Gaze and speech: Pointing device and text entry modality

Abstract

The performance of eye gaze and speech when used as a pointing device was tested using the International Organization for Standardization (ISO) multidirectional tapping task. Eye gaze and speech were used for target selection as is, as well as with the use of a gravitational well and in conjunction with magnification. This selection method was then compared to the mouse. The mouse was far superior in terms of performance when selecting targets, although the use of a gravitational well did increase the performance of eye gaze and speech. Unfortunately, owing to the nature of eye gaze and speech as well as the ease with which target selection is achieved with a gravitational well, there was an increase in the number of incorrect clicks with this interaction technique. Magnification did not improve the use of gaze and speech as a pointing device and also resulted in more target re-entries. Furthermore, eye gaze and speech were used as a modality for text entry in a popular word processor application. Users were required to focus on an on-screen keyboard and then utter a verbal command in order to type a letter in the document. Speed and accuracy measurements were captured for the input of randomly selected phrases. Results showed that the keyboard was both faster and more accurate than using a combination of eye gaze and speech. Furthermore, neither the size of the on-screen buttons nor the spacing between the buttons affected the speed or accuracy of text entry.