Neural Network Hearing Aid With Dual-Path Speech Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional hearing aids struggle to effectively separate speech from background noise in noisy environments due to limitations in computational power and the inability to adapt to varying acoustic environments, leading to decreased speech intelligibility for individuals with hearing loss.
Innovation Solution
A dual-path signal processing system in hearing aids that integrates a neural network engine (NNE) and a digital signal processor (DSP), allowing selective engagement of neural network-based audio enhancement, with a controller determining the processing path based on user inputs, environmental factors, and sensor data to optimize sound isolation and ambient noise levels.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Use of energy by moving object
If traditional hearing aids use amplification to offset decreased volume sensitivity, then volume sensitivity is improved, but speech intelligibility in noisy environments deteriorates because amplification cannot selectively attend to desired sounds
Solution Approach 1:
The patent segments the audio signal into multiple frequency bands using filter banks, allowing independent processing of different frequency components. This enables selective enhancement of speech frequencies while suppressing background noise in other bands, resolving the contradiction between amplification and noise suppression.
Solution Approach 2:
The patent applies different processing characteristics to different frequency bands - specifically applying greater amplification to speech-relevant frequencies while applying noise suppression algorithms selectively to bands containing background noise. This local differentiation allows simultaneous improvement of volume sensitivity and speech intelligibility.
2Loss of information
If traditional hearing aids use directional microphones and beamforming to increase signal-to-noise ratio, then speech intelligibility is improved, but reliability deteriorates because these methods rely on incorrect assumptions about speaker position and signal characteristics
Solution Approach 1:
The patent implements dynamic adaptation of processing parameters based on real-time environmental assessment. The system continuously monitors acoustic characteristics and adjusts filter bank parameters, amplification gains, and noise suppression strength accordingly, enabling reliable performance across diverse environments without relying on fixed assumptions about speaker position.
Solution Approach 2:
The patent changes processing parameters dynamically based on environmental conditions - adjusting the center frequencies and bandwidths of filter banks, modifying amplification gains per frequency band, and adapting noise suppression thresholds. These parameter changes enable the system to maintain speech intelligibility across varying acoustic environments.
3Loss of information
If neural networks are placed in the signal path of hearing aids to separate speech from background noise, then speech intelligibility is improved, but device complexity and power consumption increase due to limited battery capacity
Solution Approach 1:
The patent replaces complex neural network-based speech separation with a more computationally efficient filter bank approach. By using predefined frequency band filtering combined with adaptive amplification and noise suppression, the system achieves comparable speech intelligibility improvement with significantly reduced computational complexity and power consumption.
Solution Approach 2:
The patent employs computationally lightweight processing algorithms that can be executed efficiently on hearing aid hardware with limited battery capacity. The filter bank approach requires minimal computational resources compared to neural networks, enabling sustained operation throughout the day without frequent recharging.
4Loss of information
If neural networks are used to process audio in real-time, then speech separation is improved, but productivity deteriorates due to processing latency
Solution Approach 1:
The patent segments the audio signal into short time frames processed independently through the filter bank. This frame-based processing allows rapid computation of each segment with minimal cumulative latency, while maintaining accurate speech separation through the frequency-domain analysis capability of the filter bank approach.
Data Source
AI summary
The disclosure generally relates to a method, system and apparatus to improve a user's understanding of speech in real-time conversations by processing the audio through a neural network contained in a hearing device. The hearing device may be a headphone or hearing aid. In one embodiment, the disclosure relates to an apparatus to enhance incoming audio signal. The apparatus includes a controller to receive an incoming signal and provide a controller output signal; a neural network engine (NNE) circuitry in communication with the controller, the NNE circuitry activatable by the controller, the NNE circuitry configured to generate an NNE output signal from the controller output signal; and a digital signal processing (DSP) circuitry to receive one or more of controller output signal or the NNE circuitry output signal to thereby generate a processed signal; wherein the controller determines a processing path of the controller output signal through one of the DSP or the NNE circuitries as a function of one or more of predefined parameters, incoming signal characteristics and NNE circuitry feedback.