Conversational Assistant / 29.01.2013

The Rise of Voice Biometrics on Mobile Phones

Let’s be honest: most of our lives revolve around our mobile phone. We hold a lot of personal information on our phones themselves, like photos, e-mails, contacts. Moreover, we often use mobile apps or voice calls to the major institutions with which we deal throughout our lives: our bank, hospital, insurance company, etc. While this offers convenience of accessing data anywhere and anytime, it simultaneously surfaces major concerns about privacy and security.

Risks of Data Loss to Mobile Phone Users

Imagine that tomorrow you misplace your mobile phone. The prospect of all your confidential information slipping into the wrong hands is terrifying.  Even if you think your data is secure in an application, it isn’t hard for someone to guess of steal the password or PIN code that you use to unlock these applications. Therefore, both consumers and enterprises feel a sharp need for a more robust security solution to protect all the information that is traditionally passed and stored on mobile devices.

Need for Voice Biometrics in Mobile Phones

Biometric identifiers are the distinctive, measurable characteristics used to label and describe individuals. With all types of biometric applications on the rise, voice-based authentication is one approach that seems to engender less resistance among users than other biometric forms of security. Voice recognition is non-contact, non-intrusive and easy to use. Indeed, voice biometrics seems the obvious choice for securing mobile phones, given that the primary function of these devices is to enable voice communication.

By deploying voice authentication, it eliminates the need for the user to use a password for low risk access.  This helps the user since they are often forced to keep password lists since they have to deal with so many enterprises requiring them to use passwords. Overall, by using tokens the user already carries, like their smart phone, it enables easy ways to provide stronger authentication at low enterprise management costs. 

How Does Voice Biometrics Work?

Voice recognition technology is possible after making a digital model of an individual’s voice that can serve as a stored profile or template of that voice print. Words and phrases are broken down into various kinds of frequency patterns that, taken together, describe someone’s unique way of speaking. The templates are stored in databases for matching like other kinds of biometric data.

Each time the user accesses the application, they are required to repeat a passphrase or random set of numbers. The user’s voice is then compared to the template stored. If the match is within a certain threshold, the user’s voice is confirmed.

 Previous Issues with Voice Biometrics

Until recently, voice biometrics was not considered as a serious candidate for securing mobile phones because many challenges affect its accuracy. These include poor-quality voice samples; the variability in a speaker’s voice due to illness, mood, changes over time; background noise as the caller interacts with the system; and changes in the call’s technology (digital vs. analogue, upgrades to circuits and microphones, etc).  

 Current Advancements in the Field of Voice Biometrics

With recent advancements in this technology, voice biometrics has become quite robust and reliable. These technologies are continually improving and many of the former problems with this recognition technology have been overcome to make it more reliable.

For example, background noise was once a problem that could interfere with accuracy rates. However, new recognition techniques and devices are being used to reduce background noise to offer better accuracy.

Today, voice biometrics recognition technology has low error rates, making it extremely secure and reliable, and another big advantage for those who plan to use it for a security system.  With the integration of biometric fraud analytics, even better security strength can be achieved by today’s voice recognition equipment.

Large Scale Adoption

With these advancements in technology have come large-scale adoption of voice biometrics. Here are a few of the most recent examples:

 

About the Author: 

Richard McMunn, is the founder and director of the UK’s leading career website How2become.com helps people prepare for and pass recruitment process in order to acquire their dream job. The website offers a wide range of books, dvds and courses for those who want to take their preparation to the next stage. 

About Uniphore: Uniphore Software Systems is the leader in Multi lingual speech-based software solutions. Uniphore’s solutions allow any machine to understand and respond to natural human speech, thus enabling humans to use the most natural of communication modes, speech, to engage and instruct machines. Uniphore operates from its corporate headquarters at IIT Madras Research Park, Chennai, India and has sales offices in Middle East (Dubai, UAE) as well as in Manila, Philippines.