Speech Recognition: An Accommodation Planning Perspective
Alan
Cantor
Abstract
Although not yet a mature technology, speech recognition has
great potential as a partial (or total) replacement for the keyboard and mouse.
Nevertheless, many students who switch to speech input use it inefficiently,
give up on it altogether, and may even develop permanent vocal injuries. Speech
recognition failures are attributable, in part, to inadequate accommodation
planning and unrealistic expectations. This session describes an 11-stage
planning model that increases the likelihood that students will benefit from
speech recognition; and reviews common misconceptions that prevent students
from achieving success with the technology.
Part 1: Accommodating speech recognition
To highlight the concerns that should be considered when
planning an accommodation that includes speech recognition, I present an eleven
stage planning model:
1. Assessment
Assess the student’s needs
Consider a wide range of accommodation options. Few people
can be fully accommodated with one or two items; some need ten, twenty or more
adaptations. Generate specific accommodation ideas from these fourteen
categories:
¨ Building modifications ¨ Low-tech
devices
¨ Environmental adjustments ¨ Alternative formats to print
¨ Spatial reorganization ¨ Transportation
services
¨ Work station modifications ¨ Personal support services
¨ Computer-based assistive technologies ¨ Human
resource strategies
¨ Software customization ¨ Employment/educational
policy changes
¨ Electromechanical devices ¨ Training and retraining
Key assessment questions include:
· Is
the technology appropriate to the student’s age and level of development? Is it
realistic for the tasks that he or she hopes to accomplish? Is voice input really necessary? Would macro software,
abbreviation expansion software, MouseKeys, or training in keyboard-only
techniques be more effective than or a worthwhile adjunct to speech
recognition?
· Individuals
whose primary access means is the voice should be evaluated by a Speech
Language Pathologist, and receive voice training.
2. Software requirements
Choose a speech recognition product
· Does
the software have commands for revising documents by voice? For
students who write essays and other complex documents, the ability to revise
may be more important than speed and compatibility.
3. Hardware requirements
Choose the right hardware
· For
individuals who use voice input as a primary access technique, double or
quadruple the minimum RAM requirement. A fast CPU is helpful. Soundcard and
microphone quality are of paramount importance.
· Note:
microphone quality varies from unit to unit!
4. Work station set-up
Reorganize or replace work station components to ensure that the student
can work safely and comfortably while operating a PC by voice
· For
example, position the monitor so that the student is not forced to crane the
neck or bend forward to read the screen.
5. PC set-up
Optimize the PC for speech recognition
· Uninstall
superfluous software. Free system resources (e.g., in Windows 98 and ME, use
MSCONFIG to disable non-essential start-up group items.)
6. Enrollment
Create and initiate user voice files
· Run
the “Audio Setup Wizard,” coach on proper microphone placement, coach on
dictation techniques, and conduct initial training. Once completed, the student
can begin experimenting with dictation.
7. Vocabulary Builder
Run the “Vocabulary Builder”
· Tweak
the voice files to match the student’s vocabulary and writing style. (1) Create
vocabulary files containing lists of the student’s unique words, names and
expressions. Hint: base the list on custom dictionary files. (2) Assemble files
containing samples of the student’s writing. Run the “Vocabulary Builder” on
both sets of files.
8. Initial use
Practise dictating text and correcting misrecognitions
· Focus
on learning basic dictation techniques and improving voice file accuracy.
Resist the temptation to produce perfectly formatted, error-free documents.
Staying relaxed, cultivating healthy work habits, speaking clearly and fixing
misrecognitions are the best ways to gain precision, competence, and comfort
with speech input.
· Good
vocal hygiene includes performing “warm-up” and “cool-down” exercises, drinking
fluids, limiting total time on a voice input system, and taking regular breaks.
9. Intermediate use
Once dictating text and correcting misrecognitions is second-nature, begin
dictating for “real”
· The
voice files will already be quite accurate and will not improve significantly
by correcting common words. Focus on learning to revise documents.
10. “Expert” use
Once proficient with the program, increase speed and efficiency
· Experiment.
Tune the voice files by rerunning “Audio Wizard;” dictating for one or two
minutes in “General Training;” removing nuisance words from the lexicon; and
updating word-usage and style data by running the “Vocabulary Building” with
newly-created files.
11. Follow-up
After implementation, regular follow-up sessions helps to ensure that the
student is using speech recognition properly
· Follow-up
after two weeks, one month, and three months. Difficulties noted during
follow-up can usually be traced to skipping or not completing an earlier stage.
Part 2: Principles of working by voice
Many individuals become disillusioned when faced with the reality
of voice recognition. Others become competent at dictating simple texts (Stage
8 or 9), but cannot use features that would enable them to work more
effectively. When accommodating a student with speech recognition, it may be
necessary to emphasize the following principles:
1. Accept the limitations of voice recognition technology
Once good accuracy is achieved, do not try to perfect voice
files. They will never be perfect.
2. Recognize that written and spoken language differ
Learning to think and speak in grammatically-correct
sentences and paragraphs takes discipline and effort. Some people cannot do it.
3. Use the program’s proprietary editor if the dictation software works
best in it
Copying text into one’s usual word processor after a
dictation session is easy.
4. Understand the differences between correcting misrecognitions and
revising text
To use speech recognition effectively, one must be able to
do both.
5. Do not correct misrecognized words that are usually interpreted
correctly
It is faster to undo, select an entire utterance and dictate
it again, or use “Resume With...”
6. Navigate intelligently
Use “Insert Before...” and “Insert After...” instead of
“Move” commands. Specifying two or more target words can increase precision,
e.g., “Insert After can increase
precision,” “Insert Before accept the
limitations.”
7. Revise intelligently
Revise using “Select” instead of “Backspace...” and
“Delete...” commands. Select the text and dictate; it is not necessary to
explicitly delete selected text. Use “Select xxx Through yyy” to mark
larger selections.
8. Revise phrases rather than individual words
Revise phrases even if some words within a phrase are
correct.
Conclusion
Speech recognition has tremendous — but as yet unfulfilled —
potential as an educational accommodation for students with a range of
disabilities, including upper-body mobility impairments, computer-induced
repetitive strain injuries, and certain learning disabilities. Two strategies
to help people realize the promise of the technology: (1) Be methodical and
thorough in planning and implementing the accommodation so that individuals are
well-prepared to operate a PC by voice; and (2) clearly understand how current
voice input technologies do (and do not) work.
CANTOR