Quick Start - Instant Reporter Speech Recognition R10, Using M

Quick Start - Instant Reporter Speech Recognition R10, Using M
Quick Start: Instant Reporter Speech
Recognition, Using M*Modal
TCP-000568-A
®
Release 10
 For reading physicians using M*Modal Fluency Direct speech recognition with Instant
Reporter
Contents
About Speech Recognition ............................................................................ 1
The Dictation Workflow with Speech Recognition.......................................... 1
Exploring Dictation Components .................................................................... 2
Using Speech Recognition............................................................................. 4
Speech Recognition Commands ................................................................... 7
Keyboard Shortcuts ....................................................................................... 9
Managing Speech Recognition Vocabulary ................................................. 10
Additional Speech Recognition Management Tasks.................................... 19
Updating Speech Recognition Audio Files ................................................... 21
Getting Help and Information ....................................................................... 21
About Speech Recognition
Instant Reporter is a complete, integrated clinical reporting solution including dictation, transcription, reviewing, approving,
printing, faxing, storage, and Web distribution. Instant Reporter expedites reporting, provides clear documentation of critical
results, and saves costs.
The Dictation Workflow with Speech Recognition
Set up your system to recognize your speech and convert it to the intended text. After the system recognizes your speech, you
are ready to dictate reports. Speech recognition inserts text in the report from your dictation. For details on set up, see the
Instant Reporter Quick Start: Setting up M*Modal Fluency Direct Speech Recognition.
Copyright © 2014
DR Systems, Inc.
Quick Start: Instant Reporter Speech Recognition, Using M*Modal
Document ID: TCP-000568-A
Page 1 of 21
Exploring Dictation Components
Dictation dialog box components
Display exam
properties
Body
Breast coding
Click to switch to
speech recognition
Conclusion
Dictate body or
conclusion
Length
(min:sec)
File size
(KB)
Dictate
Mode of
operation
Position in
recording
Status after
you save
Delete selected
body or
conclusion
Voice and
text report
Insert or
Overwrite
Audio
Text report
only
playback
controls
Play
automatically
after rewind
Expand or
contract
dialog box
Microphone
volume
Open the
template
Revert to template
Change application
mode manually
Change role or
speech user
Opens Keyboard controls if a
microphone or foot pedal
controller gets disconnected
Clinical report components
Automatically adding information to clinical reports
DR Systems provides a set of clinical report templates
that can be customized.
These templates can be designed to automatically
import information from database into the report. For
example, inserting patients’ mammography histories.
Combine clinical reports
Reading physicians can create a single clinical report
for multiple related exams to improve accuracy and
completeness of the reports and increase efficiency for
the reading physician.
For example, if the physician is reading a patient's
mammogram and a breast ultrasound, the physician
can create a single clinical report for both exams.
Copyright © 2014
DR Systems, Inc.
Quick Start: Instant Reporter Speech Recognition, Using M*Modal
Document ID: TCP-000568-A
Page 2 of 21
Hand-held dictation microphone components
The system supports the following microphones:
 Olympus Directrec® DR-1200
 Philips SpeechMike LFH3200
 Philips SpeechMike 5276
Olympus Directrec DR-1200
Microphone front
Microphone back
Microphone
Insert/Overwrite Hide or display report.
Insert/Overwrite LED
Volume increase
Record
Insert/Overwrite
Record LED
Volume decrease
Switch between body
and conclusion
Fast rewind
Next placeholder for
missing text:
<<?>> or <<default text>>
Left mouse button
Fast Forward
Right mouse button
Trackball
Fast Rewind Jump to the previous item in
a report and highlight the text.
Left mouse
button
Play / Stop Jump to the next text
placeholder: <<?>> or <<default text>>.
Fast Forward Jump to the next item in a
report and highlight the text.
Left mouse button Insert pointer.
Right mouse button Open shortcut
menu.
Programmable function
keys:
F1 Switch between
dictation for
transcription and
dictation for speech
recognition
F2 End of paragraph
and 2 spaces
F3 Delete Findings
content
F4 Not supported
Speaker
New Switch between body and
conclusion.
Record Dictate for speech recognition.
Trackball Move pointer.
Programmable function keys
F1 Switch between dictation for
transcription and dictation
for speech recognition.
