Selective Environmental Classification Synchronization for Hearing Prostheses
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Hearing prostheses, such as cochlear implants and hearing aids, face challenges in synchronizing audio input from different environments, leading to discordant or suboptimal operation when multiple devices are exposed to varying audio conditions, potentially resulting in unpleasant or confusing stimuli for users.
Innovation Solution
A method and system that determine scene classifications and confidence values for audio environments, allowing hearing prostheses to operate based on either common or independent attributes, selecting the appropriate stimulation settings to ensure consistent and optimal sound perception by processing audio inputs and generating stimulation signals accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If multiple hearing prostheses operate independently based on their own audio input, then each device can adapt to its local audio conditions, but the devices may produce discordant or inconsistent stimulation for the user
Solution Approach 1:
The patent merges the scene classification operations of multiple hearing prostheses by having devices exchange their classifications and confidence values. The first hearing prosthesis receives the second scene classification and confidence value, then selects between the first and second scene classifications based on comparing confidence values. This combining approach allows devices to maintain adaptability to local conditions while ensuring consistency through coordinated selection of a common scene classification.
Solution Approach 2:
The system implements feedback by having hearing prostheses exchange scene classification and confidence value information with each other. The first hearing prosthesis receives feedback from the second device about its scene classification and confidence level, then uses this feedback to make an informed selection. This feedback mechanism enables devices to adjust their operation based on both local audio conditions and the classifications of other devices, resolving the contradiction between adaptability and consistency.
2Stability of the object's composition
If hearing prostheses exchange scene classification information, then synchronization and consistency improve, but device complexity and communication requirements increase
Solution Approach 1:
The patent extracts only the essential information needed for synchronization: scene classification and confidence value. Rather than exchanging comprehensive audio data or complex operational parameters, each hearing prosthesis transmits only these two key elements to other devices. This extraction approach achieves effective synchronization while minimizing the complexity of the communication mechanism and the data being exchanged.
3Productivity
If hearing prostheses use different scene classifications, then each device optimizes for its specific audio environment, but the user experiences conflicting or confusing stimuli
Solution Approach 1:
The patent implements a dynamic selection mechanism where the hearing prosthesis chooses between different scene classifications based on confidence values. The system doesn't rigidly stick to one device's classification nor does it constantly average them; instead, it dynamically selects the classification with the higher confidence value. This dynamic approach allows the system to optimize sound processing for the most reliable scene classification while avoiding the harmful effect of using conflicting classifications simultaneously.
Data Source
AI summary
Disclosed herein are methods, systems, and devices for selecting a scene classification for the operation of a sensory prosthesis, such as a hearing prosthesis. A system of two or more sensory prostheses can receive respective inputs from the environment of a recipient. A scene classification can then be determined for each sensory prosthesis based on the audio input received by each hearing prosthesis. A confidence value can also be determined for each scene classification. A scene classification can then be selected for each sensory prosthesis, from the determined scene classifications, based on the determined confidence values. Such operation can allow each sensory prosthesis to operate according to a respective selected scene classification that could be the same or that could be different from scene classifications selected for other sensory prostheses of the system.