Method for distinguishing speakers based on protective kernel Fisher distinguishing method

An implementation method and speaker technology, applied in character and pattern recognition, speech analysis, instruments, etc., can solve problems such as low recognition rate, slow speed, and complex model construction

Inactive Publication Date: 2010-02-17
ZHEJIANG UNIV OF TECH
View PDF7 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the disadvantages of low recognition rate, complex model construction, and slow speed of the existing speaker identification implementation methods, the present invention provides a Fisher discriminant based on class-preserving kernel with high recognition rate, simple model construction, and good rapidity. method of speaker identification

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
  • Method for distinguishing speakers based on protective kernel Fisher distinguishing method
  • Method for distinguishing speakers based on protective kernel Fisher distinguishing method
  • Method for distinguishing speakers based on protective kernel Fisher distinguishing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0063] The present invention will be further described below.

[0064] A method for implementing speaker identification based on the class-preserving kernel Fisher discriminant method, comprising the following steps:

[0065] ①. Preprocessing of voice signals: preprocessing of voice signals;

[0066] ②. Feature parameter extraction: After the speech signal is framed and detected, the Mel cepstrum parameters are extracted as the speaker feature vector. The Mel cepstrum parameters are 13th order cepstrum parameters, and the speaker feature description is removed. Fewer 0th order parameters, convert each frame of speech signal into 12-dimensional Mel cepstrum feature vector;

[0067] ③. Speaker identification model construction:

[0068] set x i ∈R d (i=1, 2, ..., N) is d-dimensional sample data, y i ∈ {1, 2, ..., c} is the corresponding class label, where N is the total number of samples, c is the total number of classes, c l is the number of samples of class l, then:

[...

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 relates to a method for distinguishing speakers based on a protective kernel Fisher distinguishing method. The method comprises steps as follows: (1) pretreating voice signals; (2) extracting characteristic parameters: after framing and end point detection of voice signals, extracting Mel frequency cepstrum coefficients as characteristic vectors of speakers; (3) creating a speaker distinguishing model; (4) calculating model optimal projection vector: by using optimal solution of LWFD method, calculating to obtain an optimal projection vector group; (5) distinguishing speakers: projecting original data xi to yi belonging to R<r>( r is more than or equal to 1 and less than or equal to d) according to optimal projection classification vector phi, wherein r is cut dimensionality;the optimal projection classification dimensionality of original c type data space is c-1, then solving a central value of data of each type after injection and normalizing; after projecting data tobe classified to a sub space and normalizing, calculating Euclidean distance from the normalized protecting data to the central point of each type of data in the sub space, and judging the nearest tobe a distinguishing result. The invention has high distinguishing rate, simple model construction and favorable rapidity.

Description

technical field [0001] The invention relates to the fields of signal processing, machine learning and pattern recognition, in particular to a method for realizing speaker identification. Background technique [0002] Speaker recognition (Speaker Recognition, SR), also known as speaker recognition, refers to the technology of automatically confirming the speaker through the analysis and processing of the speaker's voice signal. The speaker identification involved in the present invention is an important branch of speaker identification. The speaker recognition system must identify which one of the individuals to be investigated the speech to be recognized comes from, and sometimes reject the speech from other than this person. Speaker identification is a process of pattern matching. In this process, the computer first establishes a speech model according to the speaker's speech characteristics; that is, it analyzes the input speech signal and extracts the speaker's personali...

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): G10L17/00G10L17/04
CPCG06K9/6234G06F18/2132
Inventor 王万良郑建炜王震宇韩姗姗蒋一波郑泽萍王磊陈胜勇
Owner ZHEJIANG 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