Voice Energy Detection Circuit Dynamic Oversampling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing voice energy detection systems face challenges in accurately detecting human speech while minimizing false alarms and power consumption, particularly in noisy environments, due to limitations in signal-to-noise ratio and dynamic adaptation to background noise levels.
Innovation Solution
A voice energy detection system that assigns a VED circuit to each microphone, dynamically combines the output of multiple VEDs to improve detection probability and reduce false alarms, and adjusts the oversampling ratio and passband bandwidth based on background noise and signal levels, using a digital VED algorithm to optimize power usage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the oversampling ratio is increased to improve detection accuracy and signal-to-noise ratio, then detection precision is improved, but power consumption increases
Solution Approach 1:
The patent applies dynamic adjustment of the oversampling ratio based on detected voice energy levels and background noise conditions. The system transitions from fixed high oversampling to variable oversampling ratios, reducing the ratio when voice energy is low or background noise is high, thereby optimizing detection accuracy while minimizing power consumption during different operational states.
Solution Approach 2:
The system dynamically changes the oversampling ratio parameter as a function of voice energy detection results and background noise levels. By adjusting this critical parameter based on real-time acoustic conditions, the system achieves optimal detection precision only when necessary, reducing overall power consumption while maintaining measurement accuracy during critical detection moments.
2Reliability
If multiple VED circuits are combined to improve detection probability and reduce false alarms, then reliability is improved, but device complexity increases
Solution Approach 1:
The patent combines multiple voice energy detection circuits into a unified detection system that processes signals from multiple microphones. By merging the outputs of individual VED circuits through a combination logic unit, the system improves detection probability and reduces false alarms while managing complexity through integrated architecture rather than separate independent systems.
Solution Approach 2:
The combined VED system serves multiple functions simultaneously: it processes signals from multiple microphones, performs individual voice energy detection on each channel, combines results to improve detection reliability, and adapts oversampling ratios based on aggregate energy levels. This multi-functionality reduces the need for separate dedicated circuits for each function, managing overall system complexity.
3Use of energy by moving object
If the oversampling ratio is reduced to save power in noisy environments, then power consumption is reduced, but detection precision deteriorates
Solution Approach 1:
The system employs feedback from the voice energy detection results and background noise level measurements to dynamically adjust the oversampling ratio. When background noise is high or voice energy is low, the feedback mechanism reduces the oversampling ratio to save power. When voice energy exceeds background noise by a threshold margin, the feedback increases oversampling to maintain detection precision, creating a closed-loop adaptive system.
Solution Approach 2:
The oversampling ratio transitions from a static fixed value to a dynamic parameter that adapts to real-time acoustic conditions. The system dynamically adjusts the ratio based on the relationship between detected voice energy and background noise levels, reducing oversampling during low-signal or high-noise conditions to conserve power while maintaining adequate precision during favorable acoustic conditions.
Data Source
AI summary
A system uses a voice energy detection (VED) circuit along with a capture buffer for improved performance and lower power dissipation. With a VED assigned to each microphone in the system, combing the output of more than one VED to improve the detection probability or reduce the false alarm rate improves the post detection signal-to-noise ratio. One or more VED circuits are dynamically selected based on background energy and detection performance. Further, a digital VED algorithm dynamically changes the oversampling ratio (OSR) values and passband bandwidth as a function of the loudness of the background noise and desired signal levels. If the desired signal or noise is strong, then the OSR is reduced to save power. If desired speech is detected, then the OSR value increases to get the target SNR for the remaining audio processing needs.