NullSpeakerAudioData

Removes (deletes) an audio sample from a speaker, but does not remove the training generated from the audio data.

After running this action speakers can still be recognized but the audio cannot be retrieved from the database and cannot be used to retrain Media Server. If future versions of Media Server feature enhancements to speaker identification that require retraining, you will need to supply the audio again.

Type: synchronous

Parameter Description Required
database The name of the database that contains the speaker. Yes
identifier The identifier of the speaker whose audio samples you want to remove. Yes
audiolabels A comma-separated list of labels that specifies the audio samples to remove. If you do not set this parameter, Media Server removes all of the samples from the speaker. No

Example

/action=NullSpeakerAudioData&database=news&identifier=newsreader&audiolabels=sample1

Response

<autnresponse>
    <action>NULLSPEAKERAUDIODATA</action>
    <response>SUCCESS</response>
    <responsedata> </responsedata>
</autnresponse>

See Also

To remove an audio sample and the corresponding training, use the action RemoveSpeakerAudio.