F2 Jump to end of paragraph and add 2
spaces.
F3 Delete Findings content.
F4 Not supported.
Philips SpeechMike LFH3200
Microphone front
Microphone back
Record Dictate for speech recognition.
Microphone
Insert/Overwrite Hide or display report.
Record LED
Switch between body
and conclusion
Fast rewind
Next placeholder for
missing text:
<<?>> or
<<default text>>
Left mouse button
Speaker
Copyright © 2014
DR Systems, Inc.
EOL Switch between body and
conclusion.
Fast Rewind Jump to the previous item in
a report and highlight the text.
Play / Stop Jump to the next placeholder:
<<?>> or <<default text>>.
Insert/Overwrite
Record
Fast forward
Right mouse button
Trackball
Programmable
function keys:
F1 Switch between
dictation for
transcription and
dictation
for speech
recognition
F2 End of paragraph
and 2 spaces
F3 Delete Findings
content
Left
mouse
button
Fast Forward Jump to the next item in a
report and highlight the text.
Left mouse button Insert pointer.
Right mouse button Open shortcut
menu.
Trackball Move pointer.
Programmable function key
F1 Switch between dictation for
transcription and dictation
for speech recognition.
F2 Jump to the end of paragraph and add
2 spaces.
F3 Delete Findings content.
Quick Start: Instant Reporter Speech Recognition, Using M*Modal
Document ID: TCP-000568-A
Page 3 of 21
Clinical report status codes
Status
Description
Status
Description
ApD*
Approved and queued for automatic
update to ApD. For 30 seconds, physician
can update.
TrD
Transcribed
TrH
Transcription hold
ApD
Approved
TrP
Transcribing
ApP
Approving
ApPr
Approving by a resident
ApR
Approved by a resident
Note:
"P" at the end of the code = in process
"D" at the end of the code = done
AuD
Audited
AuP
Auditing
DiD
Dictated
DiH
Dictation on hold
DiP
Dictating
DiPr
Dictating by a resident
DiR
Dictated by resident
DiS
Dictated STAT
NoN
Stops completion of report
PrD
Purged dictation
PrP
Purging
TrB
Transcription break
Keyboard controls if microphone not
detected
If the primary microphone is not connected, shortcut keys
are available.
Using Speech Recognition
Dictating with speech recognition
1
Select an exam.
 Click the Worklist or Online tab.
 Open an exam to read it or select an exam and click Dictate
.
2
Change to speech recognition mode.
If the system displays the dictation button
, click it.
The button switches to M*Modal speech recognition
.
The system opens the standard report in Microsoft® Word®
appropriate for the exam type.
Tip: You can skip this step if you set up speech recognition as the
default dictation mode in your Reading Physician
Preferences.
Copyright © 2014
DR Systems, Inc.
Quick Start: Instant Reporter Speech Recognition, Using M*Modal
Document ID: TCP-000568-A
Page 4 of 21
3
Click the M*Modal speech recognition button.
4
Dictate the report.
 Press and hold the RECORD button on the hand-held dictating
microphone.
Tip: You can set a Reading Physician Preference to click
Record to start recording and click again to stop.
 Start dictating the report.
As the system recognizes your speech, it enters the words in
the report.
Features for efficient reporting workflow
Button or item
Action
Play button
Jumps to placeholders.
 For placeholders with default text <<default text>>, record to replace the placeholder or click Play to
accept the default text and remove the brackets.
 For <<?>>, record the placeholder replacement text.
Audio conclusion
Can be generated from dictated conclusion text.
FRW and FFW
buttons
Fast rewind and fast forward navigate the report and highlight section text.
Section headings
Can be played to avoid looking at the report while reading an exam to know where you are in the report.
EOL button
Selects the Conclusion section. If configured, numbers conclusions.
F1 button
Toggles between dictating for transcription and dictating for speech recognition.
F2 button
Moves the cursor to the end of the paragraph.
F3 button
Deletes text in the Findings section in preparation for revised findings.
Best practices using speech recognition
If the speech recognition program makes an error:



DO NOT: Yell, talk slowly, or say only one word at a time.
DO: Say full sentences and speak in your natural voice.
