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

Voiceprint recognition method, device, electronic device and storage medium

A technology of voiceprint recognition and electronic equipment, applied in speech analysis, instruments, etc., can solve the problems of recognition, unable to accurately identify singing users, unable to obtain singing voice models, etc., and achieve the effect of improving accuracy

Active Publication Date: 2021-06-22
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in actual processing, it is difficult to collect a large amount of singing voice data of users for model training, so it is impossible to obtain a model suitable for singing voice, and it is also impossible to accurately identify singing users
[0004] It can be seen that when the user pronounces in different ways, the existing recognition method cannot accurately recognize the voiceprint

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 recognition method, device, electronic device and storage medium
  • Voiceprint recognition method, device, electronic device and storage medium
  • Voiceprint recognition method, device, electronic device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] In order to make the above objects, features and advantages of the present invention more comprehensible, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0040] In the embodiment of the present invention, the embodiment of the present invention uses an adaptive method to obtain a second speech model suitable for the second type of speech based on the first speech model and the second type of speech segment. That is, based on a small amount of second-type voice segments and the existing first voice model for recognizing voiceprints, a second voice model suitable for identifying second-type voice users can be adaptively obtained, so that for the second-type voice data to be recognized, it can Recognition is performed based on the second voice model to improve the accuracy of voiceprint recognition. Among them, self-adaptation is to automatically adjust the processing method, processi...

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

Embodiments of the present invention provide a voiceprint recognition method, device, electronic equipment and storage medium, so as to improve the accuracy of voiceprint recognition. The method includes: performing adaptive processing according to the first speech model and the second-type speech segment to obtain a second speech model, wherein the first speech model is used to recognize the first-class speech, and the second speech model is used to Recognize the second type of voice; collect the second type of voice data to be recognized; input the second type of voice data to be recognized into the second voice model, and identify the corresponding voiceprint. The voiceprint recognition is performed by adopting the second speech model obtained by self-adaptation, so as to improve the accuracy of voiceprint recognition.

Description

technical field [0001] The invention relates to the technical field, in particular to a voiceprint recognition method, a voiceprint recognition device, an electronic device and a readable storage medium. Background technique [0002] Voiceprint recognition, a type of biometric technology, is also called speaker recognition, that is, the speaker is identified based on voice data, which can be used for user identification. However, the application of voiceprint recognition also has certain defects, such as the variability of a person's voice, which is easily affected by physical condition, age, emotion, etc., which may lead to inaccurate recognition results. [0003] For example, a person's singing voice is quite different from his usual speaking voice, and the voice model of the scene is trained based on the voice of the user speaking, and cannot recognize the voiceprint of the user singing. To accurately identify the user's singing voiceprint, it is necessary to use a large...

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): G10L17/02G10L17/04G10L17/12
CPCG10L17/02G10L17/04G10L17/12
Inventor 张涛涛许云飞潘逸倩陈伟
Owner BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO LTD