Manual enrollment by interaction import

Usually the interactions used to train 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 are on a Recorder in the suite. However, you can also import audio from an external source onto the recording platform Predefined logical group of server roles installed together on a physical server..

Audio import converts the audio file to the standard recording format of the Recorder. Appropriate metadata is used to create an 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. in the database. After audio is ingested, all Recorder operations such as 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., archive, and search and replay can be performed on the interaction.

Importing audio for manual enrollment can temporarily affect automatic enrollment in the following cases In Risk Management, use cases to group interactionss according to the needs of the enterprise. Interactions can reside in multiple cases simultaneously.:

  • If the Recorder Analytics Rule used for automatic enrollment uses the Minimum Days between Calls setting, an import can block voiceprint enhancement by automatic enrollment until the number of days configured in the rule elapse.

  • The interaction start time for imported audio is the time that the import occurs. If the import occurs during a period when capture occurs for an interaction, the captured interaction would not be used for automatic enrollment. To prevent the duplication of interaction usage in N+N environments, automatic enrollment rejects an interaction for the same person with a capture time that overlaps another interaction.

Related topics 

Import an audio segment for a voiceprint model

Enrollment