The speakerid
module segments audio based on speaker and classifies the speaker in each segment. If a speaker that is not trained in HPE IDOL Speech Server is present in the audio, the speakerid
module classifies the speaker as unknown.
Mode | Input | Output | Description |
---|---|---|---|
SPEAKER_DETECT
|
a
|
sid
|
Accepts audio frames, and produces speaker identification results. |
Example:
sid <- speakerid(SPEAKER_DETECT, a)
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, HPE IDOL Speech Server returns an error message.
|