Automatic Speech Intelligibility Optimization for Hearing Loss
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Hard of hearing users in telecommunication systems often fail to achieve optimal speech intelligibility when self-adjusting audio characteristics, as they tend to prioritize aesthetic quality over intelligibility, and common audio distortions require individualized mitigation strategies that go beyond simple spectral compensation.
Innovation Solution
An automatic user-specific, condition-specific intelligibility testing and optimization system that administers interactive voice response tests to identify patterns in a user's ability to discriminate between speech sounds, allowing for automatic adjustments to the speech signal, including spectral shaping and frame modifications, to maximize intelligibility.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If users self-adjust audio characteristics using tone controls or graphic equalizers, then aesthetic quality of voice is improved, but speech intelligibility deteriorates
Solution Approach 1:
The system allows users to self-adjust audio characteristics through automated intelligibility testing rather than manual tone control adjustment. The user completes an intelligibility test and the system automatically generates optimized spectral shaping parameters specific to that user's hearing loss pattern, eliminating the need for users to manually balance aesthetic quality against intelligibility.
Solution Approach 2:
The system uses feedback from intelligibility test results to automatically adjust spectral shaping parameters. By measuring the user's specific intelligibility deficits through standardized tests and using that feedback to generate personalized compensation curves, the system ensures intelligibility is maximized while maintaining aesthetic quality through automated optimization.
2Ease of operation
If simple spectral compensation is applied, then ease of operation is improved, but effectiveness in mitigating audio distortions deteriorates
Solution Approach 1:
The system automatically changes multiple audio parameters including spectral shaping curves, compression ratios, expansion factors, and noise gating thresholds based on the user's intelligibility test results and the specific communication conditions. This automated parameter optimization provides comprehensive distortion mitigation that goes far beyond simple spectral compensation while remaining easy to operate.
Solution Approach 2:
The system dynamically adjusts audio processing parameters based on real-time conditions including the user's specific hearing loss pattern, the type of audio distortion present (compression, packet loss, noise), and the communication environment. This dynamic adaptation allows effective mitigation of various audio distortions while maintaining ease of operation through automated control.
3Reliability
If individually administered intelligibility tests are used, then speech intelligibility is improved, but time consumption and system complexity increase
Solution Approach 1:
The system performs intelligibility testing and spectral shaping optimization as a preliminary action during initial device setup or during scheduled optimization sessions. By completing the intelligibility assessment and generating personalized compensation parameters in advance, the system ensures optimal speech intelligibility is established before regular communication use begins, minimizing time loss during actual communication.
Solution Approach 2:
The system enables users to self-administer intelligibility tests through automated interactive voice response protocols, eliminating the need for audiologist intervention. The user completes standardized intelligibility tests through the communication device itself, and the system automatically processes the results to generate optimized audio parameters, significantly reducing both time and complexity compared to traditional clinical testing.
Data Source
AI summary
Systems and methods for automatic user specific, condition specific communication system intelligibility testing and optimization are provided. The intelligibility of speech for a particular user is determined using a test of intelligibility administered by an interactive voice response (IVR) application running on a communication server. The intelligibility test can be run for a particular user under different conditions. For each user and/or set of conditions, a set of speech signal adjustment parameters can be determined. A set of speech signal adjustment parameters that will enhance the intelligibility of a speech signal for a user are applied when that user is involved in a communication session. The particular set of speech signal adjustment parameters selected can depend on the communication equipment and/or environment associated with the communication session.