Hearing Prosthesis Noise Suppression Using Confidence-Based Signal Control

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional hearing prostheses struggle to effectively distinguish target sounds from ambient noise, impairing speech understanding in noisy environments.

Innovation Solution

A noise reduction process that generates noise component estimates with associated confidence measures, using signal-to-noise ratio (SNR) estimation and gain application to enhance speech perception by aggressively reducing noise while maintaining distortion control.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If noise reduction processing is applied to enhance speech perception, then speech understanding improves, but signal distortion increases

Engineering Contradiction:

Improvespeech perceptionVSAvoidsignal distortion

Core Design Contradiction:

ReliabilityVSManufacturing precision

Solution Approach 1:

The system dynamically adjusts noise reduction parameters based on confidence measures. When confidence in noise estimation is high, more aggressive noise reduction is applied; when confidence is low, less processing is applied to preserve signal quality. This adaptive parameter adjustment resolves the contradiction by optimizing the trade-off between noise suppression and signal preservation based on real-time confidence assessment.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The system uses confidence measures as feedback to control the degree of noise reduction applied. The confidence measure continuously monitors the reliability of noise estimates and adjusts processing intensity accordingly, creating a closed-loop system that balances speech enhancement with distortion control.

Inventive Principle:

Principle #23Feedback

2Object-affected harmful factors

If aggressive noise removal is applied, then noise suppression improves, but speech signal integrity deteriorates

Engineering Contradiction:

Improvenoise suppressionVSAvoidspeech signal integrity

Core Design Contradiction:

Object-affected harmful factorsVSLoss of information

Solution Approach 1:

The system applies partial noise removal based on confidence levels rather than uniform aggressive processing. When confidence is high, more aggressive removal is applied; when confidence is low, minimal processing is applied. This partial action approach prevents over-processing and preserves speech signal integrity while still achieving effective noise suppression in high-confidence scenarios.

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

Different degrees of noise reduction are applied to different frequency components and time segments based on local confidence measures. High-confidence regions receive aggressive noise suppression, while low-confidence regions receive minimal processing to preserve signal integrity, creating locally optimized processing that balances noise removal with speech preservation.

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS12380907B2Sound processing with increased noise suppression

Publication Date: 2025.08.05 COCHLEAR LIMITED

AI summary

A method for processing sound that includes, generating one or more noise component estimates relating to an electrical representation of the sound and generating an associated confidence measure for the one or more noise component estimates. The method further comprises processing based on the confidence measure, the sound.