Training
|
The process of collecting speech samples for the purpose
of tuning the recognition algorithm for better performance.
|
| There are two basic ways in which data is gathered for training.
One is referred to as "supervised" and the other
is "unsupervised". |
|
Supervised Training
Here the user is asked to say specific utterances and the
samples are stored with reference to this identity.
|
Example for Speech Verification
- When a speaker attempts to verify himself with this
system, his incoming signal is compared to that of
a "key".
- This key should be a signal that produces a high
correlation for both magnitude and pitch data when
the authorized user utters the password, but not in
cases where:
- the user says the wrong word (the password
is forgotten)
- an intruder says either the password or a wrong
word
- To develop such a key, the system is trained
for recognition of the speaker. In this instance,
the speaker first chooses a password, and it is acquired
five separate times. The pitch and magnitude information
are recorded for each. The signal that matches the
other four signals best in both cases is chosen as
the key.
|
|
|
Unsupervised Training
Here the user is asked to speek but, not given a predefined,
known text reference to say. This kind of training is more
challenging to use.
|
|