Jaime González Gasque
Voice biometrics rapidly becoming most popular authentication technologies
As artificial intelligence (AI) technology becomes more sophisticated, organisations can leverage AI in ways hitherto impossible.
For instance, it could understand the inflexions and unique voice modulation of human speech to identify the person speaking, entirely without manual intervention. This is exactly what voice biometrics aims to achieve. It lets you assign a voiceprint (just as you would have a fingerprint) to every customer or prospect. The AI compares future instances of speech to that voiceprint to verify identity and automatically trigger tasks/events.
Voice biometrics is rapidly becoming one of the most popular authentication technologies among customers. Studies reveal that nearly 1 in 3 customers prefer voice-based biometric measures followed by fingerprints (27%), facial scan (20%), hand geometry (12%), and iris scan (10%).
What does this mean for contact centres? How can you leverage voice biometrics to reduce agent workloads, minimise fraud, and improve the customer experience? Let’s find out.
What is Voice Biometrics?
Voice biometrics can be defined as a technology that enables identity verification by analysing a person’s voice as a unique biological characteristic. It starts by having a voice input sample stored in the system, just like we would store your fingerprint when setting up a smartphone. Later, when the person speaks into the voice biometrics software, the audio statement is split into multiple frequencies whose behavioural attributes are identified and compared with the sample stored already in the system.
There are two types of authentication that can take place through voice biometrics:
Text-dependent authentication – The customer utters a specific phrase that is stored in the system as a sample. In future, the customer must remember and repeat this same phrase for smooth authentication.
Text independent authentication – The analysis happens purely based on the biological characteristics of the customer’s voice, not the specific contents of what they are saying. This type of voice biometrics can run in the background as your agent speaks to a customer.
Benefits of Voice Biometrics in a Contact Centre Voice biometrics can dramatically improve your contact centre efficiency by mitigating fraud risk, shrinking call durations, and improving self-service adoption. By having customers authenticate themselves through voice biometrics, you can ensure that agents do not reveal confidential information to someone impersonating a customer. An automated voice biometrics-based authentication system will also free agents from having to check customer identity manually. The system could also auto-lookup contextual customer information, further saving time.
Finally, voice biometrics could drive up your IVR self-service rates dramatically. Despite IVR being much more cost-efficient than live agents, just 20-40% of all calls are resolved during IVR self-service. Among other reasons, this can be attributed to the fact that customers consider IVR less secure than live agents. Voice biometrics would eliminate this risk and inspire confidence, shrinking call queues and reducing agent workloads.
Voice Spoofing: An Emerging Threat
Voice spoofing can trick voice biometrics systems into believing they are listening to the real, authenticated customer and not an AI bot. Make sure to check out new technologies like Void, designed to combat voice spoofing attacks.