{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T07:58:48Z","timestamp":1776931128461,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":68,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100003816","name":"Huawei Technologies","doi-asserted-by":"publisher","award":["9220140"],"award-info":[{"award-number":["9220140"]}],"id":[{"id":"10.13039\/501100003816","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003816","name":"Google","doi-asserted-by":"publisher","award":["9229068"],"award-info":[{"award-number":["9229068"]}],"id":[{"id":"10.13039\/501100003816","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\/3772318.3791209","type":"proceedings-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T05:14:30Z","timestamp":1776057270000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Desirable Unfamiliarity: Insights from Eye Movements on Engagement and Readability of Dictation Interfaces"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1715-096X","authenticated-orcid":false,"given":"Zhaohui","family":"Liang","sequence":"first","affiliation":[{"name":"School of Creative Media, City University of Hong Kong, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3081-1813","authenticated-orcid":false,"given":"Yonglin","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Creative Media, City University of Hong Kong, Hong Kong, China and Southern University of Science and Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4551-3080","authenticated-orcid":false,"given":"Naser","family":"Al Madi","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Colby College, Waterville, Maine, USA"}]},{"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, Hong Kong, China"}]}],"member":"320","published-online":{"date-parts":[[2026,4,13]]},"reference":[{"key":"e_1_3_3_3_2_2","doi-asserted-by":"crossref","unstructured":"Akiko Aizawa. 2003. An information-theoretic perspective of tf\u2013idf measures. Information Processing & Management 39 1 (2003) 45\u201365.","DOI":"10.1016\/S0306-4573(02)00021-3"},{"key":"e_1_3_3_3_3_2","unstructured":"Mehdi Allahyari Seyed\u00a0Amin Pouriyeh Mehdi Assefi Saeid Safaei Elizabeth\u00a0D. Trippe Juan\u00a0B. Gutierrez and Krys\u00a0J. Kochut. 2017. Text Summarization Techniques: A Brief Survey. CoRR abs\/1707.02268 (2017). arXiv:https:\/\/arXiv.org\/abs\/1707.02268http:\/\/arxiv.org\/abs\/1707.02268"},{"key":"e_1_3_3_3_4_2","doi-asserted-by":"crossref","unstructured":"Scott\u00a0F Beers Thomas Quinlan and Allen\u00a0G Harbaugh. 2010. Adolescent students\u2019 reading during writing behaviors and relationships with text quality: an eyetracking study. Reading and Writing 23 (2010) 743\u2013775.","DOI":"10.1007\/s11145-009-9193-7"},{"key":"e_1_3_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/1753846.1754093"},{"key":"e_1_3_3_3_6_2","doi-asserted-by":"crossref","unstructured":"Christian Bokhove and Christopher Downey. 2018. Automated generation of \u2018good enough\u2019transcripts as a first step to transcription of audio-recorded data. Methodological innovations 11 2 (2018) 2059799118790743.","DOI":"10.1177\/2059799118790743"},{"key":"e_1_3_3_3_7_2","doi-asserted-by":"crossref","unstructured":"Virginia Braun and Victoria Clarke. 2019. Reflecting on reflexive thematic analysis. Qualitative research in sport exercise and health 11 4 (2019) 589\u2013597.","DOI":"10.1080\/2159676X.2019.1628806"},{"key":"e_1_3_3_3_8_2","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared\u00a0D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et\u00a0al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877\u20131901."},{"key":"e_1_3_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3643834.3660681"},{"key":"e_1_3_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICALT.2017.11"},{"key":"e_1_3_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3172944.3172983"},{"key":"e_1_3_3_3_12_2","doi-asserted-by":"crossref","unstructured":"Patrick\u00a0M Commarford and James\u00a0R Lewis. 