Voice recognition and computers

joinherbalistΤεχνίτη Νοημοσύνη και Ρομποτική

17 Νοε 2013 (πριν από 3 χρόνια και 8 μήνες)

133 εμφανίσεις







Voice recognition and computers


This factsheet gives an overview of voice recognition, starting with the basics but then
moving onto more advanced techniques.



This factsheet is part of AbilityNet’s free
Advice and Information
service.


If you have
any questions at all about anything in this Factsheet, or any other aspect of
assistive technology, please contact us.

Helpline
:

0800 269545

Email:


enquiries@abilitynet.org.uk









Help us to help
others

Our Factsheets are part of our charitable work which relies on
donations. If you can afford it a donation will help to keep these
Factsheets free to those who can't.


You can donate now by

texting

ANET 12 £3 to 70070.

You will receive
a reply and
can then donate as little as £1 or as much as £10 to
AbilityNet.


The service is run by JustGiving and
Vodafone

but works with any
network. There's no cost to you for sending the text message, your free
allowance/bundle won’t be deducted and

AbilityNet re
ceives

100% of
your donation.


If you have any questions about the donations please call our
fundraising team on
0207 796 2144



Web:
www.abilitynet.org.uk
. Tel: 0800 269545. Email enquiries@abilitynet.org.uk

Updated April 2012

Page
2




The software has been developed to provide a fast method of writing onto a computer
and can help people with a variety of disa
bilities. It is useful for p
e
ople with physical
disabilities

who
often find typing difficult, painful or impossible
. Voice recognition
software can also help those with spelling difficulties, including dyslexic users, because
recognised words are always co
rrectly spelled.


Voice recognition software programs work by analysing sounds and converting them to
text. They also use knowledge of how English is usually spoken to decide what the
speaker most probably said. Once correctly set up, the systems should
recognise
around 95% of what is said if you speak clearly.

Several programs are available that
provide voice recognition.


A number of voice recognition programs can be used with Windows


Most specialist voice applications include a software CD, a microph
one headset, a
manual and a quick reference card.


You connect the microphone to the computer, either into the soundcard (sockets on the
back of a computer) or via a USB connection USB microphones do tend to give the
best perform. Then you can begin tal
king using the following steps.

Enrolment

Everybody sounds slightly different, so the first step in using a voice recognition system
involves reading an article displayed on the screen. This process, called enrolment,
takes less than 10 minutes and result
s in a set of files being created which tell the
software how you speak.

The enrolment only has to be done once, after which the software can be started as
needed. The new pieces of software claim that the enrolment process is even easier
then in prev
ious versions.

Dictating and Correcting

When talking, people often hesitate, mumble or slur their words. One of the key skills
in using voice recognition software is learning how to talk clearly so that the computer
can recognise what you are saying. Thi
s means planning what to say and then
delivering speech in complete phrases or sentences.









Web:
www.abilitynet.org.uk
. Tel: 0800 269545. Email enquiries@abilitynet.org.uk

Updated April 2012

Page
3


The voice recognition software will misunderstand some of the words spoken and it is
necessary to proof
-
read and then correct your mistakes. Corrections can be

made by
using the mouse and keyboard or by using your voice.

When corrections are made the voice
recognition software will adapt and learn,
so that (hopefully) the same mistake will
not occur again. Accuracy should improve
with careful dictation and cor
rection.

In the example “typing” has been
recognised as “20”. To make the
correction you say “correct
-
20” followed by
“choose
-
2”.




Editing and Formatting Text

Te
xt can be changed (edited) very easily. The text to be changed can be selected
(highlighted) by using commands like “select line”, “select paragraph” and then the
changes can be spoken into the computer. These will then replace the selected text.

Applyi
ng formatting is just as straightforward. For example, if a document has the
phrase “introductory thoughts” then this phrase can be underlined by saying “Select
-
introductory
-
thoughts” and then saying “underline that”.


Controlling the Computer

Many voice
recognition programs offer the ability to start and control programs through
spoken commands. The commands vary between voice recognition programs.



For example,

with the program Dragon NaturallySpeaking you could say “Start
Microsoft Word”, then “Open l
etter to John”.



Menus:

Menus can be selected simply by pausing and then saying the menu item.
“File” would open the file menu



On the Internet,

web addresses can be dictated and web sites can be browsed
simply by saying the text in the link.



For task
s that require a mouse
:
(e.g. drawing) there are spoken commands to
enable the mouse to be moved, dragged and clicked.



Web:
www.abilitynet.org.uk
. Tel: 0800 269545. Email enquiries@abilitynet.org.uk

Updated April 2012

Page
4


Some Example Programs

There are several main voice recognition programs available:

Dragon NaturallySpeaking

T
his program is distributed

by
Nuance.

