The human voice still remains largely unexploited in the general computing domain as a primary or supplementary input modality despite significant advances in speech recognition technology over many years While voice input has a number of potential benefits, especially for people with motor impairments, one of the major limitations of current speech-based interaction methods is their inability to provide fluid and continuous input, akin to pointing devices such as the mouse. In this dissertation, I describe work that I have conducted as part of the Vocal Joystick project to harness the non-speech characteristics of human vocalization to enable such fluid hands-free control using the voice.
The Vocal Joystick engine upon which my work is based converts various non-speech vocal features such as volume, pitch, and vowel quality into continuous as well as discrete signals 100 times a second. I conducted a number of user studies to determine the performance characteristics of using such vocal input for various tasks including target selection, steering, and rapid discrete inputs. A key result shows that with only 10 hours of practice, users can approach the level of performance comparable to a manual joystick for pointing, and exceed the performance of an existing speech-based pointer control method.
I also present a number of concrete voice-driven applications that I built and evaluated to situate the study of non-speech vocal input in realistic contexts. VoiceDraw is a hands-free drawing program that enables the user to create free-hand-style drawings with dynamically-controlled stroke thickness and speed using only their voice. VoiceGame Controller rapidly transforms various vocal signals into keyboard and mouse signals making it possible to play conventional computer games hands-free. VoicePen augments digital stylus input with continuous voice input. Voice Controller seamlessly integrates voice-driven pointer control with conventional speech commands and dictation functionality, creating a powerful and practical hands-free input modality.
|Advisor:||Landay, James A., Wobbrock, Jacob D.|
|School:||University of Washington|
|School Location:||United States -- Washington|
|Source:||DAI-B 71/05, Dissertation Abstracts International|
|Keywords:||Computer interfaces, Hands-free controls, Voice controls|
Copyright in each Dissertation and Thesis is retained by the author. All Rights Reserved
The supplemental file or files you are about to download were provided to ProQuest by the author as part of a
dissertation or thesis. The supplemental files are provided "AS IS" without warranty. ProQuest is not responsible for the
content, format or impact on the supplemental file(s) on our system. in some cases, the file type may be unknown or
may be a .exe file. We recommend caution as you open such files.
Copyright of the original materials contained in the supplemental file is retained by the author and your access to the
supplemental files is subject to the ProQuest Terms and Conditions of use.
Depending on the size of the file(s) you are downloading, the system may take some time to download them. Please be