How it works

The process of enrolling an individual’s voice as a “voicekey” works as follows:

1.

Audio recordings of the individual saying a specific phrase are collected and, along with a Unique Identifier(UID), are passed to a Voicekey server for processing.

2.

The audio signal data is processed through a series of transformations to enable key sound features to be extracted as an input to multiple neural networks.

3.

A “voicekey” is produced by the neural networks to create a unique ‘unhackable’ security token for future identity verification.

4.

The voicekey is encrypted and for future use stored either in some form of centralised database or portable smart devices e.g. mobile, watch, etc.

The verification of the individual at some future time works as follows:

1.

A new audio recording of the individual saying a verification phrase is collected

2.

The audio recording, the related user “voicekey” and UID are passed to a Voicekey server for processing

3.

The voicekey is unwrapped and the original set of neural network weights are reconstructed

4.

Feature data is extracted from the new audio signal and passed through the reconstructed NN for comparison 

5.

A similarity score is derived and passed out to a client system for use as part of multi-factor ruleset for determining the identity verification outcome.

How Voicekey is different

Flexible Deployment

Voicekey servers can be deployed on-premise, in the cloud as a public/private SAAS and combinations thereof; such that an enrolment server can be in the cloud and an unconnected verification Voicekey server can be on-premise.

 
Secure Biometrics

Voicekey avoids the usual threats associated with hacking central databases by enabling storage of the “Voicekey” token on a mobile device.

Cross-Platform

Storing the “Voicekey” token on a portable device means Voicekey, as a product, can operate cross-channel, platform, infrastructure and organisation

No Fixed-Phrase

Unlike other voice-biometric products, that rely on the same fixed phrase for both enrolment and verification, Voicekey decouples this dependency. Voicekey enables flexible verification options that can be used to address liveness and spoofing threats; and a better more natural user experience.

Simple Enrolment

Unlike other voice biometric products that typically requirement enrolment per channel Voicekey can be utilised as a single source of identity verification in omni-channel customer environments via a single enrolment process.

Ease of Integration

Voicekey can be easily integrated into web & mobile applications and all vxml based IVR systems (such as Amazon Connect) and a number of other voice-based technologies.