NaturallySpeaking is recognised as the market
leader and is the alternative most frequently recommended by AbilityNet
.

Web:

www.nuance.co.uk/naturallyspeaking


Dragon Dictate for Mac

Th
is product is also distributed by Nuance and is available for the Apple Macintosh
computer. It shares a lot of the characteristics with Dragon Naturally Speaking.

http://www.macspeech.com/



The programs most comm
only recommended by AbilityNet are:



Dragon NaturallySpeaking
Preferred Version 11.5
(approx £80 inc VAT
)

Dragon NaturallySpeaking
Professional Version 11.5
(approx
£660 incl VAT
)

Overview

A good choice for people with
physical difficulties and
dyslexi
a.




A⁣ mp牥ren獩se⁳ 琠of
捯mmand猠so⁡汬ow⁶oi捥
捯n瑲t氠l映瑨e⁣ mpu瑥r



Speechu瑰u琠晡捩c楴楥猠so
he汰lw楴i⁣ 牲e捴楯ns



䥴⁣ n⁢e⁵獥d⁷楴i⁰or瑡b汥l
牥捯牤r牳



A 牥⁡dvan捥d⁶e牳ron 景爠ru獩se獳s
u獥牳⁡nd†景爠reop汥 whoeed 瑯
wo牫⁣rmp汥le汹⁨
ands
-
f牥r:




Vo楣攠捯mmand猠景爠ro瑵猠乯瑥猠
and⁍ 捲潳c晴⁏u瑬to欮



The⁡b楬楴i⁴o⁷r楴iew⁶o楣攠
捯mmand猠so⁡獳楳s⁥a獹⁨ands
-
f牥e⁵se映瑨e⁣ mputer


Alternative
suppliers

www.nuance.co.u
k/naturallyspeaking/locator

gives suppliers from
around the country. Also available from
www.amazon.co.uk


Website

www.nuance.co.uk/naturallyspeaking








Web:
www.abilitynet.org.uk
. Tel: 0800 269545. Email enquiries@abilitynet.org.uk

Updated April 2012

Page
5





Free Voice Recognition Software

If you have a computer running either Windows Vista or Windows 7 you now have the
opportunity to try out voice recognition for free as part of the Accessibility features. For
a lot of the people that we talk to it is

an ideal solution. You can not only write emails
but you can browse the web and control your computer. Enrolment will take around 30
-
45 minutes
. All you need to do is to get a headset microphone (normally costs £10
-
£15)
and a little bit of patience!




Web:
www.abilitynet.org.uk
. Tel: 0800 269545. Email enquiries@abilitynet.org.uk

Updated April 2012

Page
6


Tr
aining and Support

People who are new to voice recognition software often need to arrange a number of
one
-
to
-
one training to get the most out of the software. There are a number of
specialist suppliers of voice recognition solutions who can provide you wi
th training,
suggest suitable computer systems and assist with installation.

Frequently Asked Questions



How is it affected by background noise?

The headset microphones supplied
with the products are fairly good at filtering out background noise. If backgr
ound
noise is a particular issue then a higher specification microphone will be needed.



What about technical jargon?

Modern voice recognition systems already
“know” thousands of words including much specialist language from the legal
and medical fields. N
ew words and phrases can be added and trained easily.



Is “voice strain” a risk?

When working with speech recognition systems, steps
should be taken to minimise strain: sit comfortably; speak at a normal
pitch/volume; take breaks and drink regularly.



What

about catching colds?


Some people’s voices change when they have a
cold and this may result in slightly worse recognition.



How many people can use the software on one computer?

There is no limit
on the number of users. Each one will require 20
-
30MB o
f space on the hard
disk of the machine. Each person needs to load their own voice settings before
they start to dictate.



Can the software be used to transcribe meetings?

No
-

they only work with
one speaker at a time.



Can recording devices be used with
speech recognition systems?

Yes


speech recorded onto pocket sized recorders can be transferred onto a PC and
then “transcribed” to text. (See the AbilityNet factsheet “Voice Recognition:
Advanced Features)














Web:
www.abilitynet.org.uk
. Tel: 0800 269545. Email enquiries@abilitynet.org.uk

Updated April 2012

Page
7


Troubleshooting

Voice recognition s
oftware may raise issues where users have certain difficulties or
ways of working. Contact us to discuss these issues further.



The software runs too slowly:

voice recognition systems need relatively new
computers with a lot of memory. The more memory yo
u can have on your
system, the quicker the system will run.



Poor recognitio
n
: this can be a problem if the computer is not getting a clear
signal from the microphone or if the user is not speaking clearly.




Difficulty spotting mistakes in work:

this can b
e an issue particularly for
dyslexic users. Choose a package that includes text
-
to
-
speech so that text can
be spoken by the computer and reading avoided


then you can listen out for
mistakes. For further information see the AbilityNet factsheet called “
Dyslexia
and Voice Recognition Software”.



