Contact Us
General Enquiries Tel: 020 8326 8326
Need Support? Tel: 020 8326 8300
red box logo
NICE fully colourised logo
NICE in contact fully colourised logo
Verint fully colourised logo
Microsoft fully colourised logo
man looking over a graph on a tablet

NICE Perform – Fraud Detection Solution

3 min read
Author Business Systems UK
Date Dec 11, 2005
Category Call Recording Technology

A smart tool for financial organisations is a clever little software application from NICE Systems; it uses the latest voice biometrics technology to produce ‘voiceprints’ which help differentiate between bonafide and fraudulent telephone calls. The software is an ‘add-on’ to the existing Call Recording solution and runs on an industry standard server.

How does it work? The software creates a voiceprint by analysing a recorded call and extracts the speaker’s unique voice characteristics; it then compares the voice print to a pre-built list for positive or negative matching. Negative matching to a ‘blacklist’ will identify known fraudsters or suspects, where as matching to a ‘whitelist’ will confirm bonafide callers.
To create a voiceprint, the system uses voice biometrics to analyse an individual’s vocal characteristics using physiological measurements such as vocal tract resonance and vocal chord vibration frequency. This process makes the voiceprint as unique to an individual as a fingerprint.
The software has three modules: Database, Rules and Reporting. The database stores all the voiceprints, the rules module defines the comparison parameters for look up and the reporting function defines the escalation requirement once a match/mismatch is established.

The rules part of the software enables comparisons to be set based on predefined types of calls – ie, change of address calls or those requesting an increase in credit limit. The reporting module can display calls with a high probability of being a fraudster. Most organisations would then get specialists to play these calls and compare them against voice samples of fraudsters.