Voiceprint identity recognition method and device and electronic equipment

An identity recognition and voiceprint technology, applied in the field of identity recognition, can solve the problems of no time-varying ability, poor anti-noise ability, large number of samples, etc.

Pending Publication Date: 2021-01-29
湖南华威金安企业管理有限公司
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The object of the present invention is to provide a method, device and electronic equipment for voiceprint identification, so as to alleviate the problem that the existing voiceprint identification model does not have time-varying resistance, poor anti-noise ability, and the number of samples required for training. big technical problem

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 identity recognition method and device and electronic equipment
  • Voiceprint identity recognition method and device and electronic equipment
  • Voiceprint identity recognition method and device and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] In order to facilitate the understanding of this embodiment, a voiceprint identification method disclosed in the embodiment of the present invention is first introduced in detail, see figure 1 The flow chart of a voiceprint identification method shown mainly includes the following steps:

[0051] Step S102, acquiring the spectral features of the voiceprint to be identified;

[0052] The above-mentioned voiceprint to be recognized may specifically be a recording of a speaker, and the above-mentioned spectral features are obtained by performing Fourier transform on the voiceprint to be recognized.

[0053] Step S104, identify the spectral features through the voiceprint identification model to obtain the identity information corresponding to the voiceprint to be identified and the attribute information of the voiceprint to be identified, wherein the voiceprint identification model is a model obtained by pre-training the InfoGAN network, and the identity The information i...

Embodiment 2

[0088] The embodiment of the present invention also provides an image authenticity identification device, the image authenticity identification device is mainly used to implement the image authenticity identification method provided in the above content of the embodiment of the present invention, the following provides the embodiment of the present invention The identification device for image authenticity will be introduced in detail.

[0089] Image 6 It is a schematic diagram of a voiceprint identification device according to an embodiment of the present invention, such as Image 6 As shown, the device for voiceprint identification mainly includes: an acquisition unit 10 and an identification unit 20, wherein:

[0090] an acquisition unit, configured to acquire the spectral features of the voiceprint to be identified;

[0091]The identification unit is used to identify the spectral features through the voiceprint identification model to obtain the identity information cor...

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 identity recognition method and device and electronic equipment. The voiceprint identity recognition method comprises the steps of acquiring frequency spectrum features of a voiceprint to be recognized; and identifying the frequency spectrum features through a voiceprint identification model to obtain identity information corresponding to the voiceprint to be recognized and attribute information of the voiceprint to be recognized. The voiceprint identification model is obtained by training the InfoGAN network in advance, the data volume of the required training sample is small, and after the frequency spectrum features are identified through the voiceprint identification model, an object identifier corresponding to the voiceprint to be regonized can be obtained, the age of the object corresponding to the voiceprint to be recognized, and the noise information and volume information of the voiceprint to be recognized can be obtained, so that the anti-time-varying capability and anti-noise capability of the model are improved, and the technical problems that an existing voiceprint identity recognition model does not have the anti-time-varying capability, the anti-noise capability is poor, and the number of samples required during training is large are solved.

Description

technical field [0001] The invention relates to the technical field of identification, in particular to a voiceprint identification method, device and electronic equipment. Background technique [0002] The voiceprint identity authentication method is generally to perform identity authentication by training a voiceprint identity recognition model, using the output of the last layer of the model as the voiceprint feature, and calculating the similarity score of two voiceprint features. If the similarity score is higher than the threshold, they are considered to be the same person; otherwise, they are considered not to be the same person. That is, the voiceprint identification technology is the foundation and key of the voiceprint identification technology. [0003] The voiceprint identification technology has developed from the traditional i-vector technology to the current d-vector technology, and has achieved remarkable results. The deep learning technology involved in d-...

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): G10L17/04G10L17/20
CPCG10L17/04G10L17/20
Inventor 黄明明
Owner 湖南华威金安企业管理有限公司
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap