Microphone Array Self-Diagnosis for Aberrant Signal Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Individual microphones in network microphone devices may suffer from performance issues due to hardware problems or obstructions, leading to aberrant audio signals that impair the functionality of voice control systems, such as network microphone devices, by causing noise, distortion, or other artifacts that affect downstream processing.
Innovation Solution
The system evaluates the audio input from individual microphones by comparing their frequency responses to a median or mean value, identifying aberrant behavior by detecting deviations beyond a threshold, and takes corrective measures or alerts to address the issue, ensuring privacy by using frequency-domain data that does not reveal the original audio content.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the system continuously monitors and evaluates microphone performance data to detect aberrant behavior, then the reliability of voice control systems is improved, but the loss of information increases due to processing and transmitting performance data
Solution Approach 1:
The system extracts only the essential performance characteristics (frequency response deviations beyond threshold) from the complete microphone performance data, transmitting only this extracted information to the remote evaluator. This extraction approach maintains reliability by detecting aberrant behavior while minimizing information loss by not transmitting the entire raw data set.
2Object-affected harmful factors
If the system uses frequency-domain data for evaluation, then user privacy is protected, but the measurement precision of microphone performance detection may be reduced
Solution Approach 1:
The frequency-domain representation acts as an intermediary between the raw time-domain audio data and the performance evaluation process. This intermediary transformation protects user privacy by removing identifiable audio content while maintaining sufficient information to detect microphone aberrations through frequency response analysis and threshold comparisons.
3Ease of operation
If the system compares each microphone's frequency response to median or mean values and applies threshold detection, then the ease of operation is improved through automated detection, but the device complexity increases due to the evaluation and comparison mechanisms
Solution Approach 1:
The playback device performs self-diagnosis by automatically evaluating its own microphone performance data against predetermined thresholds and comparing frequency responses to median or mean values. This self-service approach improves ease of operation by eliminating manual microphone testing while the complexity is managed by implementing the evaluation logic within the device's existing processor and software architecture.
Data Source
AI summary
Systems and methods for determining and adapting to changes in microphone performance of playback devices are disclosed herein. In one example, an audio input is received at an array of individual microphones of a network microphone device. Output microphone signals are generated from each of the individual microphones based on the audio input. The output microphone signals are analyzed to detect a trigger event. After detecting the trigger event, the output microphone signals are compared to detect aberrant behavior of one or more of the microphones. Optionally, corrective actions can be taken or suggested based on the detection of aberrant behavior of one or more microphones.