Manually approve a voiceprint model audio segment

Control the integrity of audio files used to create a voiceprint model by listening to an audio segment and then, optionally, approving the audio. Approval of audio for models requires that the Approve/Unapprove Interactions for Enrollment privilege is assigned to your role in User Management.

Before you begin

Create a person
.
Enroll the person by creating a voiceprint model. You can use manual enrollment (by searching existing interactions or by uploading audio from an external source) or automatic enrollment (by a Recorder Analytics Rule).

Procedure

Access the Voiceprint Model for the person whose model you need to update.
Do one of the following:
- To approve an existing audio segment as an acceptable source, click approve . The segment is added to the voiceprint model.
  
  The approve option is available only to users with the role privilege of Approve/Unapprove Interactions for Enrollment.
- To search for more audio already recorded in the system, click search , and enter the search criteria for an audio segment.
- To import audio that is not already in the system, click upload , and then complete the procedure for uploading audio.

When you approve an audio segment for an already trained model, the Training Status changes to Invalidated. The system retrains the model using only approved audio segments. Training requires approximately 30–60 seconds as the audio is processed and the model is trained/retrained.