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

Vocal print identification method, electronic device and computer readable storage medium

A voiceprint recognition and computer program technology, applied in the electronic field, can solve the problem of low accuracy of voiceprint recognition and achieve the effect of real-time evaluation of false positive rate

Active Publication Date: 2018-11-16
SHENZHEN UNIV
View PDF13 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Due to the complexity of the actual situation, different types of recognition subsystems in the prior art may not necessarily adapt to the initial weights. Therefore, the method of using fixed weights makes the accuracy of voiceprint recognition not high.

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
  • Vocal print identification method, electronic device and computer readable storage medium
  • Vocal print identification method, electronic device and computer readable storage medium
  • Vocal print identification method, electronic device and computer readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] The embodiment of this application provides a voiceprint recognition method, please refer to Figure 1-a , the voiceprint recognition method mainly includes the following steps:

[0058] 101. Obtain voice data to be analyzed;

[0059] The embodiment of the present invention is applied to a voiceprint recognition system, and the voiceprint recognition system includes K subsystems, where K is an integer greater than zero. The system architecture of the voiceprint recognition system in the embodiment of the present invention can refer to Figure 1-b .

[0060] Wherein, each subsystem in the voiceprint recognition system can correspond to different types of voiceprint recognition, and the types of voiceprint recognition include: emotion recognition, age recognition, and language recognition. Furthermore, each subsystem can also correspond to each subcategory in a recognition scenario. For example, in speech recognition, a subsystem corresponds to a language (such as Chine...

Embodiment 2

[0097] In the embodiment of the present invention, error-prone classifiers need to be constructed, please refer to Figure 1-c Methods include:

[0098] 201. Establish a training database;

[0099] Take the short-term speech data set as the test data set of each subsystem, mark all misjudged speech segments in the test process as N different labels according to different subsystems, and use it as a training database, and the N is an integer greater than zero .

[0100] 202. Extracting MFCC Mel frequency cepstral coefficient features;

[0101] For each piece of short-term speech data in the training database, Mel Frequency Cepstrum Coefficient (MFCC) features are extracted.

[0102] 203. Train the overall change matrix;

[0103]According to the extracted MFCC features, the universal background model (Universal Background Model, UBM) is trained, and the overall change matrix T is trained.

[0104] 204. Obtain the change factor feature of the short-term voice data;

[0105]...

Embodiment 3

[0115] In the embodiment of the present invention, taking the hybrid system of language recognition as an example, the voiceprint recognition method in the embodiment of the present invention is described in detail, including:

[0116] 1. For the architecture of the hybrid system for language recognition in the embodiment of the present invention, please refer to Figure 1-b , each subsystem independently gives the probability values ​​of N different languages.

[0117] 2. Let x be an input voice, and the output of each subsystem is shown in the following table:

[0118] Language code

Language 1

Language 2

…

LanguageN

Language Probability

P(L 1 |x)

P(L 2 |x)

…

P(L N |x)

[0119] P f (L j |x)(i=1,2,…,N) Each subsystem independently gives a certain input voice belonging to a certain language L j (j=1,2,...,N) probability, and the sum of all probabilities is also 1, namely:

[0120]

[0121] Arrange the probabilities...

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 present invention provides a vocal print identification method, an electronic device and a computer readable storage medium. The vocal print identification method comprises the steps of: obtainingvoice data to be analyzed; extracting change factor features in the voice data; performing misjudgment classification of the voice data according to the change factor features through a fallible point classifier to obtain the relative misjudgment probability of the voice data being misjudged in K sub systems; determining the offset of the relative misjudgment probability corresponding to any onesub system and the average relative misjudgment probability of the K sub systems, and calculating the final fusion weights of the corresponding sub systems according to the offset; and performing weighing of the identification result of each sub system according to the final fusion weight, and obtaining an integrated identification result according to the identification result of each sub system after weighing.

Description

technical field [0001] The present application relates to the field of electronic technology, and in particular to a voiceprint recognition method, an electronic device, and a computer-readable storage medium. Background technique [0002] With the popularity of smart devices and related hardware facilities, voice interaction has become an indispensable part of human-computer interaction. There are more and more application scenarios related to voiceprint in voice interaction, including but not limited to: voiceprint attendance check-in, software login, bank transfer and account opening verification, wake-up of virtual voice assistant, personalized interaction for different user groups Wait, these systems all use voiceprint without exception. The so-called voiceprint refers to the unique voice characteristics of each person. In real life, everyone's voice has its own characteristics when speaking. Generally speaking, voiceprint recognition is divided into the following ca...

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
IPC IPC(8): G10L17/06G10L25/24G10L25/51
CPCG10L17/06G10L25/24G10L25/51
Inventor 郑能恒林吉
Owner SHENZHEN 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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com