VeriSpeak SDK
Speaker recognition for stand-alone or Web applications
VeriSpeak voice identification technology is designed for biometric system developers and integrators. The text-dependent speaker recognition algorithm assures system security by checking both voice and phrase authenticity. Voiceprint templates can be matched in 1-to-1 (verification) and 1-to-many (identification) modes.
Available as a software development kit that enables the development of stand-alone and Web-based speaker recognition applications on Microsoft Windows, Linux, Mac OS X, iOS and Android platforms.
Return to the list of components
Embedded Voice Extractor component
The Embedded Voice Extractor creates voice templates from audio samples and is designed to be run on Android or iOS or ARM Linux devices. The Android devices should be based on at least Snapdragon S4 system-on-chip (Krait 300 processor with 4 cores running at 1.51 GHz). The component extracts a single voiceprint template in 1.34 seconds.
The Embedded Voice Extractor component can be configured to perform automatic voice activity detection, which allows to begin voice capture only when users start speaking, and finish capture when they stop speaking.
See technical specifications for the size of voice template and the requirements for voice record.
One Embedded Voice Extractor license for each of Android, iOS and ARM Linux platforms is included with VeriSpeak 10.0 Standard SDK and VeriSpeak 10.0 Extended SDK. More licenses for this component can be purchased any time by VeriSpeak 10.0 SDK customers.