2004. Models of throughput rates for dictation and voice spelling for handheld devices. International Journal of Speech Technology 7 1 (2004) 69\u201379.","DOI":"10.1023\/B:IJST.0000004809.33755.b7"},{"key":"e_1_3_3_3_13_2","doi-asserted-by":"crossref","unstructured":"Yue Dong Yikang Shen Eric Crawford Herke van Hoof and Jackie Chi\u00a0Kit Cheung. 2018. Banditsum: Extractive summarization as a contextual bandit. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1809.09672 (2018).","DOI":"10.18653\/v1\/D18-1409"},{"key":"e_1_3_3_3_14_2","doi-asserted-by":"crossref","unstructured":"Mennatallah El-Assady Annette Hautli-Janisz Valentin Gold Miriam Butt Katharina Holzinger and Daniel\u00a0A Keim. 2017. Interactive visual analysis of transcribed multi-party discourse. (2017).","DOI":"10.18653\/v1\/P17-4009"},{"key":"e_1_3_3_3_15_2","doi-asserted-by":"publisher","unstructured":"Rahhal Errattahi Asmaa El Hannani and Hassan Ouahmane. 2018. Automatic Speech Recognition Errors Detection and Correction: A Review. Procedia Computer Science 128 (2018) 32\u201337. 10.1016\/j.procs.2018.03.0051st International Conference on Natural Language and Speech Processing.","DOI":"10.1016\/j.procs.2018.03.005"},{"key":"e_1_3_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.4324\/9781315772110"},{"key":"e_1_3_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300526"},{"key":"e_1_3_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173977"},{"key":"e_1_3_3_3_19_2","unstructured":"Valentin Gold Annette Hautli-Janisz Katharina Holzinger and Mennatallah El-Assady. 2016. Visargue: analysis and visualization of deliberative political communication. Political Communication Report 26 1 (2016) 1\u20132."},{"key":"e_1_3_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642699"},{"key":"e_1_3_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3650956"},{"key":"e_1_3_3_3_22_2","doi-asserted-by":"publisher","unstructured":"Shihui Guo Yubin Shi Pintong Xiao Yinan Fu Juncong Lin Wei Zeng and Tong-Yee Lee. 2023. Creative and Progressive Interior Color Design with Eye-tracked User Preference. ACM Trans. Comput.-Hum. Interact. 30 1 Article 5 (March 2023) 31\u00a0pages. 10.1145\/3542922","DOI":"10.1145\/3542922"},{"key":"e_1_3_3_3_23_2","doi-asserted-by":"crossref","unstructured":"Thomas Hain Luk\u00e1\u0161 Burget John Dines Philip\u00a0N Garner Franti\u0161ek Gr\u00e9zl Asmaa El\u00a0Hannani Marijn Huijbregts Martin Karafiat Mike Lincoln and Vincent Wan. 2011. Transcribing meetings with the AMIDA systems. IEEE Transactions on Audio Speech and Language Processing 20 2 (2011) 486\u2013498.","DOI":"10.1109\/TASL.2011.2163395"},{"key":"e_1_3_3_3_24_2","doi-asserted-by":"crossref","unstructured":"Jaakko Hakulinen Tuuli Keskinen Markku Turunen and Sanni Siltanen. 2021. Design space for voice-based professional reporting. Multimodal Technologies and Interaction 5 1 (2021) 3.","DOI":"10.3390\/mti5010003"},{"key":"e_1_3_3_3_25_2","first-page":"372","volume-title":"Proceedings of the first World Congress on fluency disorders","volume":"2","author":"Howell Peter","year":"1995","unstructured":"Peter Howell and Stevie Sackin. 1995. Automatic recognition of repetitions and prolongations in stuttered speech. In Proceedings of the first World Congress on fluency disorders , Vol.\u00a02. University Press Nijmegen Nijmegen, The Netherlands, 372\u2013374."},{"key":"e_1_3_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3715669.3726846"},{"key":"e_1_3_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSET59111.2023.10295108"},{"key":"e_1_3_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1014"},{"key":"e_1_3_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.295"},{"key":"e_1_3_3_3_30_2","doi-asserted-by":"crossref","unstructured":"Annessa Kernberg Jeffrey\u00a0A Gold and Vishnu Mohan. 2024. Using ChatGPT-4 to Create Structured Medical Notes From Audio Recordings of Physician-Patient Encounters: Comparative Study. Journal of Medical Internet Research 26 (2024) e54419.","DOI":"10.2196\/54419"},{"key":"e_1_3_3_3_31_2","doi-asserted-by":"publisher","unstructured":"Anam\u00a0Ahmad Khan Joshua Newn Ryan\u00a0M. Kelly Namrata Srivastava James Bailey and Eduardo Velloso. 2021. GAVIN: Gaze-Assisted Voice-Based Implicit Note-taking. ACM Trans. Comput.-Hum. Interact. 28 4 Article 26 (Aug. 2021) 32\u00a0pages. 