The amadaptadddata
module and its parameters are deprecated in IDOL Speech Server version 11.5 and later. Micro Focus recommends that you use the newer Deep Neural Network (DNN) techniques, rather than GMM-based acoustic models.
This module is still available for existing implementations, but it might be incompatible with new functionality. The module might be deleted in future.
Specify the treatment of words in the adaptation data that have zero duration (they occur in the transcript but are not recognized in the audio). Set either:
keep
|
Include the words in the acoustic adaptation process. Choose this option if the transcript is very trustworthy and the zero-duration words are likely to be caused by errors in the initial alignment. |
junk
|
Label the words as junk. The adaptation process uses the location of junk words in the data but ignores the words themselves. Choose this option if the transcript might contain errors. |
Type: | String |
Default: | Keep |
Required: | No |
Configuration Section: | amadaptadddata module |
Example: | ZeroDurationWords=junk
|
See Also: | ZeroDurWords (action parameter) JunkEnabled |
|