In-ear Acoustic Authentication Device Feature Correction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The accuracy of in-ear acoustic authentication varies depending on the audio device used, as the echo signal measured is influenced by both the acoustic characteristics of the ear hole and the audio device.

Innovation Solution

An in-ear acoustic authentication device that includes a feature extraction unit to input an inspection signal and extract a first feature from the echo signal, a correction unit to correct this feature to a second feature using a predetermined reference device, and an authentication unit to compare the second feature with pre-registered authentication information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If the echo signal is measured using an audio device, then the authentication can be performed, but the accuracy varies depending on the audio device used

Engineering Contradiction:
Improveauthentication accuracyVSAvoiddevice compatibility
Core Design Contradiction:
Measurement precisionVSAdaptability or versatility

Solution Approach 1:

A correction unit is introduced as an intermediary component between the audio device and the authentication unit. This correction unit receives the echo signal from the audio device and corrects it to compensate for the acoustic characteristics of the specific audio device, thereby enabling accurate authentication across different audio devices without requiring device-specific calibration of the authentication system

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If the echo signal is corrected to a reference device, then the authentication accuracy is standardized, but the processing complexity increases

Engineering Contradiction:
Improveauthentication accuracyVSAvoidprocessing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The correction unit performs preliminary processing on the echo signal by correcting it to the reference device characteristics before the authentication unit processes the signal. This preliminary correction action removes the variability introduced by different audio devices, allowing the subsequent authentication processing to be simplified and standardized without needing to account for device-specific acoustic characteristics

Inventive Principle:
Principle #10Preliminary action

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This solution enables accurate authentication of a subject regardless of the audio device used, by correcting the feature extracted from the echo signal to a standard reference, thereby stabilizing the authentication process.

Implementation Method 1

The speaker of the earphone-type device transmits an inspection signal (sound wave) toward the inside of the ear hole of the person to be authenticated. The microphone of the earphone-type device detects an echo sound from the ear hole.

Methodology Applied
Scientific EffectAcoustic echo: Echo

Implementation Method 2

the accuracy of authenticating the subject may vary depending on which audio device is used. Strictly speaking, the echo signal to be measured in the in-ear acoustic authentication depends not only on the acoustic characteristic of the ear hole of the subject but also on the acoustic characteristic of the earphone-type device

Methodology Applied
Scientific EffectAcoustic measurement: Acoustics

Data Source

PatentEP4083826B1In-ear accoustic authentication device, method and program
Publication Date: 2025.03.05 NEC CORP
  • EP4083826B1 patent drawingFigure 1
  • EP4083826B1 patent drawingFigure 2
  • EP4083826B1 patent drawingFigure 3

AI summary

The disclosure accurately authenticates a subject, regardless of which audio device is used for the in-ear acoustic authentication. A feature extraction unit (11) applies a test signal to an ear of a subject using an audio device, and upon receiving an acoustic signal from the subject, extracts, from the acoustic signal, a first feature relating to the system consisting of the audio device and the ear of the subject; a correction unit (12) corrects the first feature to a second feature that would result if a prescribed reference device were used instead of the audio device; and an authentication unit (13) authenticates the subject by comparing the second feature with a feature indicated by pre-registered authentication information.