The call metadata does not have the call attributes needed to perform identity 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. (that is, the call metadata does not include the call attribute that the Identification Rule uses to locate 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. models for a user).

The engine attempted to perform identity verification but could not find a voiceprint model for the user.

Specifically, this value indicates:

• The call metadata includes the call attributes that the Identification Rule uses to locate the voice print for a user. (This Identification Rule is specified in the Voiceprint Verification settings of the Voice Biometrics Engine Settings.)

• There is no usable voice print found in the system that is associated with the call attribute values in the call metadata. The case of no usable voice print occurs for the following reasons:

  • Unknown person: The metadata available for the interaction In Speech Analytics, an interaction represents a single part of the contact between one employee and the same customer. In Text Analytics, an interaction is the communication session between one or more employees and the same customer with a unifying contextual element. cannot be used to identify a person 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..

  • Customer opted out: The customer has opted-out from voice biometric verification.

  • Voiceprint model not trained: The customer or employee was identified through metadata, but no voiceprint was found.

  • Partially trained: The customer or employee was identified through metadata, and a voiceprint exists, but the voiceprint requires additional 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 it can be used for verification. For example:

    • The Minimum Calls for Voiceprint, as defined by the Recorder Analytics Rule, have not yet been reached.

    • The customer or employee was enrolled automatically or manually and the voiceprint is pending approval in Risk Management.

    • The customer or employee voiceprint model is in an Invalidated state. A model can be in an invalidated state temporarily after adding interaction segments while retraining of the model is pending. An invalidated state can also result from adding invalid interaction segments that block retraining of the model, which requires corrective action.

  • Customer cooling-off period: The customer voiceprint is in a cooling-off period, a time during which the customer voiceprint model is not used for verification.

A potential watch list List that contains one of more voiceprints of people who are of particular interest to an enterprise. 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. occurred as follows:

• The engine determined that the vocal characteristics of a person speaking on a call had some similarities to a voiceprint model in a watch list.

• The detection score for the watch list detection analysis was above the Minimum score for potential target detections (configured for the Voice Biometrics Engine server role Entity that contains a logical, predefined set of components (system software or certified third-party software) deployed in the Data Center and Site Zones that provide specific functionality for the system.), but below the threshold specified for one of the following Voiceprint Detection settings in the Recorder Analytics Rule:

  • Minimum Score

  • Minimum Score if Verified

  • Minimum Score if Not Verified

For details about these settings, see Voice Biometrics Engine settings.

A watch list detection occurred as follows:

• The engine determined that the vocal characteristics of a person speaking on a call were similar to a voiceprint model in a watch list.

• The detection score for the watch list detection analysis was above the threshold specified for one of the following Voiceprint Detection settings in the Recorder Analytics Rule:

  • Minimum Score

  • Minimum Score if Verified

  • Minimum Score if Not Verified

For details about these settings, see Voice Biometrics Engine settings.

The engine performed an identity verification and determined the person speaking on the call is not who they claim to be, or the engine stopped processing audio for some reason.

Specifically, the following occurred:

• The engine located a voiceprint model for a person speaking on a call and performed an identity verification analysis.

• This analysis returned a verification score that was equal to or lower than the Minimum Score setting specified in the Voiceprint Verification section of the Voice Biometrics Engine Settings.

The engine can also return this result if it stops processing audio during the identity verification analysis for any reason.