Voice authentication is quickly replacing PINs, passwords and questions asked to identify users. This technology has also been said to provide better security. It involves using your voice relying on the fact that vocal characteristics, just like fingerprints and people’s irises (eyes), are unique to an individual.

Identity theft has increased and companies want to secure data proactively. This has seen a surge in the use of voice authentication. It is the reason why companies like Safaricom have quickly embraced this technology so that they can provide customers with extra security for sensitive information.

The service from Safaricom is called ‘Jitambulishe’ and it uniquely allows customers to use their voice for authentication before they can access assisted services like resetting M-PESA PIN, and PUK. ‘Jitambulishe’ also cuts down the steps that a customer goes through before they are assisted by the customer care service.

To activate it, a customer’s voice patterns are captured and used to create a unique “voiceprint” that is stored securely. These then help to identify and verify customers whenever they call the customer care desk.

The system transcribes what a person says and how they say it by replicating the position a mouth makes when speaking a certain speech pattern.

How ‘Jitambulishe’ works

The service works by retrieving three aspects of a person’s speech.

One is ‘What you are saying’, which is retrieved using automatic speech recognition technology.

The other is ‘How you speak’, which involves language, accent and speaking style. This is the information used to identify a speaker, their culture and mood.

A third aspect, which is the most important information from a person’s voice is through the vocal tract: that is, the shape of a person’s larynx, mouth and nose. This information is unique and particular to an individual. It cannot be changed or disguised and it is not dependent on language. This is the fundamental basis on which the service works.

On enrollment into the system, a person’s voice is recorded which creates a voiceprint for comparison with samples taken for user identification.

To enhance the security of stored samples, the user may be asked to repeat pre-recorded voiceprints randomly. This is what the system uses to proof a request for entry.


More on the technology

The use of voice ID has also seen the rise of the voice assistant, with Amazon’s ubiquitous voice assistant, Alexa, taking top honors. So ingrained in the E-commerce world is Alexa that JP Morgan Chase bank uses it for trades.

Other areas that voice ID can be used include, Wire Transfer, Government Immigrant Check-in, Customer Service Authentication and Employee Workforce Management Check-in.

Critics however are keen to point out that voice biometrics is not fool proof. Citing examples such as lack of accuracy or partial capture of data and binding which oft leads to system failure and which is irreversible.