[info] kurzweill: newscientist: sub-vocal speech recognition necklace

[Alejandro Dubrovsky]

(
http://technology.newscientist.com/article/dn13449-nervetapping-neckband-allows-telepathic-chat.html
video (not very impressive since it's hard to tell what is going on):
http://uk.youtube.com/watch?v=xyN4ViZ21N0
)

Nerve-tapping neckband used in 'telepathic' chat
Movie Camera

 * 17:23 12 March 2008
 * NewScientist.com news service
 * Tom Simonite

A neckband that translates thought into speech by picking up nerve
signals has been used to demonstrate a "voiceless" phone call for the
first time.

With careful training a person can send nerve signals to their vocal
cords without making a sound. These signals are picked up by the
neckband and relayed wirelessly to a computer that converts them into
words spoken by a computerised voice.

A video (right) shows the system being used to place the first public
voiceless phone call on stage at a recent conference held by microchip
manufacturer Texas Instruments. Michael Callahan, co-founder of Ambient
Corporation, which developed the neckband, demonstrates the device,
called the Audeo.

Users needn't worry about that the system voicing their inner thoughts
though. Callahan says producing signals for the Audeo to decipher
requires "a level above thinking". Users must think specifically about
voicing words for them to be picked up by the equipment.

The Audeo has previously been used to let people control wheelchairs
using their thoughts. Watch a video demonstrating thought control of
wheelchairs

"I can still talk verbally at the same time," Callahan told New
Scientist. "We can differentiate between when you want to talk silently,
and when you want to talk out loud." That could be useful in certain
situations, he says, for example when making a private call while out in
public.

The system demonstrated at the TI conference can recognise only a
limited set of about 150 words and phrases, says Callahan, who likens
this to the early days of speech recognition software.

At the end of the year Ambient plans to release an improved version,
without a vocabulary limit. Instead of recognising whole words or
phrases, it should identify the individual phonemes that make up
complete words.

This version will be slower, because users will need to build up what
they want to say one phoneme at a time, but it will let them say
whatever they want. The phoneme-based system will be aimed at people who
have lost the ability to speak due to neurological diseases like ALS –
also known as motor neurone disease.