DO: Correct errors as they occur. This helps avoid the same recognition mistakes in the future. Replace an entire
phrase rather than a small word. For example, replace the article a with the. Instead of saying, “a brain” say “the
brain.”
Common mistakes
Common mistakes many users make include speaking:



Before the Record button is on. If the first few words in your dictation are created incorrectly, you may be
speaking before pressing the Record button. To avoid this mistake, press the Record button, wait ½ second
before dictating.
Too loudly. Use a calm, regular tone of voice when speaking.
Too slowly or only a very small amount of content. For the best results, speak continuously, like a
newscaster.
Copyright © 2014
DR Systems, Inc.
Quick Start: Instant Reporter Speech Recognition, Using M*Modal
Document ID: TCP-000568-A
Page 5 of 21
Correcting mistakes in text
1
Correct text:
 Say “Select <words>” and the text you want to correct.
Or
Select the text you want to correct.
 Say “Correct selection.”
The system displays the Correction dialog and suggests possible
corrections.
Tip: You can also say “Select <words>,” or a section of the report,
such as “Findings.” The system replaces the existing text with
dictated text.
2
Select the correct choice:
3
Select the category of the corrected text: Name, Location, or
Medication.
 Click the correct choice using the mouse.
Dictating numbers
Tips if numbers present a problem:
 To include a comma in a four-digit number, speak it explicitly. Numbers with five or more digits automatically include commas.
 Use "oh" and "zero" interchangeably to get 0.
 Use or omit the word "and" as part of a number. For example, say "one hundred fifty" instead of "one hundred and fifty" to get the number
150.
 To include AND. The speech recognition system automatically deletes the word "and" in many numbers. If you want to type two dates, use
an ampersand. Say "ampersand" to enter "&."
Common number commands
To enter
Say
To enter
Say
1
One
142,015
One hundred and forty two thousand and fifteen
5
Five
35.23
Thirty five [point] two three
17
Seventeen
0.03
Zero [point] zero three
23
Twenty three
43.28%
Forty three [point] twenty eight [percent sign]
179
One hundred seventy nine
02460
Oh two four six zero
5423
Five thousand four hundred and twenty three
2 3/4
Two and three fourths
5,423
Five [comma] four twenty three
11/32
Eleven over thirty two
12,537
Twelve thousand five hundred and thirty seven
$99.50
Ninety nine dollars and fifty cents
Copyright © 2014
DR Systems, Inc.
Quick Start: Instant Reporter Speech Recognition, Using M*Modal
Document ID: TCP-000568-A
Page 6 of 21
Important Microsoft Word® tips
When Microsoft Word blocks your view of exam images
You can't view exam images if the Word window is maximized or if Word is set to always display on top of other windows.
If the Word window is maximized
1
Double-click the title bar at the top of the Microsoft Word window.
This restores the window to the size prior to maximizing.
2
To further reduce the size of the Word window:
 Click the bottom-right corner of the window.
 Drag the corner up and to the left.
Placement of Word on top of images
Single monitor systems - do not place Word on top
If you are using a single-monitor, you need to set up Microsoft Word so it doesn't block viewing of images.
1
In the Transcription dialog box, click More to display the complete
dialog box.
2
Clear the MS Word on Top checkbox.
Multiple monitor systems - OK to place Word on top
In multiple monitor systems, you do not need to change the default setting of Word on top.
You can leave the default setting unchanged:
•
Leave the MS Word on Top checkbox selected.
Speech Recognition Commands
The microphone is your primary tool for entering speech commands.
M*Modal speech commands
Say
To take this action
Say
To take this action
Boldface that
Bold selected text in the report.
Move pointer to the end of the current line.
Cap that
Capitalize the first letter of the selected word.
Go to end of
line
Caps on
Capitalize dictated text.
Go to top
Move pointer to the start of the report.
Caps off
Sentence capitalization for dictated text in
Microsoft Word document
Insert tab
Insert a tab.
Lowercase that
Lowercase selected text.
Copy that
Copy selected text to the Microsoft Windows®
clipboard.
Macro that
Save selected text as a custom speech
command.
Correct
selection
Select the word and open the replacement
editor.
New line
Insert a blank line at the pointer position.
Cut that
Copy selected text to the Windows clipboard
and delete it from the report.
