Hearing Aid Algorithm Personalization via Predictive Testing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing hearing aids lack personalized settings that account for individual hearing abilities and preferences, leading to suboptimal performance and user annoyance due to fixed audible and visual indicators.
Innovation Solution
A method for personalizing hearing aid parameters using predictive tests and machine learning, such as spectro-temporal modulation and triple digit tests, to estimate user hearing ability and preferences, and adjusting algorithms like directionality based on a cost-benefit function.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If fixed audible and visual indicators are used in hearing aids, then device complexity is reduced and ease of manufacture is improved, but adaptability to individual user needs deteriorates and user annoyance increases
Solution Approach 1:
The patent implements dynamic indicator customization where users can select from multiple audible and visual indicator patterns through a user interface. The hearing aid system allows users to choose different indicator types (e.g., different tones, LED patterns) based on their personal preferences and needs, transforming fixed indicators into adaptable, user-specific indicators without complicating the manufacturing process
Solution Approach 2:
The patent changes the parameters of indicators by allowing users to select from predefined sets of audible and visual indicator characteristics. The system stores and applies user-selected indicator parameters (tone frequency, duration, LED color, pattern) thereby personalizing the device output without requiring physical customization during manufacturing
2Device complexity
If standardized hearing aid settings are used for all users, then device complexity and configuration time are reduced, but speech intelligibility and hearing performance for individual users deteriorate
Solution Approach 1:
The patent implements preliminary user assessment through predictive tests (e.g., spectro-temporal modulation tests, triple digit tests) that evaluate individual hearing abilities before configuring the hearing aid. Based on test results, the system pre-configures personalized parameters for processing algorithms such as directionality, noise reduction, and frequency shaping, thereby achieving individualized optimization without requiring complex manual adjustment during fitting
Solution Approach 2:
The hearing aid system automatically performs predictive tests and analyzes user responses to self-determine optimal parameter settings. The device uses machine learning algorithms to process test data and automatically configure personalized hearing aid parameters, reducing the need for extensive professional fitting time and manual adjustment while achieving individualized optimization
3Measurement precision
If directional beamforming is applied to enhance front targets, then speech intelligibility for front-facing sources is improved, but speech intelligibility for side-facing sources deteriorates due to attenuation
Solution Approach 1:
The patent dynamically adjusts the directionality algorithm parameters based on individual user needs assessed through predictive tests. For users who prioritize front-facing speech understanding, the system configures stronger directional beamforming with narrower beamwidth. For users who need to attend to side sources, the system reduces directional attenuation or widens the beam pattern, thereby personalizing the trade-off between front enhancement and side attenuation rather than applying a fixed beamforming configuration to all users
4Measurement precision
If individualized predictive tests and personalized parameter configuration are implemented, then speech intelligibility and user benefit are improved, but hearing care professional time requirements and system complexity increase
Solution Approach 1:
The hearing aid system automatically administers predictive tests (such as spectro-temporal modulation tests and speech-in-noise tests) and analyzes user responses without requiring extensive professional intervention. The embedded algorithms automatically process test data, determine hearing abilities, and configure personalized parameters, thereby minimizing the time hearing care professionals need to spend on manual assessment and fitting while achieving individualized optimization
Solution Approach 2:
The system uses feedback from user responses to predictive tests to automatically adjust and personalize hearing aid parameters. The iterative process collects user performance data, analyzes it through machine learning models, and refines parameter configurations accordingly, reducing the need for multiple manual fitting sessions and minimizing professional time requirements while achieving precise individualization
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method of personalizing one or more parameters of a processing algorithm for use in a hearing aid of a specific user comprises • Performing a predictive test for estimating a hearing ability of the user when listening to signals having different characteristics; • Analyzing results of said predictive test for said user and providing a hearing ability measure for said user; • Selecting a specific processing algorithm of said hearing aid, • Selecting a cost-benefit function related to said user's hearing ability in dependence of said different characteristics for said algorithm; and • Determining, for said user, one or more personalized parameters of said processing algorithm in dependence of said hearing ability measure and said cost-benefit function.