Work Files Saved Searches
   My Account                                                  Search:   Quick/Number   Boolean   Advanced       Help   

 The Delphion Integrated View

  Buy Now:   Buy PDF- 5pp  PDF  |   File History  |   Other choices   
  Tools:  Citation Link  |  Add to Work File:    
  View:  Expand Details   |  INPADOC   |  Jump to: 
 Email this to a friend  Email this to a friend 
Title: US5995934: Method for recognizing alpha-numeric strings in a Chinese speech recognition system
[ Derwent Title ]

Country: US United States of America

View Images High


5 pages

Inventor: Tang, Donald T.; Beijing, China

Assignee: International Business Machines Corporation, Armonk, NY
other patents from INTERNATIONAL BUSINESS MACHINES CORPORATION (280070) (approx. 44,393)
 News, Profiles, Stocks and More about this company

Published / Filed: 1999-11-30 / 1998-08-28

Application Number: US1998000143186

IPC Code: Advanced: G10L 15/26;
Core: G10L 15/00;
IPC-7: G10L 9/06;

ECLA Code: G10L15/26A;

U.S. Class: Current: 704/270; 704/003; 704/009; 704/010; 704/256; 704/E15.045;
Original: 704/270; 704/003; 704/009; 704/256;

Field of Search: 704/270,256,3,9

Priority Number:
1997-09-19  CN1997000119650

Abstract: A recognition method for alpha-numeric strings in a Chinese speech recognition system, uses a special coding scheme to map each of 36 alpha-numeric symbols into an easily remembered Chinese idiom or word consisting of a multiple of Chinese characters. When representing a numeral, each idiom/word starts with the Chinese character for that numeral. When representing an English alphabet letter, each idiom/word will have a first character which starts with that English alphabet letter in its Pinyin form. If it is necessary to include some control words, idiom/words similar in semantics can be used. The method resolves the problem of unreliable recognition when a string of random alpha-numeric symbols or some control words are inputted by voice to a Chinese speech recognition system.

Attorney, Agent or Firm: Tassinari, Robert P. ;

Primary / Asst. Examiners: Wieland, Susan;

INPADOC Legal Status: Show legal status actions          Buy Now: Family Legal Status Report

Family: Show 5 known family members

First Claim:
Show all 2 claims
I claim:     1. A recognition method for alpha-numeric strings in a Chinese speech recognition system, characterized by the steps of:
  • a) selecting a coding scheme to map each alphabet letter, numeral or command into an easily remembered Chinese idiom or word consisting of a multiple of Chinese characters, which is referred to as encoded word;
  • b) creating a special vocabulary, each word of which is an alphabet letter, numeral or command; and the speech of said word is the Pinyin of its corresponding encoded word;
  • c) receiving an alphabet letter, numeral or command inputted by the speech of said encoded word, and recording the context of the speech;
  • d) determining the inputted alphabet, numeral or command by referring to said special vocabulary on the basis of acoustic model and language model.

Background / Summary: Show background / summary

Drawing Descriptions: Show drawing descriptions

Description: Show description

Forward References: Show 6 U.S. patent(s) that reference this one

U.S. References: Go to Result Set: All U.S. references   |  Forward references (6)   |   Backward references (3)   |   Citation Link

Patent  Pub.Date  Inventor Assignee   Title
Get PDF - 21pp US5764851  1998-06 Pengwu  Industrial Technology Research Institute Fast speech recognition method for mandarin words
Get PDF - 19pp US5787230  1998-07 Lee   System and method of intelligent Mandarin speech input for Chinese computers
Get PDF - 38pp US5903861  1999-05 Chan   Method for specifically converting non-phonetic characters representing vocabulary in languages into surrogate words for inputting into a computer
Foreign References: None

Inquire Regarding Licensing

Powered by Verity

Plaques from Patent Awards      Gallery of Obscure PatentsNominate this for the Gallery...

Thomson Reuters Copyright © 1997-2014 Thomson Reuters 
Subscriptions  |  Web Seminars  |  Privacy  |  Terms & Conditions  |  Site Map  |  Contact Us  |  Help