Manual enrollment

Manual enrollment provides you with complete control over the quality of voiceprint models. Manual enrollment can be time-consuming for creating many models. A best practice is to enroll manually for special circumstances only.

Do not complete this workflow if you plan to use automatic enrollment only.

Before you begin

Create a person
If you plan to import audio, ensure that the audio meets the Audio requirements for imported files.

Procedure

Choose how you want to provide audio for enrollment and use one of the following methods:

You can obtain audio segments you want to use for manual enrollment using the following methods:
- Search for interactions
  
  You can perform a basic search to identify interactions by person (employee, customer, target), watch list, and the last number of days/weeks/months/years.
- Search for interactions using advanced search
  
  You can perform an advanced search to find interactions based on any of the supported search fields.
- Import an audio segment for a voiceprint model
  
  To create a voiceprint model manually, or to enhance an existing voiceprint model, you can import one or more audio files for the person. Uploaded audio is used to model the voiceprint from a source other than the suite Recorder.
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.