Speech Intelligibility Enhancement via Noise-Adaptive Voice Tags
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users of radios, especially first responders, face challenges in ensuring the intelligibility of transmitted speech due to ambient noise, which can lead to critical information being miscommunicated.
Innovation Solution
An audio device equipped with a microphone, transmitter, and controller that determines noise levels, selects voice tags based on ambient noise, and applies an intelligibility speech enhancement filter to improve speech clarity before transmission.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If speech is transmitted in noisy environments, then communication coverage is maintained, but speech intelligibility deteriorates
Solution Approach 1:
The system performs preliminary analysis of ambient noise levels and speech characteristics before transmission, selecting appropriate voice tags and enhancement filters in advance to maintain intelligibility under predicted noise conditions
Solution Approach 2:
The system dynamically changes transmission parameters including voice tag selection, enhancement filter characteristics, and processing intensity based on measured noise levels and speech intelligibility requirements
2Reliability
If speech enhancement processing is applied, then speech intelligibility is improved, but device complexity increases
Solution Approach 1:
The system applies partial enhancement processing by selecting from multiple voice tags with different enhancement levels and applying filters only when noise levels exceed thresholds, avoiding full processing in all conditions
Solution Approach 2:
The system uses pre-recorded voice tags as templates or copies of clear speech, comparing and matching incoming speech against these templates to enhance intelligibility without complex real-time processing
3Adaptability or versatility
If voice tags are selected based on noise level, then adaptability to environment is improved, but measurement precision requirements increase
Solution Approach 1:
The system pre-categorizes voice tags according to different noise level ranges and environmental conditions, allowing noise level measurement to be matched against predefined thresholds rather than requiring continuous precise measurement
Solution Approach 2:
The system replaces complex continuous noise measurement and analysis with discrete threshold-based classification, substituting precise continuous measurement with simpler categorical assessment
Data Source
AI summary
A device and method for adjusting speech intelligibility at an audio device is provided. The device comprises a microphone, a transmitter and a controller. The controller is configured to: determine a noise level at the microphone; select a voice tag, of a plurality of voice tags, based on the noise level, each of the plurality of voice tags associated with respective noise levels; determine an intelligibility rating of a mix of the voice tag and noise received at the microphone; and when the intelligibility rating is below a threshold intelligibility rating, enhance speech received the microphone based on the intelligibility rating prior to transmitting, at the transmitter, a signal representing intelligibility enhanced speech.