The amadaptadddata
module and its parameters are deprecated in IDOL Speech Server version 11.5 and later. HPE 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.
Whether to use standard acoustic adaptation or rapid adaptation mode. The default value (0
) specifies standard acoustic adaptation mode. Where less adaptation data is available, setting a value of 10000000
enables rapid adaptation mode. Use the rapid adaptation mode in conjunction with a single accumulator file. The standard mode can combine multiple accumulator files.
Currently, you can specify only the values 0
or 10000000
. The use of fixed values rather than a simple Boolean allows the possibility of a future extension to automatically decide whether to use rapid or full adaptation modes.
Type: | Integer |
Default: | 0 (rapid adaptation mode is disabled) |
Range | 0 or 10000000 |
Required: | No |
Configuration Section: | amadaptadddata module |
Example: | MLLRMaxMins=10000000
|
See Also: | MLLRMaxMins (action parameter) MLLRMinOcc Relevance |
|