|
| PerSay Voice Biometrics |
|
PerSay technology provides exceptionally reliable text-dependent and text-independent voice biometrics.
Language and accent independent, PerSay products repeatedly score high marks with our customers as well
as independent third-party evaluations.
Core Engine
PerSay's superior core engine is the result of extensive research and development efforts begun in the late 1990s at
Comverse Technology. The algorithms originally developed at Comverse were designed to allow law enforcement agencies
to intercept calls of known suspects by analyzing voices recorded over multiple telephone channels. Since then, PerSay's
research team has invested significant time and effort in improving the baseline verification accuracy, adding new services
and features, and adapting advanced state-of-the-art classification algorithms to address the challenges faced in real-life
operational environments.
The original text-independent algorithms were extended to handle calls with more than one speaker;
text-dependent algorithms were added to allow speaker recognition with short pass phrases; and text-prompted algorithms now
allow liveness detection with random challenge questions.
For more information please go to:
http://www.persay.com
From the Press:
Voice biometrics is a newly matured technology that is essential to contact centres in today's world of identity theft,
fraud and attacks on security and privacy.
CaTS has formed an alliance with one of the world leaders in the exciting field of voice biometrics. CaTS was able to
leverage its fast knowledge of voice-related applications, VoiceXML and MRCP integration, to deliver a working test
platform in a very short-time span. The implementation of voice biometric measures will be critical, moving forward
with the ever-increasing use and application of voice interfaces for financial and contract related transactions.
Added to the compelling business case for voice biometrics is the prevalence of identity theft.
CaTS chose to make use of PerSay as its voice biometrics technology partner and has successfully developed and tested
two avenues of integration, from a standards-based environment to the PerSay Voice Biometrics system.
The voice biometrics database collects voice prints from clients or subscribers who have been successfully authenticated.
These voice prints can be a content-specific password spoken or it can be any arbitrary phrase uttered by the caller.
Each voice print is then, in turn, saved against that particular identity. As callers phone, their voice print can be
taken at the agent's request, or while they are in the process of greeting the agent. The first would be a content-specific
password and the second would be a non-content-specific password. The latter allows for an unobtrusive authentication.
CaTS always prides itself on having a propensity to integrate its existing technology with new technology and this is yet
again one of the examples.
Johan Grobler, MD of CaTS, stated: "we are very happy to have successfully conducted tests within the South African
context and believe voice biometrics is the logical next step, when virtual authentication is required from a client."
With the introduction of voice biometrics, the caller's experience is enhanced and the time spent by the agent on the
call is also drastically reduced.
Grobler concluded: "With theft of personal identity as something common today, an added layer of authentication is invaluable
for any organisation that values a high standard of customer care and satisfaction. We also see this as an easy step for any
organisation to differentiate its customer care experience."
CaTS sees the introduction of voice biometrics as an added security layer, which in most cases negates previous authentication
methods and allows callers to just speak their mind.
|
