Voiceprint Authentication System Masking Key Speech Leakage

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing voiceprint authentication systems face challenges in preventing the leakage of key-reading speech during user authentication, as the fixed or dynamic passwords can be overheard by third parties, compromising security, especially in environments where hygiene and infection control are concerns.

Innovation Solution

An authentication system that stores voiceprints associated with recorded sounds for each user ID, outputs a masking sound, acquires and removes this masking sound from the key-reading speech to determine user authority, thereby masking the authentication key from third parties.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If voiceprint authentication using fixed or dynamic passwords is used, then authentication functionality is achieved, but key-reading speech may leak to third parties compromising security

Engineering Contradiction:

Improveauthentication securityVSAvoidkey-reading speech leakage

Core Design Contradiction:

ReliabilityVSLoss of information

Solution Approach 1:

The patent converts the harmful effect of speech leakage into a beneficial feature by using the user's own voice characteristics as a masking mechanism. The system extracts voiceprint features from the user's speech and uses these features to generate masking sounds that obscure the authentication key while allowing the system to verify the user's identity through voiceprint matching.

Inventive Principle:

Principle #22Blessing in disguise (Convert harm into benefit)

Solution Approach 2:

The patent introduces voiceprint features as an intermediary element between the authentication key and the verification process. Instead of directly verifying the authentication key speech, the system uses voiceprint features extracted from the speech as an intermediate representation that both masks the original speech content and enables identity verification.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Loss of information

If masking sound is added to prevent speech leakage, then speech security is improved, but sound processing complexity increases

Engineering Contradiction:

Improvespeech leakage preventionVSAvoidsound processing complexity

Core Design Contradiction:

Loss of informationVSDevice complexity

Solution Approach 1:

The system performs self-service by using the user's own voiceprint features to generate the masking sound. The voiceprint extraction and masking sound generation processes are automatically performed by the system without requiring external intervention or complex manual configuration, reducing overall system complexity.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent merges the authentication verification process with the speech masking process. The same voiceprint features extracted for authentication purposes are simultaneously used to generate the masking sound, combining two functions into a unified process that reduces complexity.

Inventive Principle:

Principle #5Merging (Combining)

Data Source

PatentUS11776543B2Authentication system, authentication method, and, non-transitory computer-readable information recording medium for recording program

Publication Date: 2023.10.03 PASSLOGY CO LTD

AI summary

An authentication system prevents leakage of a key-reading speech during user authentication based on the key-reading speech of a user reading an authentication key. For each user ID, a storage stores a voiceprint of a user in association with a recorded sound including speech spoken previously by the user. A specifier specifies the user ID of a user attempting to receive authorization. An outputter outputs a masking sound that includes the recorded sound recorded in association with the specified user ID. An acquirer acquires a key-reading speech of the user reading the authentication key and the output masking sound. A remover acquires a second sound by removing the masking sound from the acquired first sound. A determiner determines whether the user has authority pertaining to the specified user ID based on the acquired second sound.