Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Discriminant local information distance preserving projection-based speaker confirmation method

A technology of speaker confirmation and local information, applied in speech analysis, instruments, etc., can solve the problems that the distinguishability of confusing speech needs to be improved, no focus on confusing speech, low dimensionality, etc.

Inactive Publication Date: 2018-01-26
TSINGHUA UNIV
View PDF6 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

2) Low dimensionality
However, the i-vector / PLDA technology also has shortcomings: this method maximizes the distance between all projected heterogeneous points, without focusing on the confusing speech from different classes but very similar distances, and the distinction of confusing speech Need to be improved; global linearity is also a constraint for the continued development of this technology
Compared with the traditional principal component analysis (PCA), linear discriminant analysis (LDA), and probabilistic linear discriminant analysis (PLDA) dimensionality reduction methods (please give the corresponding Chinese name), manifold learning has achieved very good results in pattern recognition problems. Recognition effect, but immature in the field of speaker verification

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
  • Discriminant local information distance preserving projection-based speaker confirmation method
  • Discriminant local information distance preserving projection-based speaker confirmation method
  • Discriminant local information distance preserving projection-based speaker confirmation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] The present invention proposes a discriminative local information distance-preserving mapping speaker confirmation method, which will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0062] The present invention proposes a speaker confirmation method for discriminative local information distance-preserving mapping. The overall process is as follows: figure 1 shown, including the following steps:

[0063] 1) Training stage; specifically includes the following steps:

[0064] 1.1) 1.1) Obtain the training voice data from the SRE10 database, the number of speakers corresponding to the training voice data is S (S ≥ 500, S=1265 in the present embodiment), and the training voice data of each speaker is greater than or equal to 5 pieces (in the present embodiment, each speaker has 10 pieces of training speech data), there are altogether N pieces of training speech data (N≥2500, N=1265*10=12650 in the present embodi...

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 present invention provides a discriminant local information distance preserving projection-based speaker confirmation method and belongs to the voiceprint recognition, pattern recognition and machine learning field. According to the method, speech data are obtained in a training phase; the i-vector of each training speech datum is extracted; the i-vector of each speaker is extracted accordingto training speech data corresponding to each speaker; training is performed, so that a discriminant local preserving projection matrix is obtained; during a speaker confirming phase, speech data to be tested are acquired, one speaker of the training speech data is selected, a distance between the speech data to be tested and the i-vector of the speaker is calculated; and if the distance is smaller than a preset distance threshold value, it is determined that the speech data to be tested belong to the speaker; and the confirmation of the speaker is completed. The method of the invention has high applicability, focuses on heterogeneous neighbor points, enhances the discrimination of the easily-confounded speech of speakers, has better distinguishing capability and improves the accuracy of speaker confirmation.

Description

technical field [0001] The invention belongs to the technical fields of voiceprint recognition, pattern recognition and machine learning, and in particular relates to a speaker confirmation method for discriminative local information distance-preserving mapping. Background technique [0002] Speaker confirmation refers to confirming the identity of the speaker based on the speaker-related information contained in the voice. With the rapid development of information technology and communication technology, speaker confirmation technology has received more and more attention and has been widely used in many fields. application. Such as identification, apprehension of criminals in the telephone channel, identity confirmation in court based on telephone recordings, telephone voice tracking, and anti-theft door opening functions. In the field of Internet applications and communications, speaker confirmation technology can be applied to voice dialing, telephone banking, telephone...

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): G10L17/04G10L17/08
Inventor 何亮陈仙红徐灿刘加
Owner TSINGHUA UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products