NEWS & EVENTS
Jule 10, 2017
GritTec has ported code of voice identification technology for using it in Node.js environment
GritTec has created the wrapper of voice identification technology GritTec's Speaker-ID (Version 4.10) for using in Node.js (x86/x64) enviroment under MS Windows x86/x64 platforms. The code for Node.js language is available in the following modes:
- voice enrollment with addition of a new voice sample for target speaker;
- voice verification (Accepted/Rejected) for comparing with the voice samples of the current target speaker;
- voice verification (Accepted/Rejected) for comparing with the voice samples of all database of target speakers.
GriTec offer to use this code in server solutions in Call centers and in commercial banks for the purpuses of a person verifying by voice.
The SDK package contains the test cases for:
- voice enrollment in synchronous mode, an example of calling the voice enrollment function for an audio file with a target voice;
- voice enrollment in asynchronous mode, an example of a parallel calling the voice enrollment function for several (N) audio files with target voices;
- voice verification in synchronous mode, an example of calling the voice verification function for an audio file with a unknown voice;
- voice verification in asynchronous mode, an example of a parallel calling the voice verification function for several (N) audio files with unknown voices.
In mode of voice verification, developers have opportunity to tune the output of verification results with detailing of acceptance error (FAR) and rejection error (FRR).
Currently the GritTec's Speaker-ID SDK with Node.js environment is available under MS Windows x86/x64 platforms with both software license and hardware license (USB key). To test of GritTec's Speaker-ID SDK in Node.js, please contact us via Online Request form.
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.