PRODUCTS
|
|
 NEWS & EVENTS
March 18, 2011
GritTec has presented a release of new version of GritTec's Speaker-ID (Version 3,00).
After long researches GritTec has received a release of the new
version of GritTec's Speaker-ID (Version 3.00). GritTec's Speaker-ID
is a technology of text independent voice identification and voice
verification of unknown speaker by paired comparing with voice
samples of target speaker.
GritTec's developers managed essentially to increase recognition
accuracy during various experiments and researches, at the expense
of integration of noise cancellation engine into DSP module of
GritTec's Speaker-ID engine and additional tuning of the noise
compensation module. Efficiency of the new version was checked in
comparison with the previous version on real records received from
various GSM channels.
The libraries in a new SDK are accessible to developers in the form
of objective code with supporting of Intel x86, x64 platforms and
with examples of test projects under MS Visual Studio C ++ 2008
compiler.
The release of the new version is received for SDK with API
functions of high level which in a consequence will be delivered
only. All functions and procedures in API high level are presented
in the unified form, that allows developers to reduce time
integration of identification engine under another compilers
(distinct from the C/C ++), i.e. without creation of special
wrappers modules for using of GritTec's libraries.
To learn more details about a new version of
GritTec's Speaker-ID
engine and to test a demo program, please visit home page of this
product or contact us via Online Request
form.
About GritTec
GritTec Laboratory (GritTec Ltd.) specializes on research and
development of algorithms and technologies in the field of speech
and audio processing. GritTec's research is focused on speech
enhancement, speech concealment, voice biometric, speech recognition,
speech synthesis and other speech and audio technologies.
Url: http://www.grittec.com
|
|
|
|
