GUIRHome|Projects|People|Publications|Links

MultiPoint

Building Presentations Using Multimodal Interaction

MultiPoint is a speech and pen user interface for building presentations, implemented as an add-on to Microsoft PowerPointTM. In this study, we compared users' performance between building presentations with MultiPoint using speech and pen and with PowerPoint using keyboard and mouse. We also compared participants' performance between using Wizard of Oz (WOz) speech recognition and computer speech recognition. In aggregate, six participants with WOz recognition completed tasks in about the same time and with about the same number of errors, as they did using PowerPoint alone. Six participants with computer speech recognition took twice the time and committed four times as many errors, as they did using PowerPoint.
A participant using MultiPoint on a tablet computer

Screenshots


The MultiPoint spoken command “make a rectangle” converts a sketched rectangle into neatened form.

Write-ups

  • MultiPoint: A Case Study of Multimodal Performance for Building Presentations. Anoop K. Sinha, Michael Shilman, Niraj Shah.  CHI 2001 Student Posters. PDF (150k). Poster PPT (263 kb).
  • Usability of MultiPoint. Anoop K. Sinha. Quantitative Usability Methods (Sims 271) Class Project.  Longer version of the above paper. PDF (100 kb)

Contact Information

Anoop Sinha
· Copyright © 1998-2003 by the Regents of the University of California · Last updated Wednesday December 18 2002