Speaker recognition method based on Gaussian super vector and deep neural network

A technology of deep neural network and speaker recognition, which is applied in speech analysis, instruments, etc., can solve problems such as destroying data correlation, decreasing system recognition rate, and reducing feature expression ability

Inactive Publication Date: 2019-08-09
HUBEI UNIV OF TECH
View PDF14 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Usually, the input of the neural network must be consistent in size. If the MFCC feature is intercepted or zero-filled, this requirement can be met, but this operation will destroy the correlation between the data, reduce the expressive ability of the feature, and cause the system recognition rate. greatly decreased

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
  • Speaker recognition method based on Gaussian super vector and deep neural network
  • Speaker recognition method based on Gaussian super vector and deep neural network
  • Speaker recognition method based on Gaussian super vector and deep neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0067] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention.

[0068] Examples of the described embodiments are shown in the drawings, wherein like or similar reference numerals designate like or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention.

[0069] refer to Figure 1-4 , a speaker recognition method based on Gaussian supervectors and deep neural networks, including:

[0070] S1: Speaker feature extraction;

[0071] 1-1) Collect the original speech signal and pre-emphasize, frame, window, fast Fourier transform...

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 discloses a speaker recognition method based on a Gaussian super vector and a deep neural network. The method comprises a speaker feature extraction stage, a deep neural network design stage, and a speaker identification and decision-making stage. According to the invention, the deep neural network is fused with a speaker recognition system model, and the obvious effect of a multilayer structure combining the Gaussian super vector and the deep neural network in the aspect of improving the characterization capability of an evaluation model is achieved. The speaker recognition method provided by the invention can effectively improve the recognition performance of a system in the environment of background noise, reduces the influence of the noise on the system performance, improves the robustness of the system noise, optimizes the system structure, and improves the competitiveness of a corresponding speaker recognition product.

Description

technical field [0001] The invention relates to the technical field of speech recognition, in particular to a speaker recognition method based on a Gaussian supervector and a deep neural network. Background technique [0002] Speaker recognition is a special biometric technology based on voice information. After decades of development, the speaker recognition technology under the condition of no noise interference has been relatively mature. The current mainstream methods are GMM-UBM, GMM-SVM and i-vector. However, in the actual application environment, due to the existence of background noise and channel noise, the performance of the speaker recognition algorithm will be significantly reduced. Therefore, how to improve the noise robustness of existing speaker recognition systems has become a research hotspot in this field in recent years. [0003] To solve this problem, researchers have tried at different levels of speech signal processing. Relevant literature proves th...

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): G10L17/02G10L17/08G10L17/18
CPCG10L17/02G10L17/08G10L17/18
Inventor 曾春艳马超峰武明虎朱栋梁赵楠朱莉王娟
Owner HUBEI UNIV OF TECH
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