Sony ICD-UX71F - Manual (Page 77)

ICD-UX71/UX81/UX71F/UX81F 4-114-023-11(1)

GB
U
tili
zin
g Y
ou
r Co
m
pu
te
r
Creating a user file adapted
to your recorded speech
(Training)
What is “Training”?
Before you can transcribe
recorded messages using Dragon
NaturallySpeaking, you must create a
user file specifically adapted to the sound
of your recorded speech. This procedure
is called “training.”
When training is complete, Dragon
NaturallySpeaking creates a user speech
file containing information about your
recorded speech.
Refer to the operating instructions
or the help supplied with Dragon
NaturallySpeaking, as some parts of
training are the same as those required
for dictating directly to the computer
using a headset microphone.
Even if you have already created a user
speech file with a headset microphone,
you should create a separate speech
file for the IC recorder to get better
recognition accuracy.


Tips on using the IC recorder
When transcribing messages recorded
using the IC recorder, the following
tips will help you obtain maximum
recognition accuracy.
Set “REC MODE” to “ST,” “STSP,”
“STLP” or “SP” in the menu.
When creating a user speech file
(training), set “REC MODE” to the mode
you normally use for voice recognition
software.
Set “MIC SENSITIVITY” to “LOW (L)”
in the menu.
Hold the IC recorder firmly and
start recording.
Hold the IC recorder so that the
microphone is about an inch (2 - 3 cm)
from the corner of your mouth, not
directly in front of it. This minimizes the
sound of your breath in the recordings,
enabling maximum recognition
accuracy.
Note
Avoid recording in a noisy place, such as on a
subway platform, in order to obtain maximum
recognition accuracy.