New paragraph
Insert 1 or 2 blank lines at the pointer position.
Number of blank lines is configurable.
Delete that
Delete selected text.
Paste that
Insert text used in Copy or Cut speech
commands.
Go to beginning
of line
Move pointer to the beginning of the current
line.
Go to bottom
Move pointer to the end of the report.
Copyright © 2014
DR Systems, Inc.
Quick Start: Instant Reporter Speech Recognition, Using M*Modal
Document ID: TCP-000568-A
Page 7 of 21
Say
To take this action
Say
To take this action
Replace
Select a paragraph heading and say “replace”
to delete the text after the heading.
Show user
vocabulary
Opens the Dictionary.
This command deletes the text after the
selected heading and places the pointer to the
right of the heading.
Space bar
Insert a single space at the pointer.
Undo that
Undo the last action. Equivalent to the
keyboard shortcut: Ctrl+Z.
Uppercase that
Capitalize selected text.
Select [word or
phrase]
Select a specific word or phrase to replace,
correct, or format.
Show
command
browser
Opens the Command browser.
Tip:
Access the M*Modal list of commands from the Dictation dialog box:
1. Click More.
2. Click SpR Management.
3. Click List commands.
Note: You must use voice commands to copy, cut, and paste. During speech recognition, the following keyboard shortcuts are
not available: Ctrl+C, Ctrl+X, and Ctrl+V.
Punctuation and special characters
Say
To enter
Close quote
"
Open parenthesis
(
Close parenthesis
)
Say
To enter
Percent sign
%
Period
.
Comma
,
Getting help with sample commands
Question mark
?
Colon
:
Say
To
What can I say?
Semicolon
;
Display a brief list of available
commands.
Open quote
"
Dominator speech commands
The following speech commands for reading images are also listed in the Dictation dialog box > More > SpR Management >
Command list and from the Help menu > Dominator Speech Commands. Keyboard shortcuts can be used with a standard
keyboards or programmable gaming mice with on-board memory.
Say
Action
Keyboard
shortcut
Say
Action
Keyboard
shortcut
Dom [1, 2, 3, 4,
5, 6, 7, 8, or 9]
Opens number of images.
1, 2, 3, 4, 5,
6, 7, 8, 9
Dom Compare
Switches to exam compare
mode.
D
Dom [F2, F3, F4,
F5, F6, F7, or
F8]
Runs function. F2-F8 are
customizable.
F2, F3, F4,
F5, F6, F7,
F8
Dom Copy
Findings
Copies findings content for
another report.
Dom All mode
Switches to All Mode.
Applies image edits to all
images in a series.
. [period]
Dom Done
Marks exam read. Returns
to worklist. Same as Done
button.
Dom
Annotations
Displays or hides system
annotations.
A
Dome End
Displays last image. Exact
function depends on display
mode.
End
Dom Blank
Deletes clinical report
contents between Findings
and Conclusion. Places the
pointer for adding Findings.
Ctrl+Shift+9
Dom Exam
Displays series-per-monitor.
C
Dom CAD
Displays and hides CAD
marks.
K
Dom Cine All
Runs cine on all images.
{
Dom Cine None
Stops cine on all images.
}
Dom Clear
Closes comparison exams.
Copyright © 2014
DR Systems, Inc.
Mammo: exam-per-monitor.
Dom Format to
fit
Changes format of current
exam:
/ [slash]
 Shows all series.
 Shows all images.
Quick Start: Instant Reporter Speech Recognition, Using M*Modal
Document ID: TCP-000568-A.
Unity Release 10 is available for Pre-production evaluation only.
Page 8 of 21
Say
Action
Keyboard
shortcut
Say
Action
Keyboard
shortcut
Dom Go
Marks exam read, saves
report edits, goes to next
exam in the worklist without
saving image edits.
Bypasses warning dialogs
about incomplete image
viewing and saving edits.
Ctrl+Shift+?
Dom Shrink
Switches between Shrink
On and Shrink Off.
S
Dom Shuffle
In mammography only:
Display all loaded exams in
shuffle mode.
V
Dom Help
Displays Help.
F1
Dom Home
Displays first image. Exact
function depends on display
mode.
Home
Dom Image
Switches to image-persquare mode.
