Biometric Voice Security
Voice biometrics is a cutting-edge technology developed for the future. With the growing usage of online services, passwords and text or email authentications are no longer adequate to secure your data. Whispeak voice biometrics offers a secure solution to authenticate you easily and quickly.
Whispeak API allows you to enroll, authenticate, and identify someone using the speaker’s voice.
- Enrollment: generate a signature from a speaker voice record.
- Authentication: Compare a voice recording with a signature to check if they belong to the same speaker.
- Identification: Find if some signatures are close to a tested audio file signature.
The purpose could be to find the owner of the recorded voice.
To do so we test the sent audio file against a group of previously enrolled speakers’ signatures.
Regarding the configuration of your identification API, this will return a list of the 0-n closest signatures and/or above the comparison threshold.
Applications
To use this API, you need a dedicated application.
An “Application” needs to be configured with a specific type (e.g. Authentification or Identification).
Each application can be referred inside the URI (e.g. /v1/apps/auth-app) for the concerned endpoints.
Enrollment
The enrollment stage consists to generate a signature from audio files recorded with the speaker’s voice.
Enrollment consists of creating your application users (aka speakers) by feeding it with their signatures.
To do so you need to pass an audio file to the enrollment endpoint and the signature will be generated regarding the parameters you set in the application configuration.
Authentication
The aim of “Authentication” is to compare a signature against an audio file (voice sample) to determine whether or not they belong to the same speaker.
Identification
The “Identification” process finds the signatures that are most similar to a voice sample (in an audio file) to find to which speaker it could belong.
Regarding the related configuration of the processed identification, the response will be a list of n speakers ordered from the closest one to the furthest.
So to perform “Identification”, you need to pass an audio file and a “group” of speaker signatures. This “group” can be generated with the corresponding endpoint.
Whispeak is a speaker recognition software that makes it easy to add a biometric factor to authentication processes. Don’t choose between security and fluidity. With Whispeak, let your users and customers speak to prove who they are. Fully respectful of user privacy and 100% compliant with GDPR requirements, it is available as SaaS, on-premise, or embedded.
Performance
Whispeak relies on artificial intelligence for speaker recognition to achieve state-of-the-art performance
GDPR
Whiskpeak’s technology complies with the General Data Protection Regulation as well as the CNIL’s recommendations on the storage of biometric templates.
Security
Whispeak encrypts and signs voice signature data. This way only users are able to use their template