Real-Time Audio Quality Estimation Using Factor-Based MOS Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for estimating audio quality in real-time communications are limited, particularly in their ability to extend to new sources of distortion, require expertise, and lack real-time capabilities, with existing models like the E-model being offline-focused and requiring reference signals not always available.
Innovation Solution
A technique that generates real-time measurements of audio quality factors, assigns separate Mean Opinion Score (MOS) values to each factor, combines these values to produce an overall quality measure, and provides remedial actions through a server apparatus connected to computing devices, enabling easy application and extension to new distortion sources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If the E-model is used for estimating audio quality, then offline network planning capability is provided, but real-time measurement capability and ease of use are lost
Solution Approach 1:
The patent replaces complex manual audio quality assessment methods (E-model, MOS testing) with an automated electronic system that continuously measures multiple audio factors and computes quality metrics in real-time. The system substitutes human expertise and manual planning with algorithmic processing of audio signals, enabling both real-time measurement and ease of use simultaneously.
Solution Approach 2:
The system performs self-assessment of audio quality by automatically measuring audio factors, computing MOS values, and identifying degradation sources without requiring external human intervention or reference signals. The communication device itself serves as both the subject and object of quality assessment, enabling real-time self-monitoring.
2Adaptability or versatility
If conventional audio quality estimation methods are used, then existing audio distortions can be assessed, but extension to new distortion sources is difficult
Solution Approach 1:
The patent segments audio quality assessment into multiple independent audio factors (signal-to-noise ratio, distortion, packet loss, etc.), each measured separately and contributing to the overall quality metric. This modular segmentation allows new distortion sources to be added by introducing new factor measurements without redesigning the entire assessment system.
Solution Approach 2:
The system employs a universal measurement framework that can assess various types of audio degradation through a common set of audio factors and MOS computation methods. The same computational infrastructure handles different distortion sources uniformly, enabling easy extension to new distortion types while maintaining system simplicity.
3Measurement precision
If reference signals are used for quality assessment, then accurate quality measurement is achieved, but real-time application is limited due to unavailability of reference signals
Solution Approach 1:
The patent extracts quality assessment capability from the reference signal dependency, creating a method that measures audio factors directly from the transmitted signal itself. By removing the reference signal requirement, the system achieves both accurate measurement and real-time capability, as the assessment can be performed on the actual communication signal without needing a separate reference.
Solution Approach 2:
Instead of comparing the transmitted signal against a reference signal to assess quality, the system inverts the approach by measuring audio factors directly from the transmitted signal and computing quality metrics from these measurements. This inversion eliminates the reference signal requirement while maintaining measurement accuracy.
Data Source
AI summary
A technique for estimating and enhancing audio quality in a real-time communication session between parties over a computer network produces real-time measurements of factors that are known to impact audio quality, assigns a separate MOS value to each of the measured factors, and combines the MOS values for the various factors to produce an overall measure of audio quality. At least one party to the real-time communication session operates a computing device that runs a software program, and the technique further includes directing the software program to render an indication of the overall audio quality, thereby enabling the party operating the computing device to take remedial action to improve the audio quality.