X
Dom Insets
Displays or hides Cross-ref
scout.
I (letter i)
Dom Montage
Displays or hides the
montage.
M
Dom Next
Marks exam read, closes
the current exam, and
opens the montage for the
next exam.
Ctrl+Shift+:
Dom Number
Conclusion
Removes the warning
statement in the Conclusion
section of a clinical report
and creates a numbered list
for new conclusion items.
Ctrl+Shift+C
Dom Page Down
Goes to the next image in
the exam. In Series-per
Square mode, scrolls
through the next series
square assignments.
Page Down
Goes to the previous image
in the exam. In Series-per
Square mode, scrolls
through the previous series
square assignments.
Page Up
Dom Play
Plays a prerecorded audio
conclusion.
P
Dom Report
Display primary or
comparison exam report,
depending on the cursor
selection.
F9
Dom Req
Displays or hides the
Electronic Requisition.
Spacebar
Dom Save Go
Marks exam read, saves
image edits, and opens the
next exam on the worklist.
Bypasses warning dialogs
about incomplete image
viewing and saving edits.
Ctrl+Shift+~
Dom Series
Switches to Series-persquare mode.
Z
Dom Series edit
Displays or hides the Edit
Series dialog box.
F12
Dom Series
select
Displays or hides the Series
Selection dialog box to
select another series in the
exam.
F11
Dom Page Up
Copyright © 2014
DR Systems, Inc.
In Ultrasound Stress
Echocardiogram only:
Stress Images by View.
Dom Tools
Displays the toolbox.
T
Keyboard Shortcuts
From the Help menu, click Keyboard Shortcuts.
Function keys
F1
Display Online Help.
F9
Display primary or comparison exam
report.
F10
Copy case or single image to removable
media.
F11
Select another series in the exam.
F12
Display the Edit Series dialog box.
Arrow keys specific to clinical reporting
Ctrl+Alt+↑
or
Wind+Alt+↑
Increase the volume.
Ctrl+Alt+↓
or
Wind+Alt+↓
Decrease the volume
Ctrl+Alt+→
or
Wind+Alt+→
Increase the recall interval.
Ctrl+Alt+←
or
Wind+Alt+←
Decrease the recall interval.
Note: See the Dominator Diagnostic Reading Workstation
Quick Start for alpha-key keyboard shortcuts.
Quick Start: Instant Reporter Speech Recognition, Using M*Modal Release 10
Document ID: TCP-000568-A
Unity Release 10 is available for Pre-production evaluation only.
Page 9 of 21
Alpha keys specific to clinical reporting
Tip: Physicians can quickly approve reports using a few of the
following keyboard shortcuts.
Backspace
In mammography only:
Switch from one comparison exam to the
next.
Ctrl+Alt+C
or
Wind+Alt+C
Switch display of body or conclusion.
Ctrl+Alt+X
or
Wind+Alt+X
Show or hide the text
Ctrl+Alt+S
or
Wind+Alt+S
Slow the audio speed.
Ctrl+Alt+F
or
Wind+Alt+F
Increase the audio speed.
Ctrl+Alt+D
or
Wind+Alt+D
Reset the audio speed to Direct one.
Ctrl+Shift+9
Clear text in the Findings section and
place the pointer for adding Findings.
Ctrl+Shift+?
Marks exam read, save report edits, go to
next exam without saving image edits.
Ctrl+Shift+:
Close the current exam and open the
montage for the next exam.
Ctrl+Shift+C
Convert conclusions to a numbered list.
Ctrl+Shift+~
Mark exam read, save image edits, and
open the next exam.
Other function keys
End
Display last image.
Esc
Close exam and return to the last
displayed list window. Same as Done.
Home
Display first image.
Pg Dn
Go to the next image in the exam.
In Series-per Square mode, scroll through
the next series square assignments.
Alt+Pg Dn
Go to the next series.
Ctrl+Pg Dn
Automatically scroll the images. Requires
that looping (L) is on.
PgUp
Go to the previous image in the exam. In
Series-per Square mode, scroll through
the previous series square assignments.
Alt+PgUp
Go to the previous series.
Managing Speech Recognition Vocabulary
Manage speech recognition users, vocabulary, report formats, and training from the Speech Recognition User Management
dialog box.
