Multidimensional motion state evaluation method and system assisted based on voice biomarker

By collecting and fusing the features of speech and heart rate signals in real time, and using a multimodal fusion model to generate multidimensional motion state assessment results, the problem of lack of deep heterogeneous fusion of speech and heart rate signals in existing technologies is solved, and more accurate and personalized motion state assessment is achieved.

CN122350690APending Publication Date: 2026-07-10XIANGYA HOSPITAL CENT SOUTH UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
XIANGYA HOSPITAL CENT SOUTH UNIV
Filing Date
2026-04-09
Publication Date
2026-07-10

AI Technical Summary

Technical Problem

In existing technologies, there is a lack of deep heterogeneous fusion between voice and heart rate signals, making it difficult to extract stable physiological features under motion interference, resulting in one-sided and delayed motion state assessment results.

Method used

By acquiring speech and heart rate signals in real time, separating the human voice segment from the silent segment, extracting time-domain breathing features and frequency-domain stability features, removing motion artifacts from the heart rate signal, and using a multimodal fusion model to perform dual-path feature extraction and multi-head attention fusion, a multidimensional motion state assessment result is generated.

Benefits of technology

It improves the comprehensiveness, real-time performance, anti-interference capability, and personalized guidance accuracy of motion status assessment, provides personalized motion intensity adjustment instructions, and enhances the accuracy and reliability of the assessment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122350690A_ABST
    Figure CN122350690A_ABST
Patent Text Reader

Abstract

The application discloses a multi-dimensional motion state evaluation method and system based on voice biomarker assistance, relates to the technical field of data processing, and comprises the following steps: synchronously collecting voice and heart rate signals during user motion, extracting time domain breathing features and frequency domain stability features as voice biomarkers by separating human voice and silent sections and identifying non-grammatical pauses, simultaneously extracting nonlinear heart rate variability features and recovery indicators as heart rate features after denoising the heart rate signals, inputting a multi-modal fusion model for double-path feature extraction and multi-head attention fusion, and outputting multi-dimensional motion state evaluation results and generating motion intensity adjustment instructions. The application solves the technical problems of the prior art, such as lack of deep heterogeneous fusion of voice and heart rate signals, difficulty in extracting stable physiological features under motion interference, and resulting in one-sided and lagged motion state evaluation results, and achieves the technical effects of improving the comprehensiveness, real-time performance, anti-interference performance and personalized guidance accuracy of motion state evaluation.
Need to check novelty before this filing date? Find Prior Art