|
BOOT CAMP 056
THE POWER OF SPEECH
You might be interested to know that this first paragraph of
Boot Camp was written using a highly respected speech recognition program.
Almost any recent Windows PC can be programmed to recognise and respond to the
user's voice, converting speech into text, for writing letters, composing
E-mails or faxes.
It took a little over ten minutes to enter those fifty or so
words, which is why the rest of this piece is being typed on a keyboard; life
is too short… In the past few years speech recognition software has improved in
leaps and bounds but even the very best systems still require a lot of patience
and hard work to get them up to anything like a useful speed. In the early stages
it's not much faster than one-fingered, hunt-and-peck typing and it all goes to
pot if you catch a cold, loose your voice or work in a noisy environment.
But what if you cannot type, either through physical
disability or a keen dislike/fear of the keyboard? In that case voice
recognition is a practical way of getting your words into a PC, however, do not
expect instant hands-free computing. Even the fastest and most efficient voice
recognition programs have to go through a long-winded training process, to
learn the user's voice before they can achieve worthwhile accuracy. Moreover
some speech recognition systems make heavy weather of menu commands and program
controls so you could still end up using the keyboard and/or mouse for a lot of
routine operations.
Although several voice recognition programs are available
that work on older and slower PCs for the best results you will need a fairly
recent and speedy Pentium or Pentium class multimedia machine. Other basic
requirements are Windows 95 or 98, at least 16Mb of RAM and upwards of 60
megabytes of free hard disc space. The PC should have an up to date soundcard
plus you will need a microphone or headset with a boom mike. A headset type
microphone is preferable as these are less sensitive to background noises and
the performance is usually more consistent.
The three big players in this market are Dragon Systems, IBM
and Talking Technologies. Basic packages cost from around £55, rising to over
£500 for the latest version of IBM VoiceType, however most home and office
programs sell for less than £150. You probably won't be surprised to learn that
Microsoft is also taking a very keen interest in this technology. Its web site
(see contacts list) has lots of information and some interesting downloads for
developers and experimenters. These include beta versions of soon to be
launched voice recognition and text to speech 'engines' called SAPI (Speech
Application Programming Interface).
Users of Microsoft Word might also like to try a program
called Kurzweil Voice Commands, which controls all of the word processor's
functions using simple spoken phrases, like 'select the next two paragraphs' or
'set this word to lowercase'. A fully working 60-day trial version is available
from the Office Update section of the Microsoft web site (see contacts).
Installing a voice recognition program from CD-ROM normally
only takes a few minutes, and that's when the fun begins. The program's first
action is to go into a set-up routine, to measure background noise levels then
test and adjust the sensitivity of the microphone. The amount of vocal training
these packages require varies quite a lot. Dragon Naturally Speaking, for
example, depends on the user reading long passages of text (an excerpt from
Arthur C. Clark's 3001). The initial session can easily last more than half an
hour, and it needs continual training to maintain accuracy. Kurzweil Voice on
the other hand can be up and running in a few minutes, though first attempts
are likely to be riddled with mistakes as it learns as it goes along.
The programs also work in slightly different ways. Most of
them have the option (though not always included as standard) to enter text
directly onto the page of your chosen word processor, as you speak. Others have
their own text window. Once a file has been created and corrected it is
exported to an application, such as a word processor, fax program or Internet
E-mail window.
Even after a program has been fully trained it is important
to remember to speak clearly and slowly using a consistently natural voice and
accent, or at least the same voice that you used when setting up the program
and above all keep calm! Even the best programs make frequent mistakes and
there is a natural tendency to raise the pitch of the voice in frustration,
which makes it even harder for the program to follow what you're saying.
Voice recognition is a fast moving technology with huge
vested interests in getting it to work properly. There is absolutely no doubt
that within a very few years we'll all be chatting merrily to our PCs and the
keyboard will become obsolete. The bottom line is that at the present state of
development it is a very worthwhile aid for those who cannot use a keyboard.
For everyone else, with fully functioning hands and fingers, voice recognition
ranks as an interesting novelty -- it's quite spooky to see words appear on the
screen as they are spoken -- but if you're looking for an easy ride forget it.
There's a good chance you'll end up expending more time and effort, than if you
simply learned to type.
Next week: choosing an Internet Service Provider
JARGON FILTER
BETA
Beta software is usually a near final version of a program
or application, made available to testers and volunteers on an
at-their-own-risk basis, to help identify any last remaining bugs, glitches and
conflicts
ENGINE
A self-contained program designed to do a specific task that
operates within a larger application
SOUND CARD
A more or less standard fitment on modern desktop PCs,
generating the sounds and music heard through the PCs speakers. Most sound
cards also have a microphone input, necessary for voice recognition
CONTACTS
Dragon Dictate/Naturally Speaking
Dragon Systems (01242) 678575,
http://www.dragonsys.com
ViaVoice/Simply speaking/Voice Type
IBM (0990) 727272, www.ibm.com
Kurzweil Voice/VoicePad Pro
Talking Technologies 0171-602 4107. www.talk-systems.com
TOP TIP
The Solitaire game in Windows must be one of the greatest
time-wasters of all time -- it drives office managers crazy -- but even though
it is so simple it can be highly addictive. If you're one of the millions
hooked on it then you have probably figured out by now that the Draw 3 option
-- selected by default -- slows the game down, increases the odds against you
winning and makes it harder to play. Of course you could just switch to
easy-peasy Draw 1 setting and play it that way but where's the fun in that? The
next time you're in a fix try this simple little cheat. Press and hold down the
Crtl, Alt and Shift keys, then click on the top card and you'll find that you
can now select cards one at a time.
|