A moving speech

A new software allows the physically challenged to use
a computer by making simple sounds; could be used to
paint, play video games and even control a wheelchair

 With agency inputs

Student Brandi House uses Vocal Joystick to control
the movement of a robotic arm. The screen on the lower
right shows how the software analyses her
vocalisations
to create instructions for the arm's movement.
People with motor disabilities often find it
frustrating or impossible to use a computer mouse.
Now, engineers in the US have developed a program that
provides an alternative, by using one of the oldest
and versatile modes of communication: the human voice.

“There are many people who have perfect use of their
voice, but don’t have use of their hands and arms,”
said Jeffrey Bilmes, associate professor of electrical
engineering at the University of Washington, who led
the team that developed the ‘Vocal Joystick’ software.


The technology already helps the disabled in
activities such as browsing the Web, drawing on a
screen, and playing a video game. 

IN THEORY…
Vocal Joystick – an inexpensive technology – requires
only a microphone, a computer with a standard sound
card and a user who can produce vocal sounds.

Bilmes and his team assigned vowel sounds to
correspond to mouse movements: Up is ‘a’ as in ‘cat’,
right is ‘aw’ as in ‘Aw, shucks.’ There are sounds for
more complex movements as well: ‘Down and to the
right’ is ‘oh’ as in bold.
The program also gives users control over the mouse
pointer’s speed. A very quiet ‘ee’ as in ‘beet’ will
move the cursor slowly to the right; a loud ‘oo’
as in ‘boot’ sends it plunging downward.

Once users are accustomed to the commands, they can do
sophisticated on-screen work, such as illustrations or
digital photo restoration.

Early tests suggest that an experienced user of Vocal
Joystick would have as much control as someone using a
handheld device.

A screenshot of the VoiceDraw application showing (a)
the status bar, (b) help overlay, and (c) canvas area.
The first author created this painting using
only his voice in about 2.5 hours.
...AND IN PRACTICE
In the laboratory, student Jonathan Malkin, who helped
develop the tool, uses Vocal Joystick to play a game
called Fish Tale. It takes only two minutes
to train the program for his voice. 

The newest development uses the program to control a
robotic arm. The pitch of the tone moves the arm up
and down; other commands are unchanged. 

This is the first time that vocal commands have been
used to control a three-dimensional object, Bilmes
said.

Voice painter Philip Chavez, who has been using tools
like speech recognition to create art on his computer
for 15 years, is already praising the new painting
application, VoiceDraw.

“Doing it by voice really allows me to work much
longer,” he said.

Although the researchers initially wondered if people
would feel silly making the sounds, their  first test
reassured them. 

“It’s an exciting idea. I think it has tremendous
potential,” said Kurt Johnson, a professor of
rehabilitation medicine who is helping with the tests.

Bilmes said he hopes people will become more adept at
using the system over time. Future research will
incorporate advanced controls that use more aspects
of the human voice, such as vibrato, degree of
nasality and trills.

A version also exists for operating a robotic arm, and
Bilmes believes the technology could be used to
control an electronic wheelchair.


      Chat on a cool, new interface. No download required. Go to 
http://in.messenger.yahoo.com/webmessengerpromo.php

To unsubscribe send a message to [EMAIL PROTECTED] with the subject unsubscribe.

To change your subscription to digest mode or make any other changes, please 
visit the list home page at
  http://accessindia.org.in/mailman/listinfo/accessindia_accessindia.org.in

Reply via email to