Small Multielectrode Arrays for High-Resolution Neuronal Speech Decoding

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for decoding speech from neuronal activity, particularly in individuals with speech impairments, face challenges due to low spatial resolution and high invasiveness of electrode grids, leading to noisy and less specific signal capture, which can frustrate users with high error rates and slow transmission.

Innovation Solution

The use of small, multielectrode arrays implanted in specific brain regions, combined with voltage threshold filtering and wireless data telemetry, allows for high spatial resolution and efficient data processing, enabling accurate decoding of intended speech through neuronal signal recorders and decoders.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Area of stationary object

If electrode grids are used to decode speech from neuronal activity, then coverage area is increased, but spatial resolution deteriorates and signal quality becomes noisier

Engineering Contradiction:
Improvecoverage areaVSAvoidspatial resolution
Core Design Contradiction:
Area of stationary objectVSMeasurement precision

Solution Approach 1:

The patent divides the brain surface into multiple regions, each equipped with its own multielectrode array. This segmentation allows each array to provide high spatial resolution for its local region while collectively covering a broad area through multiple arrays positioned at different locations.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent transitions from a two-dimensional surface montage to a three-dimensional configuration by implanting multielectrode arrays at different depths and locations within the brain. This dimensional change enables simultaneous achievement of high spatial resolution and extensive coverage through volumetric sampling.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Reliability

If invasive electrode implants are used to capture neuronal signals, then signal acquisition capability is improved, but invasiveness and user comfort deteriorate

Engineering Contradiction:
Improvesignal acquisition capabilityVSAvoidinvasiveness
Core Design Contradiction:
ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The patent changes the physical parameters of the electrode arrays, using smaller arrays with fewer electrodes implanted at specific strategic locations rather than large comprehensive grids. This parameter change reduces the invasive burden while maintaining sufficient signal acquisition capability through optimized electrode placement.

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If comprehensive electrode grids are implanted, then decoding accuracy is improved, but transmission speed and system efficiency deteriorate

Engineering Contradiction:
Improvedecoding accuracyVSAvoidtransmission speed
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent extracts and transmits only the most critical neuronal signal features and decoded speech information rather than transmitting all raw signal data from comprehensive electrode grids. This extraction approach maintains decoding accuracy while significantly improving transmission efficiency and speed.

Inventive Principle:
Principle #2Taking out (Extraction)

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

This approach provides high-fidelity speech decoding with reduced invasiveness, enabling efficient communication for speech-impaired individuals by integrating with brain-computer interface systems without additional implants, and supporting wireless data transmission.

Implementation Method 1

a multielectrode array, controller circuitry, and a communication circuitry capable of transmitting data to a neuronal signal decoder

Methodology Applied
Scientific EffectElectrical signal detection: Electric Field

Implementation Method 2

the controller circuitry includes a voltage threshold filtering circuitry, and the voltage threshold filtering circuitry is configured to produce a binary value indicating the presence or absence of an action potential

Methodology Applied
Scientific EffectVoltage threshold filtering: Filter (electronic)

Data Source

PatentUS12431136B2Systems and methods for decoding intended speech from neuronal activity
Publication Date: 2025.09.30 VITESCO TECHNOLOGIES USA LLC
  • US12431136B2 patent drawing
  • US12431136B2 patent drawing
  • US12431136B2 patent drawing

AI summary

Systems and methods for decoding indented speech from neuronal activity in accordance with embodiments of the invention are illustrated. One embodiment includes a neuronal speech system for decoding intended speech from neuronal signals includes a neuronal signal recorder implanted into a user's brain, including a multielectrode array, controller circuitry, and a communication circuitry capable of transmitting data to a neuronal signal decoder, the neuronal signal decoder located externally from the user's body, including a processor, an input/output interface, and a memory, where the memory contains a neuronal speech application that directs the processor to obtain neuronal signal data from the neuronal signal recorder, where the neuronal signal data describes neuronal activity proximal to the implanted neuronal signal recorder, decode speech features from the neuronal signal data using a neuronal decoding model, construct a speech string from the decoded speech features; and output the constructed speech string via an output device.