Accessing the Speech Recognition User Management dialog box
1
Open the Dictation dialog box.
 From the Worklist tab or Online tab, select an exam and
click the Dictate button
2
.
Select M*Modal.
 If the M*Modal button
Dictation button
3
Copyright © 2014
DR Systems, Inc.
is not displayed, click the
.
Expand the Dictation dialog box.
 Click More.
Quick Start: Instant Reporter Speech Recognition, Using M*Modal Release 10
Document ID: TCP-000568-A
Unity Release 10 is available for Pre-production evaluation only.
Page 10 of 21
A
B
C
G
D
H
E
I
F
J
K
Copyright © 2014
DR Systems, Inc.
4
Open speech recognition.
5
Select the Speech Recognition User Management
option:
 Click SpR Management.
Options
Description
A
Audio setup
complete?
System checks if the user profile audio
setup is complete.
B
User
trained?
System checks if the user profile
completed training by speaking for about
5 minutes.
C
Check your
audio
settings
Adjust the sound quality. Opens
Microphone Settings to Choose a
microphone. See the Instant Reporter
Quick Start: Setting up M*Modal Fluency
Direct Speech Recognition.
D
Perform
additional
training
Train the system to recognize your voice.
Opens Profile Training dialog box: Train
your profile with your voice. See Instant
Reporter Quick Start: Setting up M*Modal
Fluency Direct Speech Recognition.
E
Commands
Opens Commands dialog box to create
personal speech recognition commands.
See Managing your speech recognition
vocabularyon page 12.
F
Options
Formats reports generated from speech
recognition. See Specify report
component format options on page 19.
G
List
commands
Lists the M*Modal Fluency Direct
commands and Dominator speech
recognition commands. See Dominator
speech commands on page 8.
H
Manage
user
vocabulary
Manage your personal vocabulary. See
page 12. Or say "Show user vocabulary."
I
Manage
site
vocabulary
Manage the site-wide vocabulary for all
users. See Managing the site vocabulary
on page 17. Or say, “Show site
vocabulary.”
J
Speech
domain
Select a vocabulary domain for
specialists: Cardiology. General
Medicine, Radiology. See Select the
speech recognition domain on page 20.
K
Text To
Speech
Select properties of Text-to-speech
including voice, speed, and audio output.
See Select text-to-speech format options
on page 20.
Quick Start: Instant Reporter Speech Recognition, Using M*Modal Release 10
Document ID: TCP-000568-A
Unity Release 10 is available for Pre-production evaluation only.
Page 11 of 21
Managing your speech recognition vocabulary
Speech recognition uses a library of your spoken vocabulary from the Dictionary.
1
Open the Dictionary.
 Say “Show user vocabulary."
OR
 Access the Speech Recognition User Management dialog
box and click Manage user vocabulary.
Modifications to the Dictionary only affect your profile. They
do not change the site vocabulary or any other user profile.
Adding words to your vocabulary
1
In the Dictionary:
 Click the Add/Train.
The Vocabulary Editor opens.
2
In the Vocabulary Editor:
 Type the vocabulary word and click Record Pronunciation.
 Say the typed word.
 Select the category.
The system requires a category to organize your
vocabulary. For example, type “oxygen,” record your
pronunciation of oxygen, and select Other for the category.
Note: You can enter only a single word for the category
Other. A Name, Location, or Medication can be a
phrase.
 Click Save.
3
Copyright © 2014
DR Systems, Inc.
The system adds the new word to the list.
Quick Start: Instant Reporter Speech Recognition, Using M*Modal Release 10
Document ID: TCP-000568-A
Unity Release 10 is available for Pre-production evaluation only.
Page 12 of 21
Training words
Train as many words as you can to allow M*Modal Fluency Direct to interpret correctly the words you dictate, and enter the
appropriate text in reports.
1
In the Dictionary:
 Select the word to train.
 Click Add/Train.
2
In the Vocabulary Editor:
 Type the vocabulary word and click Record Pronunciation.
 Say the typed word.
 Select the category: Name, Location, Medication, or Other.
 Click Save.
Searching for vocabulary words
You can search for a specific word in the Dictionary.
1
In the Dictionary:
2
The Dictionary displays only words matching your search
criteria.
 Type the word in the Search text box.
