Speech-centric multimodal interfaces

Posted on January 19, 2005

I just read an article in IEEE Signal Processing Magazine that talked about using gaze and gesture recognition to augment speech recognition for human-computer interaction. Link (IEEE membership required). This seems like a very interesting idea for controlling a computer. For example, you might say “move this to here” and it would interpret you gaze at “this” and “here” to determine what you wanted to do. I would very much like to give something like this a go.

For those of you without IEEE membership, here’s a paper on the web from 1997 that appears to talk about the same ideas: An interface integrating eye gaze and voice recognition for hands-free computer access.

tags [ ]

» Filed Under Blogger Posts

Comments

Leave a Reply




  • Pages

  • Recent Posts

  • Categories

  • Interesting from Elsewhere

  • Meta