Method for identifying all languages by voice and inputting individual characters by voice

A technology of voice input and single character, applied in the field of voice recognition of all languages ​​and voice input of single characters, which can solve the problems of difficulty in compressing the same features, complicated and time-consuming compression process, and poor voice recognition.

Inactive Publication Date: 2012-11-07
黎自奋 +4
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the compression process is complex and time-consuming, and it is difficult to compress the same features of the same tone to the same time position, and it is difficult to identify similar tones
As for voice input text, there is no way at present, because the current computer voice recognition is not very good

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 identifying all languages by voice and inputting individual characters by voice
  • Method for identifying all languages by voice and inputting individual characters by voice
  • Method for identifying all languages by voice and inputting individual characters by voice

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0095] The present invention will be further described below with reference to the embodiments. The embodiments of the present invention are only used to illustrate the technical solutions of the present invention and do not limit the present invention.

[0096] use figure 1 and figure 2 Describe the procedure for implementing the invention. figure 1 Indicates the establishment of m databases of common words with different similar sounds, and m groups of unigrams with different similar sounds. figure 2 Indicates that the user recognizes words and sentences and enters the words to execute the program.

[0097] First, there are m different unknown tones and sample 1, and the continuous sound wave of an unknown single-tone sample is converted into a digitized signal point 10, and noise or silence 20 is removed. The method of the present invention is to calculate the sum of the distance between two consecutive signal points and the sum of general noise or silence in a short p...

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 provides a method for identifying all languages by voice and inputting individual characters by voice. The invention is characterized by representing m inhomogeneities with a group of m unknown or known different monotones; pronouncing common single words once; converting the pronunciation of each single word into a linearity preestimate coding cepstrum matrix; classifying the common words into one type in m types by a bayesian classification method or a distance classification method; looking for F most similar unknown monotones from the m unknown monotones by the bayesian classification method or the distance classification method after a user pronounces a single word tone; and arranging all single words according to the degree of similarity and letters (or stroke number) of the single word to be pronounced in F types represented by the F similar unknown monotones; and the words required can be found quickly after the user pronounced. The invention has the advantages that the method is simple, a sample is not required, typewriting is not required, each person can be qualified, the words with non-standard pronunciation or mispronunciation also can be input, the speed is rapid, and the accuracy rate is high.

Description

technical field [0001] Chinese has 408 single tones, plus four tones, modern phonetic methods can not recognize 408 × 4 single tones, English more. The present invention divides common words into m (=500) or so different similar sound groups (classes), and the words of each class of similar sounds are represented by an unknown similar sound. When the user pronounces a single word, the present invention uses the Bayesian classification method to find out several unknown single sounds that are most similar to the pronunciation of the single word in m types of unknown single sounds, and then from the class represented by these several similar unknown single sounds. Find the word and sentence you want. [0002] The present invention uses 12 elastic frames (windows) of equal length, no filter, and no overlap to convert a single tone sound wave of different lengths into a 12×12 linear prediction coding cepstrum (LPCC) matrix. [0003] The invention includes the Bayesian comparison...

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): G10L15/06G10L15/08G06F3/16G10L15/07
Inventor 黎自奋李台珍黎世聪黎世宏廖丽娟
Owner 黎自奋
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