Method for protecting mobile terminal privacy based on voiceprint recognition

A voiceprint recognition and privacy protection technology, applied in speech recognition, speech analysis, instruments, etc., can solve the problems of low recognition efficiency, low recognition accuracy and efficiency, and large memory space occupied by voice feature models. , to achieve the effect of eliminating correlation, protecting integrity and security, and eliminating slow calculation speed

Inactive Publication Date: 2011-11-02
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF3 Cites 34 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The existing voiceprint recognition technology is rarely used in mobile terminals, and the voice feature model will occupy a large amount of memory space during the training process, and the recognition accuracy and efficiency cannot reach a high level, especially when multiple people are speaking. Under the influence of the environment and the speaker's physical condition, age, emotion, etc., the efficiency of recognition will be significantly reduced

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 protecting mobile terminal privacy based on voiceprint recognition
  • Method for protecting mobile terminal privacy based on voiceprint recognition
  • Method for protecting mobile terminal privacy based on voiceprint recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] A mobile terminal privacy protection method based on voiceprint recognition, including analysis and extraction of voice information features, model training and voiceprint recognition:

[0036] 1. The analysis and extraction of speech information features include: sound collection, A / D conversion, pre-emphasis processing, framing, windowing, autocorrelation analysis, obtaining LPC coefficients, obtaining LPC inverted coefficients, and extracting speech feature information; In the process of extracting speech by the time-energy method, the silence in the speech is firstly extracted.

[0037] Only when the digital signal of the sound is obtained can it be effectively processed and feature extracted. Through the microphone of the mobile terminal, the sound wave is converted into an analog signal, and the analog signal is then filtered while properly compensating for channel loss. After filtering, the bandwidth of the signal is limited to around the Nyquist rate (half the ...

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 protecting mobile terminal privacy based on voiceprint recognition. The method comprises the following steps: analysis and extraction of voice message characteristics, model training and voiceprint recognition. In the method, the efficiency of the voiceprint recognition is high, and the performances and the recognition efficiency of the voiceprint recognition are not associated with the texts and the language. The voice length of a speaker is not required specially, and only voice messages in minutes are required so as to acquire the voice feature messages of the speaker, thereby carrying out the model training and the recognition. Applications of a voiceprint recognition algorithm in the intelligent mobile terminal have the advantages of high stability and recognition accuracy, and a voice feature model which is trained occupies small memory space of the intelligent mobile terminal. The method can be utilized to preferably protect the private information of a user in the intelligent mobile terminal and avoid the private information from being revealed and stolen when a mobile phone is lost.

Description

technical field [0001] The invention belongs to the technical field of computer information security, and in particular relates to a protection method for identifying and confirming mobile terminal user identities through voiceprint recognition. Different individuals are identified through the principle of voiceprint recognition, thereby ensuring the privacy of mobile terminals and users. Security of data and other information. Background technique [0002] Voiceprint Recognition (VR), or Speaker Recognition SR (Speaker Recognition SR), is a kind of biometric recognition technology. It is a voice parameter that reflects the physiological and behavioral characteristics of voiceprint in the voice waveform. The technology of voiceprint identity. It is a research on voiceprint recognition algorithm with better robustness and self-adaptation. [0003] Different from speech recognition, voiceprint recognition uses the characteristics of the voiceprint sound itself in the speech ...

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): G10L15/06G10L17/00G10L15/02G10L17/02G10L17/04G10L17/24
Inventor 佘堃何元吴娱
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products