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


 The Delphion Integrated View

  Buy Now:   Buy PDF- 11pp  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: US5963905: Method and apparatus for improving acoustic fast match speed using a cache for phone probabilities
[ Derwent Title ]


Country: US United States of America

View Images High
Resolution

 Low
 Resolution

 
11 pages

 
Inventor: Novak, Miroslav; Mohegan Lake, NY
Picheny, Michael Alan; White Plains, 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: 1999-10-05 / 1997-10-24

Application Number: US1997000957200

IPC Code: IPC-7: G10L 5/06;

ECLA Code: G10L15/10; S10L15/08A;

U.S. Class: Current: 704/254; 704/243; 704/256; 704/256.4;
Original: 704/254; 704/256; 704/243;

Field of Search: 704/256,254,243

Priority Number:
1997-10-24  US1997000957200

Abstract:     Methods and apparatus for performing a tree search based acoustic fast match in a speech recognition system for decoding a speech utterance, the tree having a tree root and tree nodes connected by tree branches, the tree nodes having phonetic models associated therewith, are provided. An illustrative embodiment of the method comprises: providing a cache having cache cells for storing phone probabilities therein; selecting a first branch leading to a next node, said branch selection starting at the tree root; accessing the cache to select a particular cache cell where the probability of a particular match is stored; evaluating the phonetic model to obtain the probability and storing the probability and an associated end time in the cache cell, if the cache cell accessed in the accessing step does not contain the required probability; using the probability value and the associated end time stored in the cache cell, if the cache cell accessed in the accessing step contains the required probability; selecting a new branch to proceed to the next node; and iteratively continuing from the accessing step until the whole tree is traversed and all possible word candidates associated with the speech recognition system are evaluated.

Attorney, Agent or Firm: F. Chau & Associates, LLP ;

Primary / Asst. Examiners: Hudspeth, David R.; Abebe, Daniel

INPADOC Legal Status: Show legal status actions

Family: None

First Claim:
Show all 18 claims
What is claimed is:     1. A method for performing a tree search based acoustic fast match in a speech recognition system for decoding a speech utterance, the tree having a tree root and tree nodes connected by tree branches, the tree nodes having phonetic models associated therewith, the method comprising the steps of:
  • (a) providing a cache having cache cells for storing phone probabilities therein;
  • (b) selecting a first branch leading to a next node, said branch selection starting at the tree root;
  • (c) accessing the cache to select a particular cache cell where the probability of a particular match is stored;
  • (d) evaluating the phonetic model to obtain the probability and storing the probability and an associated end time in the cache cell, if the cache cell accessed in the accessing step does not contain the required probability;
  • (e) using the probability value and the associated end time stored in the cache cell, if the cache cell accessed in the accessing step contains the required probability;
  • (f) selecting a new branch to proceed to the next node; and
  • (g) iteratively continuing from the accessing step until the tree is traversed and the word candidates associated with the speech recognition system are evaluated.


Background / Summary: Show background / summary

Drawing Descriptions: Show drawing descriptions

Description: Show description

Forward References: Show 3 U.S. patent(s) that reference this one

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

Buy
PDF
Patent  Pub.Date  Inventor Assignee   Title
Get PDF - 35pp US4759068  1988-07 Bahl et al.  International Business Machines Corporation Constructing Markov models of words from multiple utterances
Get PDF - 50pp US4977599  1990-12 Bahl et al.  International Business Machines Corporation Speech recognition employing a set of Markov models that includes Markov models representing transitions to and from silence
Get PDF - 17pp US5621859  1997-04 Schwartz et al.  BBN Corporation Single tree method for grammar directed, very large vocabulary speech recognizer
       
Foreign References: None

Other References:
  • Gopalakrishnan et al., "A Tree Search Strategy for Large-Vocabulary Continuous Speech Recognition", Proceedings of the IEEE ICASSP, pp. 572-575, 1995.
  • Bahl et al., "Performance of the IBM Large Vocabulary Continuous Speech Recognition System on the ARPA Wall Street Journal Task", Proceedings of the IEEE ICASSP, pp. 41-44, 1995.
  • Bahl et al., "A Fast Approximate Acoustic Match for Large Vocabulary Speech Recognition", IEEE Transactions on Speech and Audio Processing, vol. 1, No. 1, pp. 59-67, Jan. 1993.
  • Austin et al., "The Forward-Backward Search Algorithm", Proceedings of the IEEE ICASSP, pp. 697-700, 1991.
  • Bahl et al., "A Maximum Likelihood Approach to Continuous Speech Recognition", IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-5, No. 2, pp. 179-190, Mar. 1983. (12 pages) Cited by 42 patents


  • 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