EMG Inner Speech Filtering for Eye Blink Interference Removal
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing EMG speech systems face accuracy issues due to interference from involuntary gestures like eye blinks, which reduce the efficiency of detecting inner speech, and require overt physical movements for communication, leading to privacy concerns and resource inefficiency.
Innovation Solution
An EMG communication device filters out interfering components such as eye blinks from EMG signals using independent component analysis, regenerates filtered signals, and synthesizes inner speech into audible or visual outputs for messaging applications without requiring overt muscle movements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If EMG signals are used to detect inner speech, then communication efficiency is improved, but accuracy deteriorates due to interference from involuntary gestures like eye blinks
Solution Approach 1:
The patent applies Independent Component Analysis (ICA) to decompose the mixed EMG signal into separate independent components, each representing different muscle sources. This segmentation allows the system to identify and isolate speech-related components from interference components like eye blinks, thereby maintaining both communication efficiency and detection accuracy.
Solution Approach 2:
The system extracts and removes interfering components (eye blink signals) from the EMG signal while retaining the useful speech-related components. This extraction process eliminates the harmful interference without losing the valuable inner speech information, resolving the contradiction between efficiency and accuracy.
2Measurement precision
If overt physical movements are required for communication, then detection accuracy is improved, but privacy concerns and resource consumption increase
Solution Approach 1:
The patent replaces the need for overt mechanical speech production with detection of subtle muscle activation signals using EMG sensors. This substitution allows users to communicate through inner speech without visible facial movements, reducing resource consumption while maintaining detection accuracy through signal processing techniques.
3Reliability
If overt physical movements are used for communication, then reliability is improved, but ease of operation deteriorates due to privacy concerns
Solution Approach 1:
The EMG sensors and signal processing system act as an intermediary that enables reliable communication without requiring overt physical movements. This intermediary layer preserves user privacy by detecting subtle muscle signals that are not visible to others, while still providing reliable communication through accurate speech detection.
Data Source
AI summary
Systems and methods are provided for performing operations comprising: detecting, by a plurality of electromyograph (EMG) electrodes of an EMG communication device, subthreshold muscle activation signals of one or more muscles associated with speech production, the subthreshold muscle activation signals being generated in response to inner speech of a user; applying a transform to the subthreshold muscle activation signals detected by the plurality of EMG electrodes to represent the subthreshold muscle activation signals as a plurality of maximally independent components; accessing an interference template corresponding to an eye blink component; filtering the plurality of maximally independent components based on the interference template to provide filtered maximally independent components; and regenerating a filtered version of the subthreshold muscle activation signals based on the filtered maximally independent components.