10.1145\/3453988","DOI":"10.1145\/3453988"},{"key":"e_1_3_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/2207676.2208386"},{"key":"e_1_3_3_3_33_2","doi-asserted-by":"crossref","unstructured":"Dani\u00ebl Lakens. 2013. Calculating and reporting effect sizes to facilitate cumulative science: a practical primer for t-tests and ANOVAs. Frontiers in psychology 4 (2013) 863.","DOI":"10.3389\/fpsyg.2013.00863"},{"key":"e_1_3_3_3_34_2","unstructured":"Md\u00a0Tahmid\u00a0Rahman Laskar Xue-Yong Fu Cheng Chen and Shashi\u00a0Bhushan Tn. 2023. Building real-world meeting summarization systems using large language models: A practical perspective. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.19233 (2023)."},{"key":"e_1_3_3_3_35_2","doi-asserted-by":"crossref","unstructured":"Jae\u00a0Hwa Lee and Aviv Segev. 2012. Knowledge maps for e-learning. Computers & Education 59 2 (2012) 353\u2013364.","DOI":"10.1016\/j.compedu.2012.01.017"},{"key":"e_1_3_3_3_36_2","doi-asserted-by":"crossref","unstructured":"Gondy Leroy and David Kauchak. 2014. The effect of word familiarity on actual and perceived text difficulty. Journal of the American Medical Informatics Association 21 e1 (2014) e169\u2013e172.","DOI":"10.1136\/amiajnl-2013-002172"},{"key":"e_1_3_3_3_37_2","doi-asserted-by":"crossref","unstructured":"Junwei Liao Sefik Eskimez Liyang Lu Yu Shi Ming Gong Linjun Shou Hong Qu and Michael Zeng. 2023. Improving readability for automatic speech recognition transcription. ACM Transactions on Asian and Low-Resource Language Information Processing 22 5 (2023) 1\u201323.","DOI":"10.1145\/3557894"},{"key":"e_1_3_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642217"},{"key":"e_1_3_3_3_39_2","doi-asserted-by":"crossref","unstructured":"Eden Litt and Eszter Hargittai. 2016. The imagined audience on social network sites. Social Media+ Society 2 1 (2016) 2056305116633482.","DOI":"10.1177\/2056305116633482"},{"key":"e_1_3_3_3_40_2","doi-asserted-by":"crossref","unstructured":"Paria\u00a0Jamshid Lou and Mark Johnson. 2020. End-to-end speech recognition and disfluency removal. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2009.10298 (2020).","DOI":"10.18653\/v1\/2020.findings-emnlp.186"},{"key":"e_1_3_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1300"},{"key":"e_1_3_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3571884.3597134"},{"key":"e_1_3_3_3_43_2","doi-asserted-by":"crossref","unstructured":"Sandip Modha Prasenjit Majumder Thomas Mandl and Chintak Mandalia. 2020. Detecting and visualizing hate speech in social media: A cyber watchdog for surveillance. Expert Systems with Applications 161 (2020) 113725.","DOI":"10.1016\/j.eswa.2020.113725"},{"key":"e_1_3_3_3_44_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1158"},{"key":"e_1_3_3_3_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411763.3450391"},{"key":"e_1_3_3_3_46_2","doi-asserted-by":"crossref","unstructured":"Keith Rayner. 1998. Eye movements in reading and information processing: 20 years of research. Psychological bulletin 124 3 (1998) 372.","DOI":"10.1037\/0033-2909.124.3.372"},{"key":"e_1_3_3_3_47_2","doi-asserted-by":"crossref","unstructured":"Keith Rayner Kathryn\u00a0H Chace Timothy\u00a0J Slattery and Jane Ashby. 2006. Eye movements as reflections of comprehension processes in reading. Scientific studies of reading 10 3 (2006) 241\u2013255.","DOI":"10.1207\/s1532799xssr1003_3"},{"key":"e_1_3_3_3_48_2","doi-asserted-by":"crossref","unstructured":"Virgile Rennard Guokan Shang Julie Hunter and Michalis Vazirgiannis. 2023. Abstractive meeting summarization: A survey. Transactions of the Association for Computational Linguistics 11 (2023) 861\u2013884.","DOI":"10.1162\/tacl_a_00578"},{"key":"e_1_3_3_3_49_2","doi-asserted-by":"crossref","unstructured":"Stuart Rose Dave Engel Nick Cramer and Wendy Cowley. 2010. Automatic keyword extraction from individual documents. Text mining: applications and theory (2010) 1\u201320.","DOI":"10.1002\/9780470689646.ch1"},{"key":"e_1_3_3_3_50_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-27648-9_121-1"},{"key":"e_1_3_3_3_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICALT.2014.127"},{"key":"e_1_3_3_3_52_2","unstructured":"Selina Sharmin Mari Wiklund and Liisa Tiittula. 