A recognition method based on voiceprint extraction and multi-index feature screening

By employing a method based on voiceprint extraction and multi-index feature screening, the problems of subjectivity and ineffective feature screening in the process of voice signal acquisition are solved, achieving efficient and accurate identification of depression, which is suitable for on-site analysis in hospitals and mental health centers.

CN117095676BActive Publication Date: 2026-05-29BEIJING INST OF TECH
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
BEIJING INST OF TECH
Filing Date
2022-12-07
Publication Date
2026-05-29

AI Technical Summary

Technical Problem

Existing technologies for identifying depression suffer from subjective influences during the voice signal acquisition process and ineffective voice feature selection, leading to low classification accuracy and overfitting.

Method used

A voiceprint-based extraction method is adopted, which processes speech signals by framing and windowing, combines statistical feature extraction, difference and correlation calculation, performs multi-index feature screening, and uses linear support vector machine for classification.

Benefits of technology

It reduces the influence of semantic subjectivity when subjects read passages and words aloud, improves the accuracy and efficiency of depression identification, has a wider range of applications, reduces deployment costs, and is suitable for places such as hospitals and mental health centers.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117095676B_ABST
    Figure CN117095676B_ABST
Patent Text Reader

Abstract

The application relates to a recognition method based on voiceprint extraction and multi-index feature screening, and belongs to the technical field of speech processing and machine learning. The method comprises the following steps: pre-processing collected voice signals to obtain effective signals; performing feature extraction on the effective signals to obtain statistical features; calculating the difference degree and the correlation degree of the statistical features; performing multi-index feature screening according to the correlation degree and the difference degree of the statistical features to obtain effective features; and feeding the effective features into a linear support vector machine for classification. The method realizes high classification accuracy.
Need to check novelty before this filing date? Find Prior Art