Machine Learning Sound-Transfer Modeling for Hearing-Device Fitting

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Hearing devices face fitting errors due to variations in earpiece components such as tube lengths and wax filters, which affect frequency responses and are difficult to account for in existing fitting methods, especially when replacing earpieces with different geometries.

Innovation Solution

A method using a machine learning algorithm to determine sound transfer system parameters by analyzing feedback threshold curves and transfer functions, allowing for better fitting by adjusting electronic sound processing based on the specific acoustic properties of the earpiece components.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional fitting methods are used for hearing devices, then the fitting process is simple and quick, but fitting accuracy deteriorates due to unaccounted variations in earpiece components such as tube lengths and wax filters

Engineering Contradiction:

Improvefitting accuracyVSAvoidfitting process complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent introduces a sound transfer system as an intermediary component between the loudspeaker and the ear canal. This system includes a tube and wax filter that can be characterized independently. By measuring and characterizing this intermediary system, the patent enables accurate compensation for component variations without requiring complex direct measurements in the ear canal.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces traditional mechanical/physical measurement methods (real ear measurements requiring specialized equipment and expertise) with an automated system using microphones, loudspeakers, and computer algorithms. The fitting process is transformed from a manual, expertise-dependent procedure to an automated, objective measurement and calculation process.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If real ear measurements are performed to achieve accurate fitting, then fitting precision improves, but the cost and time requirements increase significantly

Engineering Contradiction:

Improvefitting precisionVSAvoidfitting time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary characterization of the sound transfer system components (tube and wax filter) outside the ear canal. By pre-measuring the acoustic properties of these components and storing their parameters, the system eliminates the need for time-consuming real ear measurements during the fitting appointment. The pre-characterized data is then used for accurate fitting calculations.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent creates a computational model (copy) of the sound transfer system that replicates its acoustic behavior. Instead of performing physical measurements in the complex environment of the ear canal, the system uses a simplified computational model based on measurements taken in controlled conditions, achieving the same fitting accuracy with less time and effort.

Inventive Principle:

Principle #26Copying

3Ease of manufacture

If component variations in earpieces are standardized, then manufacturing complexity reduces, but adaptability to different user needs deteriorates

Engineering Contradiction:

Improveearpiece manufacturingVSAvoidfitting adaptability

Core Design Contradiction:

Ease of manufactureVSAdaptability or versatility

Solution Approach 1:

The patent focuses on characterizing and compensating for variations in acoustic parameters (tube length, wax filter type, resonant frequencies) rather than requiring custom manufacturing for each component variation. By measuring and storing these parameters, the system can adapt to different component configurations through software adjustments rather than hardware customization, maintaining manufacturing simplicity while achieving fitting adaptability.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentEP4626037A1Using machine learning algorithm for determining parameters of a sound transfer system of a hearing device

Publication Date: 2025.10.01 SONOVA AG

Figure 1~2
Figure 3~4

AI summary

A method for determining at least one parameter (40) of a sound transfer system (28) between a loudspeaker (18) and a sound opening (24) of a hearing device (10) comprising: receiving a feedback threshold curve (34) of the hearing device (10) and/or a transfer function (36) between the loudspeaker (18) and a microphone (11) of the hearing device (10); and inputting the feedback threshold curve (34) and/or the transfer function (36) into a machine learning algorithm (38) and determining the at least one parameter (40) of the sound transfer system (38) by the machine learning algorithm (38).