Inter-channel Level Difference Tap Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electronic devices face challenges in accurately detecting tap events on surfaces using microphone audio data, often resulting in false positives due to noise and wind interference, which complicates user interactions and command recognition.
Innovation Solution
The system employs a method to detect tap events by analyzing inter-channel level differences between multiple microphones and combines audio data with motion data from accelerometers, using a trained model to confirm actual device movement and reduce false positives.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If tap detection is performed using only microphone audio data, then the detection process is simple, but false positives occur due to noise and wind interference
Solution Approach 1:
The patent combines audio data from multiple microphones with motion data from accelerometers to detect tap events. This merging of multiple data sources allows the system to distinguish between actual taps and environmental noise/wind by cross-validating signals from different sensors, thereby improving detection reliability without significantly increasing system complexity
Solution Approach 2:
The patent introduces a trained machine learning model as an intermediary between raw sensor data and tap detection decisions. This model processes and interprets the combined audio and motion data, enabling accurate differentiation between taps and false positive sources while maintaining a relatively simple overall system architecture
2Measurement precision
If multiple microphones are used to analyze inter-channel level differences, then tap detection accuracy improves, but device complexity increases
Solution Approach 1:
The patent utilizes inter-channel level difference (ILD) as a key parameter to detect taps. By analyzing the difference in audio signal levels between multiple microphones, the system can identify tap events with high precision. This approach leverages existing microphone arrays and processes their output through established signal processing techniques, avoiding the need for complex additional hardware while achieving accurate tap detection
3Reliability
If motion data from accelerometers is combined with audio data, then false positives are reduced, but processing complexity increases
Solution Approach 1:
The patent employs a trained machine learning model that has been pre-trained to recognize patterns distinguishing taps from false positives. This preliminary training action allows the model to automatically interpret combined audio and motion data during operation, reducing the need for complex real-time processing algorithms while maintaining high reliability in false positive reduction
Data Source
AI summary
A system configured to detect a tap event on a surface of a device using microphone audio data and motion data. Instead of using a physical sensor to detect the tap event, the device detects a tap event based on a power level difference between two or more microphones. When a power ratio exceeds a threshold, the device may detect a tap event and perform an action, such as delaying or ending an alarm. To reduce false positives caused by wind or loud noises close to the microphones, the device may confirm a tap event using motion data that indicates actual movement of the device. In some examples, the device may detect the tap event using a neural network processing the microphone data and the motion data. In addition, the device may embed the motion data within the microphone data using unused bits of the microphone data.