Skip to main navigation Skip to search Skip to main content

LipText: Lip Tracking Based Text Entry in VR

  • Jiaye Leng
  • , Zijun Wang
  • , Jian Wu*
  • , Lili Wang
  • *Corresponding author for this work
  • City University of Hong Kong
  • Beihang University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Text entry is an important task in virtual reality (VR), and most existing methods require hand involvement, while hands-free typing has great potential for applications in mobile scenarios. Existing hands-free text entry methods are usually implemented by combining the head and eyes with techniques such as Dwell, Blink and Gesture, which can easily fatigue the user. In this paper, we propose LipText, a lip-tracking-based text entry method in VR. We use a neural network to perform letter-level prediction on the lip data captured by the facial tracker and use head-based selection as an auxiliary to improve the accuracy. We conduct a user study to evaluate our method, the results show a typing speed of 8.63 WPM for the novice group, 9.81 WPM for the potential expert group, and the highest recorded typing speed is 11.13 WPM achieved by a potential expert. Our method is also novice-friendly, and their typing speed increased by 64.38% over a six-day practice.

Original languageEnglish
Title of host publicationExtended Reality - 1st International Conference, ICXR 2024, Proceedings
EditorsWeitao Song, Frank Guan, Shuai Li, Guofeng Zhang
PublisherSpringer Science and Business Media Deutschland GmbH
Pages162-178
Number of pages17
ISBN (Print)9789819636785
DOIs
StatePublished - 2025
Event1st International Conference on Extended Reality, ICXR 2024 - Xiamen, China
Duration: 14 Nov 202417 Nov 2024

Publication series

NameLecture Notes in Computer Science
Volume15461 LNCS
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference1st International Conference on Extended Reality, ICXR 2024
Country/TerritoryChina
CityXiamen
Period14/11/2417/11/24

Keywords

  • Hands-free
  • Text entry
  • Virtual reality

Fingerprint

Dive into the research topics of 'LipText: Lip Tracking Based Text Entry in VR'. Together they form a unique fingerprint.

Cite this