Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method for improving voiceprint security

A security and voiceprint technology, applied in the field of speaker recognition security, can solve the problem of incomplete security analysis of the speaker recognition system, and achieve the effect of improving voiceprint security and comprehensive analysis results

Active Publication Date: 2022-04-15
ZHEJIANG UNIV
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0011] Aiming at the problem of incomplete security analysis of existing speaker recognition systems, the present invention proposes a method for improving voiceprint security

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for improving voiceprint security
  • Method for improving voiceprint security
  • Method for improving voiceprint security

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] Below are specific embodiments of the present invention and in conjunction with accompanying drawing, the technical scheme of the present invention is described further, but the present invention is not limited to these embodiments.

[0029] Such as figure 1 As shown, a method for improving voiceprint security proposed by the present invention mainly includes the following steps:

[0030] Step S01, according to the workflow of the speaker recognition system, determine the factors that affect the security of the voiceprint, and construct the security model of the voiceprint. In the follow-up analysis, all the influencing factors are used as control variables to ensure the fairness of the analysis of the influence of speech content safety.

[0031] Step S01 specifically includes:

[0032] Step S11, summarizing the working flow of the speaker recognition system.

[0033] Such as figure 2 As shown, there are differences in the application scenarios of speaker authentic...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a method for improving voiceprint security, and belongs to the technical field of speaker recognition security in an intelligent voice system. Comprising the steps of constructing a voiceprint security model; atomizing the speaking content; setting a test variable; constructing a test sample; voiceprint security model training and voiceprint registration are carried out; calculating the misrecognition rate change under the single-step change of the three feature variables of richness, length and details to obtain the weight relationship of the feature variables; for the original authentication word to be authenticated, extracting phoneme features of the original authentication word, and obtaining a misrecognition rate of the original authentication word; and comparing the misrecognition rate with a threshold value, if the misrecognition rate is less than or equal to the threshold value, indicating that the voiceprint is safe, and if the misrecognition rate is greater than the threshold value, optimizing the original authentication word according to the weight relationship of the feature variables. Different from the research trend of improving a voiceprint model and audio characteristics in the existing method, the method provided by the invention aims at improving the voiceprint safety by optimizing the speaking content, and any existing or improved voiceprint model can be compounded.

Description

technical field [0001] The invention belongs to the technical field of speaker recognition security in an intelligent voice system, and in particular relates to a method for improving voiceprint security. Background technique [0002] With the popularization of smart devices and the development of artificial intelligence technology, the application of intelligent voice systems is becoming more and more extensive. The functions included in the intelligent voice system have two important branches, namely speech recognition and speaker recognition. Speech recognition is mainly used to convert voice into text with semantic meaning, and speaker recognition is mainly used to identify the identity through speech recognition. Speaker recognition technology has been widely used in financial transactions, asset management, criminal investigation, telephone services, voice assistants and other industries, and it undertakes important functions such as identity authentication and identif...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G10L17/22G10L17/02G10L17/04G10L15/02G10L15/01
Inventor 徐文渊冀晓宇何睿文程雨诗
Owner ZHEJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products