Difficulty using a headset microphone:

there are a number of alternative
designs of microphone that can be used including: stand microphones; collar
microphones; array microphones; hand
-
held microphones


one of t
hese should
work.



Impaired speech
:
voice recognition software can adapt to non
-
standard speech.
Some systems are better than others


seek advice.


























Web:
www.abilitynet.org.uk
. Tel: 0800 269545. Email enquiries@abilitynet.org.uk

Updated April 2012

Page
8


More advanced concepts

Features Explained

Vocabularies

Voice recognition systems matc
h the words they hear to a list of words stored in the
computer’s memory. They also have a backup dictionary of words that are held on the
hard disk and this list is used during correction. The number of words held in memory
varies between the programs


but all modern programs hold very large lists (150,000
words in the case of Naturally Speaking

As new words are added, words that have not been used recently are removed from
the active vocabulary. They remain on the computer's disk in the backup dictiona
ry for
future use.

Personalising the Vocabulary

As corrections are made the vocabulary will change to reflect any special words that
are used and will adapt to match the writing style of the user. This process can be “kick
-
started” by using a number of too
ls provided by the software programs


these make it
possible to:



Add individual words



Add lists of words



Analyze entire documents


new words can be added, and the program can
learn

about writing styles



Web:
www.abilitynet.org.uk
. Tel: 0800 269545. Email enquiries@abilitynet.org.uk

Updated April 2012

Page
9


Natural Language Commands (within Nuance products o
nly)

Voice recognition systems incorporate large command sets that make it easier to
control applications and manipulate text. Rather than having to use logical steps
involving multiple menu selections, Natural Language Commands, make it possible to
say w
hat you want to do.

Examples of formatting commands
provided by NaturallySpeaking for use
in Microsoft Word:

“Bold this paragraph”

“Increase the indent by three centimetres”

“Bullet the rest of the page”

“Make it arial”

“Move this paragraph down”

Dicta
tion Shortcuts/Text Macros

When writing, people often make use of standard phrases or paragraphs. These
portions of text can be stored in the voice recognition
program and, once stored, they can be typed out in
full by saying a short command.








Command Macros

Some versions of voice recognition software have a facility to allow the user to create
command macros. These record a series of steps which can then be executed with a
single command. As an example, you could record the steps nee
ded to send a
document from your computer by fax to one of your colleagues. Once recorded you
could say “Fax this to Tom”.

Text to Speech

Text
-
to
-
speech facilities are provided in speech recognition programs to provide a
proof
-
reading tool. They allow

the user to listen to what the computer has recognised.
Typically there are voice commands to allow you to:

"Read Paragraph", "Read Document"

"Read Up To Here", "Read Down From Here"

In this example sa
ying “AbilityNet Info” will
牥獵汴⁩l⁴he⁣onta捴c楮景牭a瑩on be楮i
en瑥牥d⁩ to⁴he do捵men琮



Web:
www.abilitynet.org.uk
. Tel: 0800 269545. Email enquiries@abilitynet.org.uk

Updated April 2012

Page
10


Recorded Speech

Sometimes what the program types looks very different t
o what was actually said. To
make correcting mistakes easier, some of the programs record what was said along
with the text that is recognised. The recording can be played back when work is
checked. Then you hear what was actually said and can compare
that with what is on
the screen.

Delegated Correction

Some people will find it helpful to dictate work and then ask someone else to make
corrections for them at a later time. To do this they need to be able to save their
recorded speech with the documents

they have created. A helper can then load the
files later, listen to what was said and make corrections.

Working on the Move

Voice recognition software can be installed and used on lightweight laptop computers.
A more portable solution can be provided

by using a hand
-
sized recording device.
These record speech digitally. The digital recordings are transferred onto the computer
at a later time and can then be transcribed using the voice recognition software.

If considering the use of a mobile record
er:



Seek advice from a specialist supplier:
not all devices are suitable



Remember that good dictation skills are needed
:

the user will not be able to refer to
text on the screen
.



Web:
www.abilitynet.org.uk
. Tel: 0800 269545. Email enquiries@abilitynet.org.uk

Updated April 2012

Page
11



Hands
-
Free Facilities

People who have little or no use of their hands nee
d to use a computer entirely by
voice. A hands
-
free user will need to have the following:

Microphone listening at start up:


The voice recognition program can start with the
microphone listening out for commands. It is normal to set the microphone to be
on,
but “asleep”


once the program is loaded the use can simply say “wake
-
up” to start it
.

Make corrections by voice
.

Select menus and launch programs by voice
.

Move and click the mouse by voice: different programs of
fer different ways of achieving
this.




