Voice-Based Dysarthria Detection Without Facial Image Capture

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing stroke detection systems that analyze facial images to identify carotid artery stenosis impose burdens on subjects by requiring them to position their faces appropriately for image capture, which is inconvenient and burdensome.

Innovation Solution

A dysarthria detection method that analyzes voice information using machine learning to determine if a subject has dysarthria, indicating potential stroke risk, without the need for facial image capture.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If video capture is used to detect dysarthria, then detection accuracy is improved, but ease of operation deteriorates due to burden on subject and positioning requirements

Engineering Contradiction:

Improvedysarthria detection accuracyVSAvoidconvenience for subject

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The patent replaces the mechanical/optical system of video capture with an acoustic system using microphones to record voice. This substitution eliminates the need for visual positioning and reduces subject burden while maintaining detection capability through voice-based dysarthria indicators.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces voice recording as an intermediary medium between the subject and the detection system. Instead of directly capturing visual images of the subject, the system captures voice signals that indirectly reflect dysarthria conditions, thereby simplifying the interaction process.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Ease of operation

If video capture is used to detect dysarthria, then detection capability is improved, but device complexity is reduced by using voice-based detection

Engineering Contradiction:

Improvesimplicity of detection processVSAvoiddetection system complexity

Core Design Contradiction:

Ease of operationVSDevice complexity

Solution Approach 1:

The patent replaces complex video capture and image processing systems with simpler acoustic recording and voice analysis systems. This substitution reduces device complexity while maintaining or improving ease of operation, as voice recording requires minimal subject cooperation and no positioning.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS12633304B2Dysarthria detection method, dysarthria detection device, and recording medium

Publication Date: 2026.05.19 PANASONIC HOLDINGS CORP

AI summary

A dysarthria detection method includes an obtaining step and a detecting step. In the obtaining step, voice information regarding voice uttered by a subject is obtained. In the detecting step, it is detected whether the subject has dysarthria, based on an output result obtained by inputting the voice information obtained in the obtaining step into a detection model. The detection model has been trained by machine learning to output information regarding whether the subject has dysarthria by using voice information inputted.