Speech-Based Pulmonary Assessment With Cognitive-Burden Modeling

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional pulmonary function tests require supervised, repetitive, and tiring breathing exercises, necessitating a healthcare professional's presence, and listening to speech for pulmonary assessment is challenging without professional supervision.

Innovation Solution

A system that analyzes an individual's ordinary speech using audio features and speech patterns to determine pulmonary conditions, employing machine learning models like CNN-LSTM to predict parameters like FEV1, FVC, and FEV1/FVC, and mitigates confounding factors through cognitive burden estimation and personalized scripts.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional pulmonary function tests are performed using spirometry or plethysmography, then measurement precision of lung function parameters is improved, but device complexity and requirement for professional supervision increase

Engineering Contradiction:

Improvelung function parametersVSAvoidtesting equipment

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces complex mechanical pulmonary function testing equipment (spirometers, plethysmographs) with an acoustic analysis system that processes speech signals. The system substitutes mechanical breath measurement devices with microphone-based audio capture and signal processing algorithms, eliminating the need for specialized medical equipment while maintaining diagnostic capability through analysis of speech acoustics parameters.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables unsupervised self-assessment of pulmonary function by allowing individuals to perform testing independently using their own speech. The automated analysis pipeline processes speech recordings without requiring professional supervision, enabling patients to conduct pulmonary assessments at home or in non-clinical settings, thus removing the dependency on healthcare professionals for routine monitoring.

Inventive Principle:

Principle #25Self-service

2Reliability

If conventional pulmonary function tests are performed, then reliability of pulmonary condition assessment is improved, but ease of operation deteriorates due to supervised repetitive breathing exercises

Engineering Contradiction:

Improvepulmonary condition assessmentVSAvoidtesting procedure

Core Design Contradiction:

ReliabilityVSEase of operation

Solution Approach 1:

Instead of requiring patients to perform standardized breathing maneuvers into a spirometer, the system inverts the approach by having patients engage in their natural activity of speaking. The pulmonary function assessment is derived not from controlled breath exhalation but from the acoustic characteristics of voluntary speech, transforming a complex procedural task into a simple, intuitive action that patients can perform naturally without training or supervision.

Inventive Principle:

Principle #13The other way round (Inversion)

Solution Approach 2:

The system replaces the mechanical act of forced breath exhalation into a device with the simpler act of speech production. By substituting the required physical maneuver (repetitive breathing exercises) with natural speech, the system maintains diagnostic reliability while dramatically improving ease of operation and patient comfort.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Ease of operation

If speech analysis is used for pulmonary assessment, then ease of operation is improved, but measurement precision deteriorates due to difficulty in listening to speech without professional supervision

Engineering Contradiction:

Improvetesting procedureVSAvoidspeech-based pulmonary parameters

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The system introduces an intermediary automated analysis pipeline that bridges natural speech and pulmonary function parameters. This intermediary consists of signal processing algorithms and machine learning models that extract relevant acoustic features from speech and translate them into quantitative pulmonary metrics, eliminating the need for professional human interpretation while ensuring measurement precision through consistent, objective analysis.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system replaces the human ear and professional judgment with automated acoustic analysis algorithms. By substituting subjective human listening with objective computational analysis of speech signals, the system achieves both ease of operation (anyone can speak) and measurement precision (automated algorithms consistently extract pulmonary parameters from speech acoustics).

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS12440150B2Speech-based pulmonary assessment

Publication Date: 2025.10.14 SAMSUNG ELECTRONICS CO LTD

AI summary

Pulmonary assessment based on speech can include identifying one or more audio features and speech patterns of a user's speech. A cognitive burden associated with the user's speech can be determined. A pulmonary condition of the user can be determined based on predetermined correlations between the one or more audio features and speech patterns of the user's speech, the cognitive burden, and a respiratory airway condition.