A process of authenticating or identifying an individual based on a sound speech signal.

The method uses multiple models to authenticate individuals, terminals, and environments from speech sound signals, addressing spoofing vulnerabilities and enhancing security through multi-factor authentication.

FR3143819B1Active Publication Date: 2025-06-20WORLDLINE SA(FR)
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
FR2022013491
Authority / Receiving Office
FR · FR
Patent Type
Patents
Current Assignee / Owner
Filing Date
2022-12-15
Publication Date
2025-06-20
Estimated Expiration
2042-12-15

AI Technical Summary

Technical Problem

Existing biometric authentication systems, particularly voice-based systems, are vulnerable to spoofing attacks such as impersonation, replay, and voice conversion, lacking robustness in identifying individuals based on speech sound signals.

Method used

A method involving multiple upstream and downstream models to extract and authenticate/identify individual, terminal, and environment factors from a single speech sound signal, using self-supervised learning to generate vector representations without labeled data, and combining these factors for secure authentication.

Benefits of technology

Enhances security by making spoofing attacks impossible and improves decision-making through multi-factor authentication, distinguishing individuals, their terminals, and environments effectively.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 00000025_0000
    Figure 00000025_0000
  • Figure 00000026_0000
    Figure 00000026_0000
  • Figure 00000027_0000
    Figure 00000027_0000
Patent Text Reader

Abstract

The present invention relates to a method for authenticating or identifying an individual, the method being characterized in that it comprises the implementation of steps of: Obtaining a speech sound signal of said individual in a candidate environment, acquired by a microphone (14) of the candidate terminal (1); Determining from said sound signal a first vector representative of the identity of the individual by applying a first upstream model; and a second vector representative of said candidate terminal (1) by applying a second upstream model, and / or a third vector representative of said candidate environment by applying a third upstream model. Authenticating or identifying said individual on the basis of the result of the application: to the first vector of a first downstream model function; and to the second vector of a second downstream model function and / or to the third vector of a third downstream model. Figure for abstract: Fig 1.
Need to check novelty before this filing date? Find Prior Art