Hearing Aid Adaptive Classifier for Program Selection Stability

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Modern hearing aids face challenges in minimizing the risk of undesired program changes, as they struggle to accurately classify auditory environments and adapt signal processing modes effectively, leading to suboptimal sound amplification and noise suppression.

Innovation Solution

A hearing system that includes a hearing aid and a personal communication device, connected via a short-range data transceiver, which uses a classifier to analyze specific characteristics of the audio signal, compare them to thresholds, and automatically select the appropriate signal processing mode, with the ability to adjust these thresholds based on user interaction and environmental data.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If the hearing aid uses automatic program selection based on classifier analysis, then adaptability to different auditory environments is improved, but the risk of undesired program changes increases

Engineering Contradiction:
Improveadaptability to auditory environmentsVSAvoidprogram selection stability
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The system performs preliminary classification of auditory environments before making program selection decisions. The classifier analyzes signal characteristics and compares them to thresholds in advance, allowing the system to prepare for appropriate program changes while avoiding impulsive or undesired switches. This preliminary analysis stabilizes program selection by ensuring changes occur only when environmental conditions genuinely warrant them.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system incorporates feedback mechanisms where the classifier continuously monitors auditory environment characteristics and adjusts program selection based on this ongoing analysis. The feedback loop allows the system to learn from previous classifications and refine its threshold comparisons, improving both adaptability to changing environments and stability against spurious program changes.

Inventive Principle:
Principle #23Feedback

2Measurement precision

If the hearing aid uses sophisticated signal processing for speech intelligibility improvement, then speech clarity is enhanced, but device complexity increases

Engineering Contradiction:
Improvespeech intelligibilityVSAvoidsignal processing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The signal processing system is divided into distinct functional segments: a classifier component that analyzes auditory environments, a program selector that chooses appropriate processing modes, and specific signal processing subsystems that execute targeted enhancements. This segmentation allows sophisticated speech intelligibility improvement through multiple specialized functions while managing overall device complexity by organizing processing tasks into modular, independent components.

Inventive Principle:
Principle #1Segmentation

3Object-affected harmful factors

If the hearing aid continuously monitors and classifies auditory environments, then noise suppression is improved, but energy consumption increases

Engineering Contradiction:
Improvenoise suppressionVSAvoidenergy consumption
Core Design Contradiction:
Object-affected harmful factorsVSUse of energy by moving object

Solution Approach 1:

The classifier monitors auditory environment characteristics at periodic intervals rather than continuously, analyzing signal characteristics and comparing them to thresholds at defined sampling rates. This periodic action maintains effective noise suppression by regularly updating environmental classification while significantly reducing energy consumption compared to continuous monitoring. The system adjusts the periodicity based on environmental stability to optimize the balance between noise suppression performance and power usage.

Inventive Principle:
Principle #19Periodic action

Data Source

PatentUS11330379B2Hearing aid having an adaptive classifier
Publication Date: 2022.05.10 WIDEX AS
  • US11330379B2 patent drawing
  • US11330379B2 patent drawing
  • US11330379B2 patent drawing

AI summary

A hearing system includes a hearing aid (10) and personal communication device (20) connected via a short range data communication link. The hearing aid has a signal processor (13) processing an audio signal according to audio processing parameters, a sub-system applying respective sets of processing parameters for at least two modes, a classifier component (51) statistically analyzing the environment by comparing specific characteristics of an electrical input signal to one or more thresholds. A program selector component (16) selects automatically an appropriate mode for the signal processing sub-system according to the classifier output. The personal communication device offers the user an interface for controlling and interacting with the program selector component of the hearing aid, and for generating and transmitting a notification to the hearing aid. Upon reception of the notification, the processor adjusts at least one of the one or more thresholds used by the classifier component.