Voice Biometrics Engine server role settings

The following settings are required for the Voice Biometrics Engine role.

Biometrics Connection Details

Property name	Instructions	Default value
Biometrics Command Port	Provide the TCP port number where the engine listens for control messages. NOTE: The port used is the same as the Enrollment Command Port configured for the Voice Enrollment Engine.	Default: 29290 Minimum: 1024 Maximum: 65535
Biometrics Data Port	Provide the starting/base TCP port number used by the engine when transmitting audio for biometric processing. The engine uses 2 ports per CPU core. Therefore, on an 8 core hyper-threaded machine (16 cores total) the engine requires 32 ports. IMPORTANT: Based on CPU cores, configure the port base number with enough available ports relative to the Enrollment Data Port of the Voice Enrollment Engine.	Default: 29348 Minimum: 1024 Maximum: 65535

Property name

Instructions

Default value

Biometrics Command Port

Provide the TCP port number where the engine listens for control messages.

NOTE: The port used is the same as the Enrollment Command Port configured for the Voice Enrollment Engine.

Default: 29290

Minimum: 1024

Maximum: 65535

Biometrics Data Port

Provide the starting/base TCP port number used by the engine when transmitting audio for biometric processing.

The engine uses 2 ports per CPU core. Therefore, on an 8 core hyper-threaded machine (16 cores total) the engine requires 32 ports.

IMPORTANT: Based on CPU cores, configure the port base number with enough available ports relative to the Enrollment Data Port of the Voice Enrollment Engine.

Default: 29348

Minimum: 1024

Maximum: 65535

Biometrics Processing Options

Property name	Instructions	Default value
Max time to wait for customer identification	Configure the maximum number of seconds to preprocess 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. audio without a customer 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 to use for comparison. Preprocessing analysis stops after the interval elapses if the attributes configured in the Identification Rules cannot be used to locate a trained, customer voiceprint model. Preprocessing also stops after the Recorder Analytics Rule setting for “Max Audio To Process” elapses.	Default: 300 Minimum: 0 Maximum: 1200
Stop preprocessing if no voiceprint	Select to stop interaction processing if the voiceprint model for a person cannot be found in the voice biometrics system. A voiceprint model will not be found if: Identification Rule attributes do not match a person in voice biometrics. Identification Rule attributes match a person in voice biometrics, but that person does not have a trained voiceprint model. When this option is cleared, preprocessing will continue; if interaction attributes configured in the Identification Rules are updated, the system attempts again to find a matching voiceprint model.	Default: Cleared

Property name

Instructions

Default value

Max time to wait for customer identification

Configure the maximum number of seconds to preprocess 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. audio without a customer 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 to use for comparison.

Preprocessing analysis stops after the interval elapses if the attributes configured in the Identification Rules cannot be used to locate a trained, customer voiceprint model.

Preprocessing also stops after the Recorder Analytics Rule setting for “Max Audio To Process” elapses.

Default: 300

Minimum: 0

Maximum: 1200

Stop preprocessing if no voiceprint

Select to stop interaction processing if the voiceprint model for a person cannot be found in the voice biometrics system.

A voiceprint model will not be found if:

Identification Rule attributes do not match a person in voice biometrics.
Identification Rule attributes match a person in voice biometrics, but that person does not have a trained voiceprint model.

When this option is cleared, preprocessing will continue; if interaction attributes configured in the Identification Rules are updated, the system attempts again to find a matching voiceprint model.

Default: Cleared

Biometrics Detection Settings

Property name	Instructions	Default value
Minimum score for potential target detections	Use this setting to control the frequency of the Potentially Detected result that is possible for target 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. activity Core component of both schedules and time records in Workforce Management (WFM). When an employee performs any kind of work, activities specify the scheduled work and capture employee adherence to their schedule.. Increasing the value generally reduces the frequency of Potentially Detected results. Decreasing the value generally increases the frequency of Potentially Detected results. This setting works as a threshold and its value works along with the minimum detection scores configured for each Recorder Analytics Rule. A score below this threshold is ignored and the interaction is not associated with detection activity. NOTE\| Applies even if the score is above the minimum detection scores configured in a rule. This threshold takes precedence over the detection thresholds configured for each rule. A score meets the condition of Potentially Detected when greater than or equal to this threshold, but below the minimum detection scores configured in a rule. A score meets the condition of Detected when above the minimum detection scores configured in a rule and this threshold.	Minimum: -100 Maximum: 100

Property name

Instructions

Default value

Minimum score for potential target detections

Use this setting to control the frequency of the Potentially Detected result that is possible for target 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. activity Core component of both schedules and time records in Workforce Management (WFM). When an employee performs any kind of work, activities specify the scheduled work and capture employee adherence to their schedule..

Increasing the value generally reduces the frequency of Potentially Detected results.
Decreasing the value generally increases the frequency of Potentially Detected results.

This setting works as a threshold and its value works along with the minimum detection scores configured for each Recorder Analytics Rule.

A score below this threshold is ignored and the interaction is not associated with detection activity.

NOTE| Applies even if the score is above the minimum detection scores configured in a rule. This threshold takes precedence over the detection thresholds configured for each rule.
A score meets the condition of Potentially Detected when greater than or equal to this threshold, but below the minimum detection scores configured in a rule.
A score meets the condition of Detected when above the minimum detection scores configured in a rule and this threshold.

Minimum:

-100

Maximum: 100