_70_1","volume-title":"Proceedings of the","author":"Turn Rein","year":"1974","unstructured":"Rein Turn. 1974. Speech as a man-computer communication channel. In Proceedings of the May 6-10, 1974, national computer conference and exposition. 139\u2013143."},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1037\/0278-7393.1.6.720"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1515\/9783110803860"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2010.5700866"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/944868.944900"},{"key":"e_1_3_2_1_75_1","volume-title":"EyeSayCorrect: Eye Gaze and Voice Based Hands-free Text Correction for Mobile Devices. In 27th International Conference on Intelligent User Interfaces. 470\u2013482","author":"Zhao Maozheng","year":"2022","unstructured":"Maozheng Zhao, Henry Huang, Zhi Li, Rui Liu, Wenzhe Cui, Kajal Toshniwal, Ananya Goel, Andrew Wang, Xia Zhao, Sina Rashidian, 2022. EyeSayCorrect: Eye Gaze and Voice Based Hands-free Text Correction for Mobile Devices. In 27th International Conference on Intelligent User Interfaces. 470\u2013482."}],"event":{"name":"CUI '23: ACM conference on Conversational User Interfaces","location":"Eindhoven Netherlands","acronym":"CUI '23","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 5th International Conference on Conversational User Interfaces"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3571884.3597134","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3571884.3597134","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:51:13Z","timestamp":1750182673000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3571884.3597134"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,19]]},"references-count":75,"alternative-id":["10.1145\/3571884.3597134","10.1145\/3571884"],"URL":"https:\/\/doi.org\/10.1145\/3571884.3597134","relation":{},"subject":[],"published":{"date-parts":[[2023,7,19]]},"assertion":[{"value":"2023-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}