2016. The reading process of dynamic text-A linguistic approach to an eye movement study. SKY Journal of Linguistics 29 (2016)."},{"key":"e_1_3_3_3_53_2","doi-asserted-by":"crossref","unstructured":"Hendrik Strobelt Daniela Oelke Bum\u00a0Chul Kwon Tobias Schreck and Hanspeter Pfister. 2015. Guidelines for effective usage of text highlighting techniques. IEEE transactions on visualization and computer graphics 22 1 (2015) 489\u2013498.","DOI":"10.1109\/TVCG.2015.2467759"},{"key":"e_1_3_3_3_54_2","unstructured":"Alexander Strukelj and Diederick\u00a0C Niehorster. 2018. One page of text: Eye movements during regular and thorough reading skimming and spell checking. Journal of Eye Movement Research 11 1 (2018)."},{"key":"e_1_3_3_3_55_2","first-page":"401","volume-title":"INTERSPEECH","author":"Tanaka Tomohiro","year":"2018","unstructured":"Tomohiro Tanaka, Ryo Masumura, Hirokazu Masataki, and Yushi Aono. 2018. Neural Error Corrective Language Models for Automatic Speech Recognition.. In INTERSPEECH. 401\u2013405."},{"key":"e_1_3_3_3_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/2381416.2381430"},{"key":"e_1_3_3_3_57_2","doi-asserted-by":"crossref","unstructured":"Mark Torrance Roger Johansson Victoria Johansson and \u00c5sa Wengelin. 2016. Reading during the composition of multi-sentence texts: an eye-movement study. Psychological Research 80 (2016) 729\u2013743.","DOI":"10.1007\/s00426-015-0683-8"},{"key":"e_1_3_3_3_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642876"},{"key":"e_1_3_3_3_59_2","doi-asserted-by":"crossref","unstructured":"Adhika\u00a0Pramita Widyassari Supriadi Rustad Guruh\u00a0Fajar Shidik Edi Noersasongko Abdul Syukur Affandy Affandy et\u00a0al. 2022. Review of automatic text summarization techniques & methods. Journal of King Saud University-Computer and Information Sciences 34 4 (2022) 1029\u20131046.","DOI":"10.1016\/j.jksuci.2020.05.006"},{"key":"e_1_3_3_3_60_2","doi-asserted-by":"publisher","unstructured":"Jen-Her Wu and Yufei Yuan. 2003. Improving searching and reading performance: the effect of highlighting and text color coding. Inf. Manage. 40 7 (Aug. 2003) 617\u2013637. 10.1016\/S0378-7206(02)00091-5","DOI":"10.1016\/S0378-7206(02)00091-5"},{"key":"e_1_3_3_3_61_2","unstructured":"Hao Xiong Ruiqing Zhang Chuanqiang Zhang Zhongjun He Hua Wu and Haifeng Wang. 2019. Dutongchuan: Context-aware translation model for simultaneous interpreting. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1907.12984 (2019)."},{"key":"e_1_3_3_3_62_2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1013"},{"key":"e_1_3_3_3_63_2","unstructured":"Xuyu Yang Wengxi Li Matthew\u00a0G. Lee Zhuoyang Li J.\u00a0D. Zamfirescu-Pereira and Can Liu. 2025. Rambler in the Wild: A Diary Study of LLM-Assisted Writing With Speech. arxiv:https:\/\/arXiv.org\/abs\/2502.05612\u00a0[cs.HC] https:\/\/arxiv.org\/abs\/2502.05612"},{"key":"e_1_3_3_3_64_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3134"},{"key":"e_1_3_3_3_65_2","doi-asserted-by":"crossref","unstructured":"Patricia\u00a0M Zebrowski. 1991. Duration of the speech disfluencies of beginning stutterers. Journal of Speech Language and Hearing Research 34 3 (1991) 483\u2013491.","DOI":"10.1044\/jshr.3403.183"},{"key":"e_1_3_3_3_66_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1062"},{"key":"e_1_3_3_3_67_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1088"},{"key":"e_1_3_3_3_68_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581260"},{"key":"e_1_3_3_3_69_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.366"}],"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\/3772318.3791209","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T09:03:18Z","timestamp":1776416598000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3772318.3791209"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,13]]},"references-count":68,"alternative-id":["10.1145\/3772318.3791209","10.1145\/3772318"],"URL":"https:\/\/doi.org\/10.1145\/3772318.3791209","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"}}]}}