Work

UniKey: Enabling Surface-Based Typing with Commodity Smartwatches via Cross-Modal Learning

Year: 2025

Type: conference-paper

Abstract: InferenceFigure 1: Figure illustrates our vision for how Unikey can enable users to type on any surface without a physical keyboard, using only a accelerometer and microphone aboard a commodity smartwatch to sense keystrokes.What sets Unikey apart is its out-of-the-box functionality, requiring no lengthy collection of training data on watch sensors.Instead, it applies typing patterns learned from a user's regular typing on physical keyboard to infer typed text.

Source: ACM Symposium on User Interface Software and Technology (UIST)

DOI: 10.1145/3746059.3747611

Authors: Sean Rui Xiang Tan, Mun Choon Chan, Jun Han

Institutions: National University of Singapore, Korea Advanced Institute of Science and Technology

Language: English

Topic: User Authentication and Security Systems

Subfield: Information Systems

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: National Research Foundation, National Research Foundation of Korea, Ministry of Science and ICT, South Korea

Awards: G4362234508, G7400092454