Creating replacement text
Replacement text displays a list of alternative content to select from.
Copyright © 2014
DR Systems, Inc.
1
In the Dictionary:
2
 Click Add/Train.
 Click Replacement rules.
Quick Start: Instant Reporter Speech Recognition, Using M*Modal Release 10
Document ID: TCP-000568-A
Unity Release 10 is available for Pre-production evaluation only.
Page 13 of 21
3
In the Replacement Editor:
 Type the Original word, for example, there.
 Type the Replacement with word, for example, their.
 Click Save.
The system lists the replacement text and displays the
replacement when suggesting corrections.
Managing incorrect vocabulary
If the system repeatedly replaces your spoken word with an incorrect word, exclude the incorrect word from the vocabulary.
For example, if you say “facet” and M*Modal Fluency Direct enters “cassette,” exclude the word “cassette.” Or, if you say
“Pierre” and M*Modal enters “period,” exclude the word “period.”
1
In the Dictionary:
Click Excluded words.
2
 Click Add/Train.
 Type the word in the Written as field.
 Click Save.
The system excludes the word from the M*Modal vocabulary
and adds the excluded word to the Excluded Words list.
This action only excludes the word from your user
vocabulary. The site vocabulary and other user profiles
are not affected.
Copyright © 2014
DR Systems, Inc.
Quick Start: Instant Reporter Speech Recognition, Using M*Modal Release 10
Document ID: TCP-000568-A
Unity Release 10 is available for Pre-production evaluation only.
Page 14 of 21
Managing personal commands
Create your own shortcuts to maximize your reporting efficiency. You can create macros to enter text, replace text, specify key
strokes to represent text, and advanced scripting.
1
Open the Command browser:
2
From the Command browser:
3
 Select Add Group.
4
 Type the name of the Group.
 Say “Show command browser.”
OR
 Click Commands from the Speech Recognition User
Management dialog box.
 Click Add.
M*Modal Fluency Direct uses the Group name to organize
your vocabulary of macros.
 Click Apply to save your entry and continue working.
Copyright © 2014
DR Systems, Inc.
Quick Start: Instant Reporter Speech Recognition, Using M*Modal Release 10
Document ID: TCP-000568-A
Unity Release 10 is available for Pre-production evaluation only.
Page 15 of 21
Option to specify application using the macro:
Dominator uses Microsoft Word. If your site uses other
applications, such as Microsoft Excel, you can specify that a
macro is available only from the other application.
5
Add commands:
 Select the Group name you added.
 Click Add and Add Command.
6
 Type the command name.
7
 Continue adding Groups and Commands.
8
Apply commands:
 When finished, click OK.
 Place the pointer in a report where you want to enter the
text for a command.
 Say the command name.
The system inserts the text.
Copyright © 2014
DR Systems, Inc.
Quick Start: Instant Reporter Speech Recognition, Using M*Modal Release 10
Document ID: TCP-000568-A
Unity Release 10 is available for Pre-production evaluation only.
Page 16 of 21
Creating personal macros
Use personal macros to convert text to a command shortcut.
1
In the report:
 Select the text.
 Say “Macro that.”
2
Add the macro to the Dictionary:
 Use an existing group.
Select the group name from the list.
Or
 Create a new group.
Type the group name.
 Type the Command Name.
3
Apply commands:
 Place the pointer in a report where you want to enter the
text for a command.
 Say the command name.
The system inserts the text.
Managing the site vocabulary
All sites should assign a physician site leader who manages the Site Vocabulary regularly. The site leader should review the
default words, add necessary words, and delete words that are not used.
Accessing the site vocabulary
1
Open the Dictionary:
 Access the Speech Recognition User Management dialog
box.
 Click Manage site vocabulary.
Modifications to the site vocabulary affect all profiles.
Copyright © 2014
DR Systems, Inc.
Quick Start: Instant Reporter Speech Recognition, Using M*Modal Release 10
Document ID: TCP-000568-A
Unity Release 10 is available for Pre-production evaluation only.
Page 17 of 21
The Site Vocabulary Editor opens.
Using spoken vs. written form
Using the M*Modal Fluency Direct spoken vs. written form is necessary if your site has a different spoken form of a word than
the written word or phrase. For example, to have the text Fig: entered in your report when you are labeling figures, use a
different spoken form of the word than the written.
