Microphone Array Self-Check for Aberrant Voice Input Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network microphone devices in smart home systems may suffer from impaired performance due to hardware issues or obstructions, leading to aberrant audio signals that affect the accuracy of voice command processing.
Innovation Solution
A method and system for evaluating the frequency responses of individual microphones in an array to identify aberrant behavior by comparing them against a median or mean value, and taking corrective measures such as modifying operation or providing alerts to address defective microphones without sending recorded audio content.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If microphone performance is not monitored and corrected, then the system operates with potentially defective microphones, but voice command processing accuracy deteriorates
Solution Approach 1:
The system performs preliminary evaluation of microphone frequency responses by comparing them against median or mean values to identify aberrant behavior before it significantly impacts voice command processing accuracy. This proactive approach allows corrective measures to be taken in advance.
Solution Approach 2:
The system continuously monitors microphone performance by evaluating frequency responses and provides feedback when aberrant behavior is detected. This feedback mechanism enables the system to identify and address defective microphones, maintaining both reliability and processing accuracy.
2Measurement precision
If recorded audio content is sent for analysis, then comprehensive performance evaluation is possible, but user privacy is compromised
Solution Approach 1:
The system extracts only the necessary performance evaluation data (frequency response characteristics) from the audio signals while leaving the actual recorded audio content on the user's device. This extraction approach enables comprehensive performance evaluation without transmitting or storing private audio content.
Solution Approach 2:
The system uses an intermediary evaluation process that analyzes microphone performance locally on the user's device rather than sending audio content to remote servers. This intermediary approach maintains measurement precision while preserving user privacy by keeping sensitive audio data local.
3Productivity
If all microphones are used for processing, then the system operates at full capacity, but defective microphones cause aberrant audio signals
Solution Approach 1:
The system performs self-diagnosis by evaluating its own microphone performance and automatically identifies aberrant microphones through frequency response comparison. This self-service capability allows the system to maintain full operational capacity by excluding only the specific defective microphones from processing.
Solution Approach 2:
The system applies local quality control by evaluating each microphone's frequency response individually and identifying aberrant behavior in specific microphones rather than treating all microphones uniformly. This allows the system to maintain high audio signal quality by excluding only locally identified defective microphones while keeping other microphones operational.
Data Source
Figure 1
Figure 2A~2B
Figure 3A~3D
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.