printer friendly version

As unique as a fingerprint

Dimension Data partnership with PerSay fights identity theft and offers secure authentication and risk management in contact centre environments.

Dimension Data is now able to offer secure voice transactions and identity verification for businesses in sub-Saharan Africa with its recent partnership agreement which it has signed with PerSay, a voice biometric technology provider.

Secure verification is a requirement for effective risk management, compliance and industry regulations in the financial services or any contact centre environment that has access to a customer’s personal details. Increasing incidents of fraud and identity theft are deteriorating customer confidence, compromising personal information and confidential data which has resulted in an increased requirement for multifactor authentication.

Dimension Data’s 10th annual Global Contact Centre Benchmarking Report in 2008 revealed that self service in contact centres is continuing its upward trend and shows little sign of abating with 31% of all inbound transactions completed on a self service channel. While simplifying the end user experience and increasing efficiency in contact centres, personal data and passwords can easily fall into the wrong hands. Voice identification through a spoken phrase is the most efficient and secure verification methods available on the telephony channel today.

“Traditional verification methods including passwords and challenge questions no longer provide the necessary safeguards for secure account access through a contact centre,” explains Stephen Strydom, general manager, Customer Interactive Solutions, Dimension Data. “The security is placed solely in a contact centre agent’s hands and as all other verification data can be obtained through various methods by criminals, the most accurate way to verify identity is through voice biometric technology.”

How does voice biometrics work?

Voice biometrics identifies speakers using only their vocal characteristics. The concept is similar to other well-known biometric technologies, such as fingerprint and face recognition. All methods are based on physiological identifiers unique to every individual. In voice biometrics, these identifiers are related to the shape of the vocal tract.

During enrolment of new speakers, the identifiers, also known as features, are extracted from several voice samples and are used to create a voice template, or voiceprint, which is stored in the system’s database. The voice template describes the distribution of the features, but does not contain actual voice samples.

During verification, the features are extracted from the test segment and compared with a single voice template or a set of voice templates. The result of this comparison is a numerical score, describing the likelihood that the same speaker who created the voice template is speaking in the test segment. Comparing this numerical score with a threshold yields a binary accept/reject decision. This process can be repeated for several voice templates, providing one-to-many identification results.

What is multifactor authentication?

The FFIEC (Federal Financial Institutions Examinations Council, USA), has released guidance on ‘Authentication in an Internet/Electronic Banking Environment’ several times, and calls for increased security measures, stating that ‘reliable authentication is imperative for financial institutions engaging in any form of electronic banking or commerce’. The guidance calls for financial institutions to employ two of the following three factors to maximise security:

* Something the user possesses – (eg, a token, ATM card).

* Something the user knows – (eg, a shared secret, password, or account number).

* Something the user is – (eg, a fingerprint, iris scan or voiceprint). It is clear that voice biometrics is the only practical technology to enable multifactor authentication in the telephony channel.

Share this article:

Further reading: