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

Large-scaled speaker identification method

A speaker identification and speaker technology, which is applied in the fields of biometrics, computer science and speech processing, can solve the problems of difficulty in meeting the needs of practical applications and the decline in accuracy

Inactive Publication Date: 2013-08-21
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF3 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when the number of people to be identified continues to increase, the accuracy of the above method will drop significantly. When the number of people increases to a certain scale, it will be difficult to meet the needs of practical applications. This is an important problem that text-independent speaker recognition technology needs to solve

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
  • Large-scaled speaker identification method
  • Large-scaled speaker identification method
  • Large-scaled speaker identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0080] In order to better illustrate the purpose and advantages of the present invention, the implementation of the method of the present invention will be further described in detail below in conjunction with the accompanying drawings and examples.

[0081] All the following tests are completed on the same computer, the specific configuration is: Intel dual-core CPU (main frequency 1.8G), 1G memory, WindowsXP SP3 operating system.

[0082] first link

[0083] This section will use the voice files of the TIMIT audio library to describe in detail the specific process of speaker registration / training and speaker identification in the present invention when the target speaker size is 600.

[0084] The TIMIT speech library is a standard library jointly produced by MIT, Stanford Research Institute, and Texas Instruments. It contains the corpus of 630 speakers (438 males and 192 females), each with 10 voices.

[0085] Randomly select all voice data of 600 people from all speakers, ...

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 text-independent speaker identification method, wherein the text-independent speaker identification method is based on 2D-Haar voice frequency characteristics and suitable for large-scaled speakers. The invention provides conception and a calculation method of the 2D-Haar voice frequency characteristics, and foundational voice frequency characteristics are used to form a voice frequency characteristic graph at first; then the voice frequency characteristic graph is used to extract 2D-Haar voice frequency characteristics; then an AdaBoost.MH algorithm is used to accomplish screening of the 2D-Haar voice frequency characteristics and training of a speaker classifier; finally the trained speaker classifier is used to achieve the identification of speakers. Compared with the prior art, the large-scaled speaker identification method can effectively restrain decay of identification accuracy rate in a large-scale speaker identification situation, and has high identification accuracy rate and identification speed. The text-independent speaker identification method is not only applied to a desktop computer, but also applied to mobile calculation platforms like a cell phone, a tablet and the like.

Description

technical field [0001] The invention relates to a text-independent speaker identification method suitable for large-scale speakers, which belongs to the technical field of biological identification; from the perspective of technical realization, it also belongs to the technical field of computer science and voice processing. Background technique [0002] Speaker Identification (Speaker Identification) technology is an important branch of Speaker Recognition (SR) technology. It uses the characteristics of each speaker's voice signal to extract speaker information from a piece of voice, and then judges whether the voice is Which one of several people said is a "many choice one" pattern recognition problem. With the rapid development of modern electronic technology in recent years, the application requirements of speaker recognition technology have become stronger and stronger (such as court identification, criminal suspect voice tracking and positioning, voice retrieval, etc.)...

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): G10L17/02
Inventor 罗森林谢尔曼潘丽敏
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
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