Follow

infokey shop 

GreekEnglish (UK)

Voice Identification - Verispeak SDK

 

Verispeak SDK 02

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. Verispeak is available as a software development kit that enables the development of stand-alone and Web-based applications on Microsoft Windows, Linux, Mac OS X and Android platforms.

  • Description
  • Advantages
  • Features
  • System Requirements
  • Reliability Tests

 

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 a-to-many (identification) modes.  VeriSpeak extracts a template in 0.6 seconds and can match up to 8,000 voiceprints per second on a PC. A single voice template requires about 4 kilobytes, when 5-second voice samples are used. VeriSpeak is available as a software development kit that enables the development of stand-alone and Web-based applications on Microsoft Windows, Linux, Mac OS X and Android platforms.

Reliability Tests

The VeriSpeak 2.1 algorithm has been tested with voice samples taken from the XM2VTS Database, as well as with voice samples from Neurotechnology's internal database.

 

Suitable for

 

  • Banks
  • State
  • Business
  • Stores
  • Hotels

 

 

 

 

 

Advantages of Verispeak SDK

 

  • Text-dependent algorithm prevents unauthorized access with a covertly-recorded user voice.
  • Two-factor authentication by checking voice biometrics and pass-phrace authenticity.
  • Regular microphones and smartphones are suitable for for recording user voices.
  • Available as a multiplatform SDK that supports multiple programming languages.

 

VeriSpeak features and capabilities 

The VeriSpeak offers text-dependent and text-independent speaker recognition and capable of performing voiceprint verification and identification. Multiple samples of the same phrase and fused matching can be used to improve recognition quality.

 

Recommendations and constraints for speaker recognition

VeriSpeak has certain requirements for microphone settings and position, as well as user behavior and environment. A passphrase should be kept secret and spoken in an environment where others may hear it.

 

 

 

VeriSpeak SDK minimum requirements  

Minimum requirements: 

FeatureMinimum requirements
CompatibilityOperating System Windows (for x86 and x86-64), Linux (for x86 and x86-64), Mac OSX(for x86 and x86-64) and Android (for ARM-based processors).
MicrophoneAny microphone that is supported by the operating system can be used.

 

 

System Requirements

VeriSpeak-based software can be run on PCs or mobile/embedded devices. Windows (for x86-64), Mac OS X (for x86 and x86-64) amd Android (for ARM-based processors) platforms are supported. A regular microphone and smartphone is suitable for voice capture.  

PC and Mac specific:

  • PC or Mac with x86 (32-bit) or x86-64 (64bit) compatible processors 2 GHz or better processor is recommended.
  • At least 128MB of free RAM should be available for the application. Additional RAM is required for applications that perform 1-to-many identification, as all biometric templates need to be stored in RAM for matching.For example 1,000 templates (each containing 1 voice record) require about 5MB of additional RAM.
  • Free space on hard disk drive (HDD):
    • Αt least 1GB for the development.
    • 100 MB required for VeriSpeak components deployment.
    • Additional space would be required in these cases:
      • VeriSpeak does not require the original voice sample to be stored for the matching; only the templates need to be stored. However, storing voice samples on hard drive for the potential future usage is recommended.
      • Usually a database engine runs on a separate computer (back-end server). However, DB engine can be installed on the same computer for standalone applications. In this case HDD sapce for templates storage must be available. For example, 10,000 templates (each containing 1 voice record extracted from 5-seconds long sample) stored using a relational database would require about 50 MB of free HDD space. Also, the database engine itself requires HDD space running. Please refer to HDD space requirements from the database engine providers.

Smartphone and tablet specific:

  • A Smartphone or tablet or other device that running Android OS.
  • ARM-based 1.5 GHz processor recommended for processing a voiceprint in the specified time.Slower processors may be also used, but the voiceprint processing will take longer time.
    • At least 20 MB of free RAM should be available for the application. Additional RAM is required for applications that perform 1-to-many identification, as all biometric templates need to be stored in RAM for matching. For example, 1,000 templates (each containing 1 voiceprint record) require about 5MB of additional RAM.
  • Free storage space (built-in flash or external memory card):
    • 30MB required for embedded voice components deployment for each separate application.
    • Additional space would be required if an application needs to store original audio samples. VeriSpeak does not require the original audio sample to be stored for the matching; only the templates need to be stored.
  • Microphone. Any microphone that is supported by the operating system can be used.
  • Network/LAN connection (TCP/IP) for the client/server applicaions. Also, network connection is required for using Matching server component (included in VeriSpeak Extended SDK). Communication with Matching servers not encrypted therefore, if communication must be secured, a dedicated network (not accessible outside the system) or a secured network (such as VPN; VPN must be configured using operating system or third party tools) is recommended.
  • Database engine or connection with it. VeriSpeak templates can be saved into any DB (including files) supporting binary data saving:
    • Microsoft SQL Server(only for Microsoft Windows)
    • My SQL, Oracle, Postgre SQL(forMicrosoft Windows and Linux platforms)
    • SQLite(for Microsoft Windows, Linux,Mac OS X platforms)

 

The VeriSpeak 2.1 algorithm has been tested with voice samples taken from th XM2VTS Database, as well as with voice samples from Neurotechnology's internal database.

These voice templates matching experiments were performed with the Verispeak 2.1 text-dependent engine:

  • Experiment 1used voice samples from the XM2VTS database. All samples include the same fixed phrase pronounced by all subjects.
  • Experiment 2used voice samples from Neurotechnology's internal voice database 1. All samples included the same fixed phrase pronounced by all subjects.
  • Experiment 3used voice samples from Neurotechnology's internal voice database 2. Each subject pronounced a unique phrase during his/her recording.

Receiver operation characteristic (ROC) curves are usually used to demonstrate the recognition quality of an algorithm. ROC curvs show the dependence of false rejection rate (FRR) on the false acceptance rate (FAR). Charts with ROC curves for each of the experiments are available above.

 

experiment 01

 

experiment 01 02

 

pinakaki 04