Hearing System Acoustic Scene Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Modern hearing aid devices require manual program switching, which can be cumbersome and does not always optimize speech intelligibility, as users struggle to determine the best hearing program for varying acoustic environments.
Innovation Solution
A hearing system that automatically adapts to acoustic environments by using directional information linked with sound characterization data to adjust transfer function parameters, allowing for improved recognition and localization of sound sources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If manual program switching is implemented in hearing aid devices, then users can select different hearing programs for different acoustic environments, but the operation becomes cumbersome and users cannot easily determine the optimal program for each situation
Solution Approach 1:
The hearing device automatically performs acoustic scene classification and transfer function selection without user intervention. The device serves itself by continuously analyzing the acoustic environment through microphones, processing the signals through classification algorithms, and automatically switching between pre-programmed transfer functions based on the detected acoustic scene, thereby eliminating the need for manual program switching while maintaining adaptability to different environments
Solution Approach 2:
The system continuously monitors the acoustic environment through microphones and uses the classification results to automatically adjust the transfer function. This closed-loop feedback mechanism allows the device to adapt to changing acoustic conditions in real-time, providing the adaptability of multiple programs without requiring manual operation from the user
2Measurement precision
If acoustic scene classification is performed without directional information, then the classification process is simpler, but the accuracy of sound source recognition and localization is reduced
Solution Approach 1:
The classification system is divided into independent modules: acoustic signal acquisition through microphones, directional information extraction through beamforming or TDOA algorithms, sound characterization through feature extraction, and final scene classification. This segmentation allows each module to be optimized independently and facilitates the integration of directional information without overwhelming complexity in the overall system
Solution Approach 2:
The system adds the spatial dimension to acoustic scene classification by incorporating directional information from multiple microphones. Instead of classifying based solely on acoustic characteristics, the system now operates in a multi-dimensional space that includes both acoustic features and spatial coordinates, enabling more accurate sound source localization and recognition while maintaining manageable system complexity through modular architecture
3Extent of automation
If automatic acoustic scene recognition is implemented, then program switching becomes automated, but the system complexity increases and reliability of classification may be insufficient in certain situations
Solution Approach 1:
Multiple transfer functions are pre-programmed into the hearing device, each optimized for specific acoustic scenes (e.g., quiet environment, noisy environment, speech-heavy environment). The classification algorithms are also pre-trained to recognize characteristic patterns of different acoustic scenes. This preliminary preparation allows the automated system to reliably match current acoustic conditions with the most appropriate pre-configured transfer function, enhancing both automation and reliability
Solution Approach 2:
The system adjusts classification parameters and decision thresholds based on the specific acoustic conditions detected. By dynamically changing the parameters used in scene classification (such as sensitivity thresholds, feature weighting, or confidence levels), the system can maintain high reliability across different acoustic environments while fully automating the program switching process
Data Source
AI summary
The invention relates to a method for operating a hearing system comprising an input unit, an output unit and a transmission unit operationally interconnecting said input output units. Said transmission unit implements a transfer function describing, how audio signals generated by said input unit are processed in order to derive audio signals fed to said output unit, and can be adjusted by one or more transfer function parameters. Said method comprises obtaining, by means of said input unit and with a first directional characteristic, first audio signals from incoming acoustic sound; deriving from said first audio signals a first set of sound-characterizing data; and deriving, in dependence offirst directional information, which is data comprising information on said first directional characteristic, and ofsaid first set of sound-characterizing data,a value for each of said one or more transfer function parameters. This allows to gain insight into the acoustic environment and allows for better automatic adjustments of said transfer function.