Method for recognizing text-independent voice prints

A text-independent, voiceprint technology, used in speech recognition, speech analysis, instruments, etc., can solve problems such as high technical content requirements, poor flexibility and fault tolerance, and no speaker voice content, and achieve recognition efficiency. High, accurate results

Inactive Publication Date: 2012-12-19
镇江佳得信息技术有限公司
View PDF4 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Both the text-prompted type and the text-related type require the user to pronounce according to the specified content, and build a model to match according to the content of the pronunciation. Although this can make the matching effect better, it requires the user's full cooperation, and the flexibility and fault tolerance are not good; and For the text-independent type, the content of the speaker's voice is not specified. As long as the speaker's voice is recorded in the system, the speaker can be identified. Therefore, the technical content of identifying text-independent voiceprints is relatively high. It is not only The problem of matching judgment needs to be solved, and the speech features of the speaker need to be extracted in advance before judgment can be made

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 recognizing text-independent voice prints
  • Method for recognizing text-independent voice prints

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] specific implementation plan

[0021] The step flow chart of a method for identifying text-independent voiceprints of the present invention is as follows figure 1 shown, including the following steps:

[0022] Firstly, all the acoustic models for the user set are established. The flow chart of the steps is as follows: figure 1 As shown: the user’s speaker’s voice signal is collected by the peripheral audio collection device; the collected continuous speech signal is preprocessed; the feature value is extracted from the collected continuous speech signal; the extracted feature value pair is used to establish the The acoustic model of the speaker; store the acoustic model in the speech feature library;

[0023] Then carry out model matching and identification for the current user to be identified, the flow chart of the steps is as follows figure 1 Shown: Use the peripheral audio acquisition equipment to collect the speaker's speech signal; preprocess the collected cont...

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 recognizing text-independent voice prints and belongs to the field of voice signal processing. The method comprises the following steps: firstly, creating all acoustic models aiming at a user set: collecting voice signals of speakers in users by using external voice frequency collecting equipment, creating acoustic models for the speakers, and storing the acoustic models in a phonetic feature library; and matching and recognizing the models for existing users to be recognized: collecting voice signals of existing speakers by using the external voice frequency collecting equipment, creating acoustic models for the existing speakers, matching the acoustic models of the existing speakers with the all acoustic models in the phonetic feature library, and returning the most closely matched model numbers obtained by the calculation, thus identifying the users to be recognized. The method of the invention is high in the reorganization rate and exact in the result.

Description

technical field [0001] The invention belongs to the field of speech signal processing and relates to a method for recognizing text-independent voiceprints. Background technique [0002] Because each person's pronunciation organs are different, the sounds and tones they emit are different. Therefore, voiceprint is actually irreplaceable and stable as a basic feature to realize people's identification. From the perspective of the use occasions of voiceprint recognition, the source of the sound that needs to be identified is basically divided into three situations, namely, text prompt type, text-related type and text-independent type. Both the text-prompted type and the text-related type require the user to pronounce according to the specified content, and build a model to match according to the content of the pronunciation. Although this can make the matching effect better, it requires the user's full cooperation, and the flexibility and fault tolerance are not good; and For ...

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): G10L15/02G10L15/06
Inventor 周晓东刘镇
Owner 镇江佳得信息技术有限公司
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