Auditory Prosthesis Speech Control for Discreet Audio Adjustment

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Individuals with auditory prostheses face challenges in adjusting device settings discreetly and effectively in various sound environments, particularly in noisy settings like cocktail parties or sports arenas, without drawing attention to themselves.

Innovation Solution

An auditory control system that detects natural language indicators, such as 'excuse me?' or 'pardon me?', during conversations to automatically adjust audio settings, using speech recognition algorithms and environmental classification to optimize sound processing without requiring manual intervention.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If manual adjustment controls are provided on auditory prostheses, then ease of operation is improved, but device complexity and obtrusiveness increase

Engineering Contradiction:

Improveadjustment controlVSAvoidcontrol mechanism

Core Design Contradiction:

Ease of operationVSDevice complexity

Solution Approach 1:

The auditory prosthesis automatically adjusts its own audio settings by detecting control expressions in the user's speech during conversations, eliminating the need for manual controls. The system monitors the user's spoken phrases and autonomously modifies program selections based on the detected expressions.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces physical mechanical controls with an acoustic detection system that uses speech recognition algorithms to identify control expressions in the user's voice, substituting manual mechanical adjustment with automated acoustic-based control.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Adaptability or versatility

If manual adjustment is required in noisy environments, then adaptability is improved, but loss of time and ease of operation deteriorate

Engineering Contradiction:

Improveenvironmental adaptationVSAvoidadjustment time

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The system performs preliminary detection of control expressions during conversation to anticipate and prepare for upcoming environmental changes, allowing the auditory prosthesis to proactively adjust settings before the user would need to manually intervene.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system continuously monitors the user's speech for control expressions and uses this feedback to automatically adjust program selections in real-time, creating a closed-loop system that adapts to environmental changes based on user needs detected through speech patterns.

Inventive Principle:

Principle #23Feedback

3Ease of operation

If speech recognition is used for control, then ease of operation is improved, but device complexity and energy consumption increase

Engineering Contradiction:

Improvecontrol methodVSAvoidprocessing energy

Core Design Contradiction:

Ease of operationVSUse of energy by moving object

Solution Approach 1:

The system uses partial speech recognition by focusing specifically on detecting predetermined control expressions rather than performing full natural language processing. This selective approach reduces computational requirements and energy consumption while maintaining ease of operation for the specific control function.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS12350494B2Systems and methods for non-obtrusive adjustment of auditory prostheses

Publication Date: 2025.07.08 COCHLEAR LIMITED

AI summary

Systems and methods for performing non-obtrusive, automatic adjustment of an auditory prosthesis are disclosed. A control expression can be detected during a conversation. Upon detection of the control expression, an audio setting adjustment can be selected and applied to the auditory prosthesis. Multiple adjustments can be made in response to identifying multiple control expressions during a conversation.