Hearing System Own Voice Detection with Spectral Level Symmetry
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for detecting own voice content in hearing devices require specialized components and complex processing, leading to inefficient and resource-intensive operations.
Innovation Solution
A hearing system utilizing ipsilateral and contralateral microphones to determine sound pressure levels and symmetry levels of spectral portions of audio signals, combined with machine learning algorithms, to accurately identify own voice content without additional components.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional methods use specialized components and complex processing to detect own voice content, then detection accuracy is improved, but device complexity and computational requirements increase
Solution Approach 1:
The patent extracts the key identifying feature of own voice content - the spectral gap between low-frequency vocal tract resonance and high-frequency consonant energy - and uses this simplified characteristic for detection instead of complex processing. This allows accurate own voice detection using basic spectral analysis of existing microphone signals without additional specialized components.
Solution Approach 2:
The patent changes the detection parameter from complex signal processing metrics to a simple spectral energy ratio comparison. By analyzing the ratio of energy in low-frequency versus high-frequency bands, the system achieves accurate own voice detection using straightforward computational operations on standard audio signals.
2Measurement precision
If conventional methods use specialized components and complex processing to detect own voice content, then detection accuracy is improved, but computational power requirements increase
Solution Approach 1:
The patent extracts the key identifying feature of own voice content - the spectral gap between low-frequency vocal tract resonance and high-frequency consonant energy - and uses this simplified characteristic for detection instead of complex processing. This allows accurate own voice detection using basic spectral analysis of existing microphone signals without additional specialized components.
Solution Approach 2:
The patent changes the detection parameter from complex signal processing metrics to a simple spectral energy ratio comparison. By analyzing the ratio of energy in low-frequency versus high-frequency bands, the system achieves accurate own voice detection using straightforward computational operations on standard audio signals.
Data Source
AI summary
An exemplary hearing device is configured to determine a first and a second sound pressure level (SPL) of a first and second spectral portion, respectively, of an ipsilateral audio signal representative of audio content. The first and second spectral portions have frequencies included in a first and a second frequency range, respectively, with the second frequency range being higher than the first frequency range. The device may further determine that the first SPL is greater than the second SPL by at least a threshold SPL amount and determine that a symmetry level between the ipsilateral and a contralateral audio signal is at least a threshold symmetry level. Based on these determinations, the hearing device may determine that the audio content comprises own voice content.