Can Voice Biometrics be Used for Financial Authentication?

Voice recognition or voice authentication examines a person’s voice to verify their identity. The shape and movement of the mouth and jaw impact the generated voice patterns to create a unique “voiceprint.” It is not the same as speech recognition, which is the technology used in speech-to-text applications and virtual assistants like Alexa and Siri. Speech recognition cannot verify the identity of the speaker based on his or her unique vocal attributes.

For the past 5 years, a few banks and other service organizations have introduced voice biometrics to verify the identities of customers contacting their call centers. Voice authentication uses biometrics to verify calling customers’ identities while they’re explaining issues to a service representative over a phone call. It analyzes unique characteristics in a person’s vocal pattern and verifies them against a prerecorded voice print to cross-check their identity. Voice authentication cuts out the tiresome process of verifying a customer’s identity through IDs and personal details, reducing distress for customers, allowing representatives to provide meaningful help faster. It takes less than one minute for a customer to set up a voiceprint, and over one million customers in the Asia Pacific region used voice authentication within one year of its release. Users may find this more convenient and secure than sharing personal information such as their license or credit-card number for identity verification. 

The foremost use of voice-based authentication lies in hands-free mobile authentication. This is ideal for mobile phones or other settings where facial recognition, fingerprint recognition and other forms of biometric authentication are inappropriate, such as automobiles. Virtual assistants are increasingly used to place orders and perform other functions that typically require some form of identification. 

A voice biometric sample must be captured using a microphone to create a reference to compare against samples for future authentication attempts. Unique vocal qualities (duration, intensity, dynamics, and pitch) are then analyzed. The algorithm uses more than 100 different calculations to generate a voiceprint. An adaptation process can be used to track changes to a speaker’s vocal tract/voice over time as they age, avoiding any need to continuously update and maintain a voiceprint ‘identity’. Because the voiceprint is characterized by the vocal trait (a physiological trait) and not specifically the sound of the utterance, afflictions that affect the ‘sound’ of a voice; the common cold, for example, do not affect the vocal tract and don’t have an adverse effect on accuracy levels. If a speaker can provide enough vocal energy to be heard, enough of their voice will be present for verification. 

Voice Biometric is an authentication technology well suited for applications and systems in which other Biometric Technologies would be difficult or inconvenient to implement. Voice Biometrics provides a multifactor authentication of a person’s identity through a unique property: his or her voice. Just like other Biometric characteristics, the voice is unique to an individual.