Hearing Aid Noise Reduction Using Compact Neural SNR Gain Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing hearing aids face challenges in providing mathematically optimal noise reduction solutions that are not well received in terms of loudness perception, and the computational limitations of hearing aids make it impractical to implement large neural networks for signal-to-noise ratio (SNR) to gain conversion.
Innovation Solution
The use of machine learning techniques, specifically neural networks, to determine gain based on signal-to-noise ratios, where the weights of the neural network are trained with a plurality of training signals, and the SNR-to-gain converter is optimized to manage computational load effectively.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If large neural networks are used for SNR to gain conversion, then noise reduction performance is improved, but computational load becomes too high for hearing aid implementation
Solution Approach 1:
The patent segments the neural network into a smaller architecture that can be implemented in hearing aids, dividing the computational task into manageable parts that fit within device constraints while maintaining essential noise reduction functionality
Solution Approach 2:
The patent changes key parameters of the neural network including architecture size, number of layers, and computational precision to reduce computational load while preserving adequate noise reduction performance for hearing aid applications
2Measurement precision
If mathematically optimal noise reduction solutions are applied, then noise reduction effectiveness is improved, but sound quality perception deteriorates
Solution Approach 1:
The patent applies different processing strategies to different frequency regions and time segments, using the neural network to adaptively adjust gain values locally rather than applying uniform noise reduction, thereby preserving natural sound quality while maintaining effectiveness
Solution Approach 2:
The system uses feedback mechanisms where the neural network continuously adapts gain values based on real-time SNR estimates and previous processing results, allowing optimization of both noise reduction effectiveness and sound quality through iterative adjustment
Data Source
AI summary
Disclosed herein embodiments of a hearing aid configured to be worn by a user at or in an ear or to be fully or partially implanted in the head at an ear of the user. The hearing aid can include an SNR estimator for providing a target signal-to-noisy ratio (SNR) estimate, wherein the target signal-to-noisy ratio is based on the ratio between target signal components and an input signal. In certain examples, the SNR estimator comprises a neural network, wherein the weights of the neural network have been trained with a plurality of training signals, and wherein the outputs of the neural network comprise complex valued gains, or separate real valued gains and real valued phases.