AR Glasses Speech Capture Using Dual Microphone Separation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional augmented reality glasses and smartphone speech-to-text apps struggle with accurately capturing desired speech in noisy environments, fail to suppress the wearer's own voice, and are cumbersome for users with hearing loss, especially under unfavorable conditions and complex user interactions.
Innovation Solution
An augmented reality device with dual microphone systems, one inwardly targeting the wearer and one outwardly targeting the non-wearer, processes signals to distinguish between the wearer's and non-wearer's speech, and displays real-time captions on a wearable display, optionally translating languages and capturing additional voice characteristics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional augmented reality glasses use single microphone system, then device complexity is reduced, but speech capture accuracy in noisy environments deteriorates
Solution Approach 1:
The audio capture system is segmented into multiple independent microphone systems (first microphone system and second microphone system) positioned at different locations. Each microphone system independently captures audio signals from different spatial directions, enabling the device to distinguish between wearer's voice and external speech through spatial separation and signal comparison.
2Ease of operation
If smartphone speech-to-text apps are used, then real-time captions are provided, but the wearer's own voice is not suppressed requiring manual holding of device
Solution Approach 1:
The augmented reality device performs self-service by automatically detecting and suppressing the wearer's own voice through comparison of signals from multiple microphone systems. The device independently determines which audio source to caption without requiring manual intervention, enabling hands-free operation while accurately capturing desired external speech.
3Reliability
If hearing aid devices use beamforming microphone arrays, then speech directionality is improved, but processing capability for severe hearing loss is inadequate
Solution Approach 1:
The patent extracts and separates the speech-to-text processing function from the hearing aid device itself, transferring it to an external computing device (smartphone or computer). The augmented reality glasses serve only as an audio capture and display interface, while the computationally intensive speech recognition and text generation are performed externally, reducing the processing burden on the wearable device.
Data Source
AI summary
A method and apparatus to assist people with hearing loss. An augmented reality device with microphones and a display captures speech of a person talking to the wearer of the device and displays real-time captions in the wearer's field of view, while optionally not captioning the wearer's own speech. The microphone system in this apparatus inverts the use of microphones in augmented reality devices by analyzing and processing environmental sounds while ignoring the wearer's own voice.