Training statistics reference

The table provided by the Training Statistics dialog box shows a summary of voiceprint File containing a mathematical summary of the vocal patterns of a person’s voice used in the IAFD product to assist with identity verification and detection. model usage.

Usage figures show:

Number of voiceprint models by type of person. Statistics are summarized for people with Trained models, Partially Trained models, and totals of model usage for all types of people.
Number of people without voiceprint models by type of person. Statistics are summarized for people who are Untrained, Opted Out from voice biometrics, and totals for all types of people.
Sum of Total Models used.

People with models

Figures shown are included when calculating model usage relative to your voiceprint model licensing limit.

Training status	Description
Trained	The number of voiceprint models ready for use by verification Feature in voice biometrics where the speaker’s voice is compared to a collection of employee or customer voiceprints that should match the call. If a match occurs, the speaker is said to be verified. or detection Function of the IAFD product that compares a caller’s voice to one or more voiceprints in a watch list to detect if a target is participating in a call.. For customers and employees, to see a breakdown of the figure by enrollment Process in the IAFD product where an employee, customer, or target is registered and the system is then able to assist with identity verification and watch list detection when that speaker is on a call. type, rest your mouse pointer on the figure. A tooltip shows you model creation by Manual and Auto enrollment. If you use the optional customer cooling-off period, customers with models still in the cooling-off period are included in this figure.
Partially Trained	The number of voiceprint models created that require more interactions before the models can be used for verification. Applies only to customers and employees. Does not apply to targets, whose models are trained or untrained.

Training status

Description

Trained

The number of voiceprint models ready for use by verification Feature in voice biometrics where the speaker’s voice is compared to a collection of employee or customer voiceprints that should match the call. If a match occurs, the speaker is said to be verified. or detection Function of the IAFD product that compares a caller’s voice to one or more voiceprints in a watch list to detect if a target is participating in a call..

For customers and employees, to see a breakdown of the figure by enrollment Process in the IAFD product where an employee, customer, or target is registered and the system is then able to assist with identity verification and watch list detection when that speaker is on a call. type, rest your mouse pointer on the figure. A tooltip shows you model creation by Manual and Auto enrollment.
If you use the optional customer cooling-off period, customers with models still in the cooling-off period are included in this figure.

Partially Trained

The number of voiceprint models created that require more interactions before the models can be used for verification.

Applies only to customers and employees.
Does not apply to targets, whose models are trained or untrained.

People without models

Figures shown are not included when calculating voiceprint model usage.

Training status	Description
Untrained	The number of people in Risk Management Component of the Real-Time Analytics (RTA) Framework that provides interaction search and replay functionality, combined with integration of the Real-Time Analytics (RTA) Framework.who do not have a voiceprint model. People without models require voiceprint model training Semantic Intelligence (Si) process in Speech Analytics in which the system implements machine learning-based methods to extract and surface ontology-related items found in a sampling of transcribed interactions. before they can be used with verification or detection.
Opted Out	The number of customers or employees in Risk Managementwho do not have a voiceprint model as a result of the opt-out feature. An opted out person is explicitly excluded from voice biometric verification. Does not apply to targets, who cannot be opted out.

Training status

Description

Untrained

The number of people in Risk Management Component of the Real-Time Analytics (RTA) Framework that provides interaction search and replay functionality, combined with integration of the Real-Time Analytics (RTA) Framework.who do not have a voiceprint model. People without models require voiceprint model training Semantic Intelligence (Si) process in Speech Analytics in which the system implements machine learning-based methods to extract and surface ontology-related items found in a sampling of transcribed interactions. before they can be used with verification or detection.

Opted Out

The number of customers or employees in Risk Managementwho do not have a voiceprint model as a result of the opt-out feature. An opted out person is explicitly excluded from voice biometric verification.

Does not apply to targets, who cannot be opted out.