Typical commands are “Move mouse right”, “Mouse double click”, “Mouse up 10”



Navigate the internet by voice: all the programs detailed here offer voice
.
browsing using Internet Explorer
.



“Press” keys by voice: Some programs allow you to send individual
keystrokes
to the computer e.g.: “Press Alt
-
key f”
.

Select and Say Dictation

All of the programs detailed in this sheet make it possible to dictate, edit and correct
easily by voice in Microsoft Word. In this application words can be selected simply by
s
aying “select” followed by the word.

It is not possible to use this Select and Say dictation in all programs and sometimes it is
necessary to dictate into a “well behaved” word processor and then transfer the
corrected dictation. For this reason Natural
lySpeaking supply a simple word
processing application which can be used easily by voice.

Choosing a product

Up until a couple of years ago we would normally recommend Dragon naturally
Speaking (or alternatively Dragon Dictate for Mac). However since the a
dvent of
Windows Vista and latterly Windows 7 there has been a choice between paid and free
voice recognition systems. The free software which is bundled with the latest versions
of Windows is surprisingly good and we have done a lot of work with individu
als who
have used this software.
However we should stress that Naturally Speaking does
have more features then the free programs
.



Web:
www.abilitynet.org.uk
. Tel: 0800 269545. Email enquiries@abilitynet.org.uk

Updated April 2012

Page
12




Requirement

Product

To overcome difficulties with spelling

NaturallySpeaking Home Edition/Windows
Voice recognition

To h
elp reduce keyboard/mouse use

NaturallySpeaking Home Edition/Windows
Voice recognition

Hands
-
free use

NaturallySpeaking Premium

Business users wishing to limit
keyboarding and use Outlook by voice

NaturallySpeaking premium


Useful Fact
sheets

The followi
ng factsheets are also available:



Dyslexia and Voice Recognition Software
































Web:
www.abilitynet.org.uk
. Tel: 0800 269545. Email enquiries@abilitynet.org.uk

Updated April 2012

Page
13


Copyright information


This
Factsheet

is licensed
by AbilityNet
under the Creative
Commons Attribution
-
NonCommercial
-
ShareAlike 3.0 Unported
License.

V
iew
a copy of this license at
http://creativecom
mons.org/licenses/by
-
nc
-
sa/3.0/

This means you are free to:

Share



to copy, distribute and transmit the work

Remix



to adapt the work

But only under the following conditions:

Attribution



You must attrib
ute the work to AbilityNet (but not in any way that
suggests that we endorse you or your use of the work).

Noncommercial



You may not use this work for commercial purposes.

Share Alike



If you alter, transform, or build upon this work, you may distribu
te the
resulting work only under the same or similar license to this one.

With the understanding that:

Waiver



Any of the above conditions can be
waived

if you get permission from the
cop
yright holder.

Public Domain



Where the work or any of its elements is in the
public domain

under
applicable law, that status is in no way affected by the license.

Other Rights



In no way ar
e any of the following rights affected by the license:



Your fair dealing or
fai
r use

rights, or other applicable copyright exceptions and
limitations;



The author's
moral

rights;



Rights other persons may have either in the work itself or in how the work is used,
such as
publicity

or privacy rights.


We are always keen to help share knowledge about accessibility and assistive
technology
.

If you have any questions about how you may use the contents of this
Factsheet please contact us at AbilityNet and we will d
o all we can to help.



Web:
www.abilitynet.org.uk
. Tel: 0800 269545. Email enquiries@abilitynet.org.uk

Updated April 2012

Page
14


AbilityNet

Adapting Technology. Changing Lives.

Our specialist services

help

disabled

people

to

use computers and the internet to
improve their lives, whether at work, at home or in education.

Accessibility Services

Our
expert consul
tants help make websites, intranets,
office documents and mobile
technologies

accessible to all
.

Assessment

Service
s

Our professional assessors identify
the
technologies and adaptations needed to

enable

people with disabilities to be more productive

at wor
k, at home and in education
.

IT Volunteers

Our network of ove
r 8,000 IT volunteers provide high quality specialist

IT
support to
charities and people with disabilities.

Information
and Advice
Services

AbilityNet has
is

a leading authority on accessibility
and assistive

technologies. Our

Factsheets and other
free
tools help people
use

IT to address their needs.


We
charge for our
services

to

businesses and others who can pay for our expertise
.
W
e use charitable income to
deliver

services
to

people who cannot

afford to pay
,
including disabled people and charities.


Visit
www.abilitynet.org.uk/donate


for information about how
you can

support
AbilityNet
’s charitable work
.


Telephone:

0800 269545

Email:


enquiries@abilitynet.org.uk


Web:


http://www.abilitynet.org.uk


AbilityNet

is a

Charity
, registered in England and Wales, registration number

1067673
,
and in S
cotland registration number SC039866.