Voice Input Authentication with Integrated Recognition

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional electronic devices require separate passwords or additional voice inputs for voiceprint recognition, which complicates the security processing and user authentication, especially for functions that need high security levels.

Innovation Solution

An electronic device that performs voice recognition and voiceprint recognition using a single voice input, adjusting the sensitivity of voiceprint recognition based on the security level of the specific expression, allowing functions to be executed securely without additional user input for low-security tasks and requiring thorough authentication for high-security tasks.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If separate passwords or additional voice inputs are used for voiceprint recognition, then user authentication security is improved, but operation complexity increases

Engineering Contradiction:
Improveuser authentication securityVSAvoidoperation complexity
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The patent combines voice recognition and voiceprint recognition into a single integrated processing system. The processor simultaneously performs both types of recognition on the same voice input, eliminating the need for separate authentication steps while maintaining security through multi-level verification.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The voice processing system is designed to perform multiple functions: it can conduct basic voice recognition for general commands and simultaneously perform voiceprint recognition for authenticated user identification. This multi-functional approach allows the system to adapt its security level based on the specific function being accessed.

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Reliability

If additional voice inputs are required for voiceprint recognition, then authentication reliability is improved, but processing time increases

Engineering Contradiction:
Improveauthentication reliabilityVSAvoidprocessing time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs voiceprint recognition in parallel with voice recognition during the same processing cycle. By preparing and analyzing voice characteristics simultaneously rather than sequentially, the system achieves thorough authentication without requiring additional time for separate processing steps.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The voice processing operation continues uninterrupted to perform both voice recognition and voiceprint recognition. The processor maintains continuous analysis of the voice input stream, extracting multiple features simultaneously, which eliminates idle time between authentication steps.

Inventive Principle:
Principle #20Continuity of useful action

3Reliability

If security processing is enhanced with separate authentication steps, then function security is improved, but device complexity increases

Engineering Contradiction:
Improvefunction securityVSAvoidprocessing complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments the voice processing into distinct analytical components: voice recognition analysis and voiceprint recognition analysis. Each component processes different features of the same voice input independently, allowing complex security verification to be broken down into manageable processing tasks that can be executed efficiently.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP3355304B1Voice input method and electronic device supporting the same
Publication Date: 2021.10.27 SAMSUNG ELECTRONICS CO LTD
  • EP3355304B1 patent drawingFigure 1
  • EP3355304B1 patent drawingFigure 2
  • EP3355304B1 patent drawingFigure 3

AI summary

An electronic device is provided. The electronic device includes a microphone configured to receive a voice, communication circuitry configured to communicate with an external electronic device, a memory, and a processor operatively connected to the microphone, the communication circuitry, and the memory. The memory stores instructions that, when executed by the processor, cause the electronic device to perform voice recognition for voice data corresponding to the voice, and determine whether to perform voiceprint recognition for the voice data based on whether a first expression is included in a result of the voice recognition.