Unlock instant, AI-driven research and patent intelligence for your innovation.

Voiceprint identification method and device, model training method and device, equipment and storage medium

A technology of identification method and training method, applied in the field of voiceprint identification, can solve the problem of insufficient accuracy, and achieve the effect of high accuracy and improved accuracy

Pending Publication Date: 2021-02-19
北京远鉴信息技术有限公司
View PDF0 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of this application is to provide a voiceprint identification method, model training method, device, equipment and storage medium to solve the problem of determining the target voice based on a single feature dimension in the prior art, or to The method of subjectively determining the results of voiceprint identification leads to the problem of insufficient accuracy

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
  • Voiceprint identification method and device, model training method and device, equipment and storage medium
  • Voiceprint identification method and device, model training method and device, equipment and storage medium
  • Voiceprint identification method and device, model training method and device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0076] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments It is a part of the embodiments of this application, not all of them.

[0077] The components of the embodiments of the application generally described and illustrated in the figures herein may be arranged and designed in a variety of different configurations. Accordingly, the following detailed description of the embodiments of the application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of the application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art withou...

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 provides a voiceprint identification method and device, a model training method and device, equipment and a storage medium, and relates to the technical field of voiceprint identification. The voiceprint identification method comprises the following steps of: acquiring to-be-identified voice data; carrying out feature extraction on the to-be-identified voice data and to-be-matched voice data in a voice database to obtain to-be-input features, wherein the to-be-input features comprise features of multiple preset dimensions; according to the to-be-input features and a preset voiceprint identification model, identifying and acquiring whether a target voice matched with the to-be-identified voice data exists in the voice database or not; and if so, determining that the to-be-identified voice data passes the identification. Compared with the prior art, the problem that the accuracy is not high enough due to the fact that the target voice is determined according to the single feature dimension or the voiceprint identification result is determined according to subjectivity is avoided.

Description

technical field [0001] The present application relates to the technical field of voiceprint identification, in particular, to a voiceprint identification method, a model training method, a device, a device, and a storage medium. Background technique [0002] Like DNA, fingerprints and other characteristics, voiceprint is a characteristic that everyone has. It can be used to identify identity and has great potential in criminal investigation, payment, security, password and other fields. [0003] In the voiceprint identification in the prior art, the features of the voice are generally extracted first, and then the identity judgment is made by comparing the similarity between the voice features of the test material and the voice features of the sample. The main theoretical basis of the current voiceprint identification technology is the Source-Filter Model (Source-Filter Model), in which the formant only reflects the characteristics of the vocal tract, that is, the acoustic c...

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): G10L17/02G10L17/06G10L17/04
CPCG10L17/02G10L17/06G10L17/04
Inventor 曹岩岗
Owner 北京远鉴信息技术有限公司