SidPackage

Deprecated: The SidPackage task is deprecated for IDOL Server version 11.1.0. Use the SpkIdDevelFinal task instead.

This task is still available for existing implementations, but it might be incompatible with new functionality. The task might be deleted in future.

The SidPackage task packages a set of speaker templates into a single classifier file.

Parameters

Parameter Description Required
Type The task name. Set to SidPackage. Yes
Ast The speaker classifier file. See Comments.
Bias The balance bias to use between reducing false hits and reducing rejections.  
Diag Whether to generate diagnostic information.  
DiagFile The file to write the diagnostic information to.  
Out The combined classifier file to create. The file must have the .ast file extension. Yes
MaxFar Sets the maximum permissible False Acceptance Rate (FAR), which is the expected rate at which segments are labeled incorrectly as coming from a particular speaker.  
SampleFrequency The sample frequency of the audio file to process. See Comments.
SidBase The sid base pack resource to use to determine the base files to use.  
SpkList A list of speaker templates. Yes
SpkPath The path to the directory containing the speaker templates. Yes
Spo The speaker ID optimization (.spo) file to use. *
SpoList A list specifying multiple .spo files. *
SpoPath The path to the directory containing the .spo files listed in the SpoList. *
USM The USM file to use.  
USMEnabled Whether to include the Universal Speech Model in the speaker classifier file.  

*If you generated a single .spo file during optimization, set the Spo parameter. If you generated multiple .spo files during optimization, set the SpoList and SpoPath parameters instead.

Example

http://localhost:13000/action=AddTask&Type=SidPackage&SpkList=ListManager/speakers&SpkPath=C:\training&Spo=C:\training\speakers.spo&Out=AllSpeakers.asts

This action uses port 13000 to instruct Speech Server, which is located on the local machine, to package the speaker templates specified in the speakers list into the AllSpeakers.ast file, using the statistics available in the speakers.spo file.

Comments

If you do not specify the Ast parameter, the action uses the base ast file, determined by the SidBase resource. This base file does not contain any speaker information, and cannot identify speakers, but it performs gender detection and speaker segmentation.

Generally, you do not need to set the SampleFrequency parameter, because Speech Server determines the appropriate value from the speaker ID optimization file or files. However, you can set the parameter to double-check that the value in the speaker ID optimization file is what you would expect. In addition, If the speaker ID optimization file is from an old build, it might not include the sample frequency – in this case, you must set it explicitly.


_HP_HTML5_bannerTitle.htm