Speech-based cursor control: understanding the effects of target size, cursor speed, and command selection
Speech recognition can be a powerful tool when physical disabilities, environmental factors, or the tasks in which an individual is engaged hinders the individual’s ability to use traditional input devices. While state-of-the-art speech-recognition systems typically provide mechanisms for both data entry and cursor control, speech-based interactions continue to be slow when compared to similar keyboard- or mouse-based interactions. Although numerous researchers continue to investigate methods of improving speech-based interactions, most of these efforts focus on the underlying technologies or dictation-oriented applications. As a result, the efficacy of speech-based cursor control has received little attention. In this article, we describe two experiments that provide insight into the issues involved when using speech-based cursor control. The first compares two variations of a common speech-based cursor-control mechanism. One employs the standard mouse cursor while the second provides a predictive cursor designed to help users compensate for the delays often associated with speech recognition. As expected, larger targets and shorter distances resulted in shorter target selection times, while larger targets also resulted in fewer errors. Interestingly, there were no differences between the standard and predictive cursors. The second experiment investigates the delays associated with spoken input, explains why the original predictive-cursor implementation failed to provide the expected benefits, and provides insight that guided the design of a new predictive cursor.
Unable to display preview. Download preview PDF.