Generating 'oohs' and 'aahs': Vocal Joystick uses voice to surf the Internet

The Internet offers wide appeal to people with disabilities. But many of those same people find it frustrating or impossible to use a handheld mouse. Software developed at the University of Washington provides an alternative using one of the oldest and most versatile modes of communication: the human voice.

"There are many people who have perfect use of their voice who don't have use of their hands and arms," said Jeffrey Bilmes, a UW associate professor of electrical engineering. "I think there are several reasons why Vocal Joystick might be a better approach, or at least a viable alternative, to brain-computer interfaces." The tool's latest developments will be presented this month in Tempe, Ariz. at the Assets Conference on Computers and Accessibility.

Vocal Joystick detects sounds 100 times a second and instantaneously turns that sound into movement on the screen. Different vowel sounds dictate the direction: "ah," "ee," "aw" and "oo" and other sounds move the cursor one of eight directions. Users can transition smoothly from one vowel to another, and louder sounds make the cursor move faster. The sounds "k" and "ch" simulate clicking and releasing the mouse buttons.

Versions of Vocal Joystick exist for browsing the Web, drawing on a screen, controlling a cursor and playing a video game. A version also exists for operating a robotic arm, and Bilmes believes the technology could be used to control an electronic wheelchair.

Existing substitutes for the handheld mouse include eye trackers, sip-and-puff devices, head-tracking systems and other tools. Each technology has drawbacks. Eye-tracking devices are expensive and require that the eye simultaneously take in information and control the cursor, which can cause confusion. Sip-and-puff joysticks held in the mouth must be spit out if the user wants to speak, and can be tiring. Head-tracking devices require neck movement and expensive hardware.

Vocal Joystick requires only a microphone, a computer with a standard sound card and a user who can produce vocal sounds.

"A lot of people ask: 'Why don't you just use speech recognition"'" Bilmes said. "It would be very slow to move a cursor using discrete commands like 'move right' or 'go faster.' The voice, however, is able to do continuous commands quickly and easily." Early tests suggest that an experienced user of Vocal Joystick would have as much control as someone using a handheld device.

In the laboratory, doctoral student Jonathan Malkin, who helped develop the tool, uses Vocal Joystick to play a game called Fish Tale. It takes two minutes to train the program for Malkin's voice. He then moves the fish character easily around the screen, raising his voice slightly to speed up and avoid being eaten by a predator fish.

The newest development, which will be presented at the October meeting in Tempe, uses Vocal Joystick 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.

One initial concern, he said, was whether people would feel self-conscious using the tool.

"But once you try it you immediately forget what you're saying," Bilmes said. "I usually go to the New York Times' Web site to test the system and then I get distracted and start reading the news. I forget that I'm using it."

To test the device, the group has been working with about eight spinal-cord injury patients at the UW Medical Center since March.

"It's a really 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 more advanced controls that use more aspects of the human voice, such as repeated vocalizations, vibrato, degree of nasality and trills.

"While people use their voices to communicate with just words and phrases," Bilmes said, "the human voice is an incredibly flexible instrument, and can do so much more."

Source: University of Washington

Related stories:

When Fish Talk, Scientists Listen
(PhysOrg.com) -- A male midshipman, a close relative of the toadfish, doesn't need good looks to attract a mate – just a nice voice. After building a nest for his potential partner, he calls to nearby females by contracting his swim bladder, the air-filled sac fish use to maintain buoyancy. The sound he makes is not a song or a whistle, but a hum; more reminiscent of a long-winded foghorn than a ballad. Female midshipman find it very alluring, and they only approach a male's nest if he makes this call.
Superfast muscles in songbirds
Certain songbirds can contract their vocal muscles 100 times faster than humans can blink an eye – placing the birds with a handful of animals that have evolved superfast muscles, University of Utah researchers found.
To sing like Shakira, press '1' now
Vibrato -- the pulsating change of pitch in a singer's voice -- is an important aspect of a singer's expression, used extensively by both classical opera singers and pop stars like Shakira. Usually, the quality of a vibrato can only be judged subjectively by voice experts.
What It's Like to Be a Bat
Not many people think about what it's like to be a bat, but for those who do, it's enlightening and potentially groundbreaking for understanding aspects of the human brain and nervous system.
MGH researchers report successful new laser treatment for vocal-cord cancer
An innovative laser treatment for early vocal-cord cancer, developed at Massachusetts General Hospital (MGH), successfully restores patients’ voices without radiotherapy or traditional surgery, which can permanently damage vocal quality. This new option for patients, which has now been used in more than 25 patients, was reported on May 1 at the annual meeting of the American Broncho-Esophagological Association, and the data will soon be published as a supplement to the Annals of Otology, Rhinology, & Laryngology.
Amateur singers, singing teachers less likely to identify serious vocal problems
Even as American Idol reminds us of the best (and worst) that singing has to offer, a new study cautions that amateur singers and singing instructors are less sensitive than their professional peers to the subtle changes to their voices that could have a serious negative impact on their vocal health.
Bird brains suggest how vocal learning evolved
Though they perch far apart on the avian family tree, birds with the ability to learn songs use similar brain structures to sing their tunes. Neurobiologists at Duke University Medical Center now have an explanation for this puzzling likeness.
Whose voice is that? Scientists discover 'voice' area in the brain of nonhuman primate
For vocal animals, recognising species-specific vocalizations is important for survival and social interactions. In humans, a ‘voice' region has been identified that is sensitive to human voices and vocalizations. As this region also strongly responds to speech, it is unclear whether it is tightly associated with linguistic processing and thus unique to humans.

News discussion:

Technology news