Unlock instant, AI-driven research and patent intelligence for your innovation.

Phonic proving method for speech recognition system

A technology of speech recognition and verification methods, applied in speech recognition, speech analysis, instruments, etc., which can solve problems such as difficult to diversify speech, difficult to ensure normal system performance, etc.

Inactive Publication Date: 2009-02-04
LG ELECTRONIC (HUIZHOU) CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0028] However, the existing pronunciation verification method with the above characteristics, although judging whether the input voice is normally recognized or not, this method is difficult to fully reflect the diverse voices in fact, and the noise is very heavy in cars and the like. environment, it is difficult to ensure the normal performance of the system
[0029] In addition, in the case of ambiguous pronunciation, assuming that the credibility value is less than a certain cancellation rate, it is judged as the result of misrecognition and canceled, but it is also possible to judge it as the result of misrecognition of normal pronunciation

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
  • Phonic proving method for speech recognition system
  • Phonic proving method for speech recognition system
  • Phonic proving method for speech recognition system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] Embodiments of the pronunciation verification method of the speech recognition system of the present invention will be described in detail below with reference to the accompanying drawings.

[0053] Fig. 3 is a schematic diagram of structural modules of the speech recognition system in the embodiment of the present invention.

[0054] As shown in Figure 3, the speech recognition system among the present invention is made up of following structure: That is, detect the speech detector 300 of input speech interval; From above-mentioned speech detector 300, extract the feature extractor 310 of feature; Viterbi searcher 320 for Viterbi search of signal extracted in device 310 and pronunciation dictionary; identify keywords from Viterbi searcher 320, and refer to semiphone model database 360, verify pronunciation verifier 350 of pronunciation.

[0055] That is to say, after the voice information is input, the voice detector 300 will search the voice intervals except the inter...

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

This invention relates to a pronunciation verification method for a phone identification system including: testing the end of a related phone once receiving the phone order input by a user and picking up the existing part to continue picking up characters needed to be identified for phones to carry out phone identification by Viterbi search then evaluate the trust degree of the identified phone data and determine if it is greater than the pre-designed critical value, if so, a determined order of the identified data will be sent to the user and refresh said critical value before receiving the ACK order input by the user.

Description

(1) Technical field [0001] The invention relates to a pronunciation verification method of a speech recognition system for canceling misrecognized words or articles in the speech recognition system. (2) Background technology [0002] As the core technology of HCI, speech recognition technology develops simultaneously with the information age, its necessity is gradually increasing, and it is widely used in many application fields. [0003] From an industrial perspective, speech recognition technology is gradually developing into the basic technology of the next-generation user interface in various industrial fields such as information communication industry, information processing industry, home appliance industry, and automobile industry, and its own market size will also increase. It will also make an indelible contribution to the rapid expansion and creation of high added value in other industrial fields. [0004] As speech recognition technology is becoming more and more...

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 Patents(China)
IPC IPC(8): G10L15/08G10L15/00G10L25/78
Inventor 郑斗景
Owner LG ELECTRONIC (HUIZHOU) CO LTD