Foreword#

Everyone in the Contact Center industry understands that IVRs are a gold standard that allows to greatly reduce the number of agents needed to handle the influx of customer calls. In many cases, IVRs are also the "front door" to your Contact Center and so they are desgined to be as succinct as possible so as to not annoy the caller. We put a lot of careful effort when we initially design our IVR flows as we fully understand the importance of the Customer Experience (CX).

And yet, a few years later, after the IVR is out there doing its job (hopefully), only a few will know what their IVR map looks like and what their customers are facing when they call the organization.

In our attempts to optimize the Contact Center operation we keep bolting numerous integrations on to our IVRs:

• Automatic CRM / Customer record look-ups is the gold standard
• Self-service endpoints are added
• Automated authentication services are introduced
• The IVRs are being tweaked all the time to address a new business direction or handle an issue with the initial layout

A Bit of Background#

I get a lot of repeating questions when I try to explain how Voice Authentication works. One of the questions that deserves special treatment is how does the system make a decision on whether the caller's voice passes the test or not? Furthermore, if the caller does not pass the test, what does it actually mean? And what is the Accuracy of Omni Authentication (or any other Voice Biometrics solution for that argument)?

It is a tricky one and it takes quite a bit of effort to explain so I've decided to dedicate a post talking about the inner mechanisms of Voice Biometrics.

In this post we discuss the following Key Points:

• The mechanics of Voice Authentication
• Confidence Score
• Authentication Threshold
• What Voice Authentication Accuracy is

Introduction#

Over the past 80 years Contact Center (CC) has become an isolated industry with its own management practice and ethics. As such, CC’s are widely used in any “market verticals” to handle various kinds of customer interactions from sales to service.

One aspect that is common to all CC’s is that they handle a large number of calls. The volumes are so high that CC’s have trained staff that is solely dedicated to handle those calls. Therefore, any CC is notoriously expensive to run.

There are two main KPIs that CC managers strive to ‘optimize’: Customer Satisfaction (CSAT) and Handling Times (HT). Ultimately, Customer Satisfaction depends on the waiting times (they should be as short as possible) as well as the ability of the CC to address customer enquiries efficiently. Handling Time is a KPI which counts the duration of each call between Customer and Agent. The longer the Average HT, the more agents a CC would need to keep the CSAT levels high. Therefore, it is a form of art to ensure high CSAT whilst keeping Average HT low.

Introduction#

OI Voice Biometrics Quick Facts:

• Greatly improves CX
• Active Authentication and Passive Enrolment model is our default choice
• Omni Intelligence is Cloud CC-ready and has default integration with Genesys Cloud
• Low implementation and running costs - most affordable solution on the market for any business size