In-Ear Subvocalization Recognition via Vibration Sensing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing input methods, such as physical interaction and speech-based interfaces, face challenges in privacy and safety, as they either occupy users' hands or are audible, making them unsuitable for sensitive information input in certain situations.
Innovation Solution
An in-ear device equipped with sensors like microphones, accelerometers, and machine-learned subvocalization interpretation models that capture and interpret subvocalized utterances, allowing for hands-free, private data entry by converting in-ear phenomena into actionable commands or text.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If speech-based interface is used for data entry, then hands-free operation is achieved, but privacy is compromised because the interaction becomes audible to others
Solution Approach 1:
The patent replaces acoustic-based speech recognition with a mechanical/vibration-based detection system. Sensors detect vibrations of the vocal cords and surrounding tissues during subvocalization, converting the mechanical vibrations into digital signals for processing. This substitution eliminates the need for audible speech while maintaining the ability to recognize commands.
Solution Approach 2:
The patent introduces an intermediary detection layer between the user's vocal apparatus and the computing system. Instead of directly capturing audible speech waves, the system detects mechanical vibrations through the vocal tract and ear canal, serving as an intermediary that enables command recognition without producing audible output.
2Measurement precision
If physical input devices like keyboard and mouse are used, then data entry accuracy is maintained, but user convenience deteriorates due to hand occupation and visual attention requirements
Solution Approach 1:
The patent replaces mechanical input devices (keyboard, mouse, touchscreen) with a biological signal-based input system. By detecting vibrations from subvocalized speech through the ear canal, the system enables hands-free and eyes-free data entry, eliminating the need for physical interaction while maintaining command accuracy through sophisticated signal processing and machine learning models.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables private and safe hands-free data entry by interpreting subvocalized utterances, enhancing user privacy and reducing visual interface usage, thereby conserving computing resources.
Implementation Method 1
The at least one sensor can include one or more microphones that convert a sound wave located within an ear canal of the ear of the user to the sensor data. The sound wave located within the ear canal of the user can be generated by an eardrum of the user.
Data Source
AI summary
Provided is an in-ear device and associated computational support system that leverages machine learning to interpret sensor data descriptive of one or more in-ear phenomena during subvocalization by the user. An electronic device can receive sensor data generated by at least one sensor at least partially positioned within an ear of a user, wherein the sensor data was generated by the at least one sensor concurrently with the user subvocalizing a subvocalized utterance. The electronic device can then process the sensor data with a machine-learned subvocalization interpretation model to generate an interpretation of the subvocalized utterance as an output of the machine-learned subvocalization interpretation model.