Speech Intelligibility Monitoring in Noisy Reverberant Spaces
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing audio announcement systems in environments like sports stadiums and buildings often produce speech that is loud but unintelligible due to acoustical characteristics, necessitating improved methods for measuring and enhancing speech intelligibility, especially in dynamic spaces with changing conditions.
Innovation Solution
The system employs acoustic sensors to evaluate audio outputs, quantify intelligibility, and apply remediation by adjusting speech parameters such as tempo, frequency bands, and sound pressure level, using digital signal processors to shape signals and ensure compliance with performance-based standards for speech intelligibility.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Illumination intensity
If speech is projected into a region by an audio announcement system, then the speech becomes audible, but the speech may become unintelligible due to acoustical characteristics of the space
Solution Approach 1:
The system measures acoustic parameters (reverberation time, background noise levels, frequency response) and dynamically adjusts speech projection parameters (tempo, frequency bands, sound pressure level) to optimize intelligibility while maintaining audibility in the specific acoustic environment
Solution Approach 2:
The system uses acoustic sensors to continuously monitor the acoustic environment and provides real-time feedback to adjust speech projection parameters, creating a closed-loop system that adapts to changing acoustic conditions to maintain both audibility and intelligibility
2Illumination intensity
If the audio announcement system increases sound pressure level to ensure speech is heard, then audibility improves, but speech intelligibility degrades in reverberant and noisy spaces
Solution Approach 1:
Instead of simply increasing overall sound pressure level, the system selectively adjusts frequency bands to enhance speech intelligibility while controlling reverberation effects, and modifies tempo to allow sufficient decay time for speech to become inaudible before the next word
Solution Approach 2:
The system dynamically adjusts speech projection parameters based on real-time acoustic measurements, adapting the balance between loudness and intelligibility to the specific acoustic conditions rather than using fixed settings
3Loss of information
If the system applies remediation to improve speech intelligibility by adjusting speech parameters, then intelligibility improves, but system complexity increases
Solution Approach 1:
The system performs preliminary acoustic measurements during installation to characterize the space's acoustic properties, storing this information for use in real-time speech projection without requiring complex real-time analysis of all acoustic parameters
Solution Approach 2:
The system focuses on adjusting a limited set of critical speech projection parameters (tempo, frequency bands, sound pressure level) rather than attempting to control all acoustic variables, simplifying the processing requirements while maintaining effectiveness
Data Source
AI summary
A system and method to detect and remediate unacceptable levels of speech intelligibility evaluates received test audio transmitted across and received in a space or region of interest. Intelligibility is improved by altering the rate, pitch, amplitude and frequency bands energy during presentation of the speech signal.