1
In the Site Vocabulary Editor:
2
 Type Figure under Spoken form.
3
 Click Add.
The new phrase is entered in the vocabulary as a different
spoken form vs. written form.
 Type Fig: under Written form.
 Click Save.
 In the Speech Recognition User Management dialog box,
click Manage user vocabulary.
4
 With the phrase selected, click Add/Train.
5
 Type the spoken word.
 Click Record Pronunciation.
 Record the word.
 Select the category.
 Click Save.
6
Copyright © 2014
DR Systems, Inc.
 Click Done when you are finished.
The phrase is now trained and ready to use.
Quick Start: Instant Reporter Speech Recognition, Using M*Modal Release 10
Document ID: TCP-000568-A
Unity Release 10 is available for Pre-production evaluation only.
Page 18 of 21
Deleting words from the site vocabulary
Deleting a word clears it from the site vocabulary and from all user vocabularies.
1
 Select the word to delete.
2
 Click Delete.
Additional Speech Recognition Management Tasks
Check your audio settings
1
Click Check your audio settings
from the Speech Recognition User
Management dialog box.
2
The Microphone Settings dialog box
opens. For details see the Instant
Reporter Quick Start: Setting up
M*Modal Fluency Direct Speech
Recognition.
1
Click Perform additional training
from the Speech Recognition User
Management dialog box.
2
Train your profile with your voice
opens. For details, see the Instant
Reporter Quick Start: Setting up
M*Modal Fluency Direct Speech
Recognition.
1
Select Options from the Speech
Recognition User Management dialog
box.
2
Select the report component, open the
menu, and select the preferred format.
Perform additional training
Specify report component format options
Copyright © 2014
DR Systems, Inc.
Quick Start: Instant Reporter Speech Recognition, Using M*Modal Release 10
Document ID: TCP-000568-A
Unity Release 10 is available for Pre-production evaluation only.
Page 19 of 21
Select the speech recognition domain
Specify your speech recognition domain to filter your vocabulary list and address differences in vocabulary by specialty.
1
Select Speech domain from the
Speech Recognition User
Management dialog box.
1
Select Text to speech from the
Speech Recognition User
Management dialog box.
2
 Select the Text-to-speech each line
item check box.
Select text-to-speech format options
Specify how you want the results of converting text to speech formatted.
 Select the applicable text-to-speech
options.
Copyright © 2014
DR Systems, Inc.
Quick Start: Instant Reporter Speech Recognition, Using M*Modal Release 10
Document ID: TCP-000568-A
Unity Release 10 is available for Pre-production evaluation only.
Page 20 of 21
Updating Speech Recognition Audio Files
If a reading physician dictates a report, saves the audio file in the Approved state (ApD), and later changes the report with an
Addendum, Correction, or Revision, the system:


Deletes the previous audio file.
Saves newly dictated audio as a new file.
Getting Help and Information
Displaying Online Help
Accessing the Resource Center
Display a comprehensive Help program:
View and download white papers, user guides, TechNotes, technical
specifications and other documents:
• Press F1 or click Help Topics from the Help menu.
• Go to www.drsys.com and click the Resource Center
button.
Contacting DR Systems
Copyright and Notice
10140 Mesa Rim Road
San Diego, CA 92121
http://www.drsys.com
Copyright © 1997-2014 DR Systems, Inc. and its licensors. All rights
reserved.
Phone:
Protected by U.S. Patents: http://www.drsys.com/legal/
1-800-794-5955
Fax:
1-858-625-3337
E-mail:
Sales
Info
Support
Sales@drsys.com
Info@drsys.com
drsupport@drsys.com
Customer Support Online
• Go to www.drsys.com and click Customer Support
Login.
Template: TCP-000180-H
Copyright © 2014
DR Systems, Inc.
Quick Start: Instant Reporter Speech Recognition, Using M*Modal Release 10
Document ID: TCP-000568-A
Unity Release 10 is available for Pre-production evaluation only.
Page 21 of 21
Was this manual useful for you? yes no
Thank you for your participation!

* Your assessment is very important for improving the work of artificial intelligence, which forms the content of this project

Download PDF

advertising