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

 The Delphion Integrated View

  Buy Now:   Buy PDF- 29pp  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: US6374216: Penalized maximum likelihood estimation methods, the baum welch algorithm and diagonal balancing of symmetric matrices for the training of acoustic models in speech recognition
[ Derwent Title ]

Country: US United States of America

View Images High


29 pages

Inventor: Micchelli, Charles A.; Mohegan Lake, NY
Olsen, Peder A.; New York, 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: 2002-04-16 / 1999-09-27

Application Number: US1999000404995

IPC Code: Advanced: G10L 15/06;
IPC-7: G10L 15/08; G10L 15/12;

ECLA Code: G10L15/063;

U.S. Class: 704/236; 704/231;

Field of Search: 704/251-256,236-240

Priority Number:
1999-09-27  US1999000404995

Abstract:     A nonparametric family of density functions formed by histogram estimators for modeling acoustic vectors are used in automatic recognition of speech. A Gaussian kernel is set forth in the density estimator. When the densities are found for all the basic sounds in a training stage, an acoustic vector is assigned to a phoneme label corresponding to the highest likelihood for the basis of the decoding of acoustic vectors into text.

Attorney, Agent or Firm: Whitham, Curtis & Christofferson, P.C. ; Kaufman, Stephen C. ;

Primary / Asst. Examiners: Dorvil, Richemond; Nolan, Daniel A.

Maintenance Status: E1 Expired  Check current status

INPADOC Legal Status: Show legal status actions

Family: None

First Claim:
Show all 15 claims
Having thus described our invention, what we claim as new and desire to secure by Letters Patent is as follows:     1. A computer implemented method for machine recognition of speech, comprising the steps of:
  • inputting acoustic data;
  • forming a nonparametric density estimator [Figure]
  • is some specified positive kernel function, [Figure]
  • are parameters to be chosen, and {xi }iεZn is a given set of training data;
  • setting a kernel for the estimator;
  • selecting a statistical criterion to be optimized to find values for parameters defining the nonparametric density estimator; and
  • iteratively computing the density estimator for finding a maximum likelihood estimation of acoustic data.

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 (2)   |   Citation Link

Patent  Pub.Date  Inventor Assignee   Title
Get PDF - 50pp US5893058  1999-04 Kosaka  Canon Kabushiki Kaisha Speech recognition method and apparatus for recognizing phonemes using a plurality of speech analyzing and recognizing methods for each kind of phoneme
Get PDF - 13pp US6148284  2000-11 Saul  AT&T Corporation Method and apparatus for automatic speech recognition using Markov processes on curves
Foreign References: None

Other References:
  • Feng et al ("Application of Structured Composite Source Models to Problems in Speech Processing," Proceedings of the 32nd Midwest Symposium on Circuits and Systems, pp. 89-92, 14-16 Aug. 1989.).*
  • Fonollosa et al ("Application of Hidden Markov Models to Blind Channel Characterization and Data Detection," 1994 IEEE International Conference on Acoustics, Speech, and Signal Processing, pp. IV/185-IV188, Apr. 19-22, 1994).*
  • Kogan ("Hidden Markov Models Estimation via the Most Informative Stopping Times for Viterbi Algorithm," 1995 IEEE International Symposium on Information Theory Proceedings, p. 178, Sep. 17-22, 1995).*
  • L. Liporace, "Maximum Likelihood Estimation for Multivariate Observations of Markov Sources", IEEE Transactions of Information Theory, vol. IT-28, No. 5, Sep. 1982.
  • L. Baum et al., "A Maximum Technique Occurring in the Statistical Analysis of Probabilistic Functions of Markov Chains", The Annals of Mathematical Statistics, 1970, vol. 41, No. 1, 164-171. Cited by 13 patents
  • B. W. Silverman, "On the Estimation of a Probability Density Function by the Maximum Penalized Likelihood Method", The Annals of Mathematical Statistics, 1982, vol. 10, No. 4, 795-810. (16 pages)
  • A.P. Dempster et al., "Maximum Likelihood from Incomplete Data via the EM Algorithm", Journal of Royal Statistical Society, 39(B), pp. 1-38, 1977. (38 pages) Cited by 53 patents
  • A. Marshall et al., "Scaling of Matrices to Achieve Specified Row and Column Sums", Numerische Mathematik 12, 83-90 (1968).
  • R. Brualdi, et al., "The Diagonal Equivalence of a Nonnegative Matrix to a Stochastic Matrix", Journal of Mathematical Analysis and Applications 16, 31-50 (1966).
  • L.E. Baum et al., "An Inequality with Applications to Statistical Estimation for Probabilistic Functions of Markov Processes and to a Model of Ecology", Bull. Amer. Math. Soc. 73, pp. 360-363, 1967.
  • S. Basu et al., "Maximum Likelihood Estimation for Acoustic Vectors in Speech Recognition", Advanced Black-Box Techniques for Nonlinear Modeling: Theory and Applications, Kulwer Publishers (1998).
  • R. Sinkhorn, "A Relationship Between Arbitrary Positive Matrices and Doubly Stochastic Matrices", Ann. Math. Statist., 38, pp. 439-455, 1964.

  • 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