Two-Microphone Audio Source Location Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining the spatial location of an audio source require multiple microphone arrays or sophisticated signal processing and machine learning techniques, which consume additional power and increase the cost of devices, making them inefficient for real-time applications.
Innovation Solution
The use of two microphones with a pre-determined acoustic barrier filter and a lightweight algorithm that calculates variability measures to form a feature vector, which is then input to a shallow neural network for location classification, enabling 360° audio source location detection with low computer overhead and no need for complex signal processing or additional hardware.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple microphone arrays are used to determine spatial location of audio source, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent uses a simplified two-microphone configuration that copies the essential functionality of complex multi-microphone arrays. By implementing a streamlined version with only two microphones positioned at specific locations, the system achieves adequate spatial location detection without the complexity of full arrays, directly resolving the contradiction between measurement precision and device complexity
Solution Approach 2:
The patent extracts only the essential components needed for spatial location detection from complex microphone arrays. Instead of using all microphones in a full array, it selects and utilizes just two strategically positioned microphones along with a simplified signal processing approach, thereby reducing device complexity while maintaining functional capability
2Measurement precision
If sophisticated signal processing and machine learning techniques are used, then measurement precision is improved, but use of energy increases
Solution Approach 1:
The patent employs computationally inexpensive signal processing techniques that can be executed quickly and discarded, rather than relying on energy-intensive sophisticated machine learning models. The simplified processing approach consumes minimal power while achieving the necessary detection accuracy, effectively resolving the energy consumption contradiction
Solution Approach 2:
The patent applies partial signal processing - using only the essential computations needed for spatial location detection rather than exhaustive sophisticated processing. This partial action approach achieves adequate precision without the excessive energy consumption of comprehensive machine learning techniques
3Measurement precision
If multiple microphone arrays and sophisticated processing are used, then measurement precision is improved, but productivity decreases due to real-time processing requirements
Solution Approach 1:
The patent segments the spatial location detection task into simpler sub-tasks that can be processed in real-time. By dividing the problem into manageable computational steps using only two microphones and basic signal processing, the system achieves both precision and real-time processing capability, resolving the contradiction between measurement precision and productivity
Data Source
AI summary
A system is described herein. The system includes at least one hardware processor that is configured to identify a pre-determined acoustic barrier filter, wherein the acoustic barrier filter coincides with the physical acoustic barrier and receive an audio signal within a time window at the first microphone and the second microphone. The hardware processor is also configured to calculate a first measure of variability, a second measure of variability, a third measure of variability, and a fourth measure of variability. The hardware processor further concatenates the first measure of variability, the second measure of variability, the third measure of variability, and the fourth measure of variability to form a feature vector, and inputs the feature vector into a location classifier to obtain an audio source location.