Speaker identifying method and system

A speaker recognition and speaker technology, applied in the field of speaker recognition methods and systems, can solve the problems of inaccurate model training, and the recognition performance is easily affected by interference signals, and achieve the effects of improving the recognition rate, not easy to imitate, and system stability.

Inactive Publication Date: 2013-03-13
镇江每科电子科技有限公司
View PDF5 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It is necessary to solve the problems of feature extraction and model training in the existing technology that are not accurate enough, and the recognition performance is easily affected by interference signals.

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 identifying method and system
  • Speaker identifying method and system
  • Speaker identifying method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] In order to make the above-mentioned functions, processes and advantages of the present invention more obvious and easy to understand, the related technologies involved in the present invention will be introduced in detail one by one below.

[0046] refer to figure 2 , showing an embodiment of the present invention for establishing a general background model, which specifically includes the following steps:

[0047] Step 201, collecting a voice database containing a large number of (for example: 1000 or 10000) speakers;

[0048] Step 202, converting the speech signal in the speech database into cepstral features;

[0049] Step 203, using the cepstrum features of all speakers in the database to calculate the Gaussian mixture model and feature transformation prior matrix;

[0050] Step 204, calculating the mean vector and feature transformation matrix of the specific Gaussian mixture model for each speaker in the database, vectorizing the matrix and concatenating it into...

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 identifying method and a system. The speaker identifying method comprises the following steps of: establishing a universal background model; establishing a to-be-identified speaker module; and using a training voice signal of the speaker to identify the speaker. Compared with the prior art, the invention has the following advantages that the high-performance speaker identifying system is disclosed by combining model space transformation and characteristic space transformation, and personal pronunciation features of the speaker are comprehensively reflected by the transformation of the two spaces. The transformation of the two spaces is calculated by using a self-adaptive algorithm based on the universal background model, so that good stability is achieved. Compared with the way of identifying the speaker by independently adopting model space transformation in the prior art, the identification rate of the system is greatly improved. Meanwhile, the system is more stable, and not easy to imitate.

Description

technical field [0001] The invention relates to the field of biological feature identification. In particular, it relates to a speaker recognition method and system. Background technique [0002] Speaker recognition is a technology that automatically identifies the identity of the speaker based on the speech signal. Speaker recognition is a biometric technology. Biometric recognition technology is a technology that uses biological characteristics to automatically identify individuals, including fingerprint recognition, iris recognition, gene recognition, face recognition, and so on. Speaker recognition uses speech signals for identity recognition, which has the advantages of natural human-computer interaction, easy extraction of speech signals, and remote recognition. [0003] Speaker recognition is a speech signal processing technique. Speech signal processing technology is a technology to extract target information from speech signals, including speech recognition, spe...

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): G10L17/04
Inventor 朱东来鄂小松
Owner 镇江每科电子科技有限公司
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