Ear-Worn Hearing Aid Neural Network Denoising Control

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Traditional hearing aids struggle to effectively separate speech from noise in noisy environments, leading to challenges in speech intelligibility for individuals with hearing loss.

Innovation Solution

A hearing aid system that includes a first hearing aid with non-programmable user input and neural network circuitry for denoising audio signals, and a processing device for managing the neural network's enabling and disabling based on user input.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional hearing aids amplify received sound, then hearing ability is improved, but speech intelligibility in noisy environments deteriorates

Engineering Contradiction:
Improvehearing abilityVSAvoidnoise interference
Core Design Contradiction:
ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The patent segments the audio signal processing into distinct functional components: traditional amplification for overall hearing improvement, and separate neural network-based denoising for speech intelligibility enhancement. This segmentation allows each component to address specific aspects of the hearing problem independently, resolving the contradiction between amplification and noise interference.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces neural network circuitry as an intermediary between the microphones and the audio output. This intermediary processes the amplified audio signals to separate and remove noise components while preserving speech, thereby maintaining the benefits of amplification while eliminating noise interference.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Object-affected harmful factors

If neural network circuitry is added for denoising, then speech intelligibility is improved, but device complexity increases

Engineering Contradiction:
Improvenoise reductionVSAvoidcircuitry complexity
Core Design Contradiction:
Object-affected harmful factorsVSDevice complexity

Solution Approach 1:

The patent merges the neural network circuitry with the existing hearing aid architecture, integrating denoising functionality into the audio processing pipeline. By combining multiple functions (amplification, denoising, speech enhancement) into a unified system, the patent reduces overall device complexity compared to having separate independent systems.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The hearing aid system is designed with multi-functional circuitry that performs both traditional amplification and neural network-based denoising through shared hardware resources. This universality allows a single device to address multiple hearing challenges simultaneously, reducing the need for additional specialized components.

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Adaptability or versatility

If user input device is made programmable, then adaptability is improved, but ease of operation deteriorates

Engineering Contradiction:
Improvefunction customizationVSAvoiduser programming difficulty
Core Design Contradiction:
Adaptability or versatilityVSEase of operation

Solution Approach 1:

The patent implements self-service programming where the hearing aid automatically configures and optimizes its own functions based on user interactions and environmental conditions. The device performs self-diagnosis and self-adjustment, eliminating the need for users to manually program complex parameters while maintaining high adaptability to different usage scenarios.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent incorporates feedback mechanisms where the hearing aid continuously monitors user responses and environmental conditions, then automatically adjusts its programming and parameters. This closed-loop feedback system enables the device to adapt to user needs without requiring manual reprogramming, maintaining ease of operation while achieving high versatility.

Inventive Principle:
Principle #23Feedback

Data Source

PatentUS20250080928A1Neural-network based denoising of audio signals received by an ear-worn device controlled based on activation of a user input device on the ear-worn device
Publication Date: 2025.03.06 FORTELL RESEARCH INC
  • US20250080928A1 patent drawing
  • US20250080928A1 patent drawing
  • US20250080928A1 patent drawing

AI summary

A hearing aid includes a non-programmable user input device that is not programmable by a user nor by an audiologist, control circuitry configured to receive an activation signal from the non-programmable user input device, one or more microphones, neural network circuitry configured to denoise audio signals received by the one or more microphones, and communication circuitry. The hearing aid is configured to detect, using the control circuitry, user activation of the non-programmable user input device on the hearing aid; control, using the control circuitry and based on detecting the activation of the non-programmable user input device on the hearing aid, switching between enabling and disabling the neural network circuitry; and transmit, using the communication circuitry, an indication of the enabling or disabling of the neural network circuitry to a processing device in operative communication with the hearing aid.