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: US6157910: Deferred correction file transfer for updating a speech file by creating a file log of corrections
[ Derwent Title ]


Country: US United States of America

View Images High
Resolution

 Low
 Resolution

 
5 pages

 
Inventor: Ortega, Kerry A.; Deerfield Beach, FL

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: 2000-12-05 / 1998-08-31

Application Number: US1998000144013

IPC Code: Advanced: G10L 15/06; G10L 15/18;
IPC-7: G10L 15/00;

ECLA Code: G10L15/07; S10L15/063C; S10L15/063M; S10L15/183;

U.S. Class: Current: 704/231; 704/235; 704/243; 704/251; 704/E15.011; 715/202; 715/204; 715/234;
Original: 704/231; 704/251; 704/235; 704/243; 707/533;

Field of Search: 704/009,23,251,235,260,270,243,275 707/532,533

Priority Number:
1998-08-31  US1998000144013

Abstract:     A method for updating an original speaker's speech file in a speech application, comprises the steps of: creating a recognition file during a speech recognition session using the original speaker's language model on a first machine and with a first user identification; copying the recognition file; creating a file log of corrections, including changes to the language model and baseforms for newly added words, during a correction session utilizing the copied recognition file and out of association with the original speaker's language model in the first machine with the first user identification; and, copying the changes to the language model and the baseforms for newly added words from the file log back to the original speaker's speech file on the first machine using the first user identification. The copied recognition file can be opened and corrected on a second machine or with a second user identification.

Primary / Asst. Examiners: Kuntz, Curtis A.; Chawan, Vijay B

Maintenance Status: E1 Expired  Check current status

INPADOC Legal Status: Show legal status actions

Family: None

First Claim:
Show all 12 claims
What is claimed is:     1. A method for updating an original speaker's speech file in a speech application, comprising the steps of:
  • (a) creating a recognition file during a speech recognition session using said original speaker's language model on a first machine and with a first user identification;
  • (b) copying said recognition file;
  • (c) creating a file log of corrections, including changes to said language model and baseforms for newly added words, during a correction session utilizing said copied recognition file and out of association with said original speaker's language model in said first machine with said first user identification; and,
  • (d) copying said changes to said language model and said baseforms for newly added words from said file log back to said original speaker's speech file on said first machine using said first user identification.


Background / Summary: Show background / summary

Drawing Descriptions: Show drawing descriptions

Description: Show description

Forward References: Show 8 U.S. patent(s) that reference this one

       
U.S. References: Go to Result Set: All U.S. references   |  Forward references (8)   |   Backward references (10)   |   Citation Link

Buy
PDF
Patent  Pub.Date  Inventor Assignee   Title
Get PDF - 39pp US4829576  1989-05 Porter  Dragon Systems, Inc. Voice recognition system
Get PDF - 19pp US5127055  1992-06 Larkey  Kurzweil Applied Intelligence, Inc. Speech recognition apparatus & method having dynamic reference pattern adaptation
Get PDF - 14pp US5185887  1993-02 Takahashi et al.  Hitachi, Ltd. Database generation management method and system
Get PDF - 19pp US5787230  1998-07 Lee   System and method of intelligent Mandarin speech input for Chinese computers
Get PDF - 15pp US5864805  1999-01 Chen et al.  International Business Machines Corporation Method and apparatus for error correction in a continuous dictation system
Get PDF - 18pp US5875443  1999-02 Nielsen  Sun Microsystems, Inc. Internet-based spelling checker dictionary system with automatic updating
Get PDF - 69pp US5883986  1999-03 Kopec et al.  Xerox Corporation Method and system for automatic transcription correction
Get PDF - 59pp US5907825  1999-05 Tzirkel-Hancock  Canon Kabushiki Kaisha Location of pattern in signal
Get PDF - 7pp US5970451  1999-10 Lewis et al.  International Business Machines Corporation Method for correcting frequently misrecognized words or command in speech application
Get PDF - 3pp US6023678  2000-02 Lewis et al.  International Business Machines Corporation Using TTS to fill in for missing dictation audio
       
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