[speakerid] Module Configuration

The speakerid module segments audio based on speaker and classifies the speaker in each segment. If a speaker that is not trained in IDOL Speech Server is present in the audio, the speakerid module classifies the speaker as unknown.

Input and Output

Mode Input Output Description
SPEAKER_DETECT a sid Accepts audio frames, and produces speaker identification results.

Example:

sid <- speakerid(SPEAKER_DETECT, a)

Parameters

AstFile* MinSpeech
BaseAstFile* SampleFrequency*
CompSelect* SigFile*
Diag SpkIDBasePack*
DiagFile SpkSegmentCoef
DiagFileLabel SpkThreshCoef
DiscardShortSegs USMEnabled *
MinNonSpeech  

Some of these parameters do not have an internal default value. You must either set the configuration parameter to a suitable value, or set the value in the corresponding action parameter.

Set the BaseAstFile parameter in speaker training tasks and the AstFile parameter in speaker identification tasks. If you set both parameters in the module, IDOL Speech Server returns an error message.


_HP_HTML5_bannerTitle.htm