Earphone Voice Activity Detection Using Dual-Microphone Ratio Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Robust voice activity detection in noisy environments is challenging for small ear-mounted devices, often resulting in false positives and false negatives due to reliance on fixed thresholds.
Innovation Solution
A method using two microphones, one ambient and one ear-canal, with band limiting or band pass filtering, and calculating time-weighted ratios to adjust gain dynamically based on the absolute difference between these ratios, with threshold settings that can be fixed or dependent on the slow time weighted average, and optionally using Singular Value Decomposition or neural nets for voice activity determination.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If fixed thresholds are used for voice activity detection, then the system is simple to implement, but false positives and false negatives increase in noisy environments
Solution Approach 1:
The patent applies dynamics by transitioning from fixed thresholds to dynamically adaptive thresholds that automatically adjust based on environmental noise conditions. The system continuously monitors noise levels and modifies detection thresholds in real-time, enabling reliable voice activity detection across varying acoustic environments without requiring manual recalibration or complex configuration.
Solution Approach 2:
The patent implements parameter changes by modifying detection threshold values based on measured noise characteristics. The system calculates noise power spectral density and adjusts detection parameters accordingly, allowing the detector to adapt to different noise conditions (e.g., quiet offices, noisy streets, windy environments) while maintaining high detection accuracy.
2Measurement precision
If dynamic gain adjustment is implemented, then voice activity detection accuracy improves, but energy consumption increases
Solution Approach 1:
The patent applies partial action by implementing selective processing where the computationally intensive adaptive threshold calculation and dynamic gain adjustment are performed only when needed - specifically when noise levels exceed certain criteria or when voice activity is detected. During quiet periods or when confidence is high, the system uses simpler detection paths, reducing overall processor workload and energy consumption while maintaining detection accuracy when it matters most.
Data Source
AI summary
An electronic device or method for adjusting a gain on a voice operated control system can include one or more processors and a memory having computer instructions. The instructions, when executed by the one or more processors causes the one or more processors to perform the operations of receiving a first microphone signal, receiving a second microphone signal, updating a slow time weighted ratio of the filtered first and second signals, and updating a fast time weighted ratio of the filtered first and second signals. The one or more processors can further perform the operations of calculating an absolute difference between the fast time weighted ratio and the slow time weighted ratio, comparing the absolute difference with a threshold, and increasing the gain when the absolute difference is greater than the threshold. Other embodiments are disclosed.