Speech Signal Analysis for Cardiac Condition Estimation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing technologies primarily focus on estimating mental or neurological diseases from speech data, neglecting the potential to assess cardiac conditions using similar acoustic parameters.

Innovation Solution

An information processing device and method that computes cardiac condition indicators from time-series speech data by analyzing spectral power differences and integrating them into a voice modulation index (VMI), combined with other speech features like HNR and spectrograms, to estimate heart failure and other cardiac conditions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If acoustic parameters are computed from speech data to estimate mental or neurological diseases, then disease estimation capability is improved, but the system remains limited to specific disease types and cannot estimate cardiac conditions

Engineering Contradiction:

Improvedisease estimation capabilityVSAvoidcardiac condition information

Core Design Contradiction:

Adaptability or versatilityVSLoss of information

Solution Approach 1:

The system extends the speech analysis framework to perform multiple disease estimations including both mental/neurological diseases and cardiac conditions. The computing section now computes both acoustic parameters for mental disease estimation and voice modulation indices for cardiac condition estimation, making the system multi-functional rather than limited to a single disease type.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The analysis is divided into distinct processing paths: one path computes acoustic parameters from speech data for mental/neurological disease estimation, while another path computes voice modulation indices by analyzing spectral power differences for cardiac condition estimation. This segmentation allows each path to be optimized for its specific purpose while sharing the common input of speech data.

Inventive Principle:

Principle #1Segmentation

2Device complexity

If speech data is used to estimate only mental or neurological diseases, then the analysis framework is simple, but the system cannot detect cardiac conditions affecting the user

Engineering Contradiction:

Improveanalysis framework complexityVSAvoidcardiac condition detection capability

Core Design Contradiction:

Device complexityVSReliability

Solution Approach 1:

The system dynamically adapts the analysis framework by adding cardiac condition detection capabilities without completely redesigning the existing mental disease estimation system. The computing section dynamically computes both acoustic parameters and voice modulation indices from the same speech data, allowing the system to respond to different medical assessment needs while maintaining operational efficiency.

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS20260004800A1Information processing device, information processing method, information processing system, and information processing program

Publication Date: 2026.01.01 PST INC (NEWCO)

AI summary

An information processing device acquires speech data that is time series data of speech spoken by a user. Based on the speech data, the information processing device computes state information that represents a cardiac condition of the user, and the information processing device outputs the computed state information.