# US 2026/0093314 A1 · System and method for enhancing an immersive online digital experience using subvocalization and gesture-based detection control via larynx member and ar

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0093314 A1
- Document ID: US20260093314A1
- Status: Published application
- Kind: A1
- Application number: 18/901,146
- Filed: 2024-09-30
- Published: 2026-04-02
- Earliest claimed: 2024-09-30
- Assignees: Infinitus Holdings Inc.
- Applicants: Infinitus Holdings Inc.
- Inventors: Joshua Ian Cohen; John Cronin
- Web page: https://patentgrep.com/patent/US20260093314A1

## CPC

- G06F 3/011: {Arrangements for interaction with the human body, e.g. for user immersion in virtual reality (blind teaching G09B21/00)}
- G06F 3/016: {Input arrangements with force or tactile feedback as computer generated output to the user}
- G06F 3/017: {Gesture based interaction, e.g. based on a set of recognized hand gestures (interaction based on gestures traced on a digitiser G06F3/04883)}
- G06F 3/0346: with detection of the device orientation or free movement in a three-dimensional [3D] space, e.g. 3D mice, 6-DOF [six degrees of freedom] pointers using gyroscopes, accelerometers or tilt-sensors
- G06F 3/044: by capacitive means
- G06Q 30/0643: {graphically representing goods, e.g. 3D product representation}
- G10L 15/16: using artificial neural networks
- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L 15/24: Speech recognition using non-acoustical features
- G10L 15/18: using natural language modelling
- G10L 2015/223: {Execution procedure of a spoken command}
- G10L 2015/227: {of the speaker; Human-factor methodology}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

A system for enhancing an augmented reality (AR) and/or virtual reality (VR) experience, includes a larynx member comprising a piezoelectric sensing array configured to capture analog waveforms representing movements of a user's larynx muscles while subvocalizing and a processor configured to convert the analog waveforms into subvocalization data. The system also includes an AR/VR enhancement device comprising a communication interface configured to receive the subvocalization data from the larynx member, a subvocalization machine learning module configured to process the subvocalization data to interpret a first set of user commands, a capacitive touch recognition surface configured to detect one or more gestures of the user. a gestural machine learning module configured to interpret the one more gestures as a second set of user commands, and a feedback device configured to provide real-time responses to the user, wherein the real-time responses include one or more of auditory, haptic, and/or visual feedback.

## Claims

### Claim 1

A system for enhancing an immersive online digital experience, the system comprising:
a piezoelectric sensing array that detects analog waveforms that correspond to larynx muscle movements during subvocalization by a user;
a processor that executes stored instructions from a memory to convert the analog waveforms into a three-dimensional data representation of larynx muscle movement;
a subvocalization machine learning module that compares the three-dimensional data representation with a pre-established training set of larynx muscle movements thereby deriving a first set of user commands from the three-dimensional data representation;
a capacitive touch recognition surface that detects one or more gestures of the user on an X-Y grid plane of the surface;
a gestural machine learning module that interprets the one more gestures as a second set of user commands; and
an immersive digital device that provides real-time responses to the user, including auditory and visual feedback that facilitates an online transaction responsive to the first and second sets of user commands.

### Claim 2 (depends on 1)

The system of claim 1, further comprising an ultrasound gel that vibrationally transmits larynx muscle movements to the piezoelectric sensing array.

### Claim 3 (depends on 1)

The system of claim 1, further comprising an accelerometer that generates acceleration data responsive to measurement of acceleration, wherein the acceleration data and three-dimensional data representation of larynx muscle movement distinguish subvocalizations from other bodily movements.

### Claim 4 (depends on 1)

The system of claim 1, further comprising a radar that detects gestures in free space, and wherein the radar detection and capacitive touch screen allow for a determination of gestures in a three-dimensional space.

### Claim 5 (depends on 1)

The system of claim 1, wherein the immersive digital device provides for augmented reality (AR) and is coupled to a cloud-based network to facilitate the online transaction.

### Claim 6 (depends on 1)

The system of claim 1, wherein the immersive digital device provides for virtual reality (VR) and is coupled to a cloud-based network to facilitate the online transaction.

### Claim 7 (depends on 1)

The system of claim 1, wherein the online transaction is a purchase of a product or service.

### Claim 8

(canceled)

### Claim 9 (depends on 1)

The system of claim 1, wherein the subvocalization machine learning module and the gestural machine learning module each use one or more of a large language model (LLM), convolutional neural network (CNN), recurrent neural network (RNN), support vector machine (SVM), random forest, hidden Markov model (HMM), autoencoder, principle component analyzer, Bayesian network, k-nearest neighbor algorithm, reinforcement learning algorithm, Gaussian mixture model, or a transfer learning model.

### Claim 10

(canceled)

### Claim 11

A method for enhancing an immersive online digital experience, the method comprising:
detecting analog waveforms that correspond to larynx muscle movements during user subvocalization using a piezoelectric sensing array;
converting the analog waveforms into a three-dimensional data representation of larynx muscle movement responsive to a process executing instructions stored in a memory;
comparing the three-dimensional data representation with a pre-established training set of larynx muscle movements at a subvocalization machine learning module, thereby deriving a first set of user commands from the three-dimensional data representation;
detecting one or more gestures of the user on an X-Y grid plane of a capacitive touch recognition surface;
interpreting the one more gestures at a gestural machine learning module as a second set of user commands; and
providing real-time responses to the user at an immersive digital device, wherein the real-time responses include auditory and visual feedback that facilitate an online transaction responsive to the first and second sets of user commands.

### Claim 12 (depends on 11)

The method of claim 11, further comprising facilitating a vibrational transmission of larynx muscle movements to the piezoelectric sensing array using an ultrasound gel.

### Claim 13 (depends on 11)

The method of claim 11, further comprising:
generating acceleration data responsive to measurement of acceleration at an accelerometer; and
distinguishing subvocalizations from other movements based on the acceleration data and three-dimensional data representation of larynx muscle movements.

### Claim 14 (depends on 11)

The method of claim 11, further comprising determining gestures in a three-dimensional space using a radar and the capacitive touch screen, wherein the radar detects gestures in free space.

### Claim 15 (depends on 11)

The method of claim 11, wherein facilitating the online transaction takes place over a cloud-based network using an augmented reality (AR) immersive digital device

### Claim 16 (depends on 11)

The method of claim 11 wherein facilitating the online transaction takes place over a cloud-based network using a virtual reality (VR) immersive digital device.

### Claim 17 (depends on 11)

The method of claim 11, wherein the online transaction is the purchase of a product or service.

### Claim 18

(canceled)

### Claim 19 (depends on 11)

The method of claim 11, further comprising training the subvocalization machine learning module and the gestural machine learning module using one or more of a large language model (LLM), convolutional neural network (CNN), recurrent neural network (RNN), support vector machine (SVM), random forest, hidden Markov model (HMM), autoencoder, principle component analyzer, Bayesian network, k-nearest neighbor algorithm, reinforcement learning algorithm, Gaussian mixture model, or a transfer learning model.

### Claim 20

(canceled)
