A Backend i-vector Augmentation Method for Speaker Recognition System

A speaker recognition and speaker technology, applied in the field of speaker recognition, can solve the problems of complex system structure, increase of voice signal processing calculation, etc., to improve competitiveness, enhance real-time recognition, and improve system noise robustness Effect

Active Publication Date: 2020-07-24
NANJING UNIV OF POSTS & TELECOMM
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

If this method is simply used as the front-end module of the speaker recognition system, while improving the system performance to a certain extent, it also complicates the system structure and increases the amount of calculation for speech signal processing. Therefore, the integration of this method with the speaker recognition system Become the current technical difficulty

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
  • A Backend i-vector Augmentation Method for Speaker Recognition System
  • A Backend i-vector Augmentation Method for Speaker Recognition System
  • A Backend i-vector Augmentation Method for Speaker Recognition System

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The specific embodiments of the present invention will be further described below in conjunction with the accompanying drawings: figure 1 As shown, the technical solution adopted by the present invention is as follows: A DNN-based i-vector back-end enhancement method for speaker recognition system includes the following steps: divided into two stages: training and recognition, the training steps are:

[0031] The first step is to pre-process the speaker's speech signal, including pre-emphasis, endpoint detection, framing, and windowing.

[0032] (1) Pre-emphasis

[0033] Pre-emphasis is to pass the speech signal through a high-pass filter:

[0034] H(Z) = 1-μz -1

[0035] The value of μ in the formula is between 0.9-1.0, and we usually take 0.97. The purpose of pre-emphasis is to increase the high frequency part, flatten the frequency spectrum of the signal, and keep it in the whole frequency band from low frequency to high frequency, and can use the same signal-to-noise ratio t...

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 backend i-vector enhancement method for a speaker recognition system. The method is based on a deep neural network; and a backend i-vector regression model for the speaker recognition system is built on the basis of the application of the deep neural network in speech enhancement, and a backend feature processor applicable to the speaker recognition system is obtained. Compared with a conventional front-end speech enhancement algorithm, the backend i-vector enhancement method of the invention can improve the anti-noise performance of the speaker recognition system and optimize the structure model of the speaker recognition system, so that the practicability of the speaker recognition system in a noise environment can be effectively improved.

Description

Technical field [0001] The invention belongs to the technical field of speaker recognition, and particularly refers to a back-end i-vector enhancement method used in a speaker recognition system. Background technique [0002] Speaker Recognition (SR), also known as voiceprint recognition, is a biometric authentication technology that uses specific speaker information contained in the voice signal to identify the speaker. In recent years, the introduction of identity vector (i-vector) speaker modeling methods based on factor analysis has significantly improved the performance of speaker recognition systems. Experiments show that in the factor analysis of the speaker's speech, the channel subspace usually contains the speaker's information. Therefore, i-vector uses a low-dimensional total variable space to represent the speaker subspace and channel subspace, and maps the speaker's speech to this space to obtain a fixed-length vector representation (i-vector). The speaker recognit...

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): G10L15/02G10L15/06G10L15/07G10L17/02G10L17/04G10L25/18G10L25/30
CPCG10L15/02G10L15/063G10L15/07G10L17/02G10L17/04G10L25/18G10L25/30G10L2015/0635
Inventor 王昕张洪冉李宗晏
Owner NANJING UNIV OF POSTS & TELECOMM
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