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


 The Delphion Integrated View

  Buy Now:   Buy PDF- 15pp  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: US5293451: Method and apparatus for generating models of spoken words based on a small number of utterances
[ Derwent Title ]


Country: US United States of America

View Images High
Resolution

 Low
 Resolution

 
15 pages

 
Inventor: Brown, Peter F.; New York, NY
De Gennaro, Steven V.; Pawling, NY
Desouza, Peter V.; Mahopac Falls, NY
Epstein, Mark E.; Katonah, NY

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: 1994-03-08 / 1990-10-23

Application Number: US1990000602020

IPC Code: Advanced: G10L 15/06; G10L 15/14;
IPC-7: G10L 9/04;

ECLA Code: G10L15/063; G10L15/14M1;

U.S. Class: Current: 704/245; 704/E15.008; 704/E15.029;
Original: 395/002.54;

Field of Search: 395/2.54,2 381/029-53

Priority Number:
1990-10-23  US1990000602020

Abstract:     A method and apparatus for modeling words based on match scores representing (a) the closeness of a match between probabilistic word models and the acoustic features of at least two utterances, and (b) the closeness of a match between word models and the spelling of the word. A match score is calculated for a selection set of one or more probabilistic word models. A match score is also calculated for an expansion set comprising the probabilistic word models in the selection set and one probabilistic word model from a candidate set. If the expansion set match score improves the selection set match score by a selected nonzero threshold value, the word is modelled with the word models in the expansion set. If the expansion set match score does not improve the selection set match score by the selected nonzero threshold value, the word is modelled with the words in the selection set.

Attorney, Agent or Firm: Schechter, Marc D. ;

Primary / Asst. Examiners: Fleming, Michael R.; Doerrler, Michelle

Maintenance Status: E3 Expired  Check current status

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

Designated Country: DE FR GB IT 

Family: Show 7 known family members

First Claim:
Show all 16 claims
We claim:     1. A method of modeling a word uttered at least two times, each utterance having at least one acoustic feature having a value, said method comprising the steps of:
  • measuring the value of the acoustic feature of each utterance;
  • storing a selection set of one or more probabilistic word model signals, each probabilistic word model signal in the selection set representing a probabilistic model of the word;
  • calculating, for the selection set, a match score representing the closeness of a match between the probabilistic word models in the selection set and the value of the acoustic feature of each utterance;
  • storing a candidate set of one or more probabilistic word model signals, each probabilistic word model signal in the candidate set representing a probabilistic model of the word, each probabilistic word model in the candidate set being different from each probabilistic word model in the selection set;
  • storing an expansion set comprising the probabilistic word model signals in the selection set and one probabilistic word model signal from the candidate set;
  • calculating, for the expansion set, a match score representing the closeness of a match between the probabilistic word models in the expansion set and the value of the acoustic feature of each utterance; and
  • modeling the word with the word models in the expansion set if the expansion set match score surpasses the selection set match score by a nonzero threshold value.


Background / Summary: Show background / summary

Drawing Descriptions: Show drawing descriptions

Description: Show description

Forward References: Show 11 U.S. patent(s) that reference this one

       
U.S. References: Go to Result Set: All U.S. references   |  Forward references (11)   |   Backward references (7)   |   Citation Link

Buy
PDF
Patent  Pub.Date  Inventor Assignee   Title
Get PDF - 34pp US4297528  1981-08 Beno  Interstate Electronics Corp. Training circuit for audio signal recognition computer
Get PDF - 6pp US4731845  1988-02 Matsuki et al.  NEC Corporation Device for loading a pattern recognizer with a reference pattern selected from similar patterns
Get PDF - 13pp US4741036  1988-04 Bahl et al.  International Business Machines Corporation Determination of phone weights for markov models in a speech recognition system
Get PDF - 35pp US4759068  1988-07 Bahl et al.  International Business Machines Corporation Constructing Markov models of words from multiple utterances
Get PDF - 33pp US4783804  1988-12 Juang et al.  American Telephone and Telegraph Company, AT&T Bell Laboratories Hidden Markov model speech recognition arrangement
Get PDF - 39pp US4837831  1989-06 Gillick et al.  Dragon Systems, Inc. Method for creating and using multiple-word sound models in speech recognition
Get PDF - 30pp US4903305  1990-02 Gillick et al.  Dragon Systems, Inc. Method for representing word models for use in speech recognition
       
Foreign References:
Buy
PDF
Publication Date IPC Code Assignee   Title
Get PDF - 5pp EP0305215 1898-04  G10L 5/06 BRITISH TELECOMM Speech recognition 


Other Abstract Info: DERABS G92-142542

Other References:
  • Bahl, L. R., et al. "Automatic Determination of Pronunciation of Words From Their Spellings." , IBM Technical Disclosure Bulletin, vol. 32, No. 10B, Mar. 1990, pp. 19-23.
  • Lucassen, J. M., et al. "An Information Theoretic Approach to the Automatic Determination of Phonemic Baseforms." Proceedings of the 1984 IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 3, pp. 42.5.1-42.5.4, Mar. 1984.
  • Wilpon and Rabiner. "A Modified K-Means Clustering Algorithm for Use in Isolated Word Recognition." IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. ASSP-33, No. 3, Jun. 1985, pp. 587-594. (8 pages) Cited by 7 patents
  • "Composite Fenemic Phones," Research Disclosure, Emsworth, Hampshire, Great Britain, No. 256, Aug. 1985, p. 418.
  • Le K-F. "Allophone Clustering for Continuous Speech Recognition." 1990 International Conference on Acoustics, Speech, and Signal Processing, Albuquerque, New Mexico, USA, Apr. 1990, pp. 749-752.


  • 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