Ear Canal Biometric Authentication via Audio Artefact Masking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Ear biometric systems face challenges due to a low signal-to-noise ratio (SNR) in the measured response signal, exacerbated by narrow bandwidth and low amplitude acoustic stimuli, which are further complicated by noisy environments and poor fitting of earphones.
Innovation Solution
The method involves detecting user-initiated events with associated audio artefacts, such as tapping or voice interactions, to apply an acoustic stimulus during the decay envelope of these events, masking the stimulus and increasing its signal level and bandwidth, thereby improving the SNR and extracting features for biometric processes like authentication and enrolment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the acoustic stimulus is applied with high amplitude and broad bandwidth to improve signal-to-noise ratio, then the biometric measurement precision is improved, but the user experience deteriorates due to overbearing or uncomfortable sound
Solution Approach 1:
The patent converts the harmful audio artefacts (noise, tapping sounds, voice interactions) into beneficial masking signals. By detecting these artefacts and applying acoustic stimulus during their decay envelope, the previously harmful noise becomes a useful tool to hide the stimulus from user perception while enabling higher amplitude measurements
Solution Approach 2:
The system performs preliminary detection of audio artefacts and identifies their decay envelopes before applying the acoustic stimulus. This preliminary action allows timing the stimulus application precisely during periods when the user's auditory attention is occupied, preventing discomfort while enabling high-SNR measurements
2Object-affected harmful factors
If the acoustic stimulus is applied with narrow bandwidth and low amplitude to maintain user comfort, then the user experience is preserved, but the biometric measurement precision deteriorates due to low signal-to-noise ratio
Solution Approach 1:
The system employs periodic or intermittent application of acoustic stimulus during the decay envelopes of audio artefacts. Rather than continuous low-level stimulation, it uses periodic high-level stimulation timed to coincide with natural noise events, achieving both user comfort and measurement precision
Solution Approach 2:
The system dynamically adjusts the acoustic stimulus parameters (amplitude, bandwidth, timing) based on the detected audio artefact characteristics. The stimulus is adapted in real-time to exploit the temporal and spectral properties of each artefact, optimizing both user comfort and measurement quality
3Measurement precision
If the earphone is inserted deeper into the user's ear to improve acoustic coupling and signal quality, then the biometric measurement precision is improved, but the ease of operation deteriorates due to improper or uncomfortable fitting
Solution Approach 1:
The patent converts the harmful effect of poor acoustic coupling (due to improper fitting) into a beneficial opportunity. By using audio artefacts that occur during normal wearing conditions, the system can extract biometric data without requiring optimal acoustic coupling, thereby maintaining user comfort while achieving measurement precision
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 approach enhances the SNR of the measured response signal, allowing for more effective biometric authentication and enrolment by masking the acoustic stimulus within audio artefacts, improving detection accuracy and reliability.
Implementation Method 1
applying the acoustic stimulus to the user's ear during a masking period in which the acoustic stimulus is masked in the user's hearing or at the user's eardrum by the audio artefact
Implementation Method 2
the ear canal is a resonant system, and therefore one feature which may be extracted from the response signal is the resonant frequency of the ear canal
Data Source
AI summary
A method for masking an acoustic stimulus, comprising: detecting an event initiated by a user of a personal audio device, the event having an associated audio artefact; in response to detecting the event, applying the acoustic stimulus to the user's ear during a masking period in which the acoustic stimulus is masked in the user's hearing by the audio artefact; extracting, from a response signal of the user's ear to the acoustic stimulus, one or more features for use in a biometric process.


