Speaker Identification

The software solution of GritTec Speaker-ID: The mobile client (Version 1.90/ Engine 3.00) is intended for automatic voice identification of a speech signal of unknown voice by comparing with target voice samples of "speaker cards", existing in the database of system.
This software product supports the high-quality GUI interface and may be interest for centers of criminalistics, polices, call centers and the banks which purpose is text independent voice identification of unknown audio phonogram of telephone negotiations.
Designed algorithm of voice identifications is based on duel comparison spectra features of unknown voice with the spectra features of target voice.

Spectra features are calculated with provision of dynamic determinations of channel distortion level and external hindrances and noises.
Features
Operation with low SNR;
Fast adaptation to changing of channel distortion and external noises;
Minimum duration of a speech signal with a voice example used for correct reception of voice parameters for the target speaker - not less 15 seconds;
Minimum duration of a speech signal with a voice example used for voice identification or voice verification - not less 7 seconds;
Speaker identification reliability not less than 90% if both of speech signals were recorded in the same channel;
Speaker identification reliability not less then 85% if both of speech signals were recorded in different channels (cross channels);
Automatic voice identification or voice verification doesn't require special skills;
Easy integration with target applications.
Signal requirement
Signal format: 16-bits linear, Mono channel;
8 kHz sampling rate;
SNR, at least 10 db;
Frequency range: 300-3400 Hz or better.
Supported signal formats
Windows PCM, A/mu-Law Wave, Microsoft ADPCM (MS ADPCM), Intel ADPCM (IMA ADPCM), Microsoft ACM GSM 6.10 (ACM Waveform).
Availability
For MS Windows XP/Vista/Windows 7 under win32 platform.