Software embeds speaker verification

Edited by the Electronicstalk editorial team Aug 4, 2003

Kane Computing can now offer speaker verification software for PC-based systems.

Kane Computing can now offer speaker verification software for PC-based systems.

The software from Spirit is targeted at secure telephony, voice-based access systems, voice locks, childproof electronics, and other applications where it is necessary to identify a person by analysing his or her voice.

The speaker verification solution has two operating modes.

In static mode, the user has to speak a password, and the SV system makes its decision on whether the user is legal.

In dynamic mode, the user is required to speak a set of standard system keywords (such as numerals) in random order.

Dynamic mode is considered significantly more reliable, although lengthier.

Both direct and remote speaker verification - with live voice or via a phone line - is supported by the software.

User enrolment and verification can be performed under different acoustic conditions (quiet room, phone verification etc) Enrolment and verification thresholds are selectable, enabling an adjustable security level.

To improve verification reliability, the algorithm also implements signal/noise ratio and nonlinear distortion analysis.

The speaker verification software is available in the form of DLL libraries for Microsoft Windows.

Custom porting to DSP or RISC platforms is available on request.