You can use the language identification feature files to create a language classifier file.
To create a language classifier
Create a list that contains the names of all feature files. Include the file extensions but not the file paths.
The path is excluded so that you can move the data files at a later stage without needing to update the list. This is the case for most lists that HPE IDOL Speech Server uses. You must provide the path in an action parameter when you send an action.
For more information about HPE IDOL Speech Server's list manager, see Create and Manage Lists.
Send an AddTask
action to HPE IDOL Speech Server, and set the following parameters:
Type
|
The task name. Set to LangIdTrain . |
Context
|
If you are using telephony (8 kHz) data, set Context to 2 for best results. |
DataList
|
The list that specifies the feature files. |
DataPath
|
The path to the directory that contains the feature files specified in the DataList . |
Out
|
The name of the language classifier to create. |
For example:
http://localhost:13000/action=AddTask&Type=LangIdTrain&DataList=ListManager/FrenchList&DataPath=C:\LangID\Data&Out=FRFR.lcf
This action uses port 13000
to instruct HPE IDOL Speech Server, which is located on the local machine, to use the feature files specified in the FrenchList
list and stored in C:\LangID\Data
to create the FRFR.lcf
language classifier file.
This action returns a token. You can use the token to:
|