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

Training method, device, storage medium and electronic equipment of voiceprint model

A model and voiceprint technology, applied in speech analysis, speech recognition, instruments, etc., can solve the problem of low accuracy of voiceprint wake-up, and achieve the effect of improving accuracy

Active Publication Date: 2022-05-17
GUANGDONG OPPO MOBILE TELECOMM CORP LTD
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The voiceprint model training method, device, storage medium and terminal provided in the embodiment of the present application can solve the problem of low accuracy of voiceprint wake-up by users of different age groups

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
  • Training method, device, storage medium and electronic equipment of voiceprint model
  • Training method, device, storage medium and electronic equipment of voiceprint model
  • Training method, device, storage medium and electronic equipment of voiceprint model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] In order to make the purpose, technical solution and advantages of the present application clearer, the embodiments of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0029] First, some nouns involved in the embodiments of this application are explained:

[0030] Gaussian mixture model (GMM), used for Gaussian probability density function (normal distribution curve) to accurately quantify things, is a model that decomposes things into several Gaussian probability density functions.

[0031] Unit vector (identityvector): A more compact vector extracted from the GMM mean supervector.

[0032] Support vector machine (support vector machine): A class of generalized linear classifiers that perform binary classification on data in a supervised learning manner, and its decision boundary is the maximum margin hyperplane that is solved for the learning samples.

[0033] Age estimation model: used to estimate 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 embodiment of the present application discloses a voiceprint model training method, device, storage medium and electronic equipment, belonging to the field of computer technology. The method includes: performing age estimation on the voice data of the user to obtain the age estimation result, and training the model according to the voiceprint general model corresponding to the age estimation result to obtain the user's voiceprint personal model, so as to realize the user's voiceprint personal model of different age groups. Use different voiceprint personal models for voiceprint wake-up. The voiceprint personal model obtained in this application is related to the user's age, and voiceprint wake-up based on the voiceprint personal model can improve the accuracy of wake-up.

Description

technical field [0001] The present application relates to the field of speech processing, in particular to a training method, device, storage medium and electronic equipment for a voiceprint model. Background technique [0002] Voiceprint recognition is an identification technology that identifies the user's identity based on the user's biological characteristics based on the voice. Compared with traditional identification technology, voiceprint recognition has the advantages of simple extraction process and low cost, and is widely used in various occasions that require security protection, such as banks, securities, insurance and other financial institutions. Because speech is a very random process, various internal or external factors have a great influence on pronunciation, so the acoustic characteristics of the speech data sent by the user will change, and the existing wake-up methods cannot adapt to the changes, resulting in accurate wake-up. low rate problem. Conten...

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 Patents(China)
IPC IPC(8): G10L17/04G10L17/00G10L15/26G10L25/48
CPCG10L17/04G10L15/26G10L25/48G10L17/00
Inventor 陈岩
Owner GUANGDONG OPPO MOBILE TELECOMM CORP LTD
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