IP Library Granted Patent US 12664912
Granted Patent B2
US 12664912 · App. 17/796,884 · Granted Jun 23, 2026

Methods and systems to facilitate silent communication

Inventors: Caitlyn Seim (Atlanta, GA); Thad Eugene Starner (Atlanta, GA)
Assignee: Georgia Tech Research Corporation
G09B21/00G06F3/015G10L21/00
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12664912
App. No.
17/796,884
Granted
Jun 23, 2026
Kind
B2
Abstract

An exemplary embodiment of the present disclosure provides a method of communication, the method comprising receiving a signal from a subject, wherein the signal represents activity in a brain of the subject associated with one or more spatiotemporal movements of one or more portions of the subject's body, correlating the signal to a portion of a coded language system and outputting the portion of the coded language system.

Claims (28)

1 . A method comprising:

receiving, by one or more processors and via a brain-activity sensing apparatus comprising one or more non-invasive sensors positioned proximate a head of a subject and in communication with the one or more processors, one or more signals representative of activity occurring in a brain of the subject, the activity being associated with one or more spatiotemporal movements of one or more portions of a body of the subject;

correlating, by the one or more processors, the received one or more signals to one or more portions of a coded language system by (i) extracting, by the one or more processors, one or more spatiotemporal neural activation features from the received one or more signals, wherein the extracted spatiotemporal neural activation features correspond to motor representations of the one or more portions of the body of the subject, and (ii) mapping the extracted spatiotemporal neural activation features to the one or more portions of the coded language system based on an association between neural activation patterns and the motor representations;

outputting, by the one or more processors, the one or more portions of the coded language system; and

demonstrating, as part of the outputting, one or more of the spatiotemporal movements associated with the one or more portions of the coded language system by applying one or more sensory stimuli to the subject that are configured to demonstrate or validate the spatiotemporal movements associated with the mapped portions of the coded language system.

2 . The method of claim 1 , wherein:

one or more of the stimuli is selected from a group consisting of auditory stimuli, visual stimuli, tactile stimuli, gustatory stimuli, olfactory stimuli, and any combinations thereof.

3 . The method of claim 2 , wherein at least one of the one or more stimuli comprises a tactile stimulation of one or more of the portions of the body of the subject.

4 . The method of claim 3 , wherein one of more of the portions of the body of the subject is selected from a group consisting of an organ, a muscle, a tendon, a joint, a bone, skin, cartilage, and any combinations thereof.

5 . The method of claim 3 , wherein one of more of the portions of the body of the subject is selected from a group consisting of an eye, an ear, a mandible, a temple, a tongue, teeth, a buccal, a shoulder, a bicep, an elbow, a hand, a wrist, a finger, a fingernail, an abdominal, a buttocks, a thigh, a knee, an ankle, a foot, an ankle bone, a toe, a toenail, and any combinations thereof.

6 . The method of claim 3 , wherein the tactile stimulation is selected from a group consisting of temporally separated tactile stimuli, vibrational tactile stimulation, electrical tactile stimulation, and any combinations thereof.

7 . The method of claim 3 , wherein the tactile stimulation comprises electrical tactile stimulation selected from a group consisting of electrical muscle stimulation, transcutaneous electrical nerve stimulation, functional electrical stimulation, neuromuscular electrical stimulation, Russian electrical stimulation, and any combinations thereof.

8 . The method of claim 1 , wherein one or more of the spatiotemporal movements is selected from a group consisting of executed actions, attempted actions, imagined actions, and any combinations thereof.

9 . The method of claim 1 , wherein the coded language system comprises text.

10 . The method of claim 9 , wherein the text is associated to a chorded system.

11 . The method of claim 10 , wherein the chorded system comprises less than N-points; and

wherein N is less than 27.

12 . The method of claim 10 , wherein the chorded system is selected from a group consisting of Braille, CyKey, SiWriter, GKOS, EkaPad, FrogPad, Decatxt, Twiddler, ASETNIOP, stenotype, velotype, Microwriter, and any combinations thereof.

13 . The method of claim 1 , wherein the one or more non-invasive sensors is selected from a group consisting of a brain-computer interface, a functional magnetic resonance imaging (fMRI) system, a functional near infrared (fNIR) imaging system, a positron emission tomography (PET) imaging system, an electroencephalogram (EEG) system, a transcranial magnetic stimulation (TMS) system, and any combinations thereof.

14 . The method of claim 1 , wherein at least one of the one or more signals is indicative of a blood oxygenation level-dependent (BOLD) response in the subject.

15 . The method of claim 1 further comprising:

outputting at least one portion of the one or more portions of the coded language system into speech.

16 . The method of claim 1 further comprising:

silently and non-visually communicating portions of the coded language system at over 50 bits per minute (bpm).

17 . The method of claim 1 further comprising:

silently and non-visually communicating portions of the coded language system at over 100 bits per minute (bpm).

18 . The method of claim 1 , wherein the spatiotemporal neural activation features comprise one or more characteristics selected from temporal separation, activation amplitude, spatial distribution, activation sequence, or combinations thereof.

19 . The method of claim 1 , wherein applying the one or more sensory stimuli comprises eliciting a neural response used to validate or refine the extraction of the spatiotemporal neural activation features.