Hearing Device Listening-State Detection Using Motion And Own-Voice Data

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional hearing devices lack the ability to estimate a user's listening state and adjust operations accordingly, which is crucial for enhancing hearing and detecting potential health risks.

Innovation Solution

A hearing device system that determines a user's listening state through motion and own-voice data, allowing it to adjust sound processing properties, such as gain, volume, and beamforming, based on the user's attention and comprehension of speech.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a hearing device provides audio content to the user without monitoring listening state, then the device structure remains simple, but the hearing enhancement effectiveness is insufficient

Engineering Contradiction:
Improvehearing enhancement effectivenessVSAvoiddevice structure
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The hearing device automatically monitors the user's listening state using onboard sensors (accelerometer, microphone) and processors without requiring external equipment or manual input. The system self-adjusts sound processing properties based on detected head movements and speech patterns, enabling autonomous optimization of hearing enhancement effectiveness.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system continuously monitors listening state through motion sensors and audio sensors, feeds this information back to the processor, which then adjusts sound processing properties in real-time. This closed-loop feedback mechanism ensures hearing enhancement effectiveness adapts dynamically to the user's actual listening state.

Inventive Principle:
Principle #23Feedback

2Reliability

If a hearing device monitors user listening state using motion and voice data, then hearing enhancement effectiveness is improved, but device complexity increases

Engineering Contradiction:
Improvelistening state estimation accuracyVSAvoidsensor and processing requirements
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The hearing device uses a multi-functional processor that handles both traditional audio processing and the new listening state monitoring functions. The same processor analyzes motion data from accelerometers, processes audio from microphones, and adjusts sound output properties, eliminating the need for separate dedicated monitoring hardware and reducing overall device complexity.

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

Solution Approach 2:

The system uses existing audio processing components and motion sensors as intermediaries to infer listening state without requiring direct neural or physiological sensors. By analyzing head movements and speech patterns through standard sensors, the system achieves accurate listening state estimation while avoiding the complexity of specialized biomedical sensors.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Reliability

If a hearing device adjusts sound processing properties dynamically, then hearing enhancement effectiveness is improved, but energy consumption increases

Engineering Contradiction:
Improveadaptive hearing enhancementVSAvoidenergy consumption
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system performs listening state monitoring and sound processing adjustments at periodic intervals rather than continuously. The processor evaluates motion and audio data at defined sampling rates, making discrete adjustments to sound properties when changes in listening state are detected, thereby reducing overall energy consumption while maintaining adaptive hearing enhancement effectiveness.

Inventive Principle:
Principle #19Periodic action

Data Source

PatentEP4626039A1Hearing device-based systems and methods for monitoring a listening state of a user
Publication Date: 2025.10.01 SONOVA AG
  • EP4626039A1 patent drawingFigure 1
  • EP4626039A1 patent drawingFigure 2
  • EP4626039A1 patent drawingFigure 3

AI summary

An illustrative hearing device may receive, from an input transducer (106), audio data (408) including one or more speech signals representative of a speech from one or more speech sources different from the user; acquire one or more of: motion data (410) representative of head movements of the user while the user wears the hearing device; or own-voice data included in the audio data (408), the own voice data representative of an own-voice activity of the user. To allow taking into account the user's listening state when operating the hearing device, the disclosure proposes to determine, based on at least one of the motion data (410) or the own-voice data, a listening state of the user with respect to the one or more speech signals, the listening state comprising information about whether or to which degree the user is paying attention to one or more of the speech sources; and/or information about whether or to which degree the user comprehends the speech in one or more of the speech signals; and perform, based on the listening state, an operation associated with the hearing device.