Tamper-Resistant Element for Speaker Recognition Data Integrity

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current speaker recognition systems, particularly those using smart cards, are limited in their ability to perform text-independent speaker verification, lack robust security measures against attacks, and require significant bandwidth and storage for handling voice prints, making them vulnerable to tampering and data integrity breaches.

Innovation Solution

A tamper-resistant element, such as a secure smart card or module, is designed to store and process speaker information securely, performing data integrity checks and spoof detection within the element to ensure the confidentiality and authenticity of voice recognition data, using algorithms like Hidden Markov Models and i-vector approaches for text-dependent and text-independent recognition.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If speaker recognition data is stored outside a tamper-resistant element, then bandwidth and storage requirements increase, but security and data integrity are compromised

Engineering Contradiction:
Improvedata integrityVSAvoidbandwidth and storage requirements
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent extracts and stores only essential speaker recognition data (voice prints, enrollment data) within the tamper-resistant element, while keeping the system architecture simple. This selective extraction of critical data to a secure location protects data integrity without requiring complex external storage systems.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The tamper-resistant element acts as an intermediary between the speaker recognition system and external data sources. It verifies data integrity through checksum validation before accepting enrollment data and prevents unauthorized access to stored biometric information, thereby ensuring reliability while maintaining system simplicity.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If comprehensive speaker recognition processing is performed outside the tamper-resistant element, then processing speed increases, but vulnerability to tampering and attacks increases

Engineering Contradiction:
Improvesecurity against attacksVSAvoidprocessing speed
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent segments the speaker recognition system into two parts: secure verification operations performed within the tamper-resistant element and non-critical processing outside. This segmentation ensures that critical security functions (data verification, enrollment validation) are protected from attacks while non-essential operations can proceed externally.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system performs preliminary data integrity verification through checksum validation before data is stored or processed further. This preliminary anti-action prevents corrupted or malicious data from entering the system, thereby maintaining security without significantly impacting overall processing speed.

Inventive Principle:
Principle #9Preliminary anti-action

3Reliability

If all speaker recognition operations are performed outside the tamper-resistant element, then system complexity is reduced, but confidentiality of biometric data is compromised

Engineering Contradiction:
Improveconfidentiality of biometric dataVSAvoidsystem architecture
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent extracts only the most critical biometric data (voice prints and enrollment information) and stores it within the tamper-resistant element. This selective extraction ensures confidentiality of sensitive biometric data while avoiding the need for complex architecture that would require moving all processing operations inside the element.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The tamper-resistant element provides self-service security functions including automatic verification of data integrity through checksum validation, protection of stored voice prints, and prevention of unauthorized access. This self-service capability maintains confidentiality without requiring complex external security management systems.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP3373176B1Tamper-resistant element for use in speaker recognition
Publication Date: 2020.01.01 CIRRUS LOGIC INT SEMICON LTD
  • EP3373176B1 patent drawingFigure 1
  • EP3373176B1 patent drawingFigure 2
  • EP3373176B1 patent drawingFigure 3

AI summary

A tamper-resistant element for use in speaker recognition, the tamper-resistant element being adapted for storing data representing speaker information based on speaker recognition enrollment data and for checking whether information based on a speaker recognition testing signal matches the speaker information, characterized in that the tamper-resistant element is also adapted for carrying out a data integrity check, a system comprising such a tamper-resistant